DESC:Priority Claim:

[0001] This application claims priority from the provisional application numbered 202221071857 filed with Indian Patent Office, Chennai on 13th December 2022 entitled “A system to determine the prognosis based on climate change and method thereof”, the entirety of which is expressly incorporated herein by reference.
PREAMBLE TO THE DESCRIPTION:
[0002] The following specification describes the invention and the manner in which it is to be performed:

DESCRIPTION OF THE INVENTION
Technical field of the invention
[0003] The present invention generally relates to a system and a method for disease prognosis and more particularly to a system and method for detecting the impact of climate change to determine the prognosis.
Background of the invention
[0004] The climate change has a global effect on the environment, and on human health as change in the weather is caused due to increase in the amount of greenhouse gases such as carbon dioxide, methane and nitrous oxide, causing the average temperature of the earth to rise. The increased amount of greenhouse gases traps the heat in the atmosphere, thus raising air and sea temperatures. The effects of climate change are causing environmental destruction at many levels and thus endangering life and causing ecosystem damage. Human activities are contributing to climate changes and might lead to catastrophic consequences in future, if not addressed on time. Further, climate change also poses greater risks to bio-diversity ecosystems, life-support functions, and affects health and wellbeing of mankind in many ways.
[0005] The effects of climate change vary on each individual as some individuals are more vulnerable, such as children. Children are more susceptible to heat stress and dehydration as their immune systems are not fully developed, putting them at increased risk of infections. Further, pregnant women are at increased risk of heat stress during heatwaves due to the physiological demands of pregnancy. Old age individuals and individuals with pre-existing medical conditions are more prone to dehydration, heat stress, infections and exacerbation of heart and lung disease.
[0006] The information about the health effects, precautions and remedies are available to public in several public domains and also through healthcare practitioners. Further, extensive research is being conducted in the field of climate change in order to determine its impact on human health. However, from all the available information and research data, it is clear that there are no unified platform/systems are available to connect and correlate the impact of the multitude of symptoms to a particular disease, and multiple diseases to particular symptoms and take into account the weather conditions prevailing around an individual in a particular location at a given time based on the personal health score of an individual user so as to provide actionable prognosis to the user.
[0007] Further, there are several informative websites available on the internet facilitate disease prediction based on symptoms and facilitate weather condition prediction at a particular location and provide predictions up to week or fortnight in advance. Further, there is plenty of research data providing useful information related to climate change and healthcare, but they do not provide the verifiable data on the efficacy of guidance from these such websites. Further, there is no information available related to the verified impact and measurable impact of the guidance provided in the websites on the users. The informative websites do not offer any tools for tracking and monitoring of the positive impact of the actions taken by the users on their health, or lifestyle or the climate per se. There are no systems available to provide a holistic positive impact on the users based on the information and human activity. Additionally, there are no systems available to make a cohesive and meaningful sense of all available information, thus the existing information does not lead to a substantial impact on a multitude of connected yet disparate systems.
[0008] The Patent Application No. US11227690B1 entitled “Machine learning prediction of therapy response” discloses a method comprising: receiving, for each of a plurality of subjects, each having a specified type of cardiovascular or cardiometabolic disease and receiving at least one specified therapy from a set of therapies for treating cardiovascular and cardiometabolic diseases, a first score representing a first genetic predisposition in said subject to respond to one or more of said set of therapies; at a training stage, training a machine learning model on a training set comprising: (i) all of said first scores, and labels associated with a response in each of said subjects to said at least one specified therapy; and at an inference stage, apply said trained machine learning model to a target said first score received with respect to a target subject, to predict a response in said target subject to at least one of said therapies in said set.
