Computer-implemented method and system for generating comprehensive health report of user

Abstract

Disclosed is a computer-implemented method for generating a comprehensive health report of a user. The computer-implemented method comprises obtaining multi-modal data related to at least one biological modality of the user; creating a dynamically updated knowledge base associated with the obtained multi-modal data from the user; calculating a health score corresponding to each biological modality, from amongst the at least one biological modality, of the multi-modal data in the dynamically updated knowledge base; and generating the comprehensive health report of the user based on the health score corresponding to each biological modality from the multi-modal data. Disclosed also is a system for generating a comprehensive health report of a user.

Description

[0001] COMPUTER-IMPLEMENTED METHOD AND SYSTEM FOR GENERATING

[0002] COMPREHENSIVE HEALTH REPORT OF USER

[0003] TECHNICAL FIELD

[0004] The present disclosure relates to computer-implemented methods for generating comprehensive health reports of users. Moreover, the present disclosure relates to systems for generating comprehensive health reports of users. Furthermore, the present disclosure relates to computer-readable storage mediums comprising instructions for generating comprehensive health reports of users.

[0005] BACKGROUND

[0006] The field of personalized healthcare has gained significant attention in recent years. The personalized healthcare focuses on two main aspects: preventative medicine and early detection and treatment of diseases, as well as optimization of health, fitness, and nutrition. In this regard, the personalized healthcare involves measuring multiple biological parameters, which, when combined with bioinformatics, enable healthcare professionals and individuals to accurately assess an individual's current health status, disease risk, fitness level, and determine methods to mitigate said risks.

[0007] Current approaches for interpreting and presenting multiomics data are primarily centred around the analysis of individual tiers of data, neglecting the intricate interconnections within the biological systems inherent to the human body. Such current solutions for personalized healthcare include, but do not limit to, genetic counselling services, online tools (such as VarSome), service providers (such as 23andMe, AncestryDNA, Viome, and the like). Generally, the genetic counseling services involve a subject consulting with a certified genetic counselor (namely, a healthcare professional) to discuss test results and receive personalized guidance therefrom. However, the genetic counseling services face scalability challenges due to manual interpretation of the genomic data by the genetic counselors. Moreover, the genetic counseling services rely on manual labour and are time-consuming.

[0008] The online or web-based tools typically aggregate the genetic and genomic data from multiple sources and provide annotations and classifications to help interpret the genetic and genomic data. However, such online tools require the subjects to have a certain level of expertise to be effectively used, which may not be accessible to all the subjects such as those who lack a scientific background, thereby complicating the entire process.

[0009] Notably, service providers such as 23andMe and AncestryDNA, and Viome, and the like that offer direct-to-consumer focus on only one aspect of the multiomic landscape (namely, genetic testing or microbiome testing and analysis, respectively), disregards the intricate interconnectedness of multiple systems within the human body and fails to furnish a comprehensive view of human biology and health.

[0010] Therefore, in light of the foregoing discussion, there exists a need to overcome the aforementioned drawbacks.

[0011] SUMMARY

[0012] The aim of the present disclosure is to provide a computer-implemented method and a system to generate personalised, biology-tailored reports regarding health / wellness outcomes of an individual thus immersing into the field of personalised health and preventive medicine. The aim of the present disclosure is achieved by a computer-implemented method and a system for generating a comprehensive health report of a user as defined in the appended independent claims to which reference is made to. Advantageous features are set out in the appended dependent claims.

[0013] Throughout the description and claims of this specification, the words "comprise" , "include", "have", and "contain" and variations of these words, for example "comprising" and "comprises" , mean "including but not limited to" , and do not exclude other components, items, integers or steps not explicitly disclosed also to be present. Moreover, the singular encompasses the plural unless the context otherwise requires. In particular, where the indefinite article is used, the specification is to be understood as contemplating plurality as well as singularity, unless the context requires otherwise.

[0014] BRIEF DESCRIPTION OF THE DRAWINGS

[0015] FIG. 1 is an illustration of a flowchart depicting steps of a computer- implemented method for generating a comprehensive health report of a user, in accordance with an embodiment of the present disclosure; and

[0016] FIG. 2 is an illustration of a system for generating a comprehensive health report of a user, in accordance with an embodiment of the present disclosure.

[0017] DETAILED DESCRIPTION OF EMBODIMENTS

[0018] The following detailed description illustrates embodiments of the present disclosure and ways in which they can be implemented. Although some modes of carrying out the present disclosure have been disclosed, those skilled in the art would recognize that other embodiments for carrying out or practising the present disclosure are also possible.

[0019] In a first aspect, the present disclosure provides a computer- implemented method for generating a comprehensive health report of a user, the computer-implemented method comprising: obtaining multi-modal data related to at least one biological modality of the user; creating a dynamically updated knowledge base associated with the obtained multi-modal data from the user; calculating a health score corresponding to each biological modality, from amongst the at least one biological modality, from the multi-modal data ; and generating the comprehensive health report of the user based on the health score corresponding to each biological modality from the multimodal data and annotating the scores with the knowledge from the dinamically updated knowlege base regarding said score.

[0020] The proposed invention aims to provide a scalable, extendable, user- friendly, comprehensive, scientifically accurate, and easily understandable approach for interpreting and presenting multiomic data. By addressing the limitations of previous approaches, this invention aims to transform personalized health and enhance the accuracy, accesebility and utility of health assessments and disease risk management.

[0021] In a second aspect, the present disclosure provides a system for generating a comprehensive health report of a user, the system comprising a processing arrangement configured for: obtaining multi-modal data related to at least one biological modality of the user; creating a dynamically updated knowledge base associated with the obtained multi-modal data from the user; calculating a health score corresponding to each biological modality, from amongst the at least one biological modality, from the multi-modal data ; and generating the comprehensive health report of the user based on the health score corresponding to each biological modality from the multimodal data.

[0022] The system of the present disclosure applies a combination of a curated knowledge base (acquired via web scrapping of peer-reviewed scientific literature) and artificial intelligence / machine learning on multiomic biological data to generate personalised, biology-tailored reports regarding health / wellness outcomes of an individual thus immersing into the field of personalised health and preventive medicine.

[0023] In a third aspect, the present disclosure provides a computer-readable storage medium comprising instructions for generating a comprehensive health report of a user, which when executed by a processing arrangement, cause the processing arrangement to execute steps of a computer-implemented method of the first aspect.

[0024] Optionally, in the method according to the invention, the comprehensive health report is configured for use by longevity clinics and other health and wellness institutions to support personalized health optimization and preventive care strategies.

[0025] The method according to the invention and the system according to the invention are applicable in longevity clinics and other health and wellness institutions.

[0026] Throughout the present disclosure, the term "comprehensive health report" refers to a detailed document that provides a thorough overview (namely, a holistic understanding) of an individual's health status based on an analysis of various health-related data. It may be appreciated that an individual's health is governed by various factors, such as physical, mental, emotional, environmental and social dimensions, that are interrelated and influence each other. Optionally, the comprehensive health report thus includes the analysis of genetic variations and markers associated with health conditions and pharmacogenomic information related to drug metabolism, information relating to gene expression patterns, analysis of biomarkers associated with specific health conditions, small-molecule metabolites and analysis of metabolic pathways, microbial communities, standard medical data, including blood pressure, cholesterol levels, routine blood tests and diagnostic imaging, and other relevant clinical measurements, dietary habits, nutritional status, physical activity levels and exercise patterns, environmental exposures and potential health risks, personal and family medical history, past illnesses, surgeries, and medical treatments, behavioural patterns such as sleep quality, stress levels, and substance use, mental health assessments and considerations, lifestyle changes, preventive measures, or further medical interventions, etc. In other words, the comprehensive health report typically integrates information from multiple "omics" (multi-omics) technologies, traditional clinical measurements, and lifestyle factors, to provide a personalized and actionable roadmap for individuals to optimize their health and well-being. Herein, the "user" refers to a person or an animal. Notably, the person may be a patient or a healthy individual seeking a comprehensive health report thereof.

