==== Front J Transl Med J Transl Med Journal of Translational Medicine 1479-5876 BioMed Central London 2658 10.1186/s12967-020-02658-5 Review Precision medicine in the era of artificial intelligence: implications in chronic disease management Subramanian Murugan mus2012@qatar-med.cornell.edu 12 Wojtusciszyn Anne Anne.Wojtusciszyn@chuv.ch 3 Favre Lucie Lucie.Favre@chuv.ch 3 Boughorbel Sabri sboughorbel@sidra.org 4 Shan Jingxuan jis2015@qatar-med.cornell.edu 25 Letaief Khaled B. eekhaled@ust.hk 6 Pitteloud Nelly Nelly.Pitteloud@chuv.ch 3 http://orcid.org/0000-0002-2082-7924Chouchane Lotfi loc2008@med.cornell.edu 125 1 grid.5386.8000000041936877XDepartment of Microbiology and Immunology, Weill Cornell Medicine, New York, USA 2 grid.418818.c0000 0001 0516 2170Genetic Intelligence Laboratory, Weill Cornell Medicine-Qatar, Qatar Foundation, Doha, Qatar 3 grid.8515.90000 0001 0423 4662Service of Endocrinology, Diabetology and Metabolism, Lausanne University Hospital, Lausanne, Switzerland 4 Clinical Bioinformatics Section, Research Division, Sidra Medicine, Doha, Qatar 5 grid.5386.8000000041936877XDepartment of Genetic Medicine, Weill Cornell Medicine, 45 E 69th Street, Suite 432, New York, NY 10021 USA 6 grid.24515.370000 0004 1937 1450Department of Electronic and Computer Engineering, Hong Kong University of Science and Technology, Kowloon, Hong Kong 9 12 2020 9 12 2020 2020 18 4725 11 2020 2 12 2020 © The Author(s) 2020Open AccessThis article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated in a credit line to the data.Aberrant metabolism is the root cause of several serious health issues, creating a huge burden to health and leading to diminished life expectancy. A dysregulated metabolism induces the secretion of several molecules which in turn trigger the inflammatory pathway. Inflammation is the natural reaction of the immune system to a variety of stimuli, such as pathogens, damaged cells, and harmful substances. Metabolically triggered inflammation, also called metaflammation or low-grade chronic inflammation, is the consequence of a synergic interaction between the host and the exposome—a combination of environmental drivers, including diet, lifestyle, pollutants and other factors throughout the life span of an individual. Various levels of chronic inflammation are associated with several lifestyle-related diseases such as diabetes, obesity, metabolic associated fatty liver disease (MAFLD), cancers, cardiovascular disorders (CVDs), autoimmune diseases, and chronic lung diseases. Chronic diseases are a growing concern worldwide, placing a heavy burden on individuals, families, governments, and health-care systems. New strategies are needed to empower communities worldwide to prevent and treat these diseases. Precision medicine provides a model for the next generation of lifestyle modification. This will capitalize on the dynamic interaction between an individual’s biology, lifestyle, behavior, and environment. The aim of precision medicine is to design and improve diagnosis, therapeutics and prognostication through the use of large complex datasets that incorporate individual gene, function, and environmental variations. The implementation of high-performance computing (HPC) and artificial intelligence (AI) can predict risks with greater accuracy based on available multidimensional clinical and biological datasets. AI-powered precision medicine provides clinicians with an opportunity to specifically tailor early interventions to each individual. In this article, we discuss the strengths and limitations of existing and evolving recent, data-driven technologies, such as AI, in preventing, treating and reversing lifestyle-related diseases. Keywords ExposomeChronic inflammationChronic diseasesPrecision medicinePersonalized treatmentDeep phenotypingBig-data analyticsMachine leaningArtificial intelligenceWeill Cornell Medicine-QatarBMRPChouchane Lotfi issue-copyright-statement© The Author(s) 2020 ==== Body Introduction The average lifespan of humans has more than doubled in the last two hundred years, largely due to modern medicine and public health initiatives. However, an extended lifespan is associated with increases in various types of diseases among which noncommunicable diseases (NCDs), also commonly referred to as chronic diseases. Recent evidence indicates that chronic inflammatory diseases are the most significant cause of death worldwide, with over 50% of all deaths due to inflammatory conditions. For this review, we collectively refer to the following as chronic diseases: type 2 diabetes, obesity, cardiovascular disease (CVD), metabolic associated fatty liver disease (MAFLD), cancer, chronic lung and kidney disease, autoimmune and neurodegenerative diseases [1]. Today, our genes function in a world that is completely different from the one they were designed for and modern humans are subjected to an environment that has changed tremendously over the past century. The genetic predisposition to various diseases differs, from person to person and non-genetic factors pose high attributable risks, often assessed between 80 and 90% of the total risk [2, 3]. The Global Burden of Disease (GBD) study, which measured the disease burden of behavioral, environmental and occupational, and metabolic risks or clusters of risks from 1990 to 2016 in 195 countries concluded that the modifiable risk factors lead to nearly 60% of deaths worldwide [4]. Lifestyle-associated chronic diseases tend to have two common characteristics: one is homeostasis disturbance and the second is metaflammation or chronic metabolic inflammation. Therefore, the pathophysiology of chronic diseases points to the physiological rationale that connects inflammation with homeostasis [5]. It is now widely recognized that pathogenesis of disease is often the result of interactions between various genetic and environmental factors. The sum of environmental exposures (non-genetic) from conception until old age, throughout the lifespan is known as the “exposome”. The term "exposome" is used to demonstrate the complexity and extent of exposures to toxic substances, nutrition, psychosocial stressors and physical impacts and their associated biological responses. Exposomics is the study of the exposome, based on the use of internal and external assessment methods [3, 6]. Precision medicine is an emerging field in therapeutics based on an understanding of the genetic make-up, personal lifestyle, gene, and surrounding environment of an individual. We can use precision medicine to customize prevention and treatment strategies for an individual by identifying the factors that predispose this individual to a specific disease and defining the underlying molecular mechanisms that induce the disorder. The use of “OMICS” or “EXPOsOMICS” along with wearable sensors as measurement/assessment methods have the potential to generate large amounts of data (big-data), thus requiring new digital approaches and resources for analyzing, integrating, and interpreting the massive amounts of data [7, 8]. Artificial intelligence (AI): an emerging field in which computer algorithms are equipped to carry out tasks independently of human guidance. To create an efficient AI algorithm, computer systems are initially fed data that is usually organized, indicating each data point has an algorithm-recognizable label or annotation. After sufficient sets of data points and their labels are presented to the algorithm, output is evaluated to ensure accuracy. Such AI algorithms are capable of observing, analyzing vast data and identifying patterns with incredible efficiency [9]. Artificial Intelligence that we consider in this context includes machine learning (ML), deep learning (DL), and artificial neural networks (ANN). When AI is combined with high performance computing approaches, AI allows us to establish and predict disease risk based on individual’s data [10]. Translating such enormous data into clinical knowledge is now in the hands of ML/AI platforms. Promising results in predicting disease risk with greater accuracy have been shown on these platforms [11–14]. As AI enters the world of precision medicine, it can help organizations to capitalize on precision medicine in many ways and help deepen our knowledge of the origins and course of chronic diseases. This review article discusses the potential contribution of lifestyle factors and biological factors -genetic, epigenetics and the microbiome to the development and progression of chronic inflammation. We will also