Tata Consultancy Services Limited

Indian Statistical Institute

Aniruddha Sinha

Arpan Pal

Debatri Chatterjee

Kingshuk Chakravarty

Oishee Mazumder

Rohan Banerjee

Rahul Dasharath Gavas

Tanushyam Chattopadhyay

Avik Ghose

Brojeshwar Bhowmick

Arijit Sinharay

Anirban Dutta Choudhury

Rajat Kumar Das

Dibyendu Roy

Arindam Saha

Abhijit Das

Chirabrata Bhaumik

Rohit Gupta

Balamuralidhar Purushothaman

Sakyajit Bhattacharya

Prateep Misra

Diptesh Das

Aishwarya Visvanathan

Sangheeta Roy

Dhiman Chattopadhyay

Anwesha Khasnobish

Shreyasi Datta

Sanjana Sinha

Priyanka Sinha

Ramu Reddy Vempada

Apurbaa Mallik

Anupam Basu

Pratyusha Das

Ayan Chaki

Sanjoy Kumar Saha

Gautam Shroff

Soma Bandyopadhyay

Sunil Kumar Kopparapu

Deepak N Swamy

Snehasis Banerjee

Ranjan Dasgupta

Srinivasan Jayaraman

Sundeep Khandelwal

Ramesh Kumar Ramakrishnan

Hiranmay Ghosh

Venkatramanan Siva Subrahmanian

Utpal Garain

Anagha Nikhil Mehrotra

Guruprasad Seshadri

Midhun Parakkal Unni

Provat Biswas

Mohd Bilal Arif Syed

Manoj C R

Debabrata Pradhan

Soumali Roychowdhury

Uttama Lahiri

Srinivasa Chakravarthy Vaddadi

Dipayan Biswas

Sudeepto Dutta

Soumya Rajan Tripathy

Shivam Gupta

Ayush Rai

Oishee Muzumder

Sudeb Das

Meghamala Sinha

Aditi Misra

Sandeep Gattani

Aditi Mishra

Anurag Kumar

Arpit Vishwakarma

Kallol Ghosh

Ratnamala Manna

Jitendra Jain

Vedraj

Aritra Chakravorty

Pratap Pulugoru

Sachin Agsebagil

Amit Konar

Debatri Chetterjee

Soumya Ranjan Tripathy

Anirban Chowdhury

Rohit Kumar Gupta

Vedraj Vedraj

Rahul Dashrath Gavas

Midhun P Unni

Somnath Ghosh Dastidar

The present invention relates to a method and system for determining progression of atrial fibrillation (AF) based on hemodynamic metrics. In conventional CFD models, effect of the AF on a cardiovascular system is not modeled and evaluation of associated hemodynamic metrics and its effect on a Left Atrium (LA) dynamics is not considered. The method and system for determining progression of the AF based on the hemodynamic metrics, analyzes the effect of the AF on cardiovascular parameters of the LA and a left Ventricle (LV), for AF variations. A 3D-CFD model is modelled from a plurality of scan images of a heart of a subject and the AF variations are incorporated in a zero-dimensional (OD) lumped cardiovascular hemodynamic model along with a novel rhythm generator that are used for extracting a plurality of LA hemodynamic metrics of wall shear stress (WSS) that are possible indicators for progression of the AF.

Method and system for determining progression of atrial fibrillation based on hemodynamic metrics

This disclosure relates generally to a method and system that provides personalized neuro motor rehabilitation therapy using a musculoskeletal arm model. The arm model is personalized using anthropometric measures and further adapted to operate using an optimized set of muscle actuators considering associated redundancy. The method generates trajectories associated with reach motion profiles for each motion task utilizing joint kinematics and inverse dynamics by integrating forward dynamics and muscle synergy concepts to select the optimized set of muscle actuators. The generated trajectories are further ranked based on muscle synergy, minimum energy consumption and optimized trajectory to select rehabilitation therapy best suited for effective recovery. Conventional methods that work with neural dynamics in deriving muscle synergy are dependent on single tasks, leaving synergy variation with task variability unexplored. The present disclosure provides understanding of work space, task variability and synergy paradigm to derive conclusive control actions for aiding rehabilitation effectively.

Personalized neuromotor rehabilitation therapy for upper limb using a neuromusculoskeletal arm model

This disclosure relates generally to method and system for determining myocardial ischemia severity based on hemodynamic parameters estimation. Many patients suffer from myocardial ischemia due to narrowing of coronary artery resulting poor oxygen supply in cardiac muscles. The method includes receiving Electrophysiology (EP) signal from a simulated heart surface model to generate a single lead ECG template. The method further estimates hemodynamic parameters using a hemodynamic module based on the single lead ECG template and then estimates cardiac pressure-volume loop variables. The myocardial ischemia severity of the heart surface model is determined which includes one of moderate ischemia, severe ischemia and silent ischemia. Here, the cardiac source module is coupled with the hemodynamic module to determine cardiac transmembrane potential (TMP) of the heart surface model through contractility function. This method serves as a guidance platform for patient care such as synthetic data generation for disease classification pertaining to coronary artery.

