Rahul Krishnan Pathinarupothi

GeoBoids: A mobile AR application for exergaming

We have designed a mobile Augmented Reality (AR) game which incorporates video see-through and spatialized audio AR techniques and encourages player movement in the real world. In the game, called GeoBoids, the player is surrounded by flocks of virtual creatures that are visible and audible through mobile AR application. The goal is for the player to run to the location of a GeoBoid swarm in the real world, capture all the creatures there, then run to the next swarm and repeat, before time runs out, encouraging the player to exercise during game play. The most novel elements of the game are the use of audio input and output for interacting with the creatures. The interface design of the game includes AR visualization, spatialized audio, touch gestures and whistle interaction. Feedback from users in a preliminary user study was mostly positive on overall game play and the design of the UI, while the results also revealed improvements were needed for whistle interaction and the visual design of the GeoBoids.

RASPRO: rapid summarization for effective prognosis in wireless remote health monitoring

Consistent power and cost effective health monitoring has become the need of the hour especially for the unstable, chronically and critically ill. Here we present a novel architecture and algorithmic methodology combining the sensing subsystem, symptom summarization, and data transmission. Physiological parameters from multiple sensors feed into a severity quantizer and a subsequent multiplexer, the output of which is processed by the RASPRO engine to rapidly discover and alert any health criticalities. The architecture is optimized for communication and energy performance, and the algorithms result in lucid presentations to physicians. The whole system is the result of close collaboration between engineering and medical teams at one of the best known multidisciplinary universities, building on a multi-terabyte more than a million patient Amrita Hospital Information System (HIS) database, and is being readied for deployment on a large telemedicine network of more than 60 nodes in the Indian subcontinent and parts of Africa.

A real-time detection and warning of cardiovascular disease LAHB for a wearable wireless ECG device

According to the World Health Organization, an estimated 17 million people die annually due to cardiac disease, which accounts for 30% of the global deaths. Current studies on cardiac diseases indicate that 15% of the people have Left Anterior Hemiblock (LAHB), which ranks third after Right Bundle Branch Block (RBBB) and Left Bundle Branch Block (LBBB). To our knowledge, a reliably consistent disease detection and warning algorithm is not currently available for LAHB although various ECG morphologies can be monitored for real-time detection of LAHB. The objective of this research is to develop a real-time detection and warning of LAHB. The presented work describes the design of a weighted feature-based disease classification algorithm, which can be run in a resource constrained mobile environment for effective real-time diagnosis. The testing and evaluation of the algorithm indicates that it is able to detect LAHB with an accuracy of 95.3% and specificity of 100%.

Discovering vital trends for personalized healthcare delivery

Personalization of remote health monitoring and healthcare delivery is a challenging research problem faced by practitioners and researchers alike. In this paper we present techniques for trend analysis and data summarization using personalized severity based motif discovery in large time series medical data.

Effective Prognosis Using Wireless Multi-sensors for Remote Healthcare Service

Remote healthcare delivery is one of the most promising solutions to tackle global trends in falling health care access and quality of service. A wireless network of sensors, IoT devices, and cloud is presented here. New innovative algorithms for effective prognosis are designed and developed based on motifs and profile matrices. The system consisting of the sensor network and algorithms together enable delivering remote healthcare services.

Large scale remote health monitoring in sparsely connected rural regions

Remote health monitoring and intervention systems including wearable sensors, smartphones and advanced communication technologies are slated to be a game changer in the delivery of quality healthcare services, especially in developing parts of the world. However, we are yet to see large scale adoption of remote health monitoring systems due to many factors such as: lack of reliable data network coverage, high power requirements for smartphone analytics, and unreliability in the timely delivery of critical data to remote doctors. In addition to these, the huge volume of sensor data and alerts from multiple remote patients are unmanageable for already overloaded doctors. In this paper, we attempt to address each of these issues. First, we propose a novel healthcare communication architecture that connects remotely stationed telemedicine nodes and village clinics with remote doctors in specialty hospitals. Second, we present the development of disease severity pattern discovery and summarization algorithms, the result of which is a Consensus Abnormality Motif (CAM) and an associated Alert Measure Index, which suggests the immediacy of the patient data for doctors consultative time. By frequently sending CAM as SMS in the absence of data network, we ensure timely delivery of critical data. Through a Detailed Data on Demand (DD-on-D) pull data mechanism doctors can further investigate complete data from the cloud. The CAM and DD-on-D mechanisms result in energy savings of up to 25%, while the data usage is reduced tremendously. Furthermore, we present a pilot deployment of the systems using a continuous cardiac monitoring device coupled with an intervention framework including more than 60 telemedicine nodes station in villages across India.

