Ekanath Rangan - Academia.edu (original) (raw)

Papers by Ekanath Rangan

Research paper thumbnail of Adaptive Motif-Based Alerts for Mobile Health Monitoring

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, 2017

We have developed a rapid remote health monitoring architecture called RASPRO using wearable sens... more We have developed a rapid remote health monitoring architecture called RASPRO using wearable sensors and smartphones. RASPRO’s novelty comes from its techniques to efficiently compute compact alerts from sensor data. The alerts are computationally fast to run on patients’ smartphones, are effective to accurately communicate patients’ severity to physicians, take into consideration inter-sensor dependencies, and are adaptive based on recently observed parametric trends. Preliminary implementation with practicing physicians and testing on patient data from our collaborating multi-specialty hospital has yielded encouraging results.

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Heart Lung Health Monitor: Remote At-Home Patient Surveillance for Pandemic Management

2021 IEEE Global Humanitarian Technology Conference (GHTC), 2021

The COVID-19 pandemic has brought about an unprecedented shift towards Telehealth since physician... more The COVID-19 pandemic has brought about an unprecedented shift towards Telehealth since physicians are overwhelmed by the huge patient load in hospitals. This has forced policy makers to advise home quarantine for mild and moderate COVID patients. Additionally, even non-COVID patients with diabetes and cardiovascular or pulmonary diseases who do not need hospitalization are currently being monitored at home for any changes in their severity that may require a home to hospital transfer. Our research team has developed an Internet of Medical Things wearable Heart Lung Health monitor for patients with cardiovascular and pulmonary risk factors so as to enable hospitals to remotely track patient health status. Our system consists of a credit-card sized wearable 3-lead ECG device interfaced with smartphone that analyzes ECG and extracts heart and respiratory parameters, and transmits these to a dashboard for remote monitoring. We present the architecture, device, respiratory rate extraction algorithm, and its validation on 50 patients. Encouraged by these results we are readying deployment of our system for home monitoring of at-risk patients.

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Additional file 5 of Data to diagnosis in global health: a 3P approach

Moving Window QTS (B=20) Vs. MTS. The figure shows the F1-score comparison of QTS with B=20 and M... more Moving Window QTS (B=20) Vs. MTS. The figure shows the F1-score comparison of QTS with B=20 and MTS while using a moving window of size 30 mins with varying backward offset from t0. The results show that QTS is marginally better than MTS in four time slots. (PNG 22 kb)

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Additional file 4 of Data to diagnosis in global health: a 3P approach

Moving Window QTS (B=15) Vs. MTS. The figure shows the F1-score comparison of QTS with B=15 and M... more Moving Window QTS (B=15) Vs. MTS. The figure shows the F1-score comparison of QTS with B=15 and MTS while using a moving window of size 30 mins with varying backward offset from t0. The results show that MTS is better than QTS except in two time slots, and also W=10 and W=15 are better summarization windows. (PNG 21 kb)

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Additional file 3 of Data to diagnosis in global health: a 3P approach

Moving Window QTS (B=10) Vs. MTS. The figure shows the F1-score comparison of QTS with B=10 and M... more Moving Window QTS (B=10) Vs. MTS. The figure shows the F1-score comparison of QTS with B=10 and MTS while using a moving window of size 30 mins with varying backward offset from t0. The results show that MTS is better than QTS except in two time slots, and also W=10 and W=15 are better summarization windows. (PNG 22 kb)

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Additional file 1 of Data to diagnosis in global health: a 3P approach

Moving Window OTS Vs. QTS. The figure shows the F1-score while using a moving window of size 30 m... more Moving Window OTS Vs. QTS. The figure shows the F1-score while using a moving window of size 30 mins with varying backward offset from t0. The results show that QTS is always better than OTS in classifying a given window as predictor for AHE or not. (PNG 28 kb)

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Real-time alerting system for COVID-19 and other stress events using wearable data

Nature Medicine, 2021

Early detection of infectious diseases is crucial for reducing transmission and facilitating earl... more Early detection of infectious diseases is crucial for reducing transmission and facilitating early intervention. In this study, we built a real-time smartwatch-based alerting system that detects aberrant physiological and activity signals (heart rates and steps) associated with the onset of early infection and implemented this system in a prospective study. In a cohort of 3,318 participants, of whom 84 were infected with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), this system generated alerts for pre-symptomatic and asymptomatic SARS-CoV-2 infection in 67 (80%) of the infected individuals. Pre-symptomatic signals were observed at a median of 3 days before symptom onset. Examination of detailed survey responses provided by the participants revealed that other respiratory infections as well as events not associated with infection, such as stress, alcohol consumption and travel, could also trigger alerts, albeit at a much lower mean frequency (1.15 alert days per pers...

