Description:FORM 2
THE PATENTS ACT, 1970
(39 of 1970)
&
THE PATENT RULES, 2003

COMPLETE SPECIFICATION
(See Section 10 and Rule 13)

Title of invention:
A SYSTEM FOR PERSONALIZED CONVERSATIONAL CHRONIC DISEASE MANAGEMENT AND A METHOD THEREOF

Applicant:
FITTERFLY HEALTHTECH PRIVATE LIMITED
An Indian Entity
having address as:
503, Akshar Blue Chip Corporate Park,
Turbhe MIDC, Navi Mumbai 400705

The following specification particularly describes the invention and the manner in which it is to be performed.
CROSS-REFERENCE TO RELATED APPLICATIONS AND PRIORITY
The present application does not claim priority from any other patent application.
FIELD OF INVENTION
The present subject matter described herein, in general, relates to a personalized health guidance. More particularly, the present invention relates to a personalized conversational chronic disease management.
BACKGROUND OF THE INVENTION
The subject matter discussed in the background section should not be assumed to be prior art merely as a result of its mention in the background section. Similarly, a problem mentioned in the background section or associated with the subject matter of the background section should not be assumed to have been previously recognized in the prior art. The subject matter in the background section merely represents different approaches, which in and of themselves may also correspond to implementations of the claimed technology.
Diseases, characterized by their long-term nature and complex interactions, present significant challenges to healthcare systems worldwide. Effective management of disease conditions demands continuous monitoring, tailored interventions, and patient engagement. The rising prevalence of human health and related diseases, such as chronic disease, diabetes, cardiovascular disorders, and respiratory conditions, places a substantial burden on healthcare resources. Traditional approaches often rely on periodic clinic visits and standardized treatments, overlooking the dynamic nature of these diseases and the diverse needs of individual patients.
Further, Personalization is a cornerstone of effective chronic disease management. Each patient's medical history, genetics, lifestyle, and preferences play a pivotal role in determining the most suitable interventions. Empowering patients with personalized care plans encourage greater adherence to treatment regimens, leading to improved health care and reduced complications.
Traditional dialogue systems are typically designed for a limited number of use cases, in many cases a single use case. For example, users may ask a weather dialogue system for a weather forecast, book tickets for travel or entertainment by accessing the dialogue system for the relevant supplier, purchase products from retailers, and record information such as receipts with an accounting system dialogue system. Dialogue system allow users to interact with product and service providers in a simple and intuitive manner. Further, dialogue systems, for example, task-oriented dialogue systems are natural language interfaces for tasks, such as information search, customer support, e-commerce, physical environment control, and human-robot interaction. Natural language is a universal communication interface that does not require users to learn a set of task-specific commands. A spoken interface allows the user to communicate by speaking, and a chat interface by typing. A human led dialogue system faces challenges of scalability in providing personalized advice. Further, correct interpretation of user input can be challenging for automatic dialogue systems which lack the grammatical and common-sense knowledge that allows people to effortlessly interpret a wide variety of natural input.
Specifically conventional technologies in the space of disease management using automated chatbot systems either leverages solely rule based language models which lacks in providing natural language response to the natural language input by the user or leverages solely on the transformer model which are not able to offer personalized health advice at scale.
Thus, there exists a need of an innovative approach to automatic disease management that integrates hybrid Artificial Intelligence (AI) technologies with personalized patient care. Furthermore, this holistic framework combines data-driven insights with empathetic human interactions to create a comprehensive solution that addresses the complexities of health and helps to enhance patient outcomes and quality of life.
SUMMARY OF THE INVENTION
Before the present system and device and its components are described, it is to be understood that this disclosure is not limited to the system and its arrangement as described, as there can be multiple possible embodiments which are not expressly illustrated in the present disclosure. It is also to be understood that the terminology used in the description is for the purpose of describing the versions or embodiments only and is not intended to limit the scope of the present application. This summary is not intended to identify essential features of the claimed subject matter nor is it intended for use in detecting or limiting the scope of the claimed subject matter.