[0027] The computer-implemented method comprises obtaining multi-modal data related to at least one biological modality of the user. Herein, the term "multi-modal data" refers to integration of health-related information obtained from different modes or sources to provide insights into disease mechanisms, personalized treatment strategies, and overall health, where each mode represents a distinct type or aspect of health data. The term "biological modality" as used herein typically refers to a specific type of biological entity that provides insights into various aspects of biological systems. Herein, multiple biological modalities are used in combination to obtain a comprehensive understanding of biological systems. For example, integrating genomics, transcriptomics, and proteomics data can provide a more holistic view of how genetic information is expressed and translated into functional proteins within an individual. In an example, the biological modality relates to cardiovascular health and multimodal data relates to genetic data, blood data, microbiome data and / or biometrics data corresponding to the cardiovascular health. The multi-modal data may be obtained as a real-time data or as a historical data. Herein, the multi-modal historical data may be obtained from different multi-modal data sources that store or generate multimodal data. Optionally, the multi-modal data sources may include various biological age clocks (such as blood age clocks, epigenome age clocks, microbiome age clocks, telomere age clocks, and so on) platforms, hospita l / clinic patient's data, data gathered as part of research initiatives, various other patient specific databases, wearable devices, and patient surveys. Beneficially, determining biological age based on a holistic biological age clock comprising more than one type of biomarkers (such as blood, DNA, epigenome, microbiome, telomeric, protein, lipid, biometric, etc.) is a significant improvement over existing solutions that focus only on a specific biomarker (i.e., only on blood biomarker(s), only on telomere length analysis, only on epigenetic data etc.), as it offers a more comprehensive and accurate assessment of biological age. By integrating data from a wide range of sources and a state-of-the-art knowledge base in the field of ageing research, the system can reveal a more holistic picture of an individual's biological age. Additionally, the granular representation of key drivers contributing to biological age calculation provides users with an intuitive way to understand their health status, a feature lacking in most existing solutions. The feature enables individuals or their health practitioners, wellness coaches, etc. to make informed decisions about their health, wellness, and lifestyle choices, leading to improved health outcomes and potentially increased longevity.

[0028] It may be appreciated that the multi-modal data is obtained pursuant to ethical standards (informed consent from individuals contributing their data) and privacy regulations (anonymize or de-identify data). Optionally, the multi-modal data may be obtained as a user input via a user interface (III), besides the multi-modal data obtained from other data sources. Herein, the user interface is rendered on a display of a user device associated with the user. The user device refers to a communication device capable of providing user input and receiving and accessing any information and / or a notification.

[0029] Optionally, the multi-modal data comprises: a biological test data selected from at least one of: blood biomarker data, gut microbiome composition and functional biomarkers data, epigenomic biomarkers data, telomeric biomarkers data, proteomic biomarkers data, data pertaining to skin health, lipidomic data, glycan data, biomarkers based on glycosylation patterns of the immune system, transcriptome signatures data, and metabolomic biomarkers data; and a supplementary data selected from at least one of: anthropometric measurements data, physiological phenotypes data, functional and wearable measurements data corresponding to exercise and sleep, a sensor data pertaining to a specific health entity, a health data from a third-party source, a pre-stored biological data and a pre-stored sensor data pertaining to a specific health entity from a third-party source.

[0030] In this regard, the multi-modal data may include, but is not limited to, a combination of multiomics data, medical imaging data (e.g., X-rays, MRIs), clinical measurements (e.g., blood pressure, heart rate), electronic health records (EHR.) data, patient-reported outcomes, wearable device data (e.g., fitness trackers), and other types of health- related information. The multiomics data (or multiomics health data or biomarkers data) specifically refers to integration of data from different "omics" technologies (namely, genomics (study of entire genome), transcriptomics (study of gene expression), proteomics (study of proteins), metabolomics (study of small molecules / metabolites), and so on) that focus on molecular aspects of health and biology. Each of these multi-modal data types provides unique insights into different aspects of an individual's health. Integrating and analyzing such diverse multimodal data contributes to a more comprehensive understanding of biological systems, disease mechanisms, and personalized health assessments. Notably, the blood biomarker data enables analyzing substances in the blood, such as proteins, hormones, and other molecules, to assess health and disease. Similarly, the gut microbiome composition and functional biomarkers data enables examining the types and functions of microorganisms in the gut to focus on digestion, metabolism, and immune function. The epigenomic biomarkers data enables studying chemical modifications to DNA and associated proteins that influence gene expression without altering the underlying DNA sequence. The telomeric biomarkers data enables assessing the length of telomeres which are associated with cellular aging. The proteomic biomarkers data enables investigating the presence, abundance, and modifications of proteins in a biological sample. The data pertaining to skin health focuses on skin health, potentially including texture, moisture levels, wrinkling intensity, and the presence of certain biomarkers. The lipidomic data enables analyzing the composition and changes in lipid molecules, which are crucial for cellular structure and function. The glycan data enables examining the structure and function of glycans. The biomarkers based on glycosylation patterns of the immune system enables studying how the immune system's glycosylation patterns change in response to health conditions. The transcriptome signatures data enables analyzing the complete set of R.NA transcripts produced by the genome to understand gene expression patterns. The metabolomic biomarkers data enables investigating the complete set of small molecules (metabolites) in a biological sample to understand metabolic processes.

[0031] Moreover, the anthropometric measurements data such as height, weight, body mass index (BMI), waist circumference, and other physical dimensions provides information about not only external appearance of an individual but may also be suggestive of the individual's internal state, similar to that provided by the physiological phenotypes data. For example, an individual with high BMI may be susceptible to a potential cardiac condition which may be confirmed from physiological phenotypes data including heart rate, blood pressure, respiratory rate, and other indicators of bodily functions. Similarly, medical imaging techniques, such as DEXA, fMRI and 3D photonic devices, provide even more detailed insights into body composition. Importantly, these techniques have the ability to differentiate between muscle mass, bone mineral density, total fat mass, and body fat distribution (ectopic vs subcutaneous fat). The functional and wearable measurements data includes data captured by wearable devices during physical activity and sleep, to focus on active and resting state of an individual. Optionally, Internet of Things devices including the wearable devices comprises one or more sensors to measure the active and resting state of an individual, besides various sensors including, but not limited to environmental sensors, motion sensors, or other types of monitoring devices that sense data pertaining to the specific health entity. The Internet of things devices may compris devices such as: Medical alert systems, Smart pill dispensers, air quality monitors, wearable ECG monitors, Remote glucose monitoring systems, smart scales, sleep monitoring devices, pulse oximeters, blood pressure monitors, smart thermometers Herein, the term "health entity" refers to a component associated with health of a person, that may be measured by the sensors. For example, temperature sensors are configured to measure body temperature of an individual. The third-party source may be external sources, such as electronic health records (EHRs), health apps, or health monitoring platforms, that provide additional insights into an individual's medical history and conditions. The pre-stored biological or sensor data includes data from medical devices, wearables, or other sensor technologies. It may be appreciated that the multi-modal data (the biological test data or the supplementary data) may include biology and health-related data from other data sources known to a person skilled in the art, and are not just limited to the aforementioned examples.

[0032] Beneficially, integrating data from different sources allows for a holistic approach to health assessment, personalized medicine, and the identification of patterns and correlations that can inform healthcare decisions. Considering these various data sources when accessing an individual's health state and making decisions on how to improve their wellbeing is a complex task, requiring weighing a large number of values together at once. A model that algorithmically combines these inputs into an organised system of a outputs not only provides better insight and more actionable data, but also improves efficiency by saving time of analysis and minimises the amount of errors arising from combining the large amount of diverse data in a less systematic way.

