Description:FIELD OF THE INVENTION

[0001] The present invention relates to a post-surgical recovery planning system that is capable of continuously monitoring patient health, analyzing clinical data to generate personalized recovery strategies, dynamically adapting treatment plans based on real-time patient progress, and facilitating communication between healthcare providers and patients to improve recovery outcomes.

BACKGROUND OF THE INVENTION

[0002] Post-surgical recovery planning is essential to ensure patients regain optimal health and functionality after surgery. Effective recovery plans help manage pain, prevent complications, and promote timely rehabilitation. However, challenges often arise due to variability in patient responses, adherence to medication and exercise routines, and timely detection of complications. Patients struggle with following complex instructions or missing medication doses, while clinicians face difficulties in continuously monitoring progress and adjusting plans based on changing conditions. Additionally, fragmented data from various sources like wearable devices and medical records complicate comprehensive assessment. These challenges highlight the need for a mean that provides personalized, adaptive recovery plans, real-time monitoring, and effective communication between patients and healthcare providers to improve outcomes and reduce risks.

[0003] Traditional post-surgical recovery means often rely on manual data collection and periodic in-person consultations, limiting real-time monitoring and personalized care. Many existing solutions use generic recovery protocols that do not account for individual patient variability, leading to suboptimal outcomes. Wearable devices and mobile apps provide some monitoring but often operate in isolation without integrating comprehensive clinical data or expert insights. These fragmented means lack adaptive capabilities to adjust recovery plans dynamically based on patient progress or complications. Additionally, limited communication channels between patients and clinicians result in poor adherence and delayed interventions. Consequently, traditional approaches struggle to provide continuous, personalized, and data-driven recovery management, highlighting the need for more integrated and autmated solutions.

[0004] US5403263A discloses about a method of reducing anxiety and the recovery time of a patient during the preoperative, intraoperative and postoperative phases of surgery. The method includes the steps of providing music in each phase of the surgery in combination with voice-over information relating to each phase of the surgery that the patient experiences at the time, with information, reassurance and suggestions to help the patient relax and feel comfortable during the three phases of surgery.

[0005] US20140081659A1 discloses about various systems and methods are provided for surgical and interventional planning, support, post-operative follow-up, and functional recovery tracking. In general, a patient can be tracked throughout medical treatment including through initial onset of symptoms, diagnosis, non-surgical treatment, surgical treatment, and recovery from the surgical treatment. In one embodiment, a patient and one or more medical professionals involved with treating the patient can electronically access a comprehensive treatment planning, support, and review system. The system can provide recommendations regarding diagnosis, non-surgical treatment, surgical treatment, and recovery from the surgical treatment based on data gathered from the patient and the medical professional(s). The system can manage the tracking of multiple patients, thereby allowing for data comparison between similar aspects of medical treatments and for learning over time through continual data gathering, analysis, and assimilation to decision-making protocols.

[0006] Conventionally, many systems are available in market for monitoring recovery of patients, but they often lack integration of real-time data, adaptive planning, and personalized care. These limitations reduce their effectiveness in addressing individual patient needs and timely intervention, underscoring the necessity for more automated and comprehensive solutions.

[0007] In order to overcome the aforementioned drawbacks, there exists a need in the art to develop a system that requires to be capable of continuously collecting and analyzing patient data, dynamically adapting recovery plans, facilitating real-time communication between patients and clinicians, and providing personalized guidance to improve recovery outcomes and reduce complications.

OBJECTS OF THE INVENTION

[0008] The principal object of the present invention is to overcome the disadvantages of the prior art.

[0009] An object of the present invention is to develop a system that is capable of continuously gathering and analyzing patient health and recovery data from various sources in order to develop personalized recovery plans tailored to individual patient needs.

[0010] Another object of the present invention is to develop a system that is capable of dynamically updating and adjusting recovery plans in real-time based on ongoing patient progress and detection of any deviations or complications during the recovery process.

[0011] Another object of the present invention is to develop a system that is capable of generating timely alerts for healthcare providers upon identifying early signs of health risks or complications, enabling prompt interventions to reduce adverse post-surgical events.

[0012] Yet, another object of the present invention is to develop a system that is capable of facilitating clear communication by providing understandable recovery information and notifications to both patients and clinicians, thereby enhancing adherence and improving overall recovery outcomes.

[0013] The foregoing and other objects, features, and advantages of the present invention will become readily apparent upon further review of the following detailed description of the preferred embodiment as illustrated in the accompanying drawings.