In one embodiment of the present disclosure, a system for providing personalized conversational chronic disease management is disclosed. The system may comprise a user interface (UI) which is configured to receive the user input. Further, the system may comprise a memory and a processor coupled with memory. The processor may be configured to execute programmed instructions stored in the memory. Further the system may comprise a process monitoring module for monitoring user’s clinical changes over time, based on the user input. The progress monitoring module may be configured to use a hybrid machine learning system. In one exemplary embodiment, the hybrid machine learning system corresponds to combination of a rule-based natural language processing (NLP) model and a large language model (LLM). Further, the hybrid machine learning system is configured to perform the various steps for monitoring the user’s clinical changes and generating personalized conversational health advice. Further, the hybrid machine learning system comprising step of identifying user intent by providing the user input to the rule-based NLP model. The rule-based NLP model utilizes conversation and clinical context, specific to the user for identifying the user intent out of the user input. Further, the hybrid machine learning system comprising step of performing sentiment analysis of the user input to determine user motivation. The sentiment analysis is performed using the conversational clinical context which is specific to the user and stored in the memory. Furthermore, the hybrid machine learning system comprising step of generating a personalized conversational advice by providing the user intent and user motivation to the large language model (LLM). The LLM model utilizes the conversation and clinical context, specific to the user for generating the personalized conversational advice. Furthermore, the generated personalized conversational advice is presented to the user via the user interface.
In an embodiment of the present disclosure, the user interface (UI) may correspond to a chat interface for engaging with the user for the conversation. Further, the chat interface may enable the user to engage with the chat interface through one of textual chat, voice chat, video chat and a combination thereof.
In another embodiment, the user input may correspond to one of textual input, audio input, voice input, visual input, and a combination thereof.
In yet another embodiment, the system may be configured to onboard new users through a guided questionnaire and collecting user’s health parameter and medical history. Further, the collected information may be used to create a user profile and their disease profile.
In yet another embodiment, the conversation and clinical context may correspond to a context identified from user’s conversation through the UI and from the clinical information identified through the user’s health parameter and user’s medical history.
In yet another embodiment, the memory may be configured stores population level health data utilizing multi-stakeholder therapy areas such as, but not limited to, medicine, user habits, user behaviour, nutrition, physiotherapy and psychology.
In yet another embodiment, both rule-based NLP model and LLM model may be trained on the population level health data and user’s conversation and clinical context.
In yet another embodiment, the rule-based NLP model may employ a set of predefined rules and patterns to extract structured information from the user input.
In yet another embodiment, the LLM model may employ the capability to generate human like conversational advice corresponding to the user input.
In yet another embodiment, the personalized conversational advice may correspond to predictive insights and early detection of chronic illness, by assessing lifestyle risk factors based on user data and habits.
In yet another embodiment, the progress monitoring module may be configured to track progress of the user based on user’s response on the UI of the system in a predefined therapeutic program personalized to the user based on information shared by the user.
In yet another embodiment, the system enables the progress monitoring module to perform compliance monitoring for checking personalized program adherence by the user.
In yet another embodiment, the system may be configured to report feedback to the user for one of compliance adherence, compliance non-adherence, user’s behaviour changes over time, and a combination thereof.
In yet another embodiment, the system may support multilingual inferences and response advice based on the user’s input language.
In yet another embodiment, the system may correspond to a hybrid artificial intelligence (AI) based chat and coaching system. Further, the coaching system may be configured to educate users on health topics, including, but not limited to, chronic disease symptoms, treatment options, medication adherence, and healthy lifestyle practice.
In yet another embodiment, the system may progress monitoring module that may configured to track progress of the user based on user’s response on the UI of the system.
In one another embodiment, the system may correspond to a scalable personalized health advice platform. Further, the system may be configured to learn from the personalized conversational advice and optimize future advice to be generated by the system.
In another embodiment of the present disclosure, a method for providing personalized conversational chronic disease management using a hybrid machine learning system is disclosed. The method may comprise a step of receiving a user input on a user interface (UI). Further, the method may comprise a step of identifying a user intent, by providing the user input to a rule-based natural language processing (NLP) model. Further, the method may comprise a step of performing sentiment analysis of the user input to determine user motivation. Further, the method may comprise a step of generating a personalized conversational advice by providing the user intent and user motivation to a large language model (LLM). Furthermore, the method may comprise a step of presenting the personalized conversational advice to the user via the UI.
The foregoing summary is illustrative only and is not intended to be in any way limiting. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features will become apparent by reference to the drawings and the following detailed description.
BRIEF DESCRIPTION OF DRAWINGS
The detailed description is described with reference to the accompanying figures. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. The same numbers are used throughout the drawings to refer like features and components.
Figure 1 illustrates a block diagram describing a system (100) for personalized conversational chronic disease management, in accordance with an embodiment of the present subject matter; and
Figure 2 illustrates a flow diagram describing a method (200) for providing personalized conversational chronic disease management using a hybrid machine learning system, in accordance with an embodiment of the present subject matter.