[0009] The Patent Application No. WO2022130006A1 entitled “A prognosis and early diagnosis method and system and choosing the best treatment based on data fusion and information analysis by artificial intelligence, with the ability to modify and improve information and results according to machine learning” discloses a diagnosis and early prognosis method and system and choosing the best treatment based on data fusion and information analysis by artificial intelligence, with the ability to modify and improve information and results according to machine learning is a method and mechanism for early prognosis, diagnosis and treatment of diseases, which includes a computer with the ability to process information with high volume and speed as a central server or a small microchip to convert and match the input information by pre-designed compilers. The server connected to the target community's data base manually or online can enter the information related to the previous generations as well as the date of birth and death of individuals. According to the artificial intelligence analyzer system and the changes made in the estimation and diagnosis databases and algorithms, this invention can submit message through IoT devices.
[0010] The Patent Application No. WO2020102223A2 entitled “Intelligent health monitoring” discloses a health assessment and diagnosis system implemented in an artificial intelligence (AI) system. In an embodiment, a method comprises: capturing, using one or more sensors of a device, signals including information about a user's symptoms; using one or more processors of the device to: collect other data correlative of symptoms experienced by the user; and implement pre-trained data driven methods to: determine one or more symptoms of the user; determine a disease or disease state of the user based on the determined one or more symptoms; determine a medication effectiveness in suppressing at least one determined symptom or improving the determined disease state of the user; and present, using an output device, one or more evidence for at least one of the determined symptoms, the disease, disease state, or an indication of the medication effectiveness for the user.
[0011] The Patent Application No. US10699813B2 entitled “Estimating impact of property on individual health—virtual inspection” discloses a method for facilitating virtual inspection of a property area, wherein the method comprises acquiring property data associated with a property area from a data source, and identifying an area of interest of the property area based on the property data acquired. The area of interest identified represents a potential area of the property area that may negatively impact health of a user. The method further comprises providing the user an instruction for capturing image data relating to the area of interest identified, receiving the image data from the user, and extracting a first property attribute data from the image data, wherein the first property attribute data extracted is used to determine presence or movement of a first pollutant data within the property area.
[0012] In consideration of the hitherto prior arts, there is need for a unified platform or system for detecting the impact of climate change on health of a user and to provide an actionable prognosis.
Summary of the Invention
[0013] The present invention addresses the limitations of the prior art by introducing a novel health prognosis system designed for real-time analysis and user-centric prognosis. Supported by a comprehensive library of datasets, the system intricately analyses diverse aspects affecting a user's health. The analysis and prognosis unit correlates user inputs, including health parameters and symptoms, with the dataset. This correlation enables precise determinations of health prognoses customized to individual users. The recommendation unit then harnesses these prognoses to provide actionable suggestions, shaping a user-centric approach to healthcare.
[0014] The method employed by the system involves a matching and differencing process. The system matches two or more databases based on their n:n matching characteristics, creating a comparable factual outcome. By conducting a comparison that excludes the impact of specific data ranges and emphasizes relevant data aligned with goals. This matching-differencing approach, supported by observable and unobservable result filtering, strengthens the system against individual weaknesses. It also facilitates real-time updates to the dataset, ensuring the system stays dynamically aligned with decision outputs from the analysis and prognosis engine.
[0015] Furthermore, the system's recommendation unit offers value-added services, presenting information related to medicines, diseases, and symptoms in various formats such as documents, audio, and video.
[0016] Beyond traditional healthcare, it extends its reach to social events or campaigns, promoting user participation for a positive impact on society and the environment. In essence, the present invention goes beyond conventional health prognostication, embracing a holistic and user-centric approach to well-being.
Brief description of the drawings
[0017] The foregoing and other features of embodiments will become more apparent from the following detailed description of embodiments when read in conjunction with the accompanying drawings. In the drawings, like reference numerals refer to like elements.
[0018] FIG 1 illustrates the schematic representation of the system to detect the impact of climate change and various factors to determine the prognosis.
[0019] FIG 2 illustrates the schematic representation of the components of the library of dataset.
[0020] FIG 3 illustrates the schematic representation of the analysis and prognosis unit.
[0021] FIG 4 illustrates the schematic representation of the recommendation unit.