[0033] Moreover, the computer-implemented method comprises creating a dynamically updated knowledge base associated with the obtained multimodal data from the user. The term "dynamically updated knowledge base" as used herein refers to a repository of information that is continuously and automatically updated to reflect the latest information, changes, or additions. Optionally, the computer-implemented method comprises, for creating a dynamically updated knowledge base, collecting multi-modal data from various sources by for example web scraping, API integrations, or data feeds from reliable sources, in real-time or periodically (e.g., daily, weekly). In an example, the dynamically updated knowledge base is created by web scraping peer reviewed scientific literature (e.g., PubMed) and manually curating (using predefined rules) the peer reviewed scientific literature to gather scientific data regarding the multi-modal data related to the at least one biological modality of the user. In this regard, the computer-implemented method comprises extracting information (such as article titles, authors, abstracts, publication dates, results, conclusions, specific biological entities or modalities, and so on) from online sources where scholarly articles are published. Optionally, peer-reviewed scientific literature sources include publishers like PubMed, IEEE Xplore, ScienceDirect, or other academic databases. Moreover, the dynamically updated knowledge base serves as a database for storing the information and references for constructing algorithms that when implemented by at least one processor performs the method of the present disclosure.

[0034] Optionally, the dynamically updated knowledge base is scalable to handle a growing volume of data and updates without affecting performance thereof. It may be appreciated that the multi-modal data collected from various sources are compatible (namely, comprises standardized data formats, units of measurement, and data storage protocols) and can be integrated to the created dynamically updated knowledge base. Beneficially, the dynamically updated knowledge base serves as a reliable and current source of information, and supports decision-making processes regarding a health state of an individual.

[0035] Optionally, the computer-implemented method further comprises updating the dynamically updated knowledge base, by using artificial intelligence / machine learning tools, at pre-defined time intervals, wherein the dynamically updated knowledge base comprises at least one of: a plurality of published literature including scientific literature, articles, research findings, and experimental data. As mentioned above, the dynamically updated knowledge base may be updated in real-time or at pre-defined time intervals, such as daily, weekly, bi-weekly, monthly, quarterly, and so on, or based on respective update periods of the multimodal data sources. In this regard, the computer-implemented method employs artificial intelligence / machine learning tools / algorithms configured to detect changes or updates in the data sources by comparing a current state of the data sources with a previous version to identify additions, modifications, or deletions, and updating the dynamically updated knowledge base. Additionally, the dynamically updated knowledge base updates algorithms for performing the method of the present disclosure, based on the updated information in the dynamically updated knowledge base. Moreover, it may be appreciated that the dynamically updated knowledge base may be updated by only authorized individuals or systems. Optionally, the created and updated dynamically updated knowledge base may be regularly (namely, periodically) backed- up and / or recovered to safeguard against data loss or corruption.

[0036] Furthermore, the computer-implemented method comprises calculating a health score corresponding to each biological modality, from amongst the at least one biological modality, from the multi-modal data in the dynamically updated knowledge base. The term "health score" as used herein refers to a quantifier representative of a contribution of a given biological modality to a given health state of an individual. The health score is typically a number, represented as a fraction of numbers, a decimal number, a percentage, and so forth. The health score assigned to a given biological modality is calculated from an analysis of the given biological modality and its association with (or contribution to) at least one of the health-related information of the individual. Moreover, the given biological modality is assigned a health score based on a historic data recorded for the individual's health during a predetermined period of time.

[0037] In this regard, the health score corresponding to each biological modality is normalized based on populational data. The health scores are created using data processing / analysis algorithms which assess where in the distribution of health scores (i.e., which percentile) of the general population the health score of an individual falls. Typically, the population-based normalisation technique involves comparing the biomarker data of an individual to that biomarker data present in a larger population. Herein, the population data may be demographically similar to the individual (age, sex, ethnicity, etc.) or adjusted for such factors during statistical analysis. The health scores are normalized based on population data (such as by using data from databases like NHANES, 1000G, GMHI, etc.). Typically, the population-based normalized health score lies between 0 and 1, typically represents a quantitative measure of health of an indvidual with respect to the health status of a population, where 0 indicates poor health and 1 signifies optimal or perfect health of the individual. This gives us the ability to arbitrarily add other biological modality-based health scores like proteomics-based, metabolomics- based, biometrics-based, or others, which will in the future emerge as important for measuring the health state of the individual.

[0038] Moreover, a higher score of a biological modality may indicate a healthier health state of an individual, while certain variations could contribute to a lower score. For example, higher expression of a Gene A may be associated with good health and lower expression of Gene B (that is linked to diseases) may contribute to a higher score thereof. In other words, higher expression of Gene A and lower expression of Gene B are both related to a healthy individual, therefore, the corresponding expression levels of the Gene A and Gene B are provided a higher score. Similarly, normal physiological values within healthy ranges may contribute to a higher score. In an example, different biological modalities, such as single nucleotide polymorphisms (SNPs), values of a specific blood biomarker, or gut bacterial species, are assigned corresponding health score based on their effect on a health state, such as vascular health, of an individual.

[0039] Optionally, each biological modality is assigned a corresponding health score based on a correlation analysis (weighted sum analysis). In this regard, for example, if vascular health (biological) is calculated using blood vascular health, genetics vascular health and microbiome vascular health, the whole process is done by multipying a normalized score (which is between 0 and 1) with a weight (again between 0 and 1 - all weights sum to 1) corresponding to the blood vascular health, the genetics vascular health and the microbiome vascular health. A positive correlation typically indicates an increased contribution of the biological modality to the health state of the individual, while a negative correlation implies an inverse relationship, i.e., as the contribution of the biological modality increases, the health state of the individual decreases. Thus, biological modalities with stronger correlations (closer to +1 or -1) are considered more important in determining the health state of the individual and are assigned higher health scores. For example, if Biological Modality A has a correlation coefficient (or health scores) of 0.8 with the health state, it is ranked higher than Biological Modality B, which has a correlation coefficient (or health scores) of 0.5.

[0040] The technical effect of associating health scores with the biological modality based on its correlation with the health state of the individual is that it provides a clear understanding of which biological modalities play the most significant roles in the health state of the individual, and such understanding is valuable for personalised health interventions, including in the context of longevity clinics and other health and wellness institutions, sport training, nutritional and lifestyle coaching and similar, and enables targeted approaches to address specific factors influencing an individual's health state, such as biological age thereof. In contrast with current solutions, where result in data from various sources for the same health modality as well as for different health modalities are presented in various formats, this solution outputs all of this data in a structured, consistent format of scores. This allows consideration of all various relevant factors with much less effort, resulting in quicker analysis and decisions regarding interventions, while increasing consistency and minimising the risk of errors arising from "Manual" analysis of diverse data.

[0041] Optionally, the comprehensive health score is configured for use in longevity clinics and other health and wellness institutions.

[0042] Optionally, the health score is a discrete modality-specific score and / or a cumulative score corresponding to the multi-modal data in the dynamically updated knowledge base. As mentioned above, the health score may be calculated discretely for each biological modality, or by integrating information from various biological modalities, such as the blood vascular health, the genetics vascular health, the microbiome vascular health, the biometrics vascular health and the exposome vascular health, to provide an overall assessment of an individual's health, i.e., the vascular health, for example. It may be appreciated that some biological modalities may have a greater impact on health outcomes, and their discrete health scores may be given higher weights in the cumulative assessment. Optionally, generating a cumulative health score corresponding to the multi-modal data requires inputs from healthcare professionals, data scientists, and domain experts in each biological modality. Beneficially, percentile-based health scores of the biological modality allows to combine the health scores into a cumulative score which considers the contribution of different biological modalities, thus taking into account the complexity of human biology and underlying processes. Referring to the above example, it may be appreciated that different biological modalities, which are composed of different single biological modalities may differently affect the specific overall health state; i.e. vascular health may be differently affected by blood vascular health modality, genetic vascular health modality or microbiome vascular health modality etc. Thus different vascular health modalities are assigned different weights based on their discrete contribution to overall vascular health of an individual. This also allows for recommendations on improving the wellbeing of the individual to be more targeted and personalised. For example, recommendations on how to improve one's vascular health my differ if the main driver of a low score is a specific blood lipid biomarker versus a specific biometric parameter, such as V02max.