DETAILED DESCRIPTION OF THE INVENTION
Reference throughout the specification to “various embodiments,” “some embodiments,” “one embodiment,” or “an embodiment” means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. Thus, appearances of the phrases “in various embodiments,” “in some embodiments,” “in one embodiment,” or “in an embodiment” in places throughout the specification are not necessarily all referring to the same embodiment. Furthermore, the features, structures or characteristics may be combined in any suitable manner in one or more embodiments.
The words "comprising," "having," "containing," and "including," and other forms thereof, are intended to be equivalent in meaning and be open ended in that an item or items following any one of these words is not meant to be an exhaustive listing of such item or items or meant to be limited to only the listed item or items. It must also be noted that, the singular forms "a," "an," and "the" include plural references unless the context clearly dictates otherwise. Although any methods similar or equivalent to those described herein can be used in the practice or testing of embodiments of the present disclosure, the exemplary methods are described. The disclosed embodiments are merely exemplary of the disclosure, which may be embodied in various forms.
The integration of artificial intelligence (AI) techniques in medical healthcare has revolutionized the industry by leveraging advanced algorithms and machine learning (ML) to analyse vast datasets, enhance diagnostic accuracy, personalize treatment plans, and streamline administrative processes.
Further, the transformer based deep learning models such as GPT (generative pre-trained transformer) model has advanced medical healthcare systems by leveraging its natural language understanding capabilities. It can efficiently analyse vast volumes of medical literature, patient records, and clinical notes to extract valuable insights and assist in diagnosis, treatment recommendations, and medical research. GPT's ability to generate human-like text and adapt to evolving medical terminology makes it a powerful tool for enhancing communication among healthcare professionals and patients.
However, a conventional healthcare system based on the NLP (natural language processing) model has several drawbacks. It often struggles with understanding and interpreting nuanced medical language, leading to potential misinterpretations and errors in clinical documentation. NLP models are typically trained on general language corpora and may not fine tune on medical data. NLP systems can be rigid, requiring constant updates to adapt to evolving medical terminology and language patterns. They may lack the contextual awareness and comprehension capabilities that large language models possess, limiting their ability to extract meaningful insights from complex medical texts. Additionally, building and maintaining NLP-based systems can be resource-intensive and time-consuming, making them less efficient and cost-effective compared to newer LLM (large language model) approaches in healthcare.
In the light of the above-mentioned limitations, the large language models (LLMs) like GPT offer significant advantages over traditional natural language processing (NLP) models specifically in the context of healthcare. LLMs excel at understanding and contextualizing complex medical language, allowing them to analyse unstructured clinical text with greater accuracy. They adapt to evolving medical terminology and language patterns, reducing the need for constant rule-based updates. LLMs can also integrate multimodal data, such as medical images and clinical notes, for a more comprehensive analysis, improving diagnostic precision. Furthermore, these models can be fine-tuned for specific healthcare tasks, enhancing their performance. Overall, LLMs offer a more versatile, adaptable, and powerful approach to lung abnormality detection in healthcare.
In one embodiment of the present disclosure, a system for personalized conversational chronic disease management using a hybrid machine learning system is disclosed. The hybrid machine learning system corresponds to combination of rule-based Natural Language Processing (NLP) and Large Language Models (LLMs), which helps in engaging the users in a conversational and intelligent manner. The system may be capable of learning from its interactions, improving its advisory capabilities over time. The system can learn from each interaction, continuously refining its understanding of individual behaviours, response to health interaction, and ultimately, the efficiency of the personalized advice it generates.
Referring to Figure 1, a block diagram describing a system (100) for personalized conversational chronic disease management, is illustrated in accordance with an embodiment of a present subject matter. The system (100) may comprise a user interface (UI) (101), a progress monitoring module (103) and a storage memory (108). The UI (101), the progress monitoring module (103) and the storage memory (108) are communicated with each other via a network (107). The UI (101) may correspond to an interface which enables the user to interact with the system (100). The UI (101) is configured to receive user input (102) from one or more users. In one embodiment, the UI (101) may be coupled to a user device of the user, who may be interacting with the system (100). In another embodiment, the UI (101) may be coupled with a device associated with the system (100) itself. The user device may comprise one selected from a group consisting of a cell phone, personal digital assistant (PDA), laptop computer, stationary personal computer, IPTV remote control, web tablet, laptop computer, pocket PC, a television set capable of receiving IP based video services and mobile IP device. In one exemplary embodiment, the UI (101) may correspond a chat interface for enabling the users to engage with the system (100). The system (100) may take input (102) from the user on the chat interface and may provide a personalized conversational advice (106) to the user via the chat interface itself. In one implementation, the chat interface can support communication with the user through one of text chat, voice chat, video chat, and a combination thereof. In one embodiment, the user input (102) corresponds to one of textual input, audio input, voice input, visual input, and a combination thereof. The user can communicate with the system (100) through textual stream of conversation. Further, the user can communicate with the system (100) through audio stream of conversation, which may be transcribe by the system (100) before processing. Further, the user can communicate with the system (100) through video stream which may further be pre-processed by the system (100) before analysing. In a related embodiment, the system (100) is configured to utilize the UI (100) to onboard a new user to the system (100). While onboarding the new user to the system (100), the system (100) presents a set of guided questionnaire to the user, which eventually collects user’s health related information such as physiological parameters and user’s medical history including recent or past medical records or electronic health records (EHR). The collected information via the guided questionnaire may lead to creating a user profile and a corresponding disease profile of the user, to onboard the user. The chat user interface smoothens the onboarding of the new user to the system (100). In an exemplary embodiment, the system (100), post onboarding the new user, then creates a 3, 6, 9, 12-month prediction on the outcomes that can be achieved by the user based on the health parameters shared with the system (100).