[0022] FIG 5 illustrates the schematic representation logical view of the internal working mechanism of analysis and prognosis unit forming the basis for machine learning engine for generating user centric recommendations.
Detailed description of the invention:
[0023] Reference will now be made in detail to the description of the present subject matter, one or more examples of which are shown in figures. Each example is provided to explain the subject matter and not a limitation. Various changes and modifications obvious to one skilled in the art to which the invention pertains are deemed to be within the spirit, scope and contemplation of the invention.
[0024] In the context of this invention, the general term (s) and their definitions are as follows:
[0025] n: n matching: This is a method of matching in which control and treatment subjects are randomly ordered but the first n treatments are matched to n control subjects with the closest propensity score.
[0026] The present invention discloses a system to determine the impact of climate change and various factors on health of a user, wherein the system determines the prognosis based on the inputs provided by the user.
[0027] FIG 1 illustrates the schematic representation of the system to detect the impact of climate change and various factors to determine the prognosis, wherein the system (100) comprises of a library of dataset (101) for analysis, wherein the library of dataset (101) facilitates user profile-based analysis. The library of datasets (101) further comprises symptom data unit, probable disease data unit, weather impact unit and demographic data unit. The system (100) further comprises an analysis and prognosis unit (102) to provide the prognosis based on the input provided by the user. The system (100) comprises a recommendation unit to provide user centric recommendations based on the list of suggestions provided to the user. The system (100) provides suggestions related to the probable health conditions of the user based on the choice of therapeutic area. The analysis and prognosis unit (102) uses the data from the library of dataset (101) to analyze the user input and determine the prognosis, wherein the recommendation unit (103) uses the prognosis provided by the analysis and prognosis unit (102) to provide user centric recommendations based on the prognosis.
[0028] The library of dataset (101) for analysis includes dynamically enriching data pertaining to various aspects that affects the health of the user. The library of dataset (101) contains data including but not limited to diseases and a list of symptoms for each disease, a map with correlation of each symptom with multiple diseases and a map with correlation of diseases to multiple symptoms. Additionally, the library of dataset (101) comprises the data related to user profile, wherein the user profile data is stored in an encrypted form, symptom-disease data of at least one user, disease-weather data, water and sanitation data and personal health status of the user at a given point in time.
[0029] Further, the analysis and prognosis unit (102) facilitate user centric prognosis using at least one input received from the user. According to an embodiment of the invention, the user input may include but not limited to mandatory inputs such as user name, email address, gender, date of birth, blood group, personal medical history details, food allergy, drug allergy, type of medicine viz. allopathy, homeopathy, ayurveda, unani etc. The inputs provided by the user are recorded and saved in the server as user profile data, wherein the system (100) masks the Personal Identity (PII), health information (PHI) conforming to the regulatory requirements during saving the user profile data in the server. The user input data is correlated with the data in the database including diseases, symptoms, weather, water, sanitation, user health score in order to determine the prognosis.
[0030] According to an embodiment of the invention, the analysis and prognosis unit (102) is configured with a machine-based computer algorithm (104) for analyzing the user profile-based data, wherein the machine-based computer algorithm (104) facilitates user centric prognosis. The machine-based computer algorithm (104) may use the machine-learning model, wherein the machine-learning model facilitates machine-training for determining a matching pair for every element of the machine-learning model between two or more databases.
[0031] According to an embodiment of the invention, the system (100) uses a method to obtain an estimate of the impact of weather on health of the user through matching and differencing process, wherein the system (100) matches two or more databases based on their n:n matching characteristics in order to create a comparable factual outcome. Further, the system (100) facilitates comparison between the two or more databases in order to determine the differences over ranges of data by excluding the impact of certain ranges of data and focusing only on the relevant data which is aligned to the goals. Through the combination of the matching and differencing approach, the matching-differencing estimator, offsets the individual weaknesses and mitigates selection on observable and unobservable results impacting a user. According to an embodiment of the invention, the method uses matching and differencing of plurality of databases and filters the observable and unobservable results, wherein the observable and unobservable results facilitate controlling of the system (100).