[0043] Moreover, since health scores are population normalized, the weights for determining the cumulative health scores from the discrete health scores lie between 0 and 1, and all the weights for calculating discrete health score sum up to 1. For example, the weights pertaining to the discrete health modalities contributing to a specific health score may be wl, w2 and w3 for i.e., the blood vascular health, the genetic vascular health, the microbiome vascular health, respectively. In this case, the cumulative sum of wl, w2 and w3 amounts to 1.

[0044] Optionally, the computer-implemented method further comprises refining the health score based on the supplementary data associated with the user, by employing AI / ML algorithms, to provide a comprehensive health score corresponding to at least one biological modality. In this regard, advanced analytics, machine learning, or artificial intelligence are emloyed to refine the health score to provide a comprehensive health score by identifying complex patterns and relationships within multimodal data. Optionally, the computer-implemented method combines biological data (i.e., percentile based health scores) with recommendation and performance evaluation data (i.e., data from wearables) by using advanced Al and machine learning algorithms to further refine health scores and personalized recommendations based thereon. Moreover, involvment of healthcare professionals or researchers, or domain experts as well as the supplementary data associated with the user assists in the interpretation of the cumulative health score. In an example, a blood biomarker data providing a three- month average of blood sugar (HbAlc) of 5.6 and a daily exercise and walking with a low-carb diet plan log obtained from a wearable device is usable for refining the health score corresponding to insulin hormone sensitivity in the individual. Beneficially, collaborating the biological data and the supplementary data associated with the user, along with expert opinion, such as the professionals at longevity clinics and other health and wellness institutions or sports training facilities, ensures a comprehensive health score corresponding to each biological modality, and allows for personalized health management at such facilities.

[0045] Optionally, the computer-implemented method further comprises annotating the health score and / or the comprehensive health score corresponding to each biological modality from the multi-modal data. Notably, the computer-implemented method includes receiving data from online or web-based tools that aggregate the multi-modal data from multiple sources and provide annotations and classifications to help interpret the multi-modal data. The dynamically updated knowledge base is continuously updated with the latest research findings in appropriate multiomics and or other biological modalities, to calculate health scores and / or the comprehensive health score which are based on latest scientific findings, and generate comprehensive health reports with the most up-to-date and accurate information, which offer insights to better direct heath interventions at facilities optimising health and performance, such as longevity clinics and other health and wellness institutions, sports training or other consultation services.

[0046] Furthermore, the computer-implemented method comprises generating the comprehensive health report of the user based on the health score corresponding to each biological modality from the multi-modal data. The comprehensive health report based on the health score corresponding to each biological modality from the multi-modal data briefly summarizes the overall health status and highlights key drivers (or area of focus) of the health of an individual allowing for personalized health and performance management, either via a professional user or the individual themselves. The generated comprehensive health report is provided to the user device via the user interface.

[0047] The computer-implemented method and the system according to the invention is preferably configured to provide real-time monitoring and / or configured to provide real-time recommendations to the user and / or to the professionals at longevity clinics and other health and wellness institutions.

[0048] Optionally, the computer-implemented method and the system according to the invention is preferably configured to provide real-time recommendations based on the health score and data trends, enabling personalized advice. Optionally, the computer-implemented method and the system according to the invention is preferably configured to provide an actionable insights based on the at least one biological modality, including real-time recommendations through the loT-based monitoring devices.

[0049] Optionally, the comprehensive health report comprises an actionable insights based on the at least one biological modality, including real-time recommendations through the loT-based monitoring devices.

[0050] Optionally, the computer-implemented method further comprises providing an actionable insight based on the health score and / or the comprehensive health score corresponding to each biological modality from the multi-modal data. Herein, the term "actionable insight" refers to a specific, valuable, data-driven observation or interpretation that lead to informed decision-making and guided actions, such as predicting disease outcomes, or optimizing treatment plans, ensuring maximum longevity or optimising performance. Often, the actionable insight is timebound and emphasizes the importance of relevance and timeliness in decision-making lead to positive outcomes or improvements in performance. For example, a healthcare provider may identify patterns in the multi-modal data of an individual indicating a higher likelihood of recurence of a disease within a specific timeframe which might lead to specific actions to mitigate the increased risk.

[0051] Optionally, the comprehensive health report of the user comprises: at least one biological modality and a corresponding health score and / or the comprehensive health score thereto; at least one biological modality having a corresponding health score and / or the comprehensive health score value varying from a threshold value thereof; the actionable insights based on the at least one biological modality; and personalized recommendations based on the at least one biological modality. For example, while the comprehensive health report provides a complete thyroid profile with T3, T4, TSH and thyroxine levels of an individual, they categorically identify TSH as being in abnormal levels if the recorded TSH is either above or below a range of 0.4 to 4.0 mlll / L (threshold value for TSH). Moreover, based on the TSH levels for an individual, the comprehensive health report provides actionable insights and personalized recommendations to the user. Notably, actionable insights contribute to the generation of personalized recommendations. For example, insights gained from analyzing user data may lead to the development of personalized recommendations for the users. Referring to the above example, if the recorded TSH is 2.3 mlll / L, the comprehensive health report may suggest that the individual may develop hypothyroidism in future and thus should be followed very closely by a doctor. The personalized recommendation are often based on personalized multi-modal data of the individual and aim to provide targeted guidance. Herein, personalized recommendations are provided by considering other aspects, such as age, sex, etc., and not just the biological blood data of the individual. The personalized recommendations typically include lifestyle modifications, preventive measures, and health interventions.

[0052] Additionally, the comprehensive health report comprises methods used to collect, normalize, and score data from each biological modality; weighting factors or algorithms used in the aggregation process to generate the comprehensive health score corresponding to each biological modality; references to scientific literature and sources used in the assessment, and so on.

[0053] Optionally, the computer-implemented method further comprises providing an application programming interface to the user for presenting the generated comprehensive health report in a form of at least one of: a tabular representation, a graphical representation, a textual representation. The application programming interface (API) is configured to request and exchange information or data between two or more software applications, such as the dynamically updated knowledge base and the user device. Optionally, the user device may be a smartphone device comprising a mobile application or a web-based application that employs an API to interact with a remote dynamically updated knowledge base. Such A mobile application or web-based application enables patients to easily access and track their multi-modal data and comprehensive health reports over time. For instance, a health app may use an API to fetch user health data stored in a cloud -based database.

[0054] The API allows the user to filter the comprehensive health report based on specific criteria, such as healthscore range, date, and so on. Moreover, presenting the generated comprehensive health report in a form of at least one of: a tabular representation, a graphical representation, a textual representation, allows convenient understanding of the data by the user, such as some who is not technically-sound to understand the health data. For example, tabular representations allow for comparing the heath data values across different categores. In above example, the tabular representation of TSH values of a person and a threshold value thereof makes it easier for the user to compare the current user TSH values to the threshold value thereof and ascertain the variation therebetween. An additional coloumn in such tabular representation may comprises a historical value of the user's TSH levels, which helps the user to identify if there is any improvement in their TSH levels over time as a result of following personalized recommendations, for example. Moreover, visual representation of data, such as by means of graphs, charts, plots, and so on, allows for faster and more user-friendly comprehension of data by a broader audience. For example, graphs may be used to plot blood pressure of an individual over time, to analyse an improvement therein or not over a given period of time. Furthermore, textual representations include explanations and interpretations for educating the user about health, medication usage and so on. Furthermore, a combination of such representations to cater to a broader audience with different comprehension abilities. Moreover, aforementioned ways of representing data enables customisable report templates, allowing healthcare professionals to choose specific insights and data points relevant to their patients' needs.

[0055] Moreover, the API enables providing (presenting) the comprehensive health reports to the users (patients and healthcare professionals) through a secure, user-friendly platform or format.