In an embodiment, the information collected by the system (100) in onboarding the new user, may be used as a population level health data, and stored in the memory (108). The population level health data may be leveraged by the system (100) to provide personalized health guidance. In one embodiment, the system (100) may store information on multi-stakeholder therapy areas such as Medicine, Nutrition, Physiotherapy and Psychology, into the population level health data stored in the memory (108). Further, in another embodiment, the system (100) may store conversational context into the population level health data stored in the memory (108). The conversational context may correspond to the context derived from the user level conversation with the system (100), performed via the UI (101). This helps in identifying user level context or prompts of the user. Further, in another embodiment, the system (100) may store clinical context into the population level health data stored in the memory (108). The clinical context may correspond to the context derived from the user level outcomes of user’s previous therapeutic programs or sessions, user’s health parameter and user’s medical history. The memory (108) in one embodiment may comprise any computer-readable medium known in the art including but not limited to volatile memory, such as static random-access memory (SRAM) and dynamic random-access memory (DRAM), and/or non-volatile memory, such as read-only memory (ROM), solid state memory, erasable programmable ROM, flash memories, hard disks, optical disks, memory cards, virtual memory and distributed cloud storage. The memory (108) may be removable, non-removable, or a combination thereof. In yet another embodiment, the memory (108) may be managed under a federated structure that enables efficient prompt engineering, ensuring the adaptability and responsiveness of the progress monitoring module (103). In an embodiment, the system (100) may correspond to an AI-enabled chat and coaching system that leverages population-level health data to provide personalized health guidance and nudges for individuals dealing with chronic diseases and serve as a digital therapeutic expert through conversation for improved health outcomes. The system can also help in early detection and prevention of chronic diseases by assessing lifestyle risk factors based on user data and habits. It can provide insights and suggestions even before the onset of chronic illnesses.
In an embodiment, the progress monitoring module (103) may be configured to track or monitor user’s clinical changes over time, based on the user input (102) to the UI (101) of the system (100). In an exemplary embodiment, the progress monitoring module (103) may be implemented using a hybrid machine learning system. In one implementation, the progress monitoring module (103) analyses user’s input (102) to the UI (101), by using the hybrid machine learning system and generates a personalized conversational advice (106) regarding chronic disease management. The hybrid machine learning system corresponds to combination of a rule-based natural language processing (NLP) model (104) and a large language model (LLM) (105).
In general, a rule-based NLP model (104) is a component of a larger system that processes and understands human language text based on predefined rules. Unlike machine learning-based approaches that learn patterns from data, rule-based NLP (104) relies on explicit rules created by linguists, developers, or domain experts to structurally parse and extract meaning from text. The rule-based NLP model (104) employs a set of predefined rules and patterns to extract structured information from the user input (102). The rule-based NLP model (104) may be trained on the population level health data and user’s conversation and clinical context. In the exemplary embodiment, the rule-based NLP model (104) may process the user input (102) and identify user intent. The user intent can be identified by the rule-based NLP model (104) based on the trained data such as the population level health data and user’s conversation and clinical context. The rule-based NLP model (104) provides a structured approach to intent recognition, allowing for a more directed and meaningful conversation. Further, the rule-based NLP model (104) may be configured to perform sentiment analysis of the user input (102) to determine user motivation. The user motivation can be identified by the rule-based NLP model (104) based on the trained data such as the population level health data and user’s conversation and clinical context. Additionally, the rule-based NLP model (104) may be configured to map and summarize, the user intent and the sentiments derived from the user input (102). In one embodiment, the mapped and summarized output by the rule-based NLP model (104) may be act as an input for the LLM (105) model.