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Real-time and offline techniques for identifying obstructive sleep apnea patients

2016 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC), 2016

Obstructive Sleep Apnea (OSA) is a common sleeping disorder in which persons temporarily stop bre... more Obstructive Sleep Apnea (OSA) is a common sleeping disorder in which persons temporarily stop breathing during their sleep. Untreated OSA may lead to several cardio vascular diseases, diabetes, stroke etc. Currently, overnight Polysomnography (PSG) is the widely used technique to detect sleep apnoea. However, a human expert has to monitor the patient overnight. In this paper, we use the technique of motif discovery to identify long term patterns in vital parameters obtained from a combination of smart phones and body attached sensors. We further extend this work to use hamming distance technique to identify similar patients for case based reasoning. Using this, we reduce the need for having expert intervention. As an initial implementation, we have tested our motif discovery technique on Physionet sleep apnea dataset of ECG and SpO2.

Bookmarks Related papers MentionsView impact

Research paper thumbnail of RASPRO: rapid summarization for effective prognosis in wireless remote health monitoring

2016 IEEE Wireless Health (WH), 2016

Consistent power and cost effective health monitoring has become the need of the hour especially ... more 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.

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Gaze Alignment Techniques for Multipoint Mobile Telemedicine for Ophthalmological Consultations

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, 2018

Bookmarks Related papers MentionsView impact

Research paper thumbnail of A systematic methodology to transform campuses in the developing world into sustainable communities

2016 IEEE Global Humanitarian Technology Conference (GHTC), 2016

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Multi-sensor architecture and algorithms for digital health at every doorstep

2017 Second International Conference on Electrical, Computer and Communication Technologies (ICECCT), 2017

Consistent cost effective health monitoring has become the need of the hour especially for the un... more Consistent 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 and the analytics engines. Physiological parameters from multiple sensors feed into a severity quantizer and a subsequent multiplexer, the output of which is processed by successive physician assist filters 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 our multi-disciplinary University, building on a multi-terabyte, more than a million patient 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.

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Internet-of-Things Based Respiratory Rate Monitoring for Early Detection of Cardiovascular and Pulmonary Diseases

5th EAI International Conference on IoT Technologies for HealthCare, 2019

Ubiquitous penetration of Internet-of-Things (IoT) devices is promising to be an enabler in takin... more Ubiquitous penetration of Internet-of-Things (IoT) devices is promising to be an enabler in taking healthcare services to needy patients even in remote regions. In this paper, we present our wearable IoT remote health monitoring system that includes a photoplethysmograph (PPG) based device to measure physiological parameters such as pulse rate, blood oxygen, and respiratory rate (RR). We have conducted a pilot study of our system on 25 patients, and we report the comparative performance of different techniques for deriving RR from PPG signals. The best performing algorithms achieved a mean absolute error of 0.58 breaths/min, which exhibits the potential of PPG based sensors for automated detection of many cardiovascular and pulmonary diseases, particularly, pneumonia, sleep apnea, and acute respiratory distress syndrome.

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Systems and Methods for Remote Health Monitoring and Management

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Consensus motifs as adaptive and efficient predictors for acute hypotensive episodes

2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2017

Acute hypotensive episodes (AHE) are characterized by continuously low blood pressure for prolong... more Acute hypotensive episodes (AHE) are characterized by continuously low blood pressure for prolonged time, and could be potentially fatal. We present a novel AHE detection system, by first quantizing the blood pressure data into clinically accepted severity ranges and then identifying most frequently occurring blood pressure pattern among these which we call consensus motifs. We apply machine learning techniques (support vector machine) on these consensus motifs. The results show that the use of consensus motifs instead of raw time series data extends the predictability by 45 minutes beyond the 2 hours that is possible using only the raw data, yielding a significant improvement without compromising the clinical accuracy. The system has been implemented as part of a new framework called RASPRO (Rapid Summarization for Effective Prognosis) that we have developed for Wireless Remote Health Monitoring.