SUMMARY OF THE INVENTION

[0014] The present invention relates to a post-surgical recovery planning system that is capable of continuously monitoring patient health data, analyzing recovery progress, generating personalized treatment strategies, adapting plans in real time based on patient status, and facilitating communication to improve overall recovery outcomes.

[0015] According to an aspect of the present invention, a post-surgical recovery planning system comprises a patient data acquisition module configured to receive real-time and historical data including physiological vitals, rehabilitation progress metrics, medication adherence, and compliance with prescribed exercise routines from one or more patients, a processing unit operatively coupled with an Inverse Reinforcement Learning (IRL) module, the IRL engine configured to infer latent expert strategies and reward functions by analyzing the patient data in conjunction with expert clinician demonstrations, a recovery plan generation module communicably linked with the IRL module, configured to generate individualized recovery trajectories for each patient based on inferred expert goals and current patient status.

[0016] The present system further comprises a multimodal patient monitoring module configured to interface with wearable sensors, and/or electronic health records (EHRs) to detect deviations in patient vitals, progress, medication adherence, and exercise compliance in real time, a feedback and adaptation module operatively connected to the monitoring module and the recovery plan generation module, to dynamically update recovery trajectories based on identified complications, and patient-specific needs, a clinician user-interface operatively connected to the processing unit, configured to display interpretable generated recommendations, allow plan validation or modification by clinicians, and provide real-time visualization of patient recovery progress, a patient user-interface operatively connected to the processing unit, configured to deliver dynamic instructions, medication reminders, guided physiotherapy routines, and personalized notifications, all the modules are stored in a non-transitory memory.

[0017] While the invention has been described and shown with particular reference to the preferred embodiment, it will be apparent that variations might be possible that would fall within the scope of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS

[0018] These and other features, aspects, and advantages of the present invention will become better understood with regard to the following description, appended claims, and accompanying drawings where:
Figure 1 illustrates a block diagram of a post-surgical recovery planning system; and
Figure 2 illustrates another block diagram of the post-surgical recovery planning system.

DETAILED DESCRIPTION OF THE INVENTION

[0019] The following description includes the preferred best mode of one embodiment of the present invention. It will be clear from this description of the invention that the invention is not limited to these illustrated embodiments but that the invention also includes a variety of modifications and embodiments thereto. Therefore, the present description should be seen as illustrative and not limiting. While the invention is susceptible to various modifications and alternative constructions, it should be understood, that there is no intention to limit the invention to the specific form disclosed, but, on the contrary, the invention is to cover all modifications, alternative constructions, and equivalents falling within the spirit and scope of the invention as defined in the claims.

[0020] In any embodiment described herein, the open-ended terms "comprising," "comprises,” and the like (which are synonymous with "including," "having” and "characterized by") may be replaced by the respective partially closed phrases "consisting essentially of," consists essentially of," and the like or the respective closed phrases "consisting of," "consists of, the like.

[0021] As used herein, the singular forms “a,” “an,” and “the” designate both the singular and the plural, unless expressly stated to designate the singular only.

[0022] The present invention relates to a post-surgical recovery planning system that is capable of generating adaptive, personalized recovery plans by learning from expert strategies and continuously monitoring a patient's progress to ensure they remain on an optimal, safe recovery trajectory.

[0023] Referring to Figure 1 and 2, block diagrams of a post-surgical recovery planning system are illustrated, comprising a patient data acquisition module 101, a processing unit 102 operatively coupled with an Inverse Reinforcement Learning (IRL) module 103, a recovery plan generation module 104 communicably linked with the IRL module 103, a multimodal patient monitoring module 105, a feedback and adaptation module 106 operatively connected to the monitoring module 105 and the recovery plan generation module 104, all the modules are stored in a non-transitory memory 107, a clinician user-interface 108 operatively connected to the processing unit 102, a patient user-interface 109 operatively connected to the processing unit 102.

[0024] The system includes the patient data acquisition module 101 is stored in the non-transitory memory 107 configured to collect both real-time and historical data encompassing physiological vital signs, rehabilitation progress metrics, medication adherence, and compliance with prescribed exercise regimens from one or more patients.

[0025] Once activated by the processing unit 102 of the system, the patient data acquisition module 101 immediately begins collecting both real-time and historical data, includes but not limited to, such as physiological vitals such as heart rate and blood pressure, rehabilitation progress metrics, medication adherence, and compliance with prescribed exercise routines, from diverse sources, including wearable medical devices (e.g., Fitbit, Apple Watch), mobile health applications (e.g., MyFitnessPal, Medisafe), and hospital electronic health record (EHR) systems (e.g., Epic, Cerner).