[0032] The system (100) comprises the recommendation unit (103) to provide user centric recommendations, wherein the recommendation unit (103) comprises a dataset, wherein the dataset comprises an external and internal library with information including but not limited to list of healthcare providers, devices, medicines, insurance options, health plans, coupons, offerings, location-based climate impacting key events, health-related travel options, social contribution events and participation opportunities, and health-related lifestyle impacting knowledge resources. The external and internal library further comprises several sub-libraries of datasets, wherein the recommendation unit (103) provides data on user centric recommendations including hospitals, doctors, diagnostic centers etc.
[0033] Further, the recommendation unit (103) provides user centric recommendations based on the list of suggestions provided to the user in order to determine a variety of options for facilitating communication between plurality of users in a community. According to an embodiment of the invention, the system (100) facilitates connecting the user to a community of users wherein they can share their experiences or the user may be directed to a suggested marketplace from which the user may obtain at least one medical service or purchase medicines or other products.
[0034] According to an embodiment of the invention, the recommendation unit (103) also includes value added services such as information related to medicines, diseases or symptoms in various formats such as documents, audio, and video format for the user’s better understanding and general awareness. Additionally, based on the preferred choice of user, the recommendation unit (103) also provides information pertaining to social events or campaigns, where in user can participate in their chosen social events or campaigns and make difference to the society and environment, thereby providing the user an opportunity towards making positive contribution for a better society, healthy environment and making a positive impact on climate change.
[0035] Further, according to an embodiment of the invention, the recommendation unit (103) provides a prompt to the user to visit the healthcare practitioner or the list of healthcare practitioners in the vicinity, based on the prognosis and the user’s choice of therapeutic area, in case the user is experiencing any medical condition. The recommendation unit (103) further includes a feature through which the user can book his selected appointment and receive a confirmation for the same, according to an embodiment of the invention.
[0036] According to an embodiment of the invention, the system (100) uses a method to obtain an estimate of the impact of weather on health of the user through matching and differencing process, wherein the system (100) matches two or more databases based on their n:n matching characteristics in order to create a comparable factual outcome. Further, the system (100) facilitates comparison between the two or more databases in order to determine the differences over ranges of data by excluding the impact of certain ranges of data and focusing only on the relevant data which is aligned to the goals. Through the combination of the matching and differencing approach, the matching-differencing estimator, offsets the individual weaknesses and mitigates selection on observable and unobservable results impacting a user. According to an embodiment of the invention, the method uses matching and differencing of plurality of databases and filters the observable and unobservable results, wherein the observable and unobservable results facilitate controlling of the system (100). Further, the matching process facilitates real-time updating of the library of data set based on the decision output from the analysis and prognosis engine.
[0037] For example, consider the analysis and prognosis engine (102) enabling access to at least one library of dataset (101) for analysis and facilitates identification of the disease, wherein the disease may be associated with at least one symptom and the symptom may be associated with multiple diseases. Consider n:n mapping is done from drugs-symptoms-disease dataset (101a) from the library and a range of weather conditions are mapped with a disease from the weather and disease dataset(101b), water sanitation dataset (101g) from the library. Therefore, given a situation it is determined that any change in weather conditions including water sanitation has some effect on the user’s health. Further, the system (100) facilitates calculation of the personal health profile score of the user and storing the data as dynamic numerical value based on which the analysis and prognosis engine (102) identifies a probable set of symptoms that the user may develop. The data of the probable set of symptoms are stored against the referenced user, and in the case where the user enters the symptoms, the system matches the reported symptoms of the user with the disease associated with the symptoms and enables differentiating the probable list of diseases based on the inputs provided. The analysis and prognosis engine (102) also facilitates mapping the weather conditions and water sanitation conditions prevailing in the current location of the user and matches the weather and water sanitation conditions with the diseases associated and thus mapping the same to the personal health profile score of the user in order to determine the prognosis.