[0056] Optionally, the computer-implemented method further comprises displaying a digital twin of the user along with the comprehensive health report of the user. The term "digital twin" refers to a virtual model or replica of the user that is displayed on a user interface (rendered on a display of the user device). It will be appreciated that the digital twin is used to represent a virtual working of the various biological or biophysiological processes of the user based on the respective discrete levels of the biological modalities and conformations and functioning thereof. Notably, the representation of the user as the digital twin changes in accordance with the changes in the respective levels of the biological modalities and the conformations and functioning thereof. Optionally, the digital twin is generated on basis of real-time data of levels of the biological modalities and the conformations and functioning thereof. Optionally, the digital twin provides a virtual model of an individual's brain, cardiovascular, inflammation, metabolism and muscles and bones arrangement and functioning. In an example, a digital twin of the user may be used to show the inflammation of the user as something that the user needs to focus on and therefore will be brought to their attention through a heat map. The heat map may be shaped as the user's body. Optionally, the computer-implemented method includes generating and displaying a digital twin of the user alongside a personalized health insights report. The digital twin is a dynamic virtual representation of the user, presented on a user interface, such as a display or smart loT device, and is constructed using integrated multiomics data, blood biomarkers, and continuous physiological measurements obtained from smart sensors, smart mirrors, continuous glucose monitors (CGM), and other connected health monitoring technologies. Moreover, the digital twin is constructed using the health report data. The digital twin models and visualizes the user's internal biological processes in real time, adapting to changes detected across molecular, metabolic, and systemic health parameters. These changes reflect the status and functioning of key systems, including neurological, cardiovascular, inflammatory, metabolic, and musculoskeletal processes.

[0057] As biological states shift, the digital twin dynamically updates to represent these variations. For example, the digital twin can visually highlight metabolic disruptions, or other health concerns by overlaying a heat map on the user's virtual body. In addition, the system may trigger proactive notifications and visual alerts through smart loT devices such as smart mirrors, smart displays, or wearable devices. These notifications can draw the user's attention to emerging issues, prompt timely interventions, or suggest actions based on detected abnormalities, enhancing user engagement and promoting real-time health awareness.

[0058] Optionally, the computer-implemented method further comprises creating a database, and storing and safeguarding, in the database, at least one of: the multi-modal data and the comprehensive health report of the user, a health score and / or the comprehensive health score corresponding to each biological modality, a plurality of algorithms configured to calculate a health score and / or comprehensive health score corresponding to each biological modality of the user, exposome of the user, a plurality of published literature, a historical data of the user, a historical recommendation for the user.

[0059] Herein, the database is a structured collection of data that is organized (such as into tables, fields, records) and stored electronically in the system or a remote (cloud) server. Typically, the database is designed to efficiently manage, store, retrieve, and update large volumes of data. The database serves as a centralized repository for storing comprehensive and up-to-date patient information, which may be accessed by healthcare providers to get a unified view of a patient's medical history, diagnoses, medications, allergies, and treatment plans. Beneficially, the database stores the aforementioned data to be accessed by the processing arrangement for generating the comprehensive health report of the user. Moreover, the stored data may be used by the system as a future training dataset for use by machine learning and artificial intelligence tools. It will be appreciated that the plurality of algorithms may comprise discrete algorithms to be applied on different types of normalised data or based on the end application of the system, i.e., based on the complexity of the data and the medical condition.

[0060] More optionally, the algorithms includes common algorithms used, such as decision trees, random forests, support vector machines, neural networks, logistic regression, and deep learning models. Optionally, the algorithm is selected from: a defined deterministic control algorithm, a neural network, a Hidden Markov Model, a Boltzmann machine, an adaptive neural network. The algorithm may optionally be implemented as a simple software routine (for example, a predefined deterministic routine) that merely applies pre-defined logics; alternatively, the algorithm may be implemented as a sophisticated artificial-intelligence- based software suite. It will be appreciated that the algorithm is selected based on the nature of the data and the complexity of the medical condition under study. Beneficially, by adapting to the unique characteristics of each user, the at least one algorithm is able to generate more effective output for monitoring, diagnosing and addressing specific issues of the user.

[0061] Optionally, the computer-implemented method further comprises integrating the database with electronic health records. Herein, integrating the database that stores and safeguards the aforementioned data with electronic health records (EHRs) that comprises other types of medical tests and data sources, such as imaging studies or physiological measurements, provides more comprehensive health reports. Beneficially, integrating the database with the EHRs allows for seamless access and sharing of multi-modal data and comprehensive health reports among healthcare professionals and the users.

[0062] Optionally, the computer-implemented method further comprises stratifying users, for a potential research study, based on the comprehensive health report of the user. Herein, stratifying refers to categorizing participants of a potential research study into distinct groups based on relevant criteria. Optionally, the relevant criteria may include, but not limit to, a disease status (e.g., presence or absence of specific conditions), an age or demographic information, risk factors or lifestyle indicators, biomarker levels, or health scores. Such stratification segregates the participants into homogeneous groups that share certain characteristics, allowing for more targeted and meaningful analysis. Beneficially, patient stratification based on the comprehensive health report of the user during clinical trials provides better outcomes.

[0063] Optionally, the computer-implemented method further comprises generating notifications for notifying the user about at least one of: a recent addition to the dynamically updated knowledge base corresponding to the multi-modal data of the user, a health score and / or the comprehensive health score corresponding to each biological modality. Herein, the at least one change to the dynamically updated knowledge base or the health score and / or the comprehensive health score due to an update of corresponding data sources may be implemented semi-autonomously (the updation requires a user input (or feedback) or opinion of a healthcare professional, for example a healthcare professional of a longevity clinics and other health and wellness institution) or autonomously (resulting from an updation of the corresponding data sources). Optionally, the notification is implemented as at least one of: a visual notification, an audio notification, a haptic notification, a text notification. It will be appreciated that the notification is sent to the user device associated with the user, such that the user is educated health-wise and recent developments in the field. Beneficially, sending the notification in a timely manner enables a near-real time decision-making about the user's health, by timely resolution of issues in the health thereof. Beneficially, such alert notifications give time to the user or the healthcare professional to act immediately to avert issues in the health by providing timely help.

[0064] The present disclosure also relates to the system as described above. Various embodiments and variants disclosed above, with respect to the aforementioned method, apply mutatis mutandis to the system.

[0065] The term "processing arrangement" as used herein refers to a computational element that is operable to respond to and processes instructions that drive the system. Optionally, the processing arrangement includes, but is not limited to, a microprocessor, a microcontroller, a complex instruction set computing (CISC) microprocessor, a reduced instruction set (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, or any other type of processing circuit. Furthermore, the term "processing arrangement" may refer to one or more individual processors, processing devices and various elements associated with a processing device that may be shared by other processing devices. Additionally, the one or more individual processors, processing devices and elements are arranged in various architectures for responding to and processing the instructions that drive the system. In other words, the processing arrangement is a strategic organization and deployment of various servers and computing resources within a cloud infrastructure to support the operations of the system using a data communication network.

[0066] The term "data communication network" as used herein refers to means for communication between the processing arrangement and other components of the system, in order to receive and subsequently process the data related to the functioning of the system. Notably, the data communication network refers to an arrangement of interconnected, programmable and / or non-programmable components that, when in operation, facilitate data communication between one or more electronic devices and / or databases. Furthermore, the data communication network may include, but is not limited to, a peer-to-peer (P2P) network, a hybrid peer-to-peer network, local area networks (LANs), radio access networks (RANs), metropolitan area networks (MANs), wide area networks (WANs), all of or a portion of a public network such as global computer network known as the Internet®, a private network, a cellular network and any other communication system. Additionally, the data communication network employs wired or wireless communication that can be carried out via one or more known protocols.

[0067] Optionally, the system further comprises a user interface configured to receive a user input comprising the multi-modal data; and provide the generated the comprehensive health report to the user.