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Deriving High Performance Alerts from Reduced Sensor Data for Timely Intervention in Acute Hypotensive Episodes

Alerting critical health conditions ahead of time leads to reduced mortality rates. Recently wire... more Alerting critical health conditions ahead of time leads to reduced mortality rates. Recently wirelessly enabled medical sensors have become pervasive in both hospital and ambulatory settings. These sensors pour out voluminous data that are generally not amenable to direct interpretation. For this data to be practically useful for patients, they must be translatable into alerts that enable doctors to intervene in a timely fashion. In this paper we present a novel three-step technique to derive high performance alerts from voluminous sensor data: A data reduction algorithm that takes into account the medical condition at personalized patient level and thereby converts raw multi-sensor data to patient and disease specific severity representation, which we call as the Personalized Health Motifs (PHM). The PHMs are then modulated by criticality factors derived from interventional time and severity frequency to yield a Criticality Measure Index (CMI). In the final step we generate alerts ...

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Rapid Healthcare Alerts using Multiple Sensors

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Real-time identification & alert of ischemic events in high risk cardiac patients

There is a worldwide trend of increase in cardiac related deaths. One of the major reasons is the... more There is a worldwide trend of increase in cardiac related deaths. One of the major reasons is the condition of cardiac ischemia, which implies inadequacy of blood supply to heart leading to myocardial infarction. One of the main techniques used for detection of ischemia is 12-lead ECG test. However, on most occasions the patient may not be attached to any such devices so as to provide immediate medical help. This emphasizes the need for real time detection of such events. With advances in the field of communication and smartphone-based computations, we are now able to use body attached sensors and smartphone based solutions for real-time detection of diseases. In our work, we introduce a real-time smartphone based ischemia detection system, which combines ECG signals from patients along with their activity for identification of ischemia. As an initial step, the impact of patient activity on ischemia is studied, with a comparison between severity threshold method and contextual sever...

Bookmarks Related papers MentionsView impact

Research paper thumbnail of When Less is Better: A Summarization Technique that Enhances Clinical Effectiveness of Data

The increasing number of wearable sensors for monitoring of various vital parameters such as bloo... more The increasing number of wearable sensors for monitoring of various vital parameters such as blood pressure (BP), blood glucose, or heart rate (HR), has opened up an unprecedented opportunity for personalized real-time monitoring and prediction of critical health conditions of patients. This, however, also poses the dual challenges of identifying clinically relevant information from vast volumes of sensor time-series data and of storing and communicating it to health-care providers especially in the context of rural areas of developing regions where communication bandwidth may be limited. One approach to address these challenges is data summarization, but the danger of losing clinically useful information makes it less appealing to medical practitioners. To overcome this, we develop a data summarization technique called RASPRO (Rapid Active Summarization for effective PROgnosis), which transforms raw sensor time-series data into a series of low bandwidth, medically interpretable sym...

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Real-time Alerting System for COVID-19 Using Wearable Data

medRxiv, 2021

Early detection of infectious disease is crucial for reducing transmission and facilitating early... more Early detection of infectious disease is crucial for reducing transmission and facilitating early intervention. We built a real-time smartwatch-based alerting system for the detection of aberrant physiological and activity signals (e.g. resting heart rate, steps) associated with early infection onset at the individual level. Upon applying this system to a cohort of 3,246 participants, we found that alerts were generated for pre-symptomatic and asymptomatic COVID-19 infections in 78% of cases, and pre-symptomatic signals were observed a median of three days prior to symptom onset. Furthermore, by examining over 100,000 survey annotations, we found that other respiratory infections as well as events not associated with COVID-19 (e.g. stress, alcohol consumption, travel) could trigger alerts, albeit at a lower mean period (1.9 days) than those observed in the COVID-19 cases (4.3 days). Thus this system has potential both for advanced warning of COVID-19 as well as a general system for ...