[0038] FIG 2 illustrates the schematic representation of the components of the library of datasets (101), wherein the libraries of datasets (101) for analysis further comprises the key sets of libraries including the library containing drug symptom disease data (101a), geo-weather and key weather impact related data (101d), water sanitation and water resources data (101g), user demographic data with current and historical data (101j) and externally sourced user demographic data with current and historical data (101m). The library containing drug symptom disease data (101a) contains at least one sub-libraries of data sets including but not limited to libraries with external set of data (101b) and libraries with internal set of data (101c). The library of geo-weather and key weather impact related data (101d) further comprises at least one sub-libraries of data set including but not limited to libraries with real-time external set of data (101e) and libraries with internal set of data (101f). The library of water sanitation and water resources data (101g) further comprises at least one sub-libraries of data set including but not limited to libraries with real-time external set of data (101h) and libraries with internal set of data (101i). The library of user demographic data with current and historical data (101j) further comprises at least one sub-libraries of datasets including but not limited to a user input based external set of data (101k) and historical user data with internal of data (101l). The library of externally sourced user demographic data with current and historical data (101m) further comprises at least one sub-libraries of datasets including but not limited to a user input based external set of data (101n) and historical user data with internal of data (101o).
[0039] According to an embodiment of the invention, the library containing drug, symptom, disease data (101a) further includes libraries with external set of data (101b), wherein the library with external set of data (101b) further comprises at least one dataset including drug list, adverse event list, drug-drug interaction list, food-drug interaction list, epidemic data and custom list. Further, the library containing geo-weather and key weather impact related data (101d) includes library with external set of data (101e) containing data related to weather, humidity, Air Quality Index (AQI), key impact events and custom list data. Further, the library containing water sanitation and water resources data (101g) includes library with external set of data (101h) containing data related to water sanitation, water resources, water locations, water quality, impact events and custom list data. The library of user demographic data including current and historical data (101j) includes a user input based external set of data (101k) containing information such as demographic data, disease history, symptoms, allergies and family medical conditions. The library of externally sourced user demographic data including current and historical data (101m) includes auto input data sourced from external set of data (101n) containing appropriate and adequate user centric information gather through OCR technique, connected devices, IOT devices and by interfacing with external systems.
[0040] FIG 3 illustrates the schematic representation of the method of determination of prognosis through the analysis and prognosis unit (102), wherein the analysis and prognosis unit (102) accesses the pool of libraries of dataset (101) for analysis including at least one keysets of libraries such as the library of drug symptom disease data (101a), wherein the library of drug symptom disease data (101a) is updated in real-time through cloud (102a). Subsequently, the geo-weather and key weather impact related data (101d) is also updated in real-time through cloud (102b). Additionally, the water sanitation and water resources data (101g) are also updated in real-time through cloud (102c).
[0041] The data from the library of drug symptom disease data (101a), geo-weather and key weather impact related data (101d), water sanitation and water resources data (101g) and the user demographic data containing current and historical data (101j) in conjunction with externally sourced user demographic data including current and historical data (101m) is used by the analysis and prognosis unit (102) for profiling and analyzing the data (102d), wherein the probable set of symptoms that the user may develop are identified from the library of drug symptom disease data (101a) and the reported symptoms are matched with the information in the library containing user demographic data unit with current and historical data (101j) in conjunction with externally sourced user demographic data including current and historical data (101m). Further, the probable list of diseases based on the provided inputs is differentiated and the differentiated data is mapped with the data geo-weather and key weather impact related data (101d) and water sanitation and water resources data (101g) prevailing in the current location of the user. The obtained output is matched with the diseases associated with data from the library containing drugs, symptoms and disease data (101a), wherein the output data is mapped to the personal health profile score of the user in the user demographic data unit containing current and historical data (101j) in conjunction with externally sourced user demographic data including current and historical data (101m) to determine the prognosis results (102e). The prognosis results (102e) may further include a list of user suggestions, which is provided to the user through recommendation unit (103), wherein the list of suggestions is filtered at the instant of accessing post a step called enrichment (102i) a decision process which takes into account a multitude of factors such as user selection on the system of medicine (102f), guidance based on generative artificial intelligence (102g) and historical data (102h) to provide a list of user specific Inferences (102j).