highlight the recent findings on the implementation of ML/AI algorithms in personalized medicine to better manage and prevent chronic diseases. Inflammation—a natural response In recent years, there has been a substantial improvement in our understanding of the inflammatory mechanism and its contribution to health and diseases. Inflammation is the natural response of the body to harmful pathogens and stimuli in an effort to eliminate threat and/or repair damaged tissue [5]. However, in the early 1990′s a different type of inflammation was associated with overweight and obesity was identified as a persistent and maladaptive inflammatory response that had significant variations compared to classical inflammation [15]. Such systemic inflammation characterized as ‘low-grade’ was associated with elevated levels of inflammatory mediators and increased immune cell infiltration in peripheral tissues without altering the primary function of the tissue [16, 17]. Human exposome can be categorized into external and internal. An increasing number of investigations have been addressing the human exposome, and the external exposome factors were well described in the recent articles [3, 6]. These factors were classified into four categories: (1) Lifestyle factors, such as diet, physical activity, sleep, smoking and alcohol; (2) Physical and chemical factors, such as temperature, pollution, pesticides, food contaminants etc.; (3) Ecosystem factors, such as food systems, climate, global warming, built environment, dense population etc.; (4) Social factors, such as socioeconomic status, stress, social networks, cultural standards etc. [3]. (Fig. 1). An example of environmental chemicals inducing inflammation was shown in a recent study: chemicals such as linuron (an herbicide used in agriculture) and methyl carbamate (a compound used in the fabric, polymer, and pharmaceutical industries), were shown to enhance astrocyte inflammation and neurological inflammation [18]. Accumulating evidences linked air pollution to inflammation and to further number of chronic diseases [19–21]. Likewise, the built environment is linked to the dynamics of infectious diseases such as SARS CoV2, especially in contact-borne diseases (aerosols or droplets), and climate change to vector-borne diseases [22, 23]. The internal exposome that includes, (1) molecules generated endogenously from metabolic reactions, such as oxidative stress and lipid peroxidation, (2) infections, (3) gut microbiome, and (4) other natural reactions that affects DNA and proteins within the body (Fig. 1). In addition, social stress, phycological stress, and socioeconomic status were all linked to inflammation and disease risk [24–26]. Over the past decades, extensive efforts have been made and continue to be made in pursuit of identifying the risk factors for chronic diseases [27–29]. The etiology of chronic diseases has now been convincingly linked to systemic chronic inflammation (SCI). An overwhelming body of evidences and a recent critical review have highlighted the importance of SCI and its correlation with health and chronic diseases [30].Fig. 1 Exposome—internal factors and external environmental factors role in health and disease. The totality of exposure from conception throughout the life course leads to multiple physiological changes in every individual. Internal exposures such as lipid peroxidation, oxidative stress, DNA damage, alterations in gut microbiome, and inflammation collectively plays a major role in health and chronic diseases Lifestyle factors: chronic inflammation axis The April 2002 issue of Science discussed “The puzzle of complex diseases” where diet and lifestyle were identified to be important contributors for major chronic diseases [31, 32]. Since then, numerous landmark epidemiological and biological studies have recognized that lifestyle related choices and behaviors have contributed significantly to the incidence of chronic diseases. Several studies have linked being overweight and obese with increased risk of chronic diseases, cancers, including breast cancer (in post-menopausal women), endometrium, esophagus, pancreas, liver, colorectum and kidney, and others [33, 34]. A principal lifestyle factor influencing the onset of such diseases is the diet and nutrition of each individual [35, 36]. Evidences from preclinical investigations as well as observational and interventional trials indicated that Western-type diet (WD) is a key driver of chronic, low-grade metabolic inflammation [37, 38]. The consumption of calorie-rich foods: highly processed, ultra-processed (formulations of many ingredients), in addition to sugar sweetened beverages, fructose-containing sugars, trans fats and saturated fats, salt, and other food additives have been proven to influence inflammation and lead to chronic diseases [39–43]. In addition, WD and other popular diets have been shown to alter intestinal microbiome, which in turn helps shape integrated immune responses. Prolonged consumption of such diets leads to disruption of the gut-barrier integrity, allowing harmful secretion of microbial products that can cause inflammation [44–47]. A recent study indicated that the consumption of high-fat ketogenic diets can alter the microbiome and also reduce the number of intestinal pro-inflammatory Th17 cells which are critical for acting against infectious disease [46]. The consumption of fructose-rich diet has emerged as a major contributor to dyslipidemia, NALFD, insulin resistance, and diabetes. A recent elegant study has revealed that intestinal microbiota plays a major role in converting the dietary fructose to acetate, which in turn activates the hepatic lipogenesis [48, 49]. Numerous other dietary factors have also been shown to induce inflammation and lead to SCI. These include the consumption of highly processed foods that lack essential vitamins and micronutrients and the deficiencies in minerals such as calcium, phosphorus, zinc, and magnesium [50–54]. Noteworthy, the recent Lancet Commission report on the global syndemic investigated how the human-driven methods of food production, food supply, consumption and its consequences impacting the environment and climate change. In order to counter the global syndemic of obesity, undernutrition and climate change the commission is urging the governments to reconsider the food supply chains, and business models [55]. Other lifestyle variables such as physical inactivity, lack of sleep, and tobacco smoking, can also activate multiple immune-inflammatory pathways leading to chronic inflammatory conditions [56]. Inadequate physical activity is a leading risk factor for chronic diseases and mortality. Globally, the age-standardized prevalence of insufficient physical activity was 27.5% in 2016 [57]. In addition, over 80% of the world's adolescents are not physically active enough. Several studies have linked insufficient physical activity with inflammatory conditions; even moderate physical activity has demonstrated to possess anti-inflammatory effects, further reducing the risk of chronic diseases and improving age-related multi-morbidity by strengthening the immune function [58, 59]. Tobacco-related morbidity and mortality is significant worldwide since smoking increases the risk of developing a number of serious inflammatory conditions [60]. It has been well established that the nicotine present in the tobacco stimulates neutrophils, with subsequent release of certain molecules that promote inflammation increasing in turn the risk of chronic diseases [61, 62]. Excessive alcohol use damages not only gut and liver functions, but also multi-organ interactions, contributing to chronic inflammation and eventually, increasing the risk of chronic liver diseases and certain cancers [63]. Accumulating evidence suggests that the pathogenesis of psychological disorders, such as depression and anxiety, are also associated with chronic stress and neuroinflammation [64]. Given the clear linkage of lifestyle factors with chronic diseases, their prominence in preventing diseases cannot be over-emphasized. Biological factors: genetics and epigenetics During recent years, there has been tremendous interest in the discovery of genes that are responsible for chronic diseases. Genetic variation consists of differences in the DNA sequences of individuals manifesting as single nucleotide polymorphisms (SNPs), insertions and deletions, and other structural variations. Genome-wide association studies (GWAS) that include analyses of genetic