[0068] Optionally, the multi-modal data comprises: a biological test data selected from at least one of: blood biomarker data, gut microbiome composition and functional biomarkers data, epigenomic biomarkers data, telomeric biomarkers data, proteomic biomarkers data, lipidomic data, glycan data, biomarkers based on glycosylation patterns of the immune system, transcriptome signatures data, metabolomic biomarkers data, and a lipidomics data; and a supplementary data selected from at least one of: anthropometric measurements data, physiological phenotypes data, functional and wearable measurements data corresponding to exercise and sleep, a sensor data, a health data from a third-party source, a pre-stored biological data and a pre-stored sensor data from a third-party source.

[0069] Optionally, the multi-modal data comprises exposome data and data from loT devices.

[0070] Optionally, the processing arrangement is further configured to refine the health score based on a supplementary data associated with the user, by employing AI / ML algorithms, to provide a comprehensive health score corresponding to at least one biological modality.

[0071] Optionally, the system further comprises a database configured to store and safeguard the multi-modal data and the comprehensive health report of the user, a health score and / or the comprehensive health score corresponding to each biological modality, a plurality of algorithms configured to calculate a health score and / or comprehensive health score corresponding to each biological modality of the user, a plurality of published literature, a historical data of the user, a historical recommendation for the user.

[0072] Optionally, the system further comprises a database configured to store exposome (environmental) data of the user.

[0073] Optionally, the system further comprises an application programming interface (API) configured to integrate the database with electronic health records.

[0074] Optionally, the processing arrangement is further configured to annotate the health score and / or the comprehensive health score corresponding to each biological modality from the multi-modal data. Optionally, the processing arrangement is further configured to provide actionable insight based on the health score and / or the comprehensive health score corresponding to each biological modality from the multimodal data.

[0075] Optionally, the processing arrangement is further configured to stratify users, for a potential research study, based on the comprehensive health report of the user.

[0076] Optionally, the processing arrangement is further configured to display a digital twin of the user along with the comprehensive health report of the user.

[0077] Optionally, the processing arrangement is further configured to update the dynamically updated knowledge base at pre-defined time intervals, and wherein the dynamically updated knowledge base comprises at least one of: a plurality of published literature including scientific literature, articles, research findings, and experimental data.

[0078] Optionally, the health score is a discrete modality-specific score and / or a cumulative score corresponding to the multi-modal data in the dynamically updated knowledge base.

[0079] Optionally, the system further comprises a notification module configured to generate notifications for notifying the user about at least one of: a recent addition to the dynamically updated knowledge base corresponding to the multi-modal data of the user, a health score and / or the comprehensive health score corresponding to each biological modality.

[0080] Optionally, the system further comprises an application programming interface associated with the user input device, configured to present the generated comprehensive health report in a form of at least one of: a tabular representation, a graphical representation, a textual representation. Optionally, the comprehensive health report of the user comprises: at least one biological modality and a corresponding health score and / or the comprehensive health score thereto; at least one biological modality having a corresponding health score and / or the comprehensive health score value varying from a threshold value thereof; the actionable insights based on the at least one biological modality; and personalized recommendations based on the at least one biological modality.

[0081] The present disclosure also relates to the computer-readable storage medium as described above. Various embodiments and variants disclosed above, with respect to the aforementioned method and the aforementioned system, apply mutatis mutandis to the computer- readable storage medium.

[0082] EXPERIMENTAL PART

[0083] Personalised Disease Prevention: A 35-year-old woman underwent comprehensive multiomic testing, and the Al-driven multiomic data summary reports platform processed her data. The generated report revealed that she had an increased genetic risk for type 2 diabetes. Based on the insight, her healthcare professional recommended personalised lifestyle changes, including dietary adjustments and regular exercise, to help mitigate her risk. By implementing these changes, the woman proactively reduced her chances of developing type 2 diabetes.

[0084] Optimising Nutrition and Gut Health: A 40-year-old man experienced digestive issues and decided to undergo comprehensive multiomic testing, including microbiome testing. The Al-driven multiomic data summary reports platform analysed his data, and the report highlighted specific imbalances in his gut microbiome. Based on said information, his healthcare professional recommended personalised dietary adjustments and probiotic supplements to restore balance and improve his gut health, leading to the resolution of his digestive issues.

[0085] Monitoring Ageing and Longevity: A 60-year-old woman was interested in understanding her biological age and monitoring her ageing process. She underwent comprehensive multiomic testing, including epigenome and telomere testing. The Al-driven multiomic data summary reports platform generated a report that revealed her biological age was younger than her chronological age. The report also provided insights into her genetic predispositions and offered personalised recommendations to maintain her health and potentially slow down the ageing process, such as dietary changes, exercise, and stress management techniques.

[0086] Pharmacogenomics and Personalised Medication: A 50-year-old man with high blood pressure underwent comprehensive genomic testing to better understand his genetic makeup. The Al-driven multiomic data summary reports platform analysed his data, and revealed specific genetic variations that affected his response to certain blood pressure medications. Armed with said information, his healthcare professional prescribed a medication regimen tailored to his genetic profile, that lead to better blood pressure control and a reduced risk of complications.

[0087] Moreover, the disclosed computer-implemented method and system was applied in veterinary medicine field, agriculture field, and environmental monitoring field, and adapted for research purposes, to aide scientists in the analysis of various data to advance understanding in aforementioned fields.

[0088] In an example, for creating blood-based summaries, literature scraping was done for information regarding associations between blood biomarkers and aspects of health, covered by the (i.e., vascular health, liver health, bone health, and so on), the associations that were determined to be strong enough were included in the model. The model for scoring was built by determining the negative or positive association between a biomarker value and target outcome, then comparing the individual's biomarker values to that of a comparable (NHANES) population, which resulted in either a positive or negative contribution to the specific summary score. Weight effects to each blood biomarkersummary pair were assigned based on strength of the association according to the reviewed literature. All individual biomarker contributions were combined and the resulting blood cumulative health score is compared to the relevant population to determine the final population-based normalized health score. Where applicable, the scoring model was granulated according to sex and age.

[0089] In another example, for creating genetic summaries, for each of the aspects of health (i.e., vascular health, heart health, bone health, and so on) GWAS studies that correlated with a disease / health outcome of interest were selected. Disease entities (i.e., coronary artery disease (CAD)) were mapped to health states (i.e., vascular health) and scores for the health state were calculated as absence of risk of disease. The risk of disease / tendency towards a health outcome (i.e., better sleep) was evaluated using the polygenic risk score calculation (PGS) and normalized to 1000G phase 3 reference population. In example, for calculating mood summary score, SNPs that significantly correlated with neuroticism from a GWAS study 0 O : OOOOOOOO in a discovery cohort and in an independent replication cohort were used. Similarly, for other health states, such as bone health, general inflammation, glucose metabolism, muscle health, weight, heart health, sleep, cognition, etc., other significant SNPs were selected. In addition to using SNPs that were GWAS statistically significant, other non-GWAS SNPs, with high biological-effect plausibility (according to expert opinion), were also evaluated and if appropriate added to the health score. In yet another example, to create microbiome summaries, microbial species positively / negatively associated with each of the aspects of health (i.e., vascular health, heart health, bone health, and so on) were selected. In this regard, for example, for investigating the association between the human gut microbiome and sleep, the search query used was "human gut microbiome AND sleep". Databases such as Data repository for Gut Microbiota (GMrepo) (PMID: 34788838), etc., and research papers, meta-studies, and relevant literature (Nature, Science, FEMS Microbiology, Cell and others) were used to create a dynamically updated knowledge base. Microbial species that exhibit significant associations with the specific condition or trait of interest (e.g., sleep) were identified. Weight effects were assigned to each species based on literature review, considering corresponding LDA scores derived from various studies demonstrating associations with diseases or healthy individuals. Health scores of the species in an individual were calculated by accounting for the presence of the species in the individual, the weight pertaining to that species and the populational prevalence of the species in the GMHI population (i.e., having less than average of a species 'positively' associated with the health state was considered a negative contribution to the final health score. Health scores were normalized to the scores calculated on the GHMI population and final scores were generated in the range between 0 and 1 for each health state.