Instantaneous heart rate as a robust feature for sleep apnea severity detection using deep learning

Automated sleep apnea detection and severity identification has largely focused on multivariate sensor data in the past two decades. Clinically too, sleep apnea is identified using a combination of markers including blood oxygen saturation, respiration rate etc. More recently, scientists have begun to investigate the use of instantaneous heart rates for detection and severity measurement of sleep apnea. However, the best-known techniques that use heart rate and its derivatives have been able to achieve less than 85% accuracy in classifying minute-to-minute apnea data. In our research reported in this paper, we apply a deep learning technique called LSTM-RNN (long short-term memory recurrent neural network) for identification of sleep apnea and its severity based only on instantaneous heart rates. We have tested this model on multiple sleep apnea datasets and obtained perfect accuracy. Furthermore, we have also tested its robustness on an arrhythmia dataset (that is highly probable in mimicking sleep apnea heart rate variability) and found that the model is highly accurate in distinguishing between the two.

H-Plane: Intelligent Data Management for Mobile Healthcare Applications

We present an intelligent data management framework that can facilitate development of highly scalable and mobile healthcare applications for remote monitoring of patients. This is achieved through the use of a global log data abstraction that leverages the storage and processing capabilities of the edge devices and the cloud in a seamless manner. In existing log based storage systems, data is read as fixed size chunks from the cloud to enhance performance. However, in healthcare applications, where the data access pattern of the end users differ widely, this approach leads to unnecessary storage and cost overheads. To overcome these, we propose dynamic log chunking. The experimental results, comparing existing fixed chunking against the H-Plane model, show 13 %–19 % savings in network bandwidth as well as cost while fetching the data from the cloud.

IoT Based Smart Edge for Global Health: Remote Monitoring with Severity Detection and Alerts Transmission

Global health which denotes equitable access to healthcare, particularly in remote-rural-developing regions, is characterized by unique challenges of affordability, accessibility, and availability for which one of the most promising technological interventions that is emerging is the Internet of Things (IoT)-based remote health monitoring. We present an IoT-based smart edge system for remote health monitoring, in which wearable vital sensors transmit data into two novel software engines, namely rapid active summarization for effective prognosis (RASPRO) and criticality measure index (CMI) alerts, both of which we have implemented in the IoT smart edge. RASPRO transforms voluminous sensor data into clinically meaningful summaries called personalized health motifs (PHMs). The CMI alerts engine computes an aggregate criticality score. Our IoT smart edge employs a risk-stratified protocol consisting of rapid guaranteed push of alerts and PHMs directly to the physicians, and best effort pull of detailed data-on-demand through the cloud. We have carried out both clinical validation and performance evaluation of our smart edge system. The clinical validation on 183 patients demonstrated that the IoT smart edge is highly effective in remote monitoring, advance warning and detection of cardiac conditions, as quantified by three measures, precision (0.87), recall (0.83), and F1-score (0.85). Furthermore, performance evaluation showed significant reductions in the bandwidth (98%) and energy (90%), thereby making it suitable for emerging narrow-band IoT networks. In the deployment of our system in the cardiology institute of our University hospital, we observed that our IoT smart edge helped to increase the availability of physicians by 59%. Hence, our IoT smart edge system is a significant step toward addressing the requirements for global health.

Data to diagnosis in global health: a 3P approach

BackgroundWith connected medical devices fast becoming ubiquitous in healthcare monitoring there is a deluge of data coming from multiple body-attached sensors. Transforming this flood of data into effective and efficient diagnosis is a major challenge.MethodsTo address this challenge, we present a 3P approach: personalized patient monitoring, precision diagnostics, and preventive criticality alerts. In a collaborative work with doctors, we present the design, development, and testing of a healthcare data analytics and communication framework that we call RASPRO (Rapid Active Summarization for effective PROgnosis). The heart of RASPRO is Physician Assist Filters (PAF) that transform unwieldy multi-sensor time series data into summarized patient/disease specific trends in steps of progressive precision as demanded by the doctor for patient’s personalized condition at hand and help in identifying and subsequently predictively alerting the onset of critical conditions. The output of PAFs is a clinically useful, yet extremely succinct summary of a patient’s medical condition, represented as a motif, which could be sent to remote doctors even over SMS, reducing the need for data bandwidths. We evaluate the clinical validity of these techniques using SVM machine learning models measuring both the predictive power and its ability to classify disease condition. We used more than 16,000 min of patient data (N=70) from the openly available MIMIC II database for conducting these experiments. Furthermore, we also report the clinical utility of the system through doctor feedback from a large super-speciality hospital in India.ResultsThe results show that the RASPRO motifs perform as well as (and in many cases better than) raw time series data. In addition, we also see improvement in diagnostic performance using optimized sensor severity threshold ranges set using the personalization PAF severity quantizer.ConclusionThe RASPRO-PAF system and the associated techniques are found to be useful in many healthcare applications, especially in remote patient monitoring. The personalization, precision, and prevention PAFs presented in the paper successfully shows remarkable performance in satisfying the goals of 3Ps, thereby providing the advantages of three A’s: availability, affordability, and accessibility in the global health scenario.