variants across several human genomes in order to detect associations between genotype and phenotype. These have facilitated a remarkable range of discoveries in the biology of chronic diseases [65]. Several studies have found new genetic loci and genes that predispose an individual to a number of chronic diseases, such as type 1 and type 2 diabetes, coronary heart disease, obesity, asthma, cancer, bipolar disorder, depression, rheumatoid arthritis, Crohn's disease, and hypertension [66–73]. In addition, a recent large-scale GWAS conducted among the Japanese population has identified 320 independent signals in 276 genetic loci for 27 diseases among which 25 novel loci, including certain loci specific to, the Japanese population [74]. Due to the diversity in genetic make-up and associated disease variants across populations, data obtained from one population may not be applicable to other populations [75]. However, understanding the variants, genes and mechanisms involved in specific diseases unlocks the possibilities for innovative treatments, diagnostic approaches and the efficient prevention of diseases. Candidate gene and GWAS studies have identified numerous SNPs-genetic susceptibility loci across human genome which explain only a fraction of the inter-individual variation for chronic diseases. To date, however, it has not been shown that solely defined genetic influences contribute to a large proportion of chronic disease incidence at population level. Beyond lifestyle factors and genetic susceptibility, another powerful determinant of the health outcome is epigenetics. Epigenetic alterations have emerged as surrogate markers for environmental exposure. Recently, epigenetic mechanisms have been increasingly recognized as a critical link between environmental exposure and disease risk [76]. Evidence indicates that maternally regulated environmental modulation of gene expression in offspring and gene-environment interactions are significant determinants of disease risk in later life [77, 78]. In addition, using a unique cohort of more than 700 pairs of monozygotic and dizygotic twins, it was demonstrated that both genetics and environment-inherited epigenetic signatures plays major role in regulating gene expression in the offspring [79, 80]. Moreover, changes in epigenetics are the core mechanisms by which early nutritional conditions can increase later-life susceptibility to obesity and other chronic diseases [81]. Maternal malnutrition influences altered epigenetic regulation in genes that control the metabolism of lipids and carbohydrates and those involved in the neural networks of central appetite-energy homeostasis [82]. This suggests that early experience may lead to changes in the epigenome influencing metabolic and physiological pathways, possibly changing individual’s phenotypic development and thus having critical effect on their health. As stated above, several studies have indicated that dietary components induces alterations in the genome and have linked SNPs interactions with the consumption of particular food and dietary patterns [83–85]. Nutrients and other environmental factors, either directly or indirectly, can impact the levels and turnover of epigenetic signatures (DNA methylation, acetylation of histones) thereby regulating the expression of messenger RNAs and non-coding RNAs that have been implicated in multiple chronic diseases. In summary, epigenetic mechanisms have been shown to be associated with multiple lifestyle factors or environmental exposures, including overnutrition, undernutrition, physical activity, stress, pollutants, and obesity, which have in turn been linked to chronic diseases [86–89]. Gut microbiome Multiple studies have discovered that the microbiome impacts almost every aspect of human health, and that the microbial composition, which differs from individual to individual, can be a key component in diverse manifestations ranging from gaining weight to developing stress and depression [90]. Some studies on human or mice microbiome have indicated that this variability begins with variations in host genetics [91, 92]. Several other parallel studies have found that the environment is dominant over host genetics in the development of human intestinal microbiota [93, 94]. A recent study, which looked into factors that influence the intestinal microbiome composition across nine different primate species and four human communities subject to various subsistence habit, identified environmental factors as the main driver of intestinal microbiome composition when compared to host species phylogenies [95]. In addition, the intestinal bacteria in four Himalayan populations (Tharu, Raute, Raji and the Chepang) differed according to their dietary lifestyles [96]. Such findings show that diet can dominate phylogenetic development of gut microbiome composition. Acute dietary changes (four days) was sufficient enough to bring about significant alteration to the human gut microbiota composition [97]. In a recent study that investigated on Irish traveler’s intestinal microbiome shown that microbiota is considerably different from that of a non-traveler settled population. However, the non-travelers (settled) Irish contain microbiota similar to people lives in industrialized society with a comparatively higher risk of chronic disease. Most travelers contain an ancient of microbiome that protects themselves from various chronic inflammatory conditions [98]. Moreover, microbiota-accessible carbohydrates (MACs) serve as an energy source for gut bacteria, resulting in the production of short chain fatty acids (SCFAs) which benefits the host. Further, these SCFAs including butyrate and propionate have multiple effects on signaling pathways including energy homeostasis, carbohydrate and lipid metabolism, and inhibition of inflammatory signals [99, 100]. Moreover, evidence has shown that microbial colonization of the infant occurs at birth through the vaginal canal and also some by breastfeeding and skin-to-skin contact. Babies delivered by caesarean section lack some strains of gut bacteria [101]. Furthermore, environmental exposure early in life has a strong effect on a child’s intestinal microbiome, and studies have linked environmental factors during infancy with a subsequent risk of developing allergies and asthma [102] Precision medicine In the last decade, strategies to advance precision medicine have attracted considerable investment in developing new treatments, understanding more about disease mechanisms, and eventually preventing disease. Precision medicine focused on identifying the effective approaches and the tailored treatment based on an individual’s genetic, environmental, and lifestyle factors. As explained above, we have undeniable evidence of human biological diversity in both health and disease, as shown by the findings of the Human Functional Genomics Project (HFGP) focused on 500 healthy adult subjects [103]. A number of studies have illustrated this explicitly by analyzing immune cells (cytokine) as an endpoint, showing that the cytokine types and levels vary depending on environmental factors (e.g., season driven), genetic history, and intestinal microbiome composition [104]. Furthermore, the latest study from the HFGP has shown that 11 different kinds of host factors together accounted for up to 67% of inter-individual variation in activated cytokine production in healthy subjects [105]. Overall, interpersonal variability in diet, lifestyle, sleep, stress, socioeconomic status, geography, early life experiences and exercise habits combined with gut microbiome, genetic background, metabolism, inflammatory status, are all critical factors in determining an individual’s heath and risk for disease (Fig. 2). In addition, the exposure of individual to environmental hazards is not constant and can change throughout their life, and also the effect of the exposures can vary depending on an individual's life stage. Environment-wide association studies (EWAS) have been proposed to examine new environmental factors in disease risk [106]. Therefore, the need of every individual is complex and require in-depth assessment (deep phenotyping) before interventions can be confidently applied (Fig. 2).Fig. 2 Deep phenotyping and artificial intelligence for health promotion and chronic disease prevention. Deep phenotyping provides an entire molecular profile of an individual’s physiological status. When longitudinally tested, the pathways can be tracked to identify the transformation