[0090] Typically, a decrease in abundance of a species in individuals with the condition of interest indicated a positive correlation with healthy individuals, which were assigned a positive weight (ranging between 0 and 1) for the health score. Conversely, if a species was found to be increased in patients, it was correlated with the disease and was assigned a negative weight (ranging between -1 and 0) for the health score. Moreover, the weights were assigned based on population-based normalisation, i.e., species demonstrating associations at the population level or with described mechanisms, weights higher than ±0.7 were assigned. Additionally, for associations derived from animal studies or laboratory conditions (e.g., cultures, bioreactors), the weight not exceeding ±0.3 were assigned. clock: In an implementation the biological age clock integrated the blood age clock, the microbiome age clock and the epigenetic age clock, wherein the relative contribution of said age clocks was 1 / 2 blood age clock, 1 / 3 epigenetic age clock and 1 / 6 microbiome age clock. These ratios were determined from the fact of how much the static results from each of the analysis (blood biomarker levels, microbiome species / genera levels, methylation of CpG islands) tend to change from the same person through time (intrapersonal change) and the biggest change can be seen in the microbiome, thus trusted the least.

[0091] For both the blood and microbiome age clocks, following steps were taken:

[0092] 1. Find entities (blood biomarkers / species / genera) that correlate with health / disease / all-cause mortality

[0093] 2. These correlations are normally found as Hazard ratio curves (depending on gender / age / ethnicity)

[0094] 3. Anchor these curves to population databases -> normalise to populational average

[0095] 4. Position the entity of the client on these curves

[0096] 5. Translation of hazard risk to years added or subtracted

[0097] 6. Add together the contributions of the various entities (the granulation also gives you actionable details to recommend and improve on).

[0098] Blood clock As detailed above, the blood age clock comprised 14 biomarkers (correlated with mortality; 1000+ papers screened (829 with Scimago (2020) IF > 5)). The 14 biomarkers included Total cholesterol, HDL, hcCRP, triglycerides, alkaline phosphatase, R.DW, TSH, albumin, vitamin D, iron, urea, WBC, haematocrit, Hbalc. The contribution of biomarkers to the blood age was determined, depending on the risk curve and the comparison to the relevant population, such as by employing NHANES (60k individuals). The blood age clock represented a Lego block system where biomarkers could be added or subtracted at will.

[0099] Microbiome clocks The microbiome age clock was calculated using two variables obtained from sequences of faecal samples. The genera- based taxonomy and the diversity of the microbial world in the gut (Shannon diversity) were used to calculate the microbiome age clock.

[0100] The Shannon diversity risk ratio published in the 2021 study by Salosensaari et. al (PMID: 33976176) was used, which used a Finnish population cohort (n=7211), to find that some microbiome characteristics were associated with mortality risk during a 15-year follow-up period (including diversity scores). The beta value from this study was used to calculate the risk ratio.

[0101] In contrast, the Gut Microbiome Health Index was published by Gupta et al. (PMID: 32934239) in 2020. They collected data, published by 34 different scientific articles and 4347 stool metagenomes. In this study, they also published a table of species found in healthy and unhealthy samples (corresponding to the 12 different diseases studied in different articles). Based on the prevalence published in this study, the natural logarithm of the risk ratios (LN_RR) for 17 different genera and 50 different species was calculated. Population statistics were performed for the genera and species present in all 4347 faecal metagenomes. Population prevalence of every genus / species multiplied by corresponding LN_RR was subtracted from the individual's product of LN_RR and that individual's genus or species prevalence and converted to added or subtracted years for a particular individual.

[0102] Based on the calculated Shannon Diversity risk ratios and the 17 different genera present in healthy and non-healthy individuals, these were converted into added or subtracted years based on the work published by Tsai et al. in 2021 (PMID: 34491905). The years resulting from the transformation of the risk ratios of the diversity scores and the presence of 17 different genera were summed and subtracted from the chronological age (if the sum of genera-based or species-based and diversity years was negative) or added to the chronological age (if the sum of genera-based or species-based and diversity years was positive).

[0103] DETAILED DESCRIPTION OF THE DRAWINGS

[0104] Referring to FIG. 1, illustrated is a computer-implemented method for generating a comprehensive health report of a user, in accordance with an embodiment of the present disclosure. At step 102, multi-modal data related to at least one biological modality of the user is obtained. At step 104, a dynamically updated knowledge base associated with the obtained multi-modal data from the user is created. At step 106, a health score corresponding to each biological modality, from amongst the at least one biological modality, of the multi-modal data in the dynamically updated knowledge base is calculated. At step 108, the comprehensive health report of the user is generated based on the health score corresponding to each biological modality from the multi-modal data.

[0105] Referring to FIG. 2, illustrated is a system 200 for generating a comprehensive health report of a user 202, in accordance with an embodiment of the present disclosure. The system 200 comprises a processing arrangement 204 configured for obtaining multi-modal data related to at least one biological modality of the user; creating a dynamically updated knowledge base associated with the obtained multimodal data from the user; calculating a health score corresponding to each biological modality, from amongst the at least one biological modality, of the multi-modal data in the dynamically updated knowledge base; and generating the comprehensive health report of the user based on the health score corresponding to each biological modality from the multi-modal data.

[0106] As shown, the system 200 further comprises a user interface 206 configured to receive a user input comprising the multi-modal data; and provide the generated the comprehensive health report to the user 202. Moreover, the system 200 further comprises a database 208 configured to store and safeguard the multi-modal data and the comprehensive health report of the user, a health score and / or the comprehensive health score, a plurality of algorithms, a plurality of published literature, a historical data, a historical recommendation. Furthermore, the system 200 further comprises an application programming interface (API) 210A, namely a first API, configured to integrate the database 208 with electronic health records 212; and presenting, to the user 202, the generated comprehensive health report. Furthermore, the system 200 further comprises an application programming interface (API) 210B, namely a second API, associated with a user input device 214, configured to present the generated comprehensive health to the user 202. Moreover, the processing arrangement 204 is further configured to display a digital twin 216 of the user 202 along with the comprehensive health report of the user 202.

[0107] The system 200 further comprises a notification module 218 configured to generate notifications for notifying the user 202 about at least one of: a recent addition to the dynamically updated knowledge base corresponding to the multi-modal data of the user 202, a health score and / or the comprehensive health score corresponding to each biological modality.

Claims

CLAIMS1. A computer-implemented method for generating a comprehensive health report of a user, the computer-implemented method comprising: obtaining multi-modal data related to at least one biological modality of the user; creating a dynamically updated knowledge base associated with the obtained multi-modal data from the user; calculating a health score corresponding to each biological modality, from amongst the at least one biological modality, from the multi-modal data in the dynamically updated knowledge base; and generating the comprehensive health report of the user based on the health score corresponding to each biological modality from the multimodal data.

2. A computer-implemented method of claim 1, wherein the multimodal data comprises: a biological test data selected from at least one of: blood biomarker data, gut microbiome composition and functional biomarkers data, epigenomic biomarkers data, telomeric biomarkers data, proteomic biomarkers data, data pertaining to skin health, lipidomic data, glycan data, biomarkers based on glycosylation patterns of the immune system, transcriptome signatures data, and metabolomic biomarkers data; and a supplementary data selected from at least one of: anthropometric measurements data, physiological phenotypes data, functional and wearable measurements data corresponding to exercise and sleep, a sensor data pertaining to a specific health entity, a health data from a third-party source, a pre-stored biological data and a pre-stored sensor data pertaining to a specific health entity from a third-party source.