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Adaptive Motif-Based Alerts for Mobile Health Monitoring

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, 2017

We have developed a rapid remote health monitoring architecture called RASPRO using wearable sens... more We have developed a rapid remote health monitoring architecture called RASPRO using wearable sensors and smartphones. RASPRO’s novelty comes from its techniques to efficiently compute compact alerts from sensor data. The alerts are computationally fast to run on patients’ smartphones, are effective to accurately communicate patients’ severity to physicians, take into consideration inter-sensor dependencies, and are adaptive based on recently observed parametric trends. Preliminary implementation with practicing physicians and testing on patient data from our collaborating multi-specialty hospital has yielded encouraging results.

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Heart Lung Health Monitor: Remote At-Home Patient Surveillance for Pandemic Management

2021 IEEE Global Humanitarian Technology Conference (GHTC), 2021

The COVID-19 pandemic has brought about an unprecedented shift towards Telehealth since physician... more The COVID-19 pandemic has brought about an unprecedented shift towards Telehealth since physicians are overwhelmed by the huge patient load in hospitals. This has forced policy makers to advise home quarantine for mild and moderate COVID patients. Additionally, even non-COVID patients with diabetes and cardiovascular or pulmonary diseases who do not need hospitalization are currently being monitored at home for any changes in their severity that may require a home to hospital transfer. Our research team has developed an Internet of Medical Things wearable Heart Lung Health monitor for patients with cardiovascular and pulmonary risk factors so as to enable hospitals to remotely track patient health status. Our system consists of a credit-card sized wearable 3-lead ECG device interfaced with smartphone that analyzes ECG and extracts heart and respiratory parameters, and transmits these to a dashboard for remote monitoring. We present the architecture, device, respiratory rate extraction algorithm, and its validation on 50 patients. Encouraged by these results we are readying deployment of our system for home monitoring of at-risk patients.

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Additional file 5 of Data to diagnosis in global health: a 3P approach

Moving Window QTS (B=20) Vs. MTS. The figure shows the F1-score comparison of QTS with B=20 and M... more Moving Window QTS (B=20) Vs. MTS. The figure shows the F1-score comparison of QTS with B=20 and MTS while using a moving window of size 30 mins with varying backward offset from t0. The results show that QTS is marginally better than MTS in four time slots. (PNG 22 kb)

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Additional file 4 of Data to diagnosis in global health: a 3P approach

Moving Window QTS (B=15) Vs. MTS. The figure shows the F1-score comparison of QTS with B=15 and M... more Moving Window QTS (B=15) Vs. MTS. The figure shows the F1-score comparison of QTS with B=15 and MTS while using a moving window of size 30 mins with varying backward offset from t0. The results show that MTS is better than QTS except in two time slots, and also W=10 and W=15 are better summarization windows. (PNG 21 kb)

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Additional file 3 of Data to diagnosis in global health: a 3P approach

Moving Window QTS (B=10) Vs. MTS. The figure shows the F1-score comparison of QTS with B=10 and M... more Moving Window QTS (B=10) Vs. MTS. The figure shows the F1-score comparison of QTS with B=10 and MTS while using a moving window of size 30 mins with varying backward offset from t0. The results show that MTS is better than QTS except in two time slots, and also W=10 and W=15 are better summarization windows. (PNG 22 kb)

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Additional file 1 of Data to diagnosis in global health: a 3P approach

Moving Window OTS Vs. QTS. The figure shows the F1-score while using a moving window of size 30 m... more Moving Window OTS Vs. QTS. The figure shows the F1-score while using a moving window of size 30 mins with varying backward offset from t0. The results show that QTS is always better than OTS in classifying a given window as predictor for AHE or not. (PNG 28 kb)

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Real-time alerting system for COVID-19 and other stress events using wearable data

Nature Medicine, 2021

Early detection of infectious diseases is crucial for reducing transmission and facilitating earl... more Early detection of infectious diseases is crucial for reducing transmission and facilitating early intervention. In this study, we built a real-time smartwatch-based alerting system that detects aberrant physiological and activity signals (heart rates and steps) associated with the onset of early infection and implemented this system in a prospective study. In a cohort of 3,318 participants, of whom 84 were infected with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), this system generated alerts for pre-symptomatic and asymptomatic SARS-CoV-2 infection in 67 (80%) of the infected individuals. Pre-symptomatic signals were observed at a median of 3 days before symptom onset. Examination of detailed survey responses provided by the participants revealed that other respiratory infections as well as events not associated with infection, such as stress, alcohol consumption and travel, could also trigger alerts, albeit at a much lower mean frequency (1.15 alert days per pers...