In general, a large language model is a type of artificial intelligence model designed to understand and generate human language text at an advanced level. LLMs are a subset of natural language processing (NLP) models and have gained significant attention due to their remarkable ability to handle various language-related tasks. They are particularly notable for their capacity to learn patterns, context, semantics, and even generate coherent text that closely resembles human-generated language. Further, LLM (105) model of the hybrid machine learning system employs capability to understand and generate human like text. In one embodiment, the LLM (105) model may be trained on the population level health data and user’s conversation and clinical context. Further, based on the input, mapped and summarized by the rule-based NLP model (104), the LLM (105) model may generates a personalized conversational advice (106). In a related embodiment, a human like personalized conversational advice (106) is generated by the LLM (105) model based on the user intent and user motivation identified by the rule-based NLP model (104). In an exemplary embodiment, the personalized conversational advice (106) corresponds to predictive insights and early detection of chronic illnesses, by assessing lifestyle risk factors based on user data and habits. In another embodiment, the LLM (105) model may be provided with conversational memory to maintain context throughout the interaction along with the user’s history, intent, sentiment and outcomes over the programmed duration.
In an embodiment, the hybrid machine learning system sequentially process the user input (102) through the rule-based natural language processing (NLP) model (104), output of which is processed through the large language model (LLM) (105), to generate the personalized conversational advice (104). Further, the LLM (105) may be configured to transmit the personalized conversational advice (104) to the UI (101) for presentation to the user. Further the progress monitoring module (103) is configured to track progress of the user based on user’s response on the UI (101) of the system (100) in a predefined therapeutic program personalized to the user based on information shared by the user. In an exemplary embodiment, the progress monitoring module (103) is capable of tracking progress of the user based on user responses in the chat platform on a 3, 6, 9, 12-month timeline, and recalibrate the nudges needed to be sent to the user. This drives the user to achieve improved outcomes for their morbidity by engaging with the system (100).
In an embodiment, the system (100) enables the progress monitoring module (103) to perform compliance monitoring for checking personalized program adherence by the user. In another embodiment, the system (100) is configured to report feedback to the user for one of compliance adherence, compliance non-adherence, user’s behaviour changes over time, and a combination thereof. In yet another embodiment, the system (100) supports multilingual inferences and response advice based on user’s input language. Further, the system (100) corresponds to a hybrid artificial intelligence (AI) based chat and coaching system, wherein the coaching system is configured to educate users on health topics, including chronic disease symptoms, treatment options, medication adherence, and healthy lifestyle practices. Furthermore, the system (100) corresponds to a scalable personalized health advice platform, wherein the system (100) learns from the personalized conversational advice (106), continuously refining its understanding of individual behaviours, responses to health interventions, and ultimately optimizes future advice to be generated by the system (100). The system (100) could collect valuable data (by maintaining user privacy and confidentiality) about health behaviours and outcomes on a population level that can be analyzed for research purposes, helping to advance the understanding of chronic diseases. In another embodiment, the system (100) can also serve as a patient engagement tool to educate users about various health topics, including chronic disease symptoms, treatment options, medication adherence, and healthy lifestyle practices.
In another embodiment of the present disclosure, the system (100) may further comprise a processor. The processor is coupled with the memory (108). The processor, in one embodiment, may comprise a standard microprocessor, microcontroller, central processing unit (CPU), distributed or cloud processing unit, and/or other processing logic that accommodates the requirements of the present invention. In an embodiment, the progress monitoring module (103) may utilize the processor to implement the hybrid machine learning system.
In yet another embodiment, the development and refinement of the proposed methodology, a comprehensive trailing dataset comprising patient-related data was meticulously curated. The training dataset may use a wide spectrum of medical records, diagnostic reported, treatment histories, and patient profiles, sourced from the diverse healthcare institution.
In yet another embodiment, the UI (101), the progress monitoring module (103) and the memory (108) may communicate with each other via the network (107). In one implementation, the network (107) may be a wireless network, a wired network, or a combination thereof. The network (107) can be implemented as one of the different types of networks, such as intranet, local area network (LAN), wide area network (WAN), the internet, and the like. The network (107) may either be a dedicated network or a shared network. The shared network represents an association of the different types of networks that use a variety of protocols, for example, Hypertext Transfer Protocol (HTTP), Transmission Control Protocol/Internet Protocol (TCP/IP), Wireless Application Protocol (WAP), and the like, to communicate with one another. Further, the network (107) may include a variety of network devices, including routers, bridges, servers, computing devices, storage devices, and the like.