from a health to a disease. Various omics technologies along with other physiological measurements will be used to molecularly characterize an individual’s risk for disease. Further implementation of a systems approach to the big-data analysis and integration will provide a platform for machine learning and artificial intelligence in clinical decision-making for early disease risk identification and prevention Deep phenotyping and artificial intelligence Precision oncology, AI can be used to develop a drug combination centered on a patient's own biopsy and adopt N-of-1 medication recommendations [107]. Across multiple specializations, especially in radiology AI-based algorithms have already shown improvement in diagnostic accuracy and performance [108–111]. The US Food and Drug Administration (FDA) has licensed many AI systems to promote medical imaging evaluation, including the detection of abnormal lesions that may progress to cancer [112]. A recent work highlights how AI and the advancement of technologies together are empowering the aim of personalized and precision medicine [113]. Machine learning is a key for multi omics data integration and there are several aspects in which data types are combined and their relationships are explored [114]. One of the large prospective cohort studies the UK Biobank project has collected deep genetic and phenotypic data including biological measurements, lifestyle markers, blood and urine biomarkers, and brain imaging from 500,000 individuals. This project has provided researchers with opportunities to search for genetic associations with disease risk and has resulted in several publications [115]. In addition, a precision medicine screening study that introduced a platform of deep quantitative multimodal phenotyping including genomics, metagenomics, advanced imaging, metabolomics, clinical testing and family history, provided a comprehensive, predictive, and personalized assessment of individuals health and chronic disease risk [116]. Further to big data obtained from deep phenotyping, a recent study empowered its participants with an additional behavioral coach. The Pioneer 100 wellness project (P100) was an initial effort to obtain and analyze large omics data sets to correlate molecular networks in 108 healthy individual. This study performed whole genome sequencing, proteome, microbiome, metabolome, recorded clinical data, daily physical activity, and sleep patterns for every three months over a nine months period. The investigators established personal, dense, dynamic data clouds for each participant and carried out an integrated analysis of six different data types. Further, these data-driven insights combined with behavioral coaching significantly improved the wellness of the participants with regard to nutrition, inflammation, diabetes and CVDs [117]. A similar study performed deep longitudinal omics profiling along with wearable monitoring for 109 individuals who were at increased risk for diabetes. They utilized multi-omics including genome, transcriptome, immunome, metabolome, proteome, and gut microbiome measured for up to eight years (median, 2.8 years). Such a deep analysis for this long period of time allowed the recognition of 67 clinically actionable health outcomes, including the cardiovascular disease risk [118]. Furthermore, in order to understand the molecular changes of the ageing process and associated disease risk, a recent study performed longitudinal and deep multi-omics profiling from 106 healthy individuals aged between 29 to 75 years and analyzed how diverse types of ‘omics’ results combined with clinical markers, correlated with age. This study identified various types of aging patterns called 'ageotypes,' based on the types of molecular pathways that have evolved over time in a specific person. Such ageotypes provides new possibilities for the design of early diagnosis and treatment interventions that may slow down the aging process depending on the particular biology of each individual [119]. Machine learning has been widely applied to the precision nutrition field to customize a personalized diet aimed to prevent or manage diet related diseases [120, 121]. One landmark study has successfully used a precision nutrition approach and has created a personalized diet to predict blood glucose response by considering biochemical, anthropometrics, dietary intake, physical activity, and gut microbiota data in an integrated framework. In this study, 800 healthy and prediabetic individuals were examined and their responses to the food were measured a total of 46,898 meals. The investigators adopted an ML/AI algorithm that precisely predicted postprandial glycemic responses (PPGRs) to meals. The ML/AI predictions were validated in an independent 100-individual cohort. Finally, a blinded, randomized controlled intervention based on an algorithm predicted diet resulted in significantly lower PPGRs and consistent changes in gut microbiota composition [122]. Recent independent similar studies using the personalized nutrition strategy for PPGRs to diet was confirmed in healthy individuals in an American population [123, 124]. Moreover, ML/AI is transforming the electronic health record (EHR) field and over time EHRs powered with AI were shown to reveal more about diseases. The ML/AI, tools applied to the health records of patients in EHRs and accurately predicted their probability of acquiring or developing chronic diseases [125]. AI medical assistants The management of chronic disease requires regular monitoring and recommendations. Virtual medical assistants using AI have recently matured and are being used in various products. AI assistants for diabetes have been shown useful to control patient conditions. For example, Onduo is a company that provides a virtual coaching via text messages through a mobile app. It uses AI technology for food recognition, glucose sensor and physical activities to provide recommendations. Other examples of startup companies are Virta, Wellpepper or Accolade. Another interesting solution is provided by DayTwo. It gives a personalized nutrition recommendation based on subject’s gut microbiome. The suggested meals are chosen among a large database of more than 100,000 foods to keep the glycemic range under control [123]. For cardiac diseases, AI has shown major progress in the diagnosis of atrial fibrillation. The latter is a common problem represents a 20 to 30% lifetime risk. It can occur without symptoms and increase the risk of stroke. AliveCor developed a system based on deep learning, single-lead ECG sensor and physical activity via accelerometer data [126]. The system is integrated with a smart watch and it is capable of predicting the occurrence of atrial fibrillation every 5 s. AI has also contributed in improving diagnoses based on cardiovascular imaging such as in echocardiography, MRI or ultrasound imaging. A comparative study of echocardiography interpretation of Ultromics system with cardiologist showed that more than 90 percent of the abnormalities found by board certified cardiologists overlapped with the ones found by the AI system [127]. Another example of the use of AI for chronic disease management is ResApp Health. The system uses the phone microphone to analyze the subject’s breathing. The AI algorithm is able to give an assessment of several lung conditions with high accuracy such as chronic obstructive lung disease, pneumonia or chronic asthma [128]. Taken together, while high-throughput data generation strategies are becoming more advanced, quicker, and comparatively more affordable, researchers are increasingly gaining access to large amounts of molecular knowledge from human cohorts. The volume of potential data is enormous, and it has been estimated that personal lifestyle-based data sum up to 1100 terabytes over a lifespan, with genetics and clinical data comprising 6.4 terabytes, which is less than 1% of the total. Omics technologies, GWAS, EWAS, smartphone-based digital phenotyping, sensors, EHRs, wearable devices to monitor physical activity, geography location data and climate data combined with AI have improved the prospect of implementing prevention and management strategies for chronic diseases [129–132]. Therefore, the use of such large multidimensional data requires the establishment of structured collection and big data analytics, as well as multidisciplinary integration of high-performance computational technologies and integration of ML/AI. Hence, AI is quickly becoming a