[0026] The processing unit 102 is the central controller or main processor of the system, where the patient data acquisition module 101 is a component that collects data. Activation of the patient data acquisition module 101 means the processing unit 102 sends commands or signals to start the module's operation, includes but not limited to, such as initializing sensors, starting data collection, or enabling communication protocols.

[0027] The patient data acquisition module 101 herein gathers comprehensive patient information critical to post-surgical recovery. Upon activation, the patient data acquisition module 101 establishes secure connections with multiple data sources, including the wearable medical devices, mobile health applications, and hospital electronic health record (EHR) systems via a communication module interlinked with the processing unit 102. The patient data acquisition module 101 continuously collects real-time physiological vitals, such as heart rate, blood pressure, and oxygen saturation, while also retrieving historical data related to the patient’s rehabilitation progress, medication adherence, and compliance with prescribed exercise routines. The patient data acquisition module 101 includes data interfaces for communication with the external devices and a linked database, data preprocessing units to filter and normalize incoming information, and data storage unit for efficient management and retrieval. By aggregating heterogeneous data streams, the patient data acquisition module 101 ensures a comprehensive and up-to-date patient profile, enabling downstream the processing unit 102 to generate personalized recovery plans and provide timely alerts for any detected anomalies.

[0028] In an embodiment of the present invention, the communication module used herein includes, but not limited to Wi-Fi (Wireless Fidelity) module, Bluetooth module, GSM (Global System for Mobile Communication) module. The communication module used herein is preferably a Wi-Fi module that is a hardware component that enables the processing unit 102 to connect wirelessly with the heterogeneous sources including wearable medical systems, mobile health applications, and hospital electronic health record (EHR) systems. The Wi-Fi module works by utilizing radio waves to transmit and receive data over short distances. The core functionality relies on the IEEE 802.11 standards, which define the protocols for wireless local area networking (WLAN). Once connected, the module facilitates data exchange through packet transmission, allowing the processing unit 102 to send and receive information efficiently.

[0029] The Inverse Reinforcement Learning (IRL) module 103 stored in the non-transitory memory 107 and operatively coupled with the processing unit 102, where a IRL engine is configured to infer latent expert strategies and underlying reward functions by analyzing patient data alongside expert clinician demonstrations.

[0030] The Inverse Reinforcement Learning (IRL) module 103 serves as a core computational engine of the system, responsible for interpreting complex patient data to infer optimal recovery strategies. Upon receiving the aggregated real-time and historical patient data from the patient data acquisition module 101, the processing unit 102 leverages the IRL engine to analyze patterns and behaviors exhibited in the data in conjunction with the expert clinician demonstrations received from the clinical databases and verified medical sources. The IRL module 103 enables the processing unit 102 to uncover latent reward functions and expert decision-making strategies that are not explicitly programmed but inferred from the observed clinical practices.

[0031] The Inverse Reinforcement Learning (IRL) module 103 include data integration modules that prepare and format patient data for analysis, the IRL inference engine that models clinician expertise by evaluating the alignment between the patient outcomes and expert demonstrations, and a decision-making module that synthesizes inferred strategies into actionable recovery plans. This integration allows the processing unit 102 to generate personalized, expert-informed recovery trajectories that adapt dynamically based on patient progress and emerging clinical data.

[0032] The recovery plan generation module 104 stored in the non-transitory memory 107, and communicably linked with the IRL module 103, is configured to create individualized recovery trajectories for each patient by leveraging inferred expert goals and the patient’s current status. This recovery plan generation module 104 includes a decision layer designed to evaluate multiple inferred recovery strategies and select the optimal trajectory based on the predicted patient outcomes.

[0033] The recovery plan generation module 104 functions as a critical component that translates the insights derived from the IRL module 103 into actionable, personalized recovery trajectories for each patient. Upon receiving the inferred expert goals and the current patient status received from the processing unit 102, the recovery plan generation module 104 evaluates multiple candidate recovery strategies using the decision layer that assesses predicted patient outcomes. This decision layer compares the effectiveness, risks, and expected benefits of various recovery paths, selecting the optimal trajectory tailored to the individual’s needs. Operationally, the recovery plan generation module 104 includes components for strategy evaluation, outcome prediction models, and plan synthesis, which collectively enable the recovery plan generation module 104 to create dynamic, adaptable recovery plans. These plans continuously update as new patient data arrives, ensuring alignment with evolving clinical conditions and patient progress, thereby supporting personalized and effective post-surgical rehabilitation.

