Tata Consultancy Services Limited

Conduent Business Services, LLC

Xerox Corporation

Sakyajit Bhattacharya

Vaibhav Rajan

Arpan Pal

Avik Ghose

Soma Bandyopadhyay

Vijay Huddar

Aniruddha Sinha

Rohan Banerjee

Koustuv Dasgupta

Tridib Mukherjee

Dibyendu Roy

Bhupendra Singh Solanki

Harsh Shrivastava

Shourya Roy

Arijit Chowdhury

Arijit Mukherjee

Arijit Ukil

Parijat Dilip Deshpande

Anirban Dutta Choudhury

Abhishek Tripathi

Sounak Dey

Shruti Kunde

Shreyasi Datta

Oishee Mazumder

Vivek Chandel

Prathosh Aragulla Prasad

Kayapanda Muthana Mandana

Sundeep Khandelwal

Sharanya Eswaran

Stephen Craig Fullerton

Varsha Sharma

Shisagnee Banerjee

Abhishek Sengupta

Katerina Sinclair

Dhaval Satish Jani

Todd Redmond

Ranjan Shetty K

Amith Sitaram

Vivek G Raman

James D Kirkendall

Mahima Suresh

Oishee Muzumder

Kaustab Pal

Systems and methods for modelling prediction errors in path-learning of an autonomous learning agent are provided. The traditional systems and methods provide for machine learning techniques, wherein estimation of errors in prediction is reduced with an increase in the number of path-iterations of the autonomous learning agent. Embodiments of the present disclosure provide for a two-stage modelling technique to model the prediction errors in the path-learning of the autonomous learning agent, wherein the two-stage modelling technique comprises extracting a plurality of fitted error values corresponding to a plurality of predicted actions and actual actions by implementing an Autoregressive moving average (ARMA) technique on a set of prediction error values; and estimating, by implementing a linear regression technique on the plurality of fitted error values, a probable deviation of the autonomous learning agent from each of an actual action amongst a plurality of predicted and actual actions.

Systems and methods for modelling prediction errors in path-learning of an autonomous learning agent

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 generally to methods and systems for unobtrusive digital health assessment of high risk subjects, wherein bio-markers pertaining to a disease are identified automatically using physical activity and physiology monitoring on a continuous basis. Identification of bio-markers in the medical domain is conventionally dependent on insights derived from medical tests which are obtrusive in nature. Systems and methods of the present disclosure integrate physical characteristics, lifestyle habits and prevailing medical conditions with monitored physical activities and physiological measurements to assess health of high risk subjects. Systems and methods of the present disclosure also enable automatic generation of control class and treatment class that may be effectively used for health assessment.

Systems and methods for unobtrusive digital health assessment

This disclosure relates generally to categorical time-series clustering. In an embodiment, the method for categorical time-series clustering for categorical time-series associated with distinct subjects obtained from sensors. Based on the categorical time-series, the subjects are clustered into clusters by using a Markov chain model. Clustering the subjects include assigning each subject to a cluster. The subjects are assigned to the clusters by determining cluster-specific transition matrices based on a transitional probability of the subject's transitioning between states. A semi-distance function is constructed for each cluster-specific transitional matrix between the states at multiple time instances, which us indicative of a conditional probability of movement of the subject between the states at different time instance. Using an expectation maximization (EM) model, one or more latent variables of each of the cluster-specific transitional matrices are obtained to determine a likelihood of association of the subject to the cluster.

System and method for categorical time-series clustering

This disclosure relates generally to a unified platform for domain adaptable human behaviour inference. The platform provides a unified, low level inference and high level inference of domain adaptable human behaviour inference. The low level inferences include cross-sectional analysis techniques to infer location, activity, physiology. Further the high inference that provide useful and actionable for longitudinal tracking, prediction and anomaly detection is performed based on several longitudinal analysis techniques that include welch analysis, cross-spectrum analysis, Feature of interest (FOI) identification and time-series clustering, autocorrelation-based distance estimation and exponential smoothing, seasonal and non-seasonal models identification, ARIMA modelling, Hidden Markov models, Long short term memory (LSTM) along with low level inference, human meta-data and application domain knowledge. Further the unified human behaviour inference can be obtained across multiple domains that include health, retail and transportation.

Unified platform for domain adaptable human behaviour inference

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

Non-invasive methods for accurately classifying Coronary Artery Disease (CAD) is a challenging task. In the present disclosure, a two stage classification is performed. In the first stage of classification, a metadata based rule engine is utilized to classify a subject into one of a confirmed CAD subject, a CAD subject and a non-CAD subject. Here, a set of optimal parameters are selected from a set of metadata associated with the subject based on a difference in frequency of occurrence of the CAD among a disease population and a non-disease population. Further, an optimal threshold associated with each optimal parameter is calculated based on an inflexion based correlation analysis. Further, the CAD subject, classified by the metadata based rule engine is further reclassified in a second stage by utilizing a set of cardiovascular signal into one of the CAD subject and the non-CAD subject.