crucial methodology in the advancement of precision/personalized medicine [133, 134]. Recent developments in the field One of the first large-scale, population-based, prospective studies which intended to enable comprehensive analyses of the genetic and non-genetic causes of diseases for middle and old age was the UK biobank study [115, 135]. In addition, the most ambitious longitudinal study in precision medicine so far, the “All of Us” Research Program, which aims to focus research on the link between environment, lifestyle and biology in health and disease is ongoing [136]. The All of Us program intends to enroll one million people across America and plans to implement deep phenotyping by gathering genetic and health data (using EHRs, digital health data), geography, and biospecimens for biomarker review. Similarly, a project called “The Project Baseline Health Study (PBHS)” was initiated to map human health by deep phenotyping to at least 10,000 individuals. The PBHS study established a portal that incorporates and analyzes personalized, longitudinal, multidimensional data, with a greater focus on future than past. It further explore the biological heterogeneity of healthy individuals or individuals with chronic disease in detail for a longer period of time to create reference health status by integrating various aspects of health [137]. The Human Exposome Project, 2020 from the European Union is the largest network of research programs aiming to address the environmental exposure such as diet, lifestyle, occupational and other environmental factors impact on human health (https://www.humanexposome.eu/). Such data-driven approach to exposome reduces the conventional decision-making method and it may better determine the influence of chemical exposures on particular physiological systems proven to be affected. Subsequently this would help to create novel chemicals with reduced impact on human health and the environment [138]. Over the last two decades, omics, wearables, sensors, digital medicine and emerging innovative technologies together with AI have all made incredible advancements in the field of precision/personalized medicine. Furthermore, AI is being implemented in precision oncology to help clinicians in decision making, with the aim of improving patient outcomes [139]. AI-based healthcare practices are already being implemented in high-income countries; for instance, the UK and Singapore have recently launched national strategies to tackle chronic disease burden using AI. Data driven, AI-powered health care has the potential to clarify the landscape of findings and enable clinical decisions to digitally identify, treat, and manage chronic conditions. Data protection and privacy The frequent collection of personal health and environmental data has been greatly improved through the use of decentralized sensors, measurement devices and mobile phones. A few decades ago, the measurement of blood pressure, glucose level, heart rate could only be done by medical experts. Nowadays such information can be continuously collected through mobile apps. The rapid introduction of AI technology into the precision medicine is advantageous, as AI offers an opportunity to increase the efficiency of health care delivery and the quality of patient care. However, it is necessary to mitigate the ethical risks of the AI implementation, which could include data privacy and confidentiality violations, informed consent, and patient autonomy. In the world of precision medicine, big data and AI, it is of paramount importance that data protection legislation is in place that properly ensures the privacy of individuals, particularly patients. The raise of privacy concerns related to the collection of health data has contributed in the significant progress on private AI methods such as Federated Learning or Differential Privacy in Machine Learning [140]. Countries around the world introducing laws to protect the privacy of their citizens. The Health Insurance Portability and Accountability Act (HIPAA) in USA the primary federal law to protect the privacy of health data. However, HIPAA has major gaps in current world because it protects only relevant health information produced by "covered entities" or their "business associates” [141, 142]. Whereas in Europe, The General Data Protection Regulation (GDPR) has been practical since May 25, 2018 in all European Union (EU) member states and implemented a new era of extensive data protection law within the EU [143, 144]. GDPR regulation has begun a significant global shift in data protection, creating political campaigns that advocate more privacy for data subjects, stricter laws for private corporations and governments that control emerging and increasingly evolving technology that pose a threat to data security. Conclusion Chronic diseases impose a substantial health and economic burden worldwide, with nearly one in four adults suffering from one or more chronic health conditions. To date, the longitudinal cohort studies have set the stage for enhancing human health by identifying and defining the natural history of diseases, identifying their risk factors and finding novel biomarkers. Further, the use of biosensors and the advances in multi-omics have established the foundation for better disease categorization, created targeted therapies, and have improved prognosis for many diseases. Most importantly, advances in digital medicine have helped to determine the underlying causes of diseases in individual patients. Since most chronic diseases are the consequence of primary lifestyle factors, individuals can reduce the likelihood of developing chronic conditions by making healthier lifestyle decisions. Nutrition and lifestyle preferences are affected by a wide variety of socio-economic factors including employment, education, geography, built environment, social networks, and a climate system. Combatting obesity and chronic diseases associated with diet needs careful examination of the social determinants of food systems, environment and climate change and specific public health strategies targeted at minimizing health disparities [55, 145, 146]. One aim of public health is promoting healthy lifestyle and developing novel approaches to prevent, detect, and respond to diseases that commonly affect people. With the development of precision medicine and the advent of AI, it can be misconstrued that medicine and health care is again drifting towards an individualistic approach versus a community approach to controlling diseases [147]. On the contrary, precision medicine, AI, and our deep understanding of disease conditions offer a great opportunity to save resources for those countries that have practiced a one-size-fits all and a piecemeal approach in their public health thinking and programming and have not reaped adequate return for their investments. Chronic diseases, and their multifactorial nature, the advent of technological advancements in the form of AI, and the ‘precision’ in precision medicine have the potential to redefine and replace conventional public health approaches with a new holistic paradigm [148]. There remains a huge scope for introducing educational programmes, developing policies, and strengthening systems to capitalize on the rapid development in the field and customize activities for collectives (persons who share common traits and characteristics) rather than communities. Abbreviations HPCHigh-performance computing AIArtificial intelligence MLMachine learning DLDeep learning ANNArtificial neural networks SCISystemic chronic inflammation NCDsNoncommunicable diseases MAFLDMetabolic associated fatty liver disease CVDsCardiovascular disorders GBDGlobal Burden of Disease WDWestern-type diet SNPsSingle nucleotide polymorphisms GWASGenome-wide association studies EWASEnvironment-wide association studies MACsMicrobiota-accessible carbohydrates SCFAsShort chain fatty acids HFGPHuman Functional Genomics Project FDAFood and Drug Administration PPGRsPostprandial glycemic responses HERElectronic health record PBHSProject Baseline Health Study Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations. Acknowledgements Not applicable. Authors’ contributions MS and LC developed the concepts of the manuscript and LC, NP and KL supervised the manuscript preparation. MS, AW, LF, SB, and JS performed the literature search, created the figures contributed to the manuscript writing and editing. MS and LC edited the final version of the manuscript. All authors read and approved