Costas Sideris

Using electronic health records to predict severity of condition for congestive heart failure patients

We propose a novel way to design an analytics engine based exclusively on electronic health records (EHR). We focus our efforts on Congestive Heart Failure (CHF) patients, although our approach could be extended to other chronic conditions. Our goal is to construct statistical models that predict a CHF patients length of stay and by extension the severity of his/her condition. We show that it is possible to predict length of hospital stay based on physiological data collected from the first day of hospitalization. Using 10-fold cross validation we achieve accurate predictions with a root mean square error of 3.3 days for hospital stays that are less than 15 days in duration. We also propose a clustering of patients that organizes them to risk groups according to their estimated severity of condition.

Dynamic Computation Offloading for Low-Power Wearable Health Monitoring Systems

Objective: The objective of this paper is to describe and evaluate an algorithm to reduce power usage and increase battery lifetime for wearable health-monitoring devices. Methods: We describe a novel dynamic computation offloading scheme for real-time wearable health monitoring devices that adjusts the partitioning of data processing between the wearable device and mobile application as a function of desired classification accuracy. Results: By making the correct offloading decision based on current system parameters, we show that we are able to reduce system power by as much as 20%. Conclusion: We demonstrate that computation offloading can be applied to real-time monitoring systems, and yields significant power savings. Significance: Making correct offloading decisions for health monitoring devices can extend battery life and improve adherence.

HIPAA compliant wireless sensing smartwatch application for the self-management of pediatric asthma

Asthma is the most prevalent chronic disease among pediatrics, as it is the leading cause of student absenteeism and hospitalization for those under the age of 15. To address the significant need to manage this disease in children, the authors present a mobile health (mHealth) system that determines the risk of an asthma attack through physiological and environmental wireless sensors and representational state transfer application program interfaces (RESTful APIs). The data is sent from wireless sensors to a smartwatch application (app) via a Health Insurance Portability and Accountability Act (HIPAA) compliant cryptography framework, which then sends data to a cloud for real-time analytics. The asthma risk is then sent to the smartwatch and provided to the user via simple graphics for easy interpretation by children. After testing the safety and feasibility of the system in an adult with moderate asthma prior to testing in children, it was found that the analytics model is able to determine the overall asthma risk (high, medium, or low risk) with an accuracy of 80.10±14.13%. Furthermore, the features most important for assessing the risk of an asthma attack were multifaceted, highlighting the importance of continuously monitoring different wireless sensors and RESTful APIs. Future testing this asthma attack risk prediction system in pediatric asthma individuals may lead to an effective self-management asthma program.

A flexible data-driven comorbidity feature extraction framework

Disease and symptom diagnostic codes are a valuable resource for classifying and predicting patient outcomes. In this paper, we propose a novel methodology for utilizing disease diagnostic information in a predictive machine learning framework. Our methodology relies on a novel, clustering-based feature extraction framework using disease diagnostic information. To reduce the data dimensionality, we identify disease clusters using co-occurrence statistics. We optimize the number of generated clusters in the training set and then utilize these clusters as features to predict patient severity of condition and patient readmission risk. We build our clustering and feature extraction algorithm using the 2012 National Inpatient Sample (NIS), Healthcare Cost and Utilization Project (HCUP) which contains 7 million hospital discharge records and ICD-9-CM codes. The proposed framework is tested on Ronald Reagan UCLA Medical Center Electronic Health Records (EHR) from 3041 Congestive Heart Failure (CHF) patients and the UCI 130-US diabetes dataset that includes admissions from 69,980 diabetic patients. We compare our cluster-based feature set with the commonly used comorbidity frameworks including Charlsons index, Elixhausers comorbidities and their variations. The proposed approach was shown to have significant gains between 10.7-22.1% in predictive accuracy for CHF severity of condition prediction and 4.65-5.75% in diabetes readmission prediction.