[0034] In an embodiment of the present invention, the decision layer operates as a critical analytical component within the recovery plan generation module 104, responsible for selecting the most effective recovery trajectory from multiple candidate strategies. The decision layer works by evaluating each potential recovery plan based on the predicted patient outcomes, considering factors such as effectiveness, associated risks, patient-specific needs, and expected benefits. The decision layer incorporates predictive models that simulate the potential impact of different recovery paths, integrating the clinical guidelines and patient data to estimate outcomes. The decision layer also includes risk assessment tools to identify potential complications or setbacks linked to each strategy. By synthesizing this information, the decision layer ranks and compares recovery options, ultimately selecting the optimal plan that balances safety and efficacy tailored to the individual patient. This component continuously re-evaluates and updates decisions as new patient data becomes available, ensuring that the recovery plan remains adaptive and aligned with the patient’s evolving condition.

[0035] The multimodal patient monitoring module 105 stored in the non-transitory memory 107, is designed to interface with the wearable sensors and electronic health records (EHRs) to continuously track patient vitals, rehabilitation progress, medication adherence, and compliance with prescribed exercise routines in real time. This multimodal patient monitoring module 105 monitors for deviations from expected recovery parameters and is configured to generate alerts to the clinician user-interface 108 interlinked with the processing unit 102 whenever predefined clinical thresholds are exceeded, such as abnormal vital signs, missed medication doses, or non-compliance with physiotherapy schedules. All monitored data is stored in the linked database, enabling timely clinical intervention.

[0036] The multimodal patient monitoring module 105 interfaces with the wearable sensors to capture real-time physiological vitals such as heart rate, blood pressure, oxygen saturation, and movement patterns. Simultaneously, the multimodal patient monitoring module 105 accesses the electronic health records (EHRs) to retrieve historical and current clinical data, including medication schedules, rehabilitation progress notes, and previous medical conditions.

[0037] Operationally, the multimodal patient monitoring module 105 includes data acquisition interfaces that establish secure connections with these external devices and systems. Incoming data is then preprocessed to filter noise, normalize formats, and validate measurements to ensure accuracy. Analytic components, such as anomaly detection protocols, machine learning classifiers, and threshold-based rule engines, continuously compare the real-time patient data against the predefined clinical thresholds and expected recovery trajectories. When deviations occur, such as abnormal vital signs, missed medication doses, or failure to adhere to prescribed exercise routines, the multimodal patient monitoring module 105 generates automated alerts sent directly to the clinician user-interface 108.

[0038] These alerts enable the clinicians to promptly review and respond to potential complications, ensuring timely interventions. Additionally, the multimodal patient monitoring module 105 supports dynamic feedback loops by communicating with the recovery plan generators, allowing the recovery trajectories to be adjusted based on up-to-date patient status. Through this continuous monitoring and adaptation, the multimodal patient monitoring module 105 enhances patient safety and optimizes recovery outcomes.

[0039] The feedback and adaptation module 106 stored in the non-transitory memory 107 and is operatively connected to both the multimodal patient monitoring module 105 and the recovery plan generation module 104, enabling dynamic updates to the patient recovery trajectories based on detected complications and individual patient needs. This feedback and adaptation module 106 incorporates a continuous learning loop that actively monitors patient progress and adjusts the recovery plans in response to identified anomalies, deviations, or emerging complications. By continuously integrating real-time data and clinical insights, the feedback and adaptation module 106 ensures that recovery strategies remain personalized, responsive, and optimized throughout the post-surgical healing process.

[0040] The feedback and adaptation module 106 analyzes real-time information to detect any anomalies, deviations, or complications in the patient’s recovery trajectory. Upon identifying such events, the feedback and adaptation module 106 initiates an adaptive response by communicating with the recovery plan generation module 104 to modify and update the patient’s recovery plan accordingly. This feedback and adaptation module 106 includes the continuous learning loop that incorporates new patient data and outcomes to refine future recovery trajectories, ensuring personalization and responsiveness. The feedback and adaptation module 106 further include data analysis engines that evaluate deviations, decision-making units that determine necessary plan adjustments, and communication interfaces that relay updates between the multimodal patient monitoring module 105 and recovery plan generation module 104. By providing iterative feedback and adaptation, this feedback and adaptation module 106 enhances the effectiveness of post-surgical care by dynamically tailoring recovery strategies to evolving patient-specific needs.