In another embodiment, the network (107) may include any one of the following: a cable network, the wireless network, a telephone network (e.g., Analog, Digital, POTS, PSTN, ISDN, xDSL), a cellular communication network, a mobile telephone network (e.g., CDMA, GSM, NDAC, TDMA, E-TDMA, NAMPS, WCDMA, CDMA-2000, UMTS, 3G, 4G, 5G, 6G), a radio network, a television network, the Internet, the intranet, the local area network (LAN), the wide area network (WAN), an electronic positioning network, an X.25 network, an optical network (e.g., PON), a satellite network (e.g., VSAT), a packet-switched network, a circuit-switched network, a public network, a private network, and/or other wired or wireless communications network configured to carry data.
Although the present disclosure is explained considering that the system (100) is implemented on a server, it may be understood that the system (100) may be implemented in a variety of computing systems, such as a laptop computer, a desktop computer, a notebook, a workstation, a virtual environment, a mainframe computer, a server, a network server, a cloud-based computing environment. It will be understood that the system (100) may be accessed by multiple users through one or more user devices. In one implementation, the system (100) may comprise the cloud-based computing environment in which the user may operate individual computing systems configured to execute remotely located applications. Examples of the user devices may include, but are not limited to, a portable computer, a personal digital assistant, a handheld device, and a workstation.
The system (100) can be implemented using hardware, software, or a combination of both, which includes using where suitable, one or more computer programs, mobile applications, or “apps” by deploying either on-premises over the corresponding computing terminals or virtually over cloud infrastructure. The system (100) may include various micro-services or groups of independent computer programs which can act independently in collaboration with other micro-services. The system (100) may also interact with a third-party or external computer system. Internally, the system (100) may be the central processor of all requests for transactions by the various actors or users of the system. a critical attribute of the system (100) is that it can concurrently and instantly complete an online transaction by a system user in collaboration with other systems.
Referring to Figure 2, a flow diagram describing a method (200) for providing personalized conversational chronic disease management using a hybrid machine learning system, is illustrated in accordance with an embodiment of the present disclosure. The method (200) comprises a step (201) of receiving a user input (102) in a user interface (UI) (101). Further, the method (200) comprises a step (202) of identifying user intent by providing the user input (102) to a rule-based natural language processing (NLP) model (104). Furthermore, the method (200) comprises a step (203) of performing sentiment analysis of the user input (102) to determine user motivation. Moreover, the method (200) comprises a step (204) of generating a personalized conversational advice (106) by providing the user intent and user motivation to a large language model (LLM) (105), and method (200) comprises a step (205) of presenting personalized conversational advice (106) to the user via the UI (101).
In another embodiment, the method (200) comprises enabling a chat interface for engaging with the user for conversation, wherein the user engaged with the chat interface through one of text chat, voice chat, video chat, and a combination thereof. In yet another embodiment, the user input (102) corresponds to one of textual input, audio input, voice input, visual input, and a combination thereof.
In yet another embodiment, the method (200) comprises onboarding new users through a guided questionnaire and collecting user’s health parameter and medical history, wherein the collected information is used to create a user profile and their disease profile.
In yet another embodiment, conversation and clinical context corresponds to context identified from user’s conversation through the UI (101) and from the clinical information identified through the user’s health parameter and user’s medical history.
In yet another embodiment, the method (200) comprises training both the rule-based NLP model (104) and LLM model (105) on the conversation and clinical context and a population level health data, wherein the population level health data corresponds to information on multi-stakeholder therapy areas such as Medicine, Nutrition, Physiotherapy and Psychology.
In yet another embodiment, the population level health data comprises conversation and clinical context, wherein conversation and clinical context corresponds to context identified from user’s conversation through the UI (101) and from the clinical information identified through the user’s health parameter and user’s medical history.
In yet another embodiment, the method (200) enables a hybrid artificial intelligence (AI) based chat and coaching system, wherein the coaching system educates users on health topics, including chronic disease symptoms, treatment options, medication adherence, and healthy lifestyle practices.
In yet another embodiment, the method (200) comprises the step of tracking progress of the user based on user’s response on the UI (101) in a predefined therapeutic program personalized to the user based on information shared by the user.
In yet another embodiment, the method (200) enables compliance monitoring for personalized program adherence by the user.
In yet another embodiment, the method (200) enables reporting feedback to the user for one of compliance adherence, compliance non-adherence, user’s behaviour changes over time and a combination thereof.
In yet another embodiment, the method (200) enables supporting multilingual inferences and response advice based on user’s input language.