Method and system for determining myocardial ischemia severity based on hemodynamic parameters estimation

State of the art systems and methods attempting to generate synthetic biosignals such as PPG generate patient specific PPG signatures and do not correlate with pathophysiological changes. Embodiments herein provide a method and system for generating synthetic time domain signals to build a classifier. The synthetic signals are generated using statistical explosion. Initially, a parent dataset of actual sample data of class and non-class subjects is identified, and statistical features are extracted. Kernel density estimate (KDE) is used to vary the feature distribution and create multiple data template from a single parent signal. PPG signal is again reconstructed from the distribution pattern using non-parametric techniques. The generated synthetic data set is used to build the two stage cascaded classifier to classify CAD and Non CAD, wherein the classifier design enables reducing bias towards any class.

Method and system for generating synthetic time domain signals to build a classifier

This disclosure relates to analyzing effect of a secondary cognitive load task on a primary executive task. Human random sequence generation is a marker to study cognitive functions and inability to generate random sequences (RS) can reveal underlying impairments. Traditionally, 'call out' or ‘write down’ procedures are used to obtain human generated numbers, wherein short term memory and number of previously generated entities visible to a subject plays a major role. Also precise trial-wise or response-wise analysis may not be possible. In the present disclosure, the human generated random numbers are digitized into RS and a cognitive load (CL) inducing task is imposed on the executive task. The CL demanding task disrupts randomization performance. Deviation from randomness, load index based on gaze data and deviation from pupillometry data of healthy subjects are provided as indicators of an interference effect imposed by the CL and thereby indicative of underlying impairments.

Analyzing effect of a secondary cognitive load task on a primary executive task

This disclosure provides a simulation platform to study and perform predictive analysis on valvular heart disease, Mitral stenosis (MS) and provides a control approach to correct hemodynamic imbalances during MS conditions. Conventional approaches of valve repair or replacement are often associated with risk of thromboembolism, need for anticoagulation, prosthetic endocarditis, and impaired left ventricle function. The cardiovascular hemodynamics model of the present disclosure helps to create 'what if' conditions to study variations in different hemodynamic parameters like blood flow, aortic and ventricular pressure, etc. during normal and pathological conditions. An adaptive control system in conjunction with the hemodynamic cardiovascular system (CVS) is provided to handle hemodynamic disbalance during moderate to severe MS conditions. The adaptive controller is hypothesized in line with the neuromodulation approach and modulates left ventricular contractility and vagal tone to counter the symptoms associated with MS.

Neuromodulation based adaptive controller for mitral stenosis

This disclosure relates generally to health monitoring and assessment systems, and more particularly to perform postural stability assessment of a user and quantify the assessed postural stability. In an embodiment, the system, by monitoring specific actions (which are part of certain tests done for the postural stability assessment) being performed by a user, collects inputs which are then processed to determine SLS duration, the body joint vibration, and the body sway area of the user, while performing the tests. By processing the SLS duration, the body joint vibration, and the body sway area together, a postural stability index score for the user is determined, and based on this score, postural stability assessment for the user is performed.

Method and system for postural stability assessment

Conventionally, a neuronal controller located inside the central nervous system governing the maintenance of the upright posture of the human body is designed from a control system perspective using proportional-integral-derivative (PID) controllers, wherein human postural sway is modeled either along a sagittal plan or along a frontal plane separately resulting in limited insights on intricacies of a governing neuronal controller. Also, existing neuronal controllers using a reinforcement learning (RL) paradigm are based on complex actor-critic on-policy algorithms. Analyzing human postural sway is critical to detect markers for progression of balance impairments. The present disclosure facilitates modelling the neuronal controller using a simplified RL algorithm, capable of producing postural sway characteristics in both sagittal and frontal plane together. The Q-learning technique of the RL paradigm is employed for learning an optimal state-action value (Q-value) function for a tuneable Markov Decision Process (MDP) model.