the final manuscript. Funding This work was supported by the BMRP Funding of Weill Cornell Medicine-Qatar. Availability of data and materials Not applicable. Ethics approval and consent to participate Not applicable. Consent for publication All the authors have read and approved the manuscript in all respects for publication. Competing interests The authors declare that they have no competing interests. ==== Refs References 1. Disease GBD Injury I Prevalence C Global, regional, and national incidence, prevalence, and years lived with disability for 354 diseases and injuries for 195 countries and territories, 1990–2017: a systematic analysis for the Global Burden of Disease Study 2017 Lancet 2018 392 10159 1789 1858 10.1016/S0140-6736(18)32279-7 30496104 2. Wild CP Complementing the genome with an "exposome": the outstanding challenge of environmental exposure measurement in molecular epidemiology Cancer Epidemiol Biomarkers Prev 2005 14 8 1847 1850 10.1158/1055-9965.EPI-05-0456 16103423 3. Vermeulen R The exposome and health: Where chemistry meets biology Science 2020 367 6476 392 396 10.1126/science.aay3164 31974245 4. Collaborators, G.B.D.R.F. Global, regional, and national comparative risk assessment of 84 behavioural, environmental and occupational, and metabolic risks or clusters of risks, 1990–2016: a systematic analysis for the Global Burden of Disease Study 2016 Lancet 2017 390 10100 1345 1422 10.1016/S0140-6736(17)32366-8 28919119 5. Kotas ME Medzhitov R Homeostasis, inflammation, and disease susceptibility Cell 2015 160 5 816 827 10.1016/j.cell.2015.02.010 25723161 6. Escher BI Stapleton HM Schymanski EL Tracking complex mixtures of chemicals in our changing environment Science 2020 367 6476 388 392 10.1126/science.aay6636 31974244 7. Vineis P The exposome in practice: Design of the EXPOsOMICS project Int J Hyg Environ Health 2017 220 2 Pt A 142 151 10.1016/j.ijheh.2016.08.001 27576363 8. Obermeyer Z Emanuel EJ Predicting the future—big data, machine learning, and clinical medicine N Engl J Med 2016 375 13 1216 1219 10.1056/NEJMp1606181 27682033 9. van Assen M Lee SJ De Cecco CN Artificial intelligence from A to Z: from neural network to legal framework Eur J Radiol 2020 129 109083 10.1016/j.ejrad.2020.109083 32526670 10. He J The practical implementation of artificial intelligence technologies in medicine Nat Med 2019 25 1 30 36 10.1038/s41591-018-0307-0 30617336 11. Esteva A Dermatologist-level classification of skin cancer with deep neural networks Nature 2017 542 7639 115 118 10.1038/nature21056 28117445 12. Ehteshami Bejnordi B Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer JAMA 2017 318 22 2199 2210 10.1001/jama.2017.14585 29234806 13. Poplin R Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning Nat Biomed Eng 2018 2 3 158 164 10.1038/s41551-018-0195-0 31015713 14. Bello GA Deep learning cardiac motion analysis for human survival prediction Nat Mach Intell 2019 1 95 104 10.1038/s42256-019-0019-2 30801055 15. Gregor MF Hotamisligil GS Inflammatory mechanisms in obesity Annu Rev Immunol 2011 29 415 445 10.1146/annurev-immunol-031210-101322 21219177 16. Weisberg SP Obesity is associated with macrophage accumulation in adipose tissue J Clin Invest 2003 112 12 1796 1808 10.1172/JCI200319246 14679176 17. Hotamisligil GS Inflammation, metaflammation and immunometabolic disorders Nature 2017 542 7640 177 185 10.1038/nature21363 28179656 18. Wheeler MA Environmental Control of Astrocyte Pathogenic Activities in CNS Inflammation Cell 2019 176 3 581 596 e18 10.1016/j.cell.2018.12.012 30661753 19. Dadvand P Air pollution and biomarkers of systemic inflammation and tissue repair in COPD patients Eur Respir J 2014 44 3 603 613 10.1183/09031936.00168813 24558180 20. Lelieveld J The contribution of outdoor air pollution sources to premature mortality on a global scale Nature 2015 525 7569 367 371 10.1038/nature15371 26381985 21. Zhao CN Emerging role of air pollution in autoimmune diseases Autoimmun Rev 2019 18 6 607 614 10.1016/j.autrev.2018.12.010 30959217 22. Emeruwa UN Associations Between Built Environment, Neighborhood Socioeconomic Status, and SARS-CoV-2 Infection Among Pregnant Women in New York City JAMA 2020 324 390 392 10.1001/jama.2020.11370 32556085 23. Rocklov J Dubrow R Climate change: an enduring challenge for vector-borne disease prevention and control Nat Immunol 2020 21 5 479 483 10.1038/s41590-020-0648-y 32313242 24. Powell ND Social stress up-regulates inflammatory gene expression in the leukocyte transcriptome via beta-adrenergic induction of myelopoiesis Proc Natl Acad Sci U S A 2013 110 41 16574 16579 10.1073/pnas.1310655110 24062448 25. Cohen S Janicki-Deverts D Miller GE Psychological stress and disease JAMA 2007 298 14 1685 1687 10.1001/jama.298.14.1685 17925521 26. Chen E Socioeconomic status and inflammatory processes in childhood asthma: the role of psychological stress J Allergy Clin Immunol 2006 117 5 1014 1020 10.1016/j.jaci.2006.01.036 16675327 27. Liu CH Biomarkers of chronic inflammation in disease development and prevention: challenges and opportunities Nat Immunol 2017 18 11 1175 1180 10.1038/ni.3828 29044245 28. Straub RH The brain and immune system prompt energy shortage in chronic inflammation and ageing Nat Rev Rheumatol 2017 13 12 743 751 10.1038/nrrheum.2017.172 29021568 29. Crusz SM Balkwill FR Inflammation and cancer: advances and new agents Nat Rev Clin Oncol 2015 12 10 584 596 10.1038/nrclinonc.2015.105 26122183 30. Furman D Chronic inflammation in the etiology of disease across the life span Nat Med 2019 25 12 1822 1832 10.1038/s41591-019-0675-0 31806905 31. Willett WC Balancing life-style and genomics research for disease prevention Science 2002 296 5568 695 698 10.1126/science.1071055 11976443 32. Strohman R Maneuvering in the complex path from genotype to phenotype Science 2002 296 5568 701 703 10.1126/science.1070534 11976445 33. Key TJ Diet, nutrition and the prevention of cancer Public Health Nutr 2004 7 1A 187 200 10.1079/PHN2003588 14972060 34. Khan N Afaq F Mukhtar H Lifestyle as risk factor for cancer: evidence from human studies Cancer Lett 2010 293 2 133 143 10.1016/j.canlet.2009.12.013 20080335 35. Collaborators GBDD Health effects of dietary risks in 195 countries, 1990–2017: a systematic analysis for the Global Burden of Disease Study 2017 Lancet 2019 393 10184 1958 1972 10.1016/S0140-6736(19)30041-8 30954305 36. Shan Z Association Between Healthy Eating Patterns and Risk of Cardiovascular Disease JAMA Intern Med 2020 180 1090 1100 10.1001/jamainternmed.2020.2176 32539102 37. Christ A Lauterbach M Latz E Western diet and the immune system: an inflammatory connection Immunity 2019 51 5 794 811 10.1016/j.immuni.2019.09.020 31747581 38. Minihane AM Low-grade inflammation, diet composition and health: current research evidence and its translation Br J Nutr 2015 114 7 999 1012 10.1017/S0007114515002093 26228057 39. Hall KD Ultra-processed diets cause excess calorie intake and weight gain: an inpatient randomized controlled trial of Ad libitum food intake Cell Metab 2019 30 1 67 77 e3 10.1016/j.cmet.2019.05.008 31105044 40. Katan MB Ludwig DS Extra calories cause weight gain–but how much? JAMA 2010 303 1 65 66 10.1001/jama.2009.1912 20051571 41. Srour B Ultraprocessed food consumption and risk of type 2 diabetes among participants of the NutriNet-Sante prospective cohort JAMA Intern Med 2019 180 283 291 10.1001/jamainternmed.2019.5942 42. Margina D Chronic inflammation in the context of everyday life: dietary changes as mitigating factors Int J Environ Res Public Health 2020 17 11 4135 10.3390/ijerph17114135 43. Semnani-Azad Z Association of major food sources of fructose-containing sugars with incident metabolic syndrome: a systematic review and meta-analysis JAMA Netw Open 2020 3 7 e209993 10.1001/jamanetworkopen.2020.9993 32644139 44. Blander JM Regulation of inflammation by microbiota interactions with the host Nat Immunol 2017 18 8 851 860 10.1038/ni.3780 28722709 45. Shi Z Gut microbiota: an important link between western diet and chronic diseases Nutrients 2019 11 10 2287 10.3390/nu11102287 46. Ang QY Ketogenic Diets Alter The Gut Microbiome Resulting In Decreased Intestinal Th17 cells Cell 2020 181 6 1263 1275 e16 10.1016/j.cell.2020.04.027 32437658 47. Zmora N Suez J Elinav E You are what you eat: diet, health and the gut microbiota Nat Rev Gastroenterol Hepatol 2019 16 1 35 56 10.1038/s41575-018-0061-2 30262901 48. Zhao S Dietary fructose feeds hepatic lipogenesis via microbiota-derived acetate Nature 2020 579 7800 586 591 