In yet another embodiment, the method (200) enables a hybrid artificial intelligence (AI) based chat and coaching system, wherein the coaching system is configured to educate users on health topics, including chronic disease symptoms, treatment options, medication adherence, and healthy lifestyle practices.
In yet another embodiment, the method (200) enables a scalable personalized health advice platform, wherein the platform learns from the personalized conversational advice (106) and optimizes future advice generated by the platform.
In yet another embodiment, rule-based NLP model (104) can be a rule based NLP, NLP model, rule-based model, rule-based Natural Language processing, and the like.
In yet another embodiment, a large language model (105), can be a LLM, large language module, GPT, BERT, transformer, self-attention model, transformer architecture, and the like.
The system (100) as disclosed in the disclosure may help to support chronic disease management in the following, but non-limiting applications:
a. Personalised digital therapeutics for pharmaceutical companies.
b. Patient support programs in hospitals or clinics.
c. Corporate Wellness programs.
d. Insurance company health programs for policyholders.
e. Managed care providers for cost reduction.
f. Self-service healthcare chatbot and trained to handle user queries
Various modifications to the embodiment will be readily apparent to those skilled in the art and the generic principles herein may be applied to other embodiments. However, one of ordinary skill in the art will readily recognize that the present disclosure is not intended to be limited to the embodiments illustrated but is to be accorded the widest scope consistent with the principles and features described herein.
The foregoing description shall be interpreted as illustrative and not in any limiting sense. A person of ordinary skill in the art would understand that certain modifications could come within the scope of this disclosure.
The embodiments, examples and alternatives of the preceding paragraphs or the description and drawings, including any of their various aspects or respective individual features, may be taken independently or in any combination. Features described in connection with one embodiment are applicable to all embodiments unless such features are incompatible.
, Claims:WE CLAIM:
1. A system (100) for providing personalized conversational chronic disease management, the system (100) comprises:
a user interface (UI) (101), wherein the user interface (101) is configured to receive user input (102);
a memory (108);
a processor coupled with the memory (108), wherein the processor is configured to execute programmed instructions stored in the memory (108); and
a progress monitoring module (103), for monitoring user’s clinical changes over time, based on the user input (102), using a hybrid machine learning system, wherein the hybrid machine learning system carried out by the processor, is developed by the steps of:
identifying user intent by providing the user input (102) to a rule-based natural language processing (NLP) model (104), wherein the rule-based NLP model (104) utilizes conversation and clinical context, specific to the user, stored in the memory (108);
performing sentiment analysis of the user input (102) to determine user motivation, wherein the sentiment analysis is performed using the conversation and clinical context, specific to the user, stored in the memory (108); and
generating a personalized conversational advice (106) by providing the user intent and user motivation to a large language model (LLM) (105), wherein the LLM model (105) uses the conversation and clinical context, specific to the user, stored in the memory (108);
wherein the personalized conversational advice (106) is presented to the user via the UI (101).
2. The system (100) as claimed in claim 1, wherein user interface (101) corresponds to a chat interface for engaging with the user for the conversation, wherein the user engaged with the chat interface through one of text chat, voice chat, video chat, and a combination thereof.
3. The system (100) as claimed in claim 1, wherein the user input (102) corresponds to one of textual input, audio input, voice input, visual input, and a combination thereof.
4. The system (100) as claimed in claim 1, wherein system (100) is configured to onboard new users through a guided questionnaire and collecting user’s health parameter and medical history, wherein the collected information is used to create a user profile and their disease profile.
5. The system (100) as claimed in claim 1, wherein the memory (108) stores population level health data utilizing multi-stakeholder therapy areas such as Medicine, Nutrition, Physiotherapy and Psychology.
6. The system (100) as claimed in claim 1, wherein the population level health data comprises the conversation and clinical context, wherein the conversation and clinical context corresponds to context identified from user’s conversation through the UI (101) and from the clinical information identified through user’s previous therapeutic sessions, the user’s health parameter and user’s medical history.
7. The system (100) as claimed in claims 1, 5 and 6, wherein both rule-based NLP model (104) and LLM model (105) is trained on the population level health data and user’s conversation and clinical context.
8. The system (100) as claimed in claim 1, wherein the rule-based NLP model (104) employs a set of predefined rules and patterns to extract structured information from the user input (102).
9. The system (100) as claimed in claim 1, wherein the LLM model (105) employs capability to generate human like conversational advice (106) corresponding to the user input (102).
10. The system (100) as claimed in claim 1, wherein the personalized conversational advice (106) corresponds to predictive insights and early detection of chronic illnesses, by assessing lifestyle risk factors based on user data and habits.