[0041] The clinician user-interface 108 disclosed above, operatively connected to the processing unit 102, and is configured to display clear and interpretable recommendations generated by the processing unit 102. The clinician user-interface 108 allows clinicians to validate or modify the recovery plans as necessary and provides real-time visualization of patient recovery progress.

[0042] In an embodiment of the present invention, the clinician user-interface 108 is built into a computing unit (includes, but not limited to smartphone, tablet or laptop) and is operatively connected to the processing unit 102 via the communication module, functions as a primary interactive platform through which the healthcare professionals access and manage patient recovery plans. The clinician user-interface 108 is operatively connected to the processing unit 102, enabling real-time retrieval and display of personalized recovery recommendations generated by the IRL-based engine. The clinician user-interface 108 provides intuitive visualizations of patient progress metrics, highlighting key vitals, adherence status, and rehabilitation milestones. The clinician user-interface 108 also incorporates tools, includes but not limited to, such as interactive dashboards and decision-support features, enabling clinicians to validate, adjust, or override recovery plans based on their clinical judgment.

[0043] Integrated within the clinician interface, a transparency module provides detailed insights into the rationale behind the IRL-inferred decisions by elucidating the underlying expert strategies and predicted patient outcomes that drive the system’s recommendations. The transparency module operates by extracting and presenting key decision factors from the IRL engine, such as reward functions, decision pathways, and outcome predictions, in an interpretable format for clinicians. The transparency module includes explanation generators that translate complex model outputs into human-understandable narratives, visualization tools that graphically represent decision logic and anticipated recovery trajectories, and interactive elements that allow clinicians to explore alternative scenarios or contributing factors. The clinician user-interface 108 also incorporates data rendering engines for displaying patient information, user input modules for modifying recovery plans, alert systems for notifying clinicians of critical updates, and secure communication channels to maintain data integrity and privacy. This comprehensive setup empowers clinicians to make informed, evidence-based decisions, enhancing the adaptability and personalization of patient care.

[0044] The patient user-interface 109 is also provided, built into a separate computing unit and operatively connected to the processing unit 102 via the communication module to deliver personalized, dynamic support throughout the recovery process. The patient user-interface 109 provides real-time access to tailored instructions, medication reminders, guided physiotherapy routines, and other personalized notifications to assist patients in adhering to their recovery plans. The patient user-interface 109 includes an adaptive notification scheduling that autonomously adjusts the frequency and timing of reminders based on the patient’s previous interaction history and adherence behavior, thereby enhancing engagement and improving compliance with prescribed recovery activities.

[0045] The adaptive notification scheduling included within the patient user-interface 109 operates by continuously monitoring user interaction history and adherence patterns to autonomously modify the timing and frequency of reminders. The adaptive notification scheduling comprises several operational components, including a user interaction tracker, an adherence analytics engine, and a scheduling optimizer. The user interaction tracker captures patient responses to delivered notifications, such as whether reminders are acknowledged, ignored, or delayed. The adherence analytics engine processes this data in conjunction with historical adherence records to evaluate the patient's engagement level and determine optimal intervention times. Based on these insights, the scheduling optimizer dynamically adjusts future reminder delivery, intensifying notifications during periods of low adherence and reducing frequency when adherence remains consistently high. This feedback-driven approach personalizes the reminder schedule, thereby enhancing patient compliance and engagement while minimizing unnecessary disruptions during the recovery process.