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Real-time and offline techniques for identifying obstructive sleep apnea patients

2016 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC), 2016

Obstructive Sleep Apnea (OSA) is a common sleeping disorder in which persons temporarily stop bre... more Obstructive Sleep Apnea (OSA) is a common sleeping disorder in which persons temporarily stop breathing during their sleep. Untreated OSA may lead to several cardio vascular diseases, diabetes, stroke etc. Currently, overnight Polysomnography (PSG) is the widely used technique to detect sleep apnoea. However, a human expert has to monitor the patient overnight. In this paper, we use the technique of motif discovery to identify long term patterns in vital parameters obtained from a combination of smart phones and body attached sensors. We further extend this work to use hamming distance technique to identify similar patients for case based reasoning. Using this, we reduce the need for having expert intervention. As an initial implementation, we have tested our motif discovery technique on Physionet sleep apnea dataset of ECG and SpO2.

Bookmarks Related papers MentionsView impact

Research paper thumbnail of RASPRO: rapid summarization for effective prognosis in wireless remote health monitoring

2016 IEEE Wireless Health (WH), 2016

Consistent power and cost effective health monitoring has become the need of the hour especially ... more 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.

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Gaze Alignment Techniques for Multipoint Mobile Telemedicine for Ophthalmological Consultations

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, 2018

Bookmarks Related papers MentionsView impact

Research paper thumbnail of A systematic methodology to transform campuses in the developing world into sustainable communities

2016 IEEE Global Humanitarian Technology Conference (GHTC), 2016

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Multi-sensor architecture and algorithms for digital health at every doorstep

2017 Second International Conference on Electrical, Computer and Communication Technologies (ICECCT), 2017

Consistent cost effective health monitoring has become the need of the hour especially for the un... more Consistent 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 and the analytics engines. Physiological parameters from multiple sensors feed into a severity quantizer and a subsequent multiplexer, the output of which is processed by successive physician assist filters 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 our multi-disciplinary University, building on a multi-terabyte, more than a million patient 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.

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Internet-of-Things Based Respiratory Rate Monitoring for Early Detection of Cardiovascular and Pulmonary Diseases

5th EAI International Conference on IoT Technologies for HealthCare, 2019

Ubiquitous penetration of Internet-of-Things (IoT) devices is promising to be an enabler in takin... more Ubiquitous penetration of Internet-of-Things (IoT) devices is promising to be an enabler in taking healthcare services to needy patients even in remote regions. In this paper, we present our wearable IoT remote health monitoring system that includes a photoplethysmograph (PPG) based device to measure physiological parameters such as pulse rate, blood oxygen, and respiratory rate (RR). We have conducted a pilot study of our system on 25 patients, and we report the comparative performance of different techniques for deriving RR from PPG signals. The best performing algorithms achieved a mean absolute error of 0.58 breaths/min, which exhibits the potential of PPG based sensors for automated detection of many cardiovascular and pulmonary diseases, particularly, pneumonia, sleep apnea, and acute respiratory distress syndrome.

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Systems and Methods for Remote Health Monitoring and Management

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Consensus motifs as adaptive and efficient predictors for acute hypotensive episodes

2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2017

Acute hypotensive episodes (AHE) are characterized by continuously low blood pressure for prolong... more Acute hypotensive episodes (AHE) are characterized by continuously low blood pressure for prolonged time, and could be potentially fatal. We present a novel AHE detection system, by first quantizing the blood pressure data into clinically accepted severity ranges and then identifying most frequently occurring blood pressure pattern among these which we call consensus motifs. We apply machine learning techniques (support vector machine) on these consensus motifs. The results show that the use of consensus motifs instead of raw time series data extends the predictability by 45 minutes beyond the 2 hours that is possible using only the raw data, yielding a significant improvement without compromising the clinical accuracy. The system has been implemented as part of a new framework called RASPRO (Rapid Summarization for Effective Prognosis) that we have developed for Wireless Remote Health Monitoring.