[0042] FIG 4 illustrates the schematic representation of the recommendation unit (103), wherein the recommendation unit (103) comprises a library containing keysets of libraries such as a library of list of doctors (103a), a library of list of insurance options (103b), a library of list of health plans (103c), a library of list of devices, medicines, coupons, offerings (103d), a library of list of location based climate impacting key events (103e), a library of list of location based health related travel options (103f), a library of list of location based social contribution events and participation opportunities (103g), a library of list of location based health related lifestyle impacting knowledge resources (103h), wherein each keyset of libraries further include libraries with external set of data and libraries with internal set of data.
[0043] FIG 5 illustrates yet another visual representation of the analysis and prognosis unit (102), showing the internal workings of the machine learning based user centric recommendations engine (104) is to provide a recommendation (102k) when a user input queries (102a) are made to the system leading to identification of symptoms (101c) and matching of relevant disease models (101c) from the dataset which has been made available in disease-symptom dataset (101a). Through application of a series of regression analysis the system provides its first interim output in the form of Prognosis (102e). The Prognosis (102e) output then undergoes a process of enrichment (102i) a decision process which takes into account a multitude of factors such as user selection on the system of medicine (102f), guidance based on generative artificial intelligence (102g) and historical data (102h) to provide a list of user specific Inferences (102j). By considering the Inferences (102j), the machine learning based user centric recommendations engine (104), then provides a list of user centric recommendations (102k).
[0044] Over a period, the machine learning based user centric recommendations engine (104), captures the user's symptoms and uses these, as well as prior data assets, to forecast the condition, in doing so the algorithms are taught how to make predictions or perform a task using training assets incrementally leading to improvement in the accuracy of the models thus helping in better customer aligned recommendations. The interpretation and advice in the form of user centric recommendations (102k) is presented to the users thru’ man-machine interface in the form of icons, graphs and text in the human readable language. Additional data input and interaction capabilities are also provided to the user to help train the model according to the personal situation, including activity level, surrounding information, body characteristics, eating habits, outdoor situation and geographical location.
[0045] According to an embodiment of the invention, the library of list of doctors (103a) further comprises sub-libraries of dataset including the libraries with the external set of data (103aa) and libraries with internal set of data (103ab), wherein the external set of data (103aa) further comprises dynamically increasing list of libraries of data with a general list of doctors as per system of medicine (103ac) and the libraries with internal set of data (103ab) further comprises dynamically increasing list of libraries of data with a custom list as per system of medicine (103ad).
[0046] According to an embodiment of the invention, the library of list of insurance options (103b) further comprises sub-libraries of dataset including a library with external set of data (103ba) and a library with internal set of data (103bb), wherein the sub-library (103ba) further comprises dynamically increasing list of libraries of data with a general list of insurance options (103bc). The sub-library (103bb) further comprises dynamically increasing list of libraries of data with a custom list of insurance options (103bd). Further, the library of list of health plans (103c) comprises sub-libraries of dataset including a library with external set of data (103ca) and a libraries with internal set of data (103cb), wherein the sub-library (103ca) further comprises a dynamically increasing list of libraries of data with a general list library of list of health plans (103cc) and the sub-library (103cb) further comprises dynamically increasing list of libraries of data with a custom list library of list of health plans (103cd), according to an embodiment of the invention.
[0047] Further, the library of list of devices, medicines, coupons, offerings (103d) comprise sub-libraries of dataset including a library with external set of data (103da) and a library with internal set of data (103db), wherein the sub-library (103da) further comprises dynamically increasing list of libraries of data with a general list of devices, medicines, coupons, offerings (103dc) and the sub-library (103db) further comprises dynamically increasing list of libraries of data with currently showing library of list of devices, medicines, coupons, offerings (103dd). The library of list of location based climate impacting key events (103e) comprises sub-libraries of dataset including a library with external set of data (103ea) and a library with internal set of data (103eb), wherein the sub-library (103ea) further comprises dynamically increasing list of libraries of data with a list of location based climate impacting key events (103ec) and the sub-library (103eb) further comprises dynamically increasing list of libraries of data with a custom list of location based climate impacting key events (103ed), according to an embodiment of the invention.