System and method for classification of coronary artery disease based on metadata and cardiovascular signals

According to embodiments illustrated herein, there is provided a system for predicting a health condition of a patient. The system further includes one or more processors configured to separately cluster data points from a set of medical records associated with a first class of patients and a second class of patients. A similarity value of each of the clustered data points with respect to a pre-selected subset of data points that represents landmark points may be determined, using a parameterized similarity measure. One or more classifiers are trained using the determined similarity value of each data point. The trained one or more classifiers are adapted to learn one or more parameters of the parameterized similarity measure during the training. An occurrence of the health condition of the patient may be predicted based on the trained one or more classifiers and one or more medical records of the patient.

System and method for predicting health condition of a patient

Electrocardiography (ECG) signals contain important markers for Coronary Heart Disease (CHD). State of the art systems and methods rely on clinically available multi-lead ECG for CHD classification which is not cost effective. Moreover the state of the art methods are applied on digital ECG time series data only. Also, discriminative HRV markers are not often present in short ECG recordings necessitating long hours of ECG data to analyze. In accordance with the present disclosure, systems and methods described hereinafter extract ECG time series from ECG images obtained from commercially available low-cost single lead ECG devices through a combination of image and signal processing steps including Histogram analysis, Morphological operation-thinning, Extraction of lines, Extraction of Reference Pulse, Extraction of ECG and interpolating missing data. Further, domain independent statistical features such as self-similarity of raw ECG time series and average Maharaj's distance along with domain specific features are used for classifying CHD.

Non-invasive detection of coronary heart disease from short single-lead ECG

A method, non-transitory computer readable medium and apparatus for predicting mortality of a current patient are disclosed. For example, the method includes receiving data associated with a plurality of different patients with known mortality outcomes, wherein the data includes a subset of data for each one of a plurality of different measurement timepoints for each one of the plurality of different patients, calculating n number of classifiers, wherein n is equal to a number of the plurality of different measurement timepoints, receiving data associated with the current patient at an i-th measurement timepoint, predicting the current patient has a high mortality risk based on an output of the i-th classifier of the n number of classifiers and transmitting a signal to a health administration server to cause an alarm to be generated in response to the high mortality risk that is predicted.

Method and apparatus for predicting mortality of a patient using trained classifiers

Identification of pulmonary diseases involves accurate auscultation as well as elaborate and expensive pulmonary function tests. Also, there is a dependency on a reference signal from a flowmeter or need for labelled respiratory phases. The present disclosure provides extraction of frequency and time-frequency domain lung sound features such as spectral and spectrogram features respectively that enable classification of healthy and abnormal lung sounds without the dependencies of prior art. Furthermore extraction of wavelet and cepstral features improves accuracy of classification. The lung sound signals are pre-processed prior to feature extraction to eliminate heart sounds and reduce computational requirements while ensuring that information providing adequate discrimination between healthy and abnormal lung sounds is not lost.

Systems and methods for detecting pulmonary abnormalities using lung sounds

A crime analysis system, method, and apparatus comprising at least one processor and a storage device communicatively coupled to the at least one processor, the storage device storing instructions which, when executed by the at least one processor, cause the processor to perform operations comprising receiving information provided by one or more data collection source, storing the information, wherein the stored information is formatted, processing the information to generate crime clustering data associated with at least one region and at least one crime, processing the crime clustering data associated with at least one region and at least one crime to generate benchmarking of the at least one region with at least one other region, and providing crime clustering data associated with at least one region and at least one crime, and benchmarking of the at least one region with at least one other region for presentation through a user interface.

Mixture model based time-series clustering of crime data across spatial entities

According to embodiments illustrated herein, there is provided a system for predicting a health condition of a first patient. The system includes a document processor configured to extract one or more headings from one or more medical records of the first patient based on one or more predefined rules. The document processor is further configured to extract one or more words from one or more phrases written under each of the extracted one or more headings, wherein the one or more phrases correspond to documentation of the observation of the first patient by a medical attender. The system further includes one or more processors configured to predict the health condition of the first patient based on a count of the one or more words in historical medical records and the one or more medical records.

A method and a system for predicting admission of a human subject to a first ward in a medical center are disclosed. A patient dataset is generated based on at least a measure of one or more physiological parameters associated with one or more first human subjects and a first information pertaining to the admission of each of the one or more first human subjects to the first ward. For a first human subject of the one or more first human subjects, a first score at each of the one or more first time instants is determined. Further, one or more second time instants from the one or more first time instants are identified. Further, a second score at each of the one or more second time instants is determined. In an embodiment, the first classifier is trained based on at least the second score, and the first information.

Method and system for predicting admission of a human subject to a ward in a medical center

Disclosed are embodiments of methods and systems for predicting mortality of a first patient. The method comprises categorizing a historical data into a first category and a second category. The method further comprises determining a first test parameter and a second test parameter based on at least one of a sample data of a first patient and the historical data corresponding to at least one of the first category and the second category. The method further comprises determining a probability score based on a cumulative distribution of at least one of the first test parameter and the second test parameter. The method further comprises categorizing the sample data in one of the first category and the second category based on the probability score. Further, the method comprises predicting the mortality of the first patient based on at least the categorization of the sample data of the first patient.

Methods and systems for predicting mortality of a patient

Growing community of inventors

Bengaluru, India

Sakyajit Bhattacharya