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Deriving High Performance Alerts from Reduced Sensor Data for Timely Intervention in Acute Hypotensive Episodes

Alerting critical health conditions ahead of time leads to reduced mortality rates. Recently wire... more Alerting critical health conditions ahead of time leads to reduced mortality rates. Recently wirelessly enabled medical sensors have become pervasive in both hospital and ambulatory settings. These sensors pour out voluminous data that are generally not amenable to direct interpretation. For this data to be practically useful for patients, they must be translatable into alerts that enable doctors to intervene in a timely fashion. In this paper we present a novel three-step technique to derive high performance alerts from voluminous sensor data: A data reduction algorithm that takes into account the medical condition at personalized patient level and thereby converts raw multi-sensor data to patient and disease specific severity representation, which we call as the Personalized Health Motifs (PHM). The PHMs are then modulated by criticality factors derived from interventional time and severity frequency to yield a Criticality Measure Index (CMI). In the final step we generate alerts ...

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Rapid Healthcare Alerts using Multiple Sensors

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Real-time identification & alert of ischemic events in high risk cardiac patients

There is a worldwide trend of increase in cardiac related deaths. One of the major reasons is the... more There is a worldwide trend of increase in cardiac related deaths. One of the major reasons is the condition of cardiac ischemia, which implies inadequacy of blood supply to heart leading to myocardial infarction. One of the main techniques used for detection of ischemia is 12-lead ECG test. However, on most occasions the patient may not be attached to any such devices so as to provide immediate medical help. This emphasizes the need for real time detection of such events. With advances in the field of communication and smartphone-based computations, we are now able to use body attached sensors and smartphone based solutions for real-time detection of diseases. In our work, we introduce a real-time smartphone based ischemia detection system, which combines ECG signals from patients along with their activity for identification of ischemia. As an initial step, the impact of patient activity on ischemia is studied, with a comparison between severity threshold method and contextual sever...

Bookmarks Related papers MentionsView impact

Research paper thumbnail of When Less is Better: A Summarization Technique that Enhances Clinical Effectiveness of Data

The increasing number of wearable sensors for monitoring of various vital parameters such as bloo... more The increasing number of wearable sensors for monitoring of various vital parameters such as blood pressure (BP), blood glucose, or heart rate (HR), has opened up an unprecedented opportunity for personalized real-time monitoring and prediction of critical health conditions of patients. This, however, also poses the dual challenges of identifying clinically relevant information from vast volumes of sensor time-series data and of storing and communicating it to health-care providers especially in the context of rural areas of developing regions where communication bandwidth may be limited. One approach to address these challenges is data summarization, but the danger of losing clinically useful information makes it less appealing to medical practitioners. To overcome this, we develop a data summarization technique called RASPRO (Rapid Active Summarization for effective PROgnosis), which transforms raw sensor time-series data into a series of low bandwidth, medically interpretable sym...

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Real-time Alerting System for COVID-19 Using Wearable Data

medRxiv, 2021

Early detection of infectious disease is crucial for reducing transmission and facilitating early... more Early detection of infectious disease is crucial for reducing transmission and facilitating early intervention. We built a real-time smartwatch-based alerting system for the detection of aberrant physiological and activity signals (e.g. resting heart rate, steps) associated with early infection onset at the individual level. Upon applying this system to a cohort of 3,246 participants, we found that alerts were generated for pre-symptomatic and asymptomatic COVID-19 infections in 78% of cases, and pre-symptomatic signals were observed a median of three days prior to symptom onset. Furthermore, by examining over 100,000 survey annotations, we found that other respiratory infections as well as events not associated with COVID-19 (e.g. stress, alcohol consumption, travel) could trigger alerts, albeit at a lower mean period (1.9 days) than those observed in the COVID-19 cases (4.3 days). Thus this system has potential both for advanced warning of COVID-19 as well as a general system for ...

Bookmarks Related papers MentionsView impact