Modeling a neuronal controller exhibiting human postural sway

This disclosure relates generally to a Parkinson's disease detection system. Parkinson's disease is a neuro-degenerative disorder affecting motor and cognitive functions of subjects. Since symptom manifestation is limited in Parkinson's disease, identifying Parkinson's disease in the early stage is a challenging task. The present disclosure overcomes the limitations of the conventional methods for detecting Parkinson's disease by utilizing a graph theory approach. Here, each pressure sensor attached to an insole corresponding to a plurality of pressure points associated with a foot of the subject is considered as a node of a connectivity graph. The foot dynamics analysis is performed based on a metric known as mediolateral stability index and the mediolateral stability index is calculated by utilizing a betweenness centrality associated with each node of the connectivity graph. Further, the mediolateral stability index is compared with standard values to detect the intensity of the Parkinson's disease.

Method and system for detecting Parkinson's disease progression

Collision avoidance and postural stability adjustment may provide an effective dual task paradigm to interpret the effect of proprioceptive adaptation on balance control. However, conventionally tasks are physical tasks performed under supervision in specific set up environments. Implementations of the present disclosure provide methods and systems for interpreting neural interplay involving proprioceptive adaptation in a lower limb during a dual task paradigm. The disclosed method provides a better interpreting of the neuronal mechanisms underlying adaptation and learning of skilled motor movement and to determine the relationship of lower limb proprioceptive sense and postural stability by simulating integration of a Single Limb Stance (SLS) functionality test for postural stability and a single limb collision avoidance task, in an adaptive Virtual Reality (VR) environment provided to a subject.

Method and system for interpreting neural interplay involving proprioceptive adaptation during a dual task paradigm

A system and method for risk prediction and corrective action for a contact type activity is provided. The method includes generating a personalized full body musculoskeletal model to depict the knee and ankle joint behavior of a subject during the contact type activity. Various contact type activities are simulated using the personalized full body musculoskeletal model. Injury biomarkers and their parameters based on the contact type activities are identified, parameters are indicative of risk of injury to participating muscle groups said activity. Based on the injury biomarkers, optimal muscle co-activation parameters are analyzed by a neuro-muscular controller, to adapt the participating muscle groups for providing the correction action against the predicted risk of injury. Said optimal muscle co-activation parameters are indicative of muscle synergy during the contact type activity.

Method and system for injury risk prediction and corrective action for high contact type activity

The disclosure relates to digital twin of cardiovascular system called as cardiovascular model to generate synthetic Photoplethysmogram (PPG) signal pertaining to disease conditions. The conventional methods are stochastic model capable of generating statistically equivalent PPG signals by utilizing shape parameterization and a nonstationary model of PPG signal time evolution. But these technique generates only patient specific PPG signatures and do not correlate with pathophysiological changes. Further, these techniques like most synthetic data generation techniques lack interpretability. The cardiovascular model of the present disclosure is configured to generate the plurality of synthetic PPG signals corresponding to the plurality of disease conditions. The plurality of synthetic PPG signals can be used to tune Machine Learning algorithms. Further, the plurality of synthetic PPG signals can be utilized to understand, analyze and classify cardiovascular disease progression.

Method and system for pressure autoregulation based synthesizing of photoplethysmogram signal

System and method for digitized digit symbol substitution test (DSST) are disclosed. In an example, a display area of a digitized DSST device is partitioned into multiple bins. Further, a series of number symbol pairs is displayed as a lookup table on top of the display, termed as a lookup area. Furthermore, a question and answer (QA) pair corresponding to the series of number symbol pairs to an examinee in multiple trials. In addition, feature values for the QA pair are computed in each of the multiple bins in the trials, wherein the feature values comprise a response time and an accuracy of response by the examinee. Moreover, probabilities of the feature values are determined in each of the multiple bins. Also, an entropy value based on the probabilities of the feature values is computed in each of the multiple bins providing information on distribution.

System and method for digitized digit symbol substitution test

A method for measuring blood pressure of a subject is described herein. In an implementation, the method includes obtaining a plurality of photoplethysmogram (PPG) features associated with the subject. The method further includes ascertaining one or more latent parameters associated with the subject based on the plurality of PPG features and a reference model, wherein the reference model indicates a correlation between the plurality of PPG features and the one or more latent parameters. Further, blood pressure of the subject is determined based on the one or more latent parameters and the plurality of PPG features.

Measuring blood pressure

A method and system is provided for assessing the learning experience of the person by monitoring the mental state of the person. The method involves measuring the brain signal, skin conductance using GSR device, and heart rate variability using the pulse oximeter. These physiological signals are measured when the person is performing an activity such as the modified Stroop test. Once the activity is performed, an offline questionnaire is also filled by the person. Based on the comparison of the offline questionnaire and the physiological signals, a model is generated. This model is used to assess the learning experience of the person. According to another embodiment, a method is also provided for maintaining the steady flow state of a person while performing any activity.

Method and system for assessing learning experience of a person

Growing community of inventors

Kolkata, India

Aniruddha Sinha