10.1038/s41586-020-2101-7 32214246 49. Lancaster KJ Current intake and demographic disparities in the association of fructose-rich foods and metabolic syndrome JAMA Netw Open 2020 3 7 e2010224 10.1001/jamanetworkopen.2020.10224 32644135 50. Bonaventura P Zinc and its role in immunity and inflammation Autoimmun Rev 2015 14 4 277 285 10.1016/j.autrev.2014.11.008 25462582 51. Nielsen FH Effects of magnesium depletion on inflammation in chronic disease Curr Opin Clin Nutr Metab Care 2014 17 6 525 530 10.1097/MCO.0000000000000093 25023192 52. Aune D Dietary intake and blood concentrations of antioxidants and the risk of cardiovascular disease, total cancer, and all-cause mortality: a systematic review and dose-response meta-analysis of prospective studies Am J Clin Nutr 2018 108 5 1069 1091 10.1093/ajcn/nqy097 30475962 53. Ghishan FK Kiela PR Vitamins and minerals in inflammatory bowel disease Gastroenterol Clin North Am 2017 46 4 797 808 10.1016/j.gtc.2017.08.011 29173522 54. Moe SM. Disorders involving calcium, phosphorus, and magnesium. Prim Care. 2008; 35(2): 215–37, v–vi. 55. Swinburn BA The global syndemic of obesity, undernutrition, and climate change: the lancet commission report Lancet 2019 393 10173 791 846 10.1016/S0140-6736(18)32822-8 30700377 56. Guo Y Association between lifestyle factors, vitamin and garlic supplementation, and gastric cancer outcomes: a secondary analysis of a randomized clinical trial JAMA Netw Open 2020 3 6 e206628 10.1001/jamanetworkopen.2020.6628 32589229 57. Guthold R Worldwide trends in insufficient physical activity from 2001 to 2016: a pooled analysis of 358 population-based surveys with 1.9 million participants Lancet Glob Health 2018 6 10 e1077 e1086 10.1016/S2214-109X(18)30357-7 30193830 58. Booth FW Roberts CK Laye MJ Lack of exercise is a major cause of chronic diseases Compr Physiol 2012 2 2 1143 1211 23798298 59. Duggal NA Can physical activity ameliorate immunosenescence and thereby reduce age-related multi-morbidity? Nat Rev Immunol 2019 19 9 563 572 10.1038/s41577-019-0177-9 31175337 60. Wang M Trends in smoking prevalence and implication for chronic diseases in China: serial national cross-sectional surveys from 2003 to 2013 Lancet Respir Med 2019 7 1 35 45 10.1016/S2213-2600(18)30432-6 30482646 61. Hosseinzadeh A Nicotine induces neutrophil extracellular traps J Leukoc Biol 2016 100 5 1105 1112 10.1189/jlb.3AB0815-379RR 27312847 62. West R Tobacco smoking: health impact, prevalence, correlates and interventions Psychol Health 2017 32 8 1018 1036 10.1080/08870446.2017.1325890 28553727 63. Wang HJ Zakhari S Jung MK Alcohol, inflammation, and gut-liver-brain interactions in tissue damage and disease development World J Gastroenterol 2010 16 11 1304 1313 10.3748/wjg.v16.i11.1304 20238396 64. DiSabato DJ Interleukin-1 receptor on hippocampal neurons drives social withdrawal and cognitive deficits after chronic social stress Mol Psychiatry 2020 10.1038/s41380-020-0788-3 32606375 65. Visscher PM 10 Years of GWAS discovery: biology, function, and translation Am J Hum Genet 2017 101 1 5 22 10.1016/j.ajhg.2017.06.005 28686856 66. Shungin D New genetic loci link adipose and insulin biology to body fat distribution Nature 2015 518 7538 187 196 10.1038/nature14132 25673412 67. Park SL Cheng I Haiman CA Genome-wide association studies of cancer in diverse populations Cancer Epidemiol Biomarkers Prev 2018 27 4 405 417 10.1158/1055-9965.EPI-17-0169 28637795 68. Shrine N Moderate-to-severe asthma in individuals of European ancestry: a genome-wide association study Lancet Respir Med 2019 7 1 20 34 10.1016/S2213-2600(18)30389-8 30552067 69. Wellcome Trust Case Control, C Genome-wide association study of 14,000 cases of seven common diseases and 3,000 shared controls Nature 2007 447 7145 661 678 10.1038/nature05911 17554300 70. Fuchsberger C The genetic architecture of type 2 diabetes Nature 2016 536 7614 41 47 10.1038/nature18642 27398621 71. Okbay A Genetic variants associated with subjective well-being, depressive symptoms, and neuroticism identified through genome-wide analyses Nat Genet 2016 48 6 624 633 10.1038/ng.3552 27089181 72. van der Harst P Verweij N Identification of 64 novel genetic loci provides an expanded view on the genetic architecture of coronary artery disease Circ Res 2018 122 3 433 443 10.1161/CIRCRESAHA.117.312086 29212778 73. Tomei S Obesity susceptibility loci in Qataris, a highly consanguineous Arabian population J Transl Med 2015 13 119 10.1186/s12967-015-0459-3 25890290 74. Ishigaki K Large-scale genome-wide association study in a Japanese population identifies novel susceptibility loci across different diseases Nat Genet 2020 52 7 669 679 10.1038/s41588-020-0640-3 32514122 75. Wojcik GL Genetic analyses of diverse populations improves discovery for complex traits Nature 2019 570 7762 514 518 10.1038/s41586-019-1310-4 31217584 76. Stylianou E Epigenetics of chronic inflammatory diseases J Inflamm Res 2019 12 1 14 10.2147/JIR.S129027 30588059 77. Wang G Epigenetics and early life origins of chronic noncommunicable diseases J Adolesc Health 2013 52 2 Suppl 2 S14 21 10.1016/j.jadohealth.2012.04.019 23332566 78. Kundakovic M Champagne FA Early-life experience, epigenetics, and the developing brain Neuropsychopharmacology 2015 40 1 141 153 10.1038/npp.2014.140 24917200 79. Hannon E Characterizing genetic and environmental influences on variable DNA methylation using monozygotic and dizygotic twins PLoS Genet 2018 14 8 e1007544 10.1371/journal.pgen.1007544 30091980 80. Zenk F Germ line-inherited H3K27me3 restricts enhancer function during maternal-to-zygotic transition Science 2017 357 6347 212 216 10.1126/science.aam5339 28706074 81. Vickers MH Early life nutrition, epigenetics and programming of later life disease Nutrients 2014 6 6 2165 2178 10.3390/nu6062165 24892374 82. Bellanti JA Epigenetic studies and pediatric research Pediatr Res 2020 87 2 378 384 10.1038/s41390-019-0644-9 31731288 83. Guertin KA Metabolomics in nutritional epidemiology: identifying metabolites associated with diet and quantifying their potential to uncover diet-disease relations in populations Am J Clin Nutr 2014 100 1 208 217 10.3945/ajcn.113.078758 24740205 84. Ramos-Lopez O Guide for current nutrigenetic, nutrigenomic, and nutriepigenetic approaches for precision nutrition involving the prevention and management of chronic diseases associated with obesity J Nutrigenet Nutrigenomics 2017 10 1–2 43 62 10.1159/000477729 28689206 85. Cavalli G Heard E Advances in epigenetics link genetics to the environment and disease Nature 2019 571 7766 489 499 10.1038/s41586-019-1411-0 31341302 86. Sanli E Kabaran S Maternal obesity, maternal overnutrition and fetal programming: effects of epigenetic mechanisms on the development of metabolic disorders Curr Genomics 2019 20 6 419 427 10.2174/1389202920666191030092225 32476999 87. Sailani MR Lifelong physical activity is associated with promoter hypomethylation of genes involved in metabolism, myogenesis, contractile properties and oxidative stress resistance in aged human skeletal muscle Sci Rep 2019 9 1 3272 10.1038/s41598-018-37895-8 30824849 88. Marsit CJ Influence of environmental exposure on human epigenetic regulation J Exp Biol 2015 218 Pt 1 71 79 10.1242/jeb.106971 25568453 89. Park C Stress, epigenetics and depression: a systematic review Neurosci Biobehav Rev 2019 102 139 152 10.1016/j.neubiorev.2019.04.010 31005627 90. Gilbert JA Current understanding of the human microbiome Nat Med 2018 24 4 392 400 10.1038/nm.4517 29634682 91. Goodrich JK Human genetics shape the gut microbiome Cell 2014 159 4 789 799 10.1016/j.cell.2014.09.053 25417156 92. Korach-Rechtman H Murine genetic background has a stronger impact on the composition of the gut microbiota than maternal inoculation or exposure to unlike exogenous microbiota Appl Environ Microbiol 2019 85 18 e00826-19 10.1128/AEM.00826-19 31350316 93. Rothschild D Environment dominates over host genetics in shaping human gut microbiota Nature 2018 555 7695 210 215 10.1038/nature25973 29489753 94. Vangay P US immigration westernizes the human gut microbiome Cell 2018 175 4 962 972 e10 10.1016/j.cell.2018.10.029 30388453 95. Gomez A Plasticity in the human gut microbiome defies evolutionary constraints mSphere 2019 4 4 e00271 10.1128/mSphere.00271-19 31366708 96. Jha AR Gut microbiome transition across a lifestyle gradient in Himalaya PLoS Biol 2018 16 11 e2005396 10.1371/journal.pbio.2005396 30439937 97. David LA Diet rapidly and reproducibly alters the human gut microbiome Nature 2014 505 