[0048] The library of list of location-based health related travel options (103f) comprises sub-libraries of dataset including libraries with external set of data (103fa) and libraries with internal set of data (103fb), wherein the sub-library (103fa) further comprises dynamically increasing list of libraries of data with a general list of location based health related travel options (103fc) and the sub-library (103fb) further comprises dynamically increasing list of libraries of data with a custom list of location based health related travel options (103fd). Further, the library of list of location based social contribution events and participation opportunities (103g) comprises sub-libraries of dataset including library with external set of data (103ga) and library with internal set of data (103gb), wherein the sub-library (103ga) further comprises dynamically increasing list of libraries of data with a general list of location based social contribution events and participation opportunities (103gc) and the sub-library (103gb) further comprises dynamically increasing list of libraries of data with a custom list of location based social contribution events and participation opportunities (103gd).
[0049] According to an embodiment of the invention, the library of list of location based health related lifestyle impacting knowledge resources (103h) comprises sub-libraries of dataset including a library with external set of data (103ha) and a library with internal set of data (103hb), wherein the sub-library (103ha) further comprises dynamically increasing list of libraries of data with a general list of location based health related lifestyle impacting knowledge resources (103hc) and the sub-library (103hb) further comprises dynamically increasing list of libraries of data with a custom list of location based health related lifestyle impacting knowledge resources (103hd).
[0050] According to the present invention, the system (100) facilitates determination of probable disease based on the user input, wherein the user provides the vital health parameters current blood pressure, body temperature or symptoms to the system (100). The system (100) considers the current weather and water sanitation conditions prevailing in the user’s location for predicting the probable disease, wherein the system (100) uses the data related to probable diseases from the library of data sets (101) associated with the current weather conditions stored in geo-weather and key-weather impact related data server (101d), the water sanitation and water resources data (101g), the symptoms data parameters from library containing drugs, symptoms, and diseases data (101a) and mapping of the current information with personal health information and personal health score of the user, in order to determine the probable disease.
[0051] Further, the analysis and prognosis unit (102) facilitate prediction of the probable disease or set of diseases in the user using machine-learning model and transmits the information to the user in the form of a notification or alert to associated unique user identification number on the user’s electronic device. Additionally, based on a series of calculations, the recommendation unit (103) provides the suggested list of actions to the user, wherein the suggested action may include suggesting the user to contact the healthcare practitioner, according to an embodiment of the invention.
[0052] Further, the recommendation unit (103) requests the user to select a choice of system of medicine and based on such the choice, the recommendation unit (103) prompts the user to select a possible set of options for further action, which may include providing a list of nearby health facilities/ healthcare professionals and diagnostic centers etc. Furthermore, according to an embodiment of the invention, the recommendation unit (103) prompts the user to select the choice of further action such as physical consultation or virtual consultation with the healthcare practitioner. According to an embodiment of the invention, in case of minor health conditions based on the prognosis, the recommendation unit (103) may suggest to the user to visit a pharmacy or to undertake precautions or participate in a local climate change event or social event.
[0053] There are several advantages of the present invention, wherein the system (100) facilitates providing disease-based prognosis, symptom-based prognosis and weather-based prognosis. Further, the system (100) facilitates scientific mapping of the various symptoms associated to a given disease or set of multiple diseases. The system (100) is updated in real-time, wherein the real-time update enriches manually through the analysis and prognosis unit (102) to enhance the contained scientific mapping of symptoms. The system (100) facilitates real-time prediction of the possibility of a disease or set of diseases and its impact on multitude of information on the user’s health. Further, the system (100) facilitates constant monitoring and processing of data, and provides prognosis based on the system of medicine as per user choice, which undergoes a process of enrichment and is presented in the form of recommendations.