[0046] The present invention works best in the following manner, where the patient data acquisition module 101 as disclosed in the invention acquires real-time and historical patient data, and aggregates physiological vitals, rehabilitation progress metrics, medication adherence, and exercise compliance from heterogeneous sources including wearable medical devices, mobile health applications, and hospital electronic health record (EHR) systems. The processing unit 102 integrated with the Inverse Reinforcement Learning (IRL) module 103, analyzes collected data alongside expert clinician demonstrations to infer latent expert strategies and reward functions. The recovery plan generation module 104, communicably linked to the IRL engine, generates individualized recovery trajectories tailored to inferred expert goals and current patient status, employing the decision layer to compare multiple strategies and select optimal trajectories based on predicted patient outcomes. The multimodal patient monitoring module 105 continuously interfaces with the wearable sensors and EHRs to detect deviations in patient vitals, adherence, or progress, issuing alerts to the clinician user-interface 108 upon detecting clinical threshold breaches. The feedback and adaptation module 106 dynamically updates recovery plans through the continuous learning loop that responds to anomalies, deviations, or complications, ensuring real-time adaptability. The clinician user-interface 108 provides interpretable recommendations, plan validation or modification capabilities, real-time recovery visualizations, and the transparency module that explains IRL-inferred decisions including underlying expert strategies and outcome justifications. The patient user-interface 109 delivers dynamic instructions, medication reminders, guided physiotherapy routines, and personalized notifications with adaptive notification scheduling that adjusts reminder frequency based on prior interaction and adherence patterns. All modules reside in the non-transitory memory 107 and execute under the processing unit 102, enabling continuous, expert-informed, and adaptive post-surgical recovery management aimed at improving patient outcomes and reducing risk of adverse events.

[0047] Although the field of the invention has been described herein with limited reference to specific embodiments, this description is not meant to be construed in a limiting sense. Various modifications of the disclosed embodiments, as well as alternate embodiments of the invention, will become apparent to persons skilled in the art upon reference to the description of the invention. , Claims:1) A post-surgical recovery planning system, comprising:
i) a patient data acquisition module 101 configured to receive real-time and historical data including physiological vitals, rehabilitation progress metrics, medication adherence, and compliance with prescribed exercise routines from one or more patients;
ii) a processing unit 102 operatively coupled with an Inverse Reinforcement Learning (IRL) module 103, a IRL engine configured to infer latent expert strategies and reward functions by analyzing the patient data in conjunction with expert clinician demonstrations;
iii) a recovery plan generation module 104 communicably linked with the IRL module 103, configured to generate individualized recovery trajectories for each patient based on inferred expert goals and current patient status;
iv) a multimodal patient monitoring module 105 configured to interface with wearable sensors, and/or electronic health records (EHRs) to detect deviations in patient vitals, progress, medication adherence, and exercise compliance in real time;
v) a feedback and adaptation module 106 operatively connected to the monitoring module 105 and the recovery plan generation module 104, to dynamically update recovery trajectories based on identified complications, and patient-specific needs;
vi) a clinician user-interface 108 operatively connected to the processing unit 102, configured to display interpretable generated recommendations, allow plan validation or modification by clinicians, and provide real-time visualization of patient recovery progress; and
vii) a patient user-interface 109 operatively connected to the processing unit 102, configured to deliver dynamic instructions, medication reminders, guided physiotherapy routines, and personalized notifications;
wherein all the modules are stored in a non-transitory memory 107 and are configured for execution by the processing unit 102, enabling continuous, adaptive, and expert-informed post-surgical recovery planning.

2) The system as claimed in claim 1, wherein the patient data acquisition module 101 is configured to aggregate data from heterogeneous sources including wearable medical systems, mobile health applications, and hospital electronic health record (EHR) systems.

3) The system as claimed in claim 1, wherein the recovery plan generation module 104 includes a decision layer configured to compare multiple inferred recovery strategies and select an optimal trajectory based on predicted patient outcomes.

4) The system as claimed in claim 1, wherein the recovery plans dynamically adapt in real-time based on continuous patient monitoring.

5) The system as claimed in claim 1, wherein the multimodal patient monitoring module 105 is configured to issue alerts to the clinician user-interface upon detection of predefined clinical thresholds, such as abnormal vitals, skipped medication, or deviation from physiotherapy routine.

6) The system as claimed in claim 1, wherein the processing unit 102 is further configured to evaluate system performance using historical patient recovery benchmarks and update the IRL module 103 using feedback from actual recovery outcomes.

7) The system as claimed in claim 1, wherein the feedback and adaptation module 106 comprises a continuous learning loop that modifies recovery trajectories upon detection of anomalies, deviations, or complications in the patient’s progress.

8) The system as claimed in claim 1, wherein the processing unit 102 generates alerts to clinicians upon detecting early signs of post-surgical complications, thereby reducing the risk of adverse events.

9) The system as claimed in claim 1, wherein the patient user-interface 109 includes adaptive notification scheduling that modifies reminder frequency based on prior user interaction history and adherence patterns.

10) The system as claimed in claim 1, wherein the clinician user-interface 108 further provides a transparency module configured to display explanations of the IRL-inferred recovery plan decisions, including the underlying expert strategies and predicted patient outcome justifications.