3. A computer-implemented method of claim 1 or 2, further comprising updating the dynamically updated knowledge base, by using artificial intelligence / machine learning tools, at pre-defined timeintervals, wherein the dynamically updated knowledge base comprises at least one of: a plurality of published literature including scientific literature, articles, research findings, and experimental data, and data obtained from longevity clinics and other health and wellness institutions.

4. A computer-implemented method of any of preceding claims, wherein the health score is a discrete modality-specific score and / or a cumulative score corresponding to the multi-modal data in the dynamically updated knowledge base.

5. A computer-implemented method of claim 2, further comprising refining the health score based on the supplementary data associated with the user, by employing AI / ML algorithms, to provide a comprehensive health score corresponding to at least one biological modality.

6. A computer-implemented method of claim 5, further comprising creating a database, and storing and safeguarding, in the database, at least one of: the multi-modal data and the comprehensive health report of the user, a health score and / or the comprehensive health score corresponding to each biological modality, a plurality of algorithms configured to calculate a health score and / or comprehensive health score corresponding to each biological modality of the user, a plurality of published literature, a historical data of the user, a historical recommendation for the user.

7. A computer-implemented method of any of claims 5 or 6, further comprising providing an actionable insight based on the health score and / or the comprehensive health score corresponding to each biological modality from the multi-modal data.

8. A computer-implemented method of any of preceding claims, further comprising annotating the health score and / or the comprehensive health score corresponding to each biological modality from the multimodal data.

9. A computer-implemented method of claim 6, further comprising integrating the database with electronic health records, and / or other data from longevity clinics and other health and wellness institutions.

10. A computer-implemented method of any of preceding claims further comprising incorporating data from Internet of Things based devices, preferably for continuous and / or real-time health monitoring.

11. A computer-implemented method of any of preceding claims, further comprising providing an application programming interface to the user for presenting the generated comprehensive health report in a form of at least one of: a tabular representation, a graphical representation, a textual representation.

12. A computer-implemented method of any of preceding claims, wherein the comprehensive health report of the user comprises: at least one biological modality and a corresponding health score and / or the comprehensive health score thereto; at least one biological modality having a corresponding health score and / or the comprehensive health score value varying from a threshold value thereof; the actionable insights based on the at least one biological modality; and personalized recommendations based on the at least one biological modality.

13. A computer-implemented method of any of preceding claims comprises providing an actionable insights based on the at least one biological modality, including real-time recommendations and / or recommendations through the loT-based devices.

14. A computer-implemented method of any of preceding claims, further comprising stratifying users, for a potential research study, based on the comprehensive health report of the user.

15. A computer-implemented method of any of preceding claims, further comprising displaying a digital twin of the user.

16. A computer-implemented method of any of claim 15, wherein the digital twin of the user may be integrated into longevity clinics and other health and wellness institutions for enhanced monitoring and personalized health recommendations.

17. A computer-implemented method of any of claims 15-16, further comprising involving real-time recommendations, allowing for dynamic updates to the digital twin as a new health data becomes available.

18. A computer-implemented method of any of claims 6-17, further comprising generating notifications for notifying the user about at least one of: a recent addition to the dynamically updated knowledge base corresponding to the multi-modal data of the user, a health score and / or the comprehensive health score corresponding to each biological modality.

19. A system for generating a comprehensive health report of a user, the system comprising a processing arrangement configured for: obtaining multi-modal data related to at least one biological modality of the user; creating a dynamically updated knowledge base associated with the obtained multi-modal data from the user; calculating a health score corresponding to each biological modality, from amongst the at least one biological modality, from the multi-modal data in the dynamically updated knowledge base; and generating the comprehensive health report of the user based on the health score corresponding to each biological modality from the multimodal data.

20. A system of claim 19, further comprising integrating real-time data from loT devices to provide actionable insights.

21. A system of claim 19 -20, further comprising providing real-time recommendations based on the health score and data trends, enabling personalized advice.

22. A system of claim 19-21, further comprising a user interface configured to receive a user input comprising the multi-modal data; and provide the generated the comprehensive health report.

23. A system of claim 22, wherein the user interface is further configured to providing real-time recommendations to the user and / or longevity clinics and other health and wellness institutions practitioner.

24. A system of claim 19 -23, wherein the multi-modal data comprises: a biological test data selected from at least one of: blood biomarker data, gut microbiome composition and functional biomarkers data, epigenomic biomarkers data, telomeric biomarkers data, proteomic biomarkers data, data pertaining to skin health, lipidomic data, glycan data, biomarkers based on glycosylation patterns of the immune system, transcriptome signatures data, and metabolomic biomarkers data; and a supplementary data selected from at least one of: anthropometric measurements data, physiological phenotypes data, functional and wearable measurements data corresponding to exercise and sleep, a sensor data pertaining to a specific health entity, a health data from a third-party source, a pre-stored biological data and a pre-stored sensor data pertaining to a specific health entity from a third-party source; realtime data collected form loT devices enabling continuous monitoring, with actionable recommendations for personalized optimization.

25. A system of claim 19 to 24, wherein the processing arrangement is further configured to refine the health score based on a supplementary data associated with the user, by employing AI / ML algorithms, to provide a comprehensive health score corresponding to at least one biological modality, and to integrate data from longevity clinics and other health and wellness institutions.

26. A system of any of claims 19-25, further comprising a database configured to store and safeguard the multi-modal data and the comprehensive health report of the user, a health score and / or the comprehensive health score corresponding to each biological modality, a plurality of algorithms configured to calculate a health score and / or comprehensive health score corresponding to each biological modality of the user, a plurality of published literature, a historical data of the user, a historical recommendation for the user.

27. A system of any of claims 19-26, further comprising an application programming interface (API) configured to integrate the database with electronic health records, longevity clinics and other health and wellness institutions, and loT-enabled devices to provide real-time recommendations.

28. A system of any of claims 25-27, wherein the processing arrangement is further configured to annotate the health score and / or the comprehensive health score corresponding to each biological modality from the multi-modal data.

29. A system of any of claims 25-28, wherein the processing arrangement is further configured to provide actionable insight based on the health score and / or the comprehensive health score corresponding to each biological modality from the multi-modal data.

30. A system of claims 19-29, wherein the processing arrangement is further configured to stratify users, for a potential research study, based on the comprehensive health report of the user.

31. A system of claims 19-30, wherein the processing arrangement is further configured to display a digital twin of the user along with the comprehensive health report of the user.

32. A system of claim 19-31, wherein the processing arrangement is further configured to update the dynamically updated knowledge base at pre-defined time intervals, and wherein the dynamically updated knowledge base comprises at least one of: a plurality of published literature including scientific literature, articles, research findings, and experimental data, and information from longevity and clinics and other health and wellness institutions, integrating data from real-time monitoring through loT devices, allowing for real-time recommendations based on the most current findings and health metrics.

33. A system of any of claims 25-32, wherein the health score is a discrete modality-specific score and / or a cumulative score corresponding to the multi-modal data in the dynamically updated knowledge base.

34. A system of any of claims 25-33, further comprising a notification module configured to generate notifications for notifying the user about at least one of: a recent addition to the dynamically updated knowledge base corresponding to the multi-modal data of the user, a health score and / or the comprehensive health score corresponding to each biological modality, real-time recommendations based on the user's health data, and health insights from longevity clinics and other health and wellness institutions.

35. A system of any of claims 19-34, further comprising an application programming interface associated with the user input device, configured to present the generated comprehensive health report in a form of at least one of: a tabular representation, a graphical representation, a textual representation.

36. A system of any of claims 25-35, wherein the comprehensive health report of the user comprises:at least one biological modality and a corresponding health score and / or the comprehensive health score thereto; at least one biological modality having a corresponding health score and / or the comprehensive health score value varying from a threshold value thereof; the actionable insights based on the at least one biological modality; and personalized recommendations based on the at least one biological modality.

37. A computer-readable storage medium comprising instructions for generating a comprehensive health report of a user, which when executed by a processing arrangement, cause the processing arrangement to execute steps of a computer-implemented method of any of claims 1-18.

Images