7484 559 563 10.1038/nature12820 24336217 98. Keohane DM Microbiome and health implications for ethnic minorities after enforced lifestyle changes Nat Med 2020 26 7 1089 1095 10.1038/s41591-020-0963-8 32632193 99. De Vadder F Microbiota-generated metabolites promote metabolic benefits via gut-brain neural circuits Cell 2014 156 1–2 84 96 10.1016/j.cell.2013.12.016 24412651 100. Sun M Microbiota-derived short-chain fatty acids promote Th1 cell IL-10 production to maintain intestinal homeostasis Nat Commun 2018 9 1 3555 10.1038/s41467-018-05901-2 30177845 101. Shao Y Stunted microbiota and opportunistic pathogen colonization in caesarean-section birth Nature 2019 574 7776 117 121 10.1038/s41586-019-1560-1 31534227 102. Havstad S Effect of prenatal indoor pet exposure on the trajectory of total IgE levels in early childhood J Allergy Clin Immunol 2011 128 4 880 885 e4 10.1016/j.jaci.2011.06.039 21820714 103. Netea MG Understanding human immune function using the resources from the Human Functional Genomics Project Nat Med 2016 22 8 831 833 10.1038/nm.4140 27490433 104. Ter Horst R Host and environmental factors influencing individual human cytokine responses Cell 2016 167 4 1111 1124 10.1016/j.cell.2016.10.018 27814508 105. Bakker OB Integration of multi-omics data and deep phenotyping enables prediction of cytokine responses Nat Immunol 2018 19 7 776 786 10.1038/s41590-018-0121-3 29784908 106. Hall MA et al. Environment-wide association study (EWAS) for type 2 diabetes in the Marshfield Personalized Medicine Research Project Biobank. Pac Symp Biocomput; 2014. p. 200–11. 107. Ho D Artificial intelligence in cancer therapy Science 2020 367 6481 982 983 10.1126/science.aaz3023 32108102 108. Ardila D End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography Nat Med 2019 25 6 954 961 10.1038/s41591-019-0447-x 31110349 109. Yala A A deep learning mammography-based model for improved breast cancer risk prediction Radiology 2019 292 1 60 66 10.1148/radiol.2019182716 31063083 110. Kantarjian H Yu PP Artificial intelligence, big data, and cancer JAMA Oncol 2015 1 5 573 574 10.1001/jamaoncol.2015.1203 26181906 111. Coudray N Classification and mutation prediction from non-small cell lung cancer histopathology images using deep learning Nat Med 2018 24 10 1559 1567 10.1038/s41591-018-0177-5 30224757 112. Gerke S The need for a system view to regulate artificial intelligence/machine learning-based software as medical device NPJ Digit Med 2020 3 53 10.1038/s41746-020-0262-2 32285013 113. Ho D Enabling technologies for personalized and precision medicine Trends Biotechnol 2020 38 5 497 518 10.1016/j.tibtech.2019.12.021 31980301 114. Zitnik M Machine learning for integrating data in biology and medicine: principles, practice, and opportunities Inf Fusion 2019 50 71 91 10.1016/j.inffus.2018.09.012 30467459 115. Bycroft C The UK Biobank resource with deep phenotyping and genomic data Nature 2018 562 7726 203 209 10.1038/s41586-018-0579-z 30305743 116. Perkins BA Precision medicine screening using whole-genome sequencing and advanced imaging to identify disease risk in adults Proc Natl Acad Sci U S A 2018 115 14 3686 3691 10.1073/pnas.1706096114 29555771 117. Price ND A wellness study of 108 individuals using personal, dense, dynamic data clouds Nat Biotechnol 2017 35 8 747 756 10.1038/nbt.3870 28714965 118. Schussler-Fiorenza Rose SM A longitudinal big data approach for precision health Nat Med 2019 25 5 792 804 10.1038/s41591-019-0414-6 31068711 119. Ahadi S Personal aging markers and ageotypes revealed by deep longitudinal profiling Nat Med 2020 26 1 83 90 10.1038/s41591-019-0719-5 31932806 120. Wang DD Hu FB Precision nutrition for prevention and management of type 2 diabetes Lancet Diabetes Endocrinol 2018 6 5 416 426 10.1016/S2213-8587(18)30037-8 29433995 121. de Toro-Martin J Precision nutrition: a review of personalized nutritional approaches for the prevention and management of metabolic syndrome Nutrients 2017 9 8 913 10.3390/nu9080913 122. Zeevi D Personalized nutrition by prediction of glycemic responses Cell 2015 163 5 1079 1094 10.1016/j.cell.2015.11.001 26590418 123. Mendes-Soares H Assessment of a personalized approach to predicting postprandial glycemic responses to food among individuals without diabetes JAMA Netw Open 2019 2 2 e188102 10.1001/jamanetworkopen.2018.8102 30735238 124. Mendes-Soares H Model of personalized postprandial glycemic response to food developed for an Israeli cohort predicts responses in Midwestern American individuals Am J Clin Nutr 2019 110 1 63 75 10.1093/ajcn/nqz028 31095300 125. Chaganti S Discovering novel disease comorbidities using electronic medical records PLoS ONE 2019 14 11 e0225495 10.1371/journal.pone.0225495 31774837 126. Hall A Effectiveness of a single lead AliveCor electrocardiogram application for the screening of atrial fibrillation: a systematic review Medicine (Baltimore) 2020 99 30 e21388 10.1097/MD.0000000000021388 32791751 127. Madani A Fast and accurate view classification of echocardiograms using deep learning NPJ Digit Med 2018 1 1 8 10.1038/s41746-017-0008-y 31304287 128. Porter P A prospective multicentre study testing the diagnostic accuracy of an automated cough sound centred analytic system for the identification of common respiratory disorders in children Respir Res 2019 20 1 81 10.1186/s12931-019-1046-6 31167662 129. Oh M Machine learning-based analysis of multi-omics data on the cloud for investigating gene regulations Brief Bioinform 2020 10.1093/bib/bbaa032 32337577 130. McConnell MV Feasibility of obtaining measures of lifestyle from a smartphone app: the MyHeart counts cardiovascular health study JAMA Cardiol 2017 2 1 67 76 10.1001/jamacardio.2016.4395 27973671 131. Althoff T Large-scale physical activity data reveal worldwide activity inequality Nature 2017 547 7663 336 339 10.1038/nature23018 28693034 132. Levine DM Design and testing of a mobile health application rating tool NPJ Digit Med 2020 3 74 10.1038/s41746-020-0268-9 32509971 133. Wainberg M Deep learning in biomedicine Nat Biotechnol 2018 36 9 829 838 10.1038/nbt.4233 30188539 134. Topol EJ High-performance medicine: the convergence of human and artificial intelligence Nat Med 2019 25 1 44 56 10.1038/s41591-018-0300-7 30617339 135. Sudlow C UK biobank: an open access resource for identifying the causes of a wide range of complex diseases of middle and old age PLoS Med 2015 12 3 e1001779 10.1371/journal.pmed.1001779 25826379 136. All of Us Research Program, I The "All of Us" Research Program N Engl J Med 2019 381 7 668 676 10.1056/NEJMsr1809937 31412182 137. Arges K The Project Baseline Health Study: a step towards a broader mission to map human health NPJ Digit Med 2020 3 84 10.1038/s41746-020-0290-y 32550652 138. Agier L Association between the pregnancy exposome and fetal growth Int J Epidemiol 2020 49 2 572 586 10.1093/ije/dyaa017 32167557 139. Yu SH Early experience with Watson for Oncology: a clinical decision-support system for prostate cancer treatment recommendations World J Urol 2020 10.1007/s00345-020-03214-y 32936332 140. Sattler F, Muller KR, Samek W. Clustered federated learning: model-agnostic distributed multitask optimization under privacy constraints. IEEE Trans Neural Netw Learn Syst. 2020. 141. Price WN 2nd Cohen IG Privacy in the age of medical big data Nat Med 2019 25 1 37 43 10.1038/s41591-018-0272-7 30617331 142. Cohen IG Mello MM HIPAA and protecting health information in the 21st century JAMA 2018 320 3 231 232 10.1001/jama.2018.5630 29800120 143. Yuan B Li J The policy effect of the general data protection regulation (GDPR) on the digital public health sector in the european union: an empirical investigation Int J Environ Res Public Health 2019 16 6 1070 10.3390/ijerph16061070 144. Gerke S, Minssen T, Cohen G. Ethical and legal challenges of artificial intelligence-driven healthcare. Artificial Intelligence in Healthcare. 2020; p. 295–336. 145. da Silva JG Transforming food systems for better health Lancet 2019 393 10173 e30 e31 10.1016/S0140-6736(18)33249-5 30700380 146. Kleinert S Horton R Obesity needs to be put into a much wider context Lancet 2019 393 10173 724 726 10.1016/S0140-6736(18)33192-1 30700379 147. Ramaswami R Bayer R Galea S Precision medicine from a public health perspective Annu Rev Public Health 2018 39 153 168 10.1146/annurev-publhealth-040617-014158 29166244 148. Wiemken TL Kelley RR Machine learning in epidemiology and health outcomes research Annu Rev Public Health 2020 41 21 36 10.1146/annurev-publhealth-040119-094437 31577910