Reference numbers:
Components Reference Numbers
Data-set library 101
Analysis and prognosis 102
Recommendation Unit 103
Libraries containing Drugs Symptoms Disease Data 101a
Geo Weather and Key Weather Impact Related Data 101d
Water Sanitation and Water Resources Data 101g
User Demographic Data Current and Historical 101j
Externally Sourced User Demographic Data Current and Historical 101m
Profiling and Analysing 102d
Clouds 102a,102b,102c
Prognosis 102e
System of Medicine 102f
Generative Artificial Intelligence 102g
Historical Data 102h
Library of list of doctors 103a
Library of list of Insurance Options 103b
Library of list of Health plans 103c
Library of list of devices, medicines, coupons, offerings 103d
Library of list of location-based climate impacting Key Events 103e
Library of list of location-based health related travel options 103f
Library of list of location based social contribution events and participation opportunities 103g
Library of list of location-based health related Lifestyle impacting knowledge resources 103h

,CLAIMS:1. A system to analyze the health condition, the system (100) comprises:
a. a library of datasets (101) for real-time analysis, encompassing plurality of datasets pertaining to one or more factors influencing health of a user;
b. an analysis and prognosis unit (102) configured with a machine-based computer algorithm (104) for user-centric prognosis, utilizing machine-learning models;
c. a recommendation unit (103) providing user-centric recommendations derived from the analysis and prognosis results;
wherein said analysis and prognosis unit (102) determines the prognosis by correlating user inputs, including one or more health parameters and symptoms, with the datasets in the library of datasets (101); and
wherein said recommendation unit (103) furnishes one or more actionable suggestions to the user based on the determined prognosis.

2. The system as claimed in claim 1, wherein the library of datasets (101) comprises a symptom data unit, probable disease data unit, weather impact unit and demographic data unit.

3. The system as claimed in claim 1, wherein the library of dataset (101) further includes plurality of real-time updates through clouds (102a, 102b, 102c).

4. The system as claimed in claim 1, wherein the analysis and prognosis unit (102) employ a machine-learning model facilitating machine-training for determining correlations between various health parameters and symptoms.

5. The system as claimed in claim 1, wherein the recommendation unit (103) comprises a dataset encompassing an external and internal library with information including a list of healthcare providers, devices, medicines, insurance options, health plans, coupons, offerings, location-based climate impacting key events, health-related travel options, social contribution events and participation opportunities, and health-related lifestyle impacting knowledge resources.

6. The system as claimed in claim 1, wherein the recommendation unit (103) provides plurality of value-added services, including diverse format information on medicines, diseases, and symptoms, and facilitates user participation in selected social events contributing to a better society and environment.

7. A method for estimating the impact of weather on a user’s health in a system (100), comprising steps of:

- utilizing a matching and differencing process, wherein the system matches two or more databases to create a comparable factual outcome;
- comparing two or more databases to identify differences over a specified data range, and focusing on relevant data aligned with goals;
- implementing a matching-differencing estimator to offset individual weaknesses and mitigate selection on observable and unobservable results impacting a user;
- filtering observable and unobservable results through matching and differencing of a plurality of databases, facilitating control of the system (100);
- enabling real-time updating of the library of data set (101) based on decision output from the analysis and prognosis engine.

8. The method as claimed in claim 7, wherein prioritizing certain data sources in the matching and differencing process is based on historical accuracy and relevance, thereby enhancing the reliability of the estimated impact.

9. The method as claimed in claim 7, wherein the matching-differencing estimator dynamically adjusts the parameters based on real-time feedback, enhancing adaptability to varying data conditions.

10. The method as claimed in claim 7, wherein the system (100) selectively updates the library of datasets (101) in response to specific decision thresholds reached by the analysis and prognosis engine.