11. The system (100) as claimed in claim 1, wherein the progress monitoring module (103) is configured to track progress of the user based on user’s response on the UI (101) of the system (100) in a predefined therapeutic program personalized to the user based on information shared by the user.
12. The system (100) as claimed in claim 1, wherein the system (100) enables the progress monitoring module (103) to perform compliance monitoring for checking personalized program adherence by the user.
13. The system (100) as claimed in claims 12, wherein the system (100) is configured to report feedback to the user for one of compliance adherence, compliance non-adherence, user’s behaviour changes over time, and a combination thereof.
14. The system (100) as claimed in claim 1, wherein the system (100) supports multilingual inferences and response advice based on user’s input language.
15. The system (100) as claimed in claim 1, wherein the system (100) corresponds to a hybrid artificial intelligence (AI) based chat and coaching system, wherein the coaching system is configured to educate users on health topics, including chronic disease symptoms, treatment options, medication adherence, and healthy lifestyle practices.
16. The system (100) as claimed in claim 1, wherein the system (100) corresponds to a scalable personalized health advice platform, wherein the system (100) learns from the personalized conversational advice (106) and optimizes future advice to be generated by the system (100).

17. A method (200) for providing personalized conversational chronic disease management using a hybrid machine learning system, the method comprising:
receiving (201) a user input (102) on a user interface (UI) (101);
identifying (202) user intent, by providing the user input (102) to a rule-based natural language processing (NLP) model (104);
performing (203) sentiment analysis of the user input (102) to determine user motivation;
generating (204) a personalized conversational advice (106) by providing the user intent and user motivation to a large language model (LLM) (105); and
presenting (205) the personalized conversational advice (106) to the user via the UI (101).
18. The method (200) as claimed in claim 17, wherein the method (200) comprises enabling a chat interface for engaging with the user for conversation, wherein the user engaged with the chat interface through one of text chat, voice chat, video chat, and a combination thereof.
19. The method (200) as claimed in claim 17, wherein the user input (102) corresponds to one of textual input, audio input, voice input, visual input, and a combination thereof.
20. The method (200) as claimed in claim 17, wherein the method (200) comprises onboarding new users through a guided questionnaire and collecting user’s health parameter and medical history, wherein the collected information is used to create a user profile and their disease profile.
21. The method (200) as claimed in claim 17, wherein conversation and clinical context corresponds to context identified from user’s conversation through the UI (101) and from the clinical information identified through the user’s health parameter and user’s medical history.
22. The method (200) as claimed in claim 17, wherein the method (200) comprises training both the rule-based NLP model (104) and LLM model (105) on the conversation and clinical context and a population level health data, wherein the population level health data corresponds to information on multi-stakeholder therapy areas such as Medicine, Nutrition, Physiotherapy and Psychology.
23. The method (200) as claimed in claim 21, the population level health data comprises conversation and clinical context, wherein conversation and clinical context corresponds to context identified from user’s conversation through the UI (101) and from the clinical information identified through the user’s health parameter and user’s medical history.
24. The method (200) as claimed in claim 17, wherein the personalized conversational advice (106) corresponds to predictive insights and early detection of chronic illnesses by assessing lifestyle risk factors based on user data and habits.
25. The method (200) as claimed in claim 17, wherein the method (200) enables a hybrid artificial intelligence (AI) based chat and coaching system, wherein the coaching system educates users on health topics, including chronic disease symptoms, treatment options, medication adherence, and healthy lifestyle practices.
26. The method (200) as claimed in claim 17, wherein the method (200) comprises the step of tracking progress of the user based on user’s response on the UI (101) in a predefined therapeutic program personalized to the user based on information shared by the user.
27. The method (200) as claimed in claim 17, wherein the method (200) enables compliance monitoring for personalized program adherence by the user.
28. The method (200) as claimed in claim 17, wherein the method (200) enables reporting feedback to the user for one of compliance adherence, compliance non-adherence, user’s behaviour changes over time and a combination thereof.
29. The method (200) as claimed in claim 17, wherein the method (200) enables supporting multilingual inferences and response advice based on user’s input language.
30. The method (200) as claimed in claim 17, wherein the method (200) enables a hybrid artificial intelligence (AI) based chat and coaching system, wherein the coaching system is configured to educate users on health topics, including chronic disease symptoms, treatment options, medication adherence, and healthy lifestyle practices.
31. The method (200) as claimed in claim 17, wherein the method (200) enables a scalable personalized health advice platform, wherein the platform learns from the personalized conversational advice (106) and optimizes future advice generated by the platform.
Dated this 29th day of September 2023

Deepak Pawar
Agent for the Applicant
IN/PA-2052