Remote Health Monitoring Outcome Success Prediction Using Baseline and First Month Intervention Data

Remote health monitoring (RHM) systems are becoming more widely adopted by clinicians and hospitals to remotely monitor and communicate with patients while optimizing clinician time, decreasing hospital costs, and improving quality of care. In the Womens heart health study (WHHS), we developed Wanda-cardiovascular disease (CVD), where participants received healthy lifestyle education followed by six months of technology support and reinforcement. Wanda-CVD is a smartphone-based RHM system designed to assist participants in reducing identified CVD risk factors through wireless coaching using feedback and prompts as social support. Many participants benefitted from this RHM system. In response to the variance in participants’ success, we developed a framework to identify classification schemes that predicted successful and unsuccessful participants. We analyzed both contextual baseline features and data from the first month of intervention such as activity, blood pressure, and questionnaire responses transmitted through the smartphone. A prediction tool can aid clinicians and scientists in identifying participants who may optimally benefit from the RHM system. Targeting therapies could potentially save healthcare costs, clinician, and participant time and resources. Our classification scheme yields RHM outcome success predictions with an F-measure of 91.9%, and identifies behaviors during the first month of intervention that help determine outcome success. We also show an improvement in prediction by using intervention-based smartphone data. Results from the WHHS study demonstrates that factors such as the variation in first month intervention response to the consumption of nuts, beans, and seeds in the diet help predict patient RHM protocol outcome success in a group of young Black women ages 25–45.

Building Continuous Arterial Blood Pressure Prediction Models Using Recurrent Networks

This paper presents a methodology for developing highly-accurate, continuous Arterial Blood Pressure (ABP) models using only Photoplethysmography (PPG). In contrast to prior approaches, we develop a system that exhibits dynamic temporal behavior which leads to increased accuracy in modeling ABP. We validate our approach using data from patients in the intensive care unit (ICU). We show that it is possible to build highly accurate, continuous blood pressure models using only finger pulse oximeters. Our methodology achieves accurate systolic blood pressure estimation with a root mean square error 2.58 ± 1.23 across the patient sample used. Furthermore, the continuous ABP signal is estimated with a root mean square error of 6.042 ± 3.26 and correlation coefficient of 0.95 ± 0.045. Our method enables designing robust Remote Health Monitoring Systems (RMS) for Heart Failure patients without requiring traditional blood pressure monitors.

A data-driven feature extraction framework for predicting the severity of condition of congestive heart failure patients.

In this paper, we propose a novel methodology for utilizing disease diagnostic information to predict severity of condition for Congestive Heart Failure (CHF) patients. Our methodology relies on a novel, clustering-based, feature extraction framework using disease diagnostic information. To reduce the dimensionality we identify disease clusters using cooccurence frequencies. We then utilize these clusters as features to predict patient severity of condition. We build our clustering and feature extraction algorithm using the 2012 National Inpatient Sample (NIS), Healthcare Cost and Utilization Project (HCUP) which contains 7 million discharge records and ICD-9-CM codes. The proposed framework is tested on Ronald Reagan UCLA Medical Center Electronic Health Records (EHR) from 3041 patients. We compare our cluster-based feature set with another that incorporates the Charlson comorbidity score as a feature and demonstrate an accuracy improvement of up to 14% in the predictability of the severity of condition.

Feasibility of a Secure Wireless Sensing Smartwatch Application for the Self-Management of Pediatric Asthma

To address the need for asthma self-management in pediatrics, the authors present the feasibility of a mobile health (mHealth) platform built on their prior work in an asthmatic adult and child. Real-time asthma attack risk was assessed through physiological and environmental sensors. Data were sent to a cloud via a smartwatch application (app) using Health Insurance Portability and Accountability Act (HIPAA)-compliant cryptography and combined with online source data. A risk level (high, medium or low) was determined using a random forest classifier and then sent to the app to be visualized as animated dragon graphics for easy interpretation by children. The feasibility of the system was first tested on an adult with moderate asthma, then usability was examined on a child with mild asthma over several weeks. It was found during feasibility testing that the system is able to assess asthma risk with 80.10 ± 14.13% accuracy. During usability testing, it was able to continuously collect sensor data, and the child was able to wear, easily understand and enjoy the use of the system. If tested in more individuals, this system may lead to an effective self-management program that can reduce hospitalization in those who suffer from asthma.

Computation offloading for real-time health-monitoring devices

Among the major challenges in the development of real-time wearable health monitoring systems is to optimize battery life. One of the major techniques with which this objective can be achieved is computation offloading, in which portions of computation can be partitioned between the device and other resources such as a server or cloud. In this paper, we describe a novel dynamic computation offloading scheme for real-time wearable health monitoring devices that adjusts the partitioning of data between the wearable device and mobile application as a function of desired classification accuracy.

Parallelized incomplete poisson preconditioner in cloth simulation

Efficient cloth simulation is an important problem for interactive applications that involve virtual humans, such as computer games. A common aspect of many methods that have been developed to simulate cloth is a linear system of equations, which is commonly solved using conjugate gradient or multi-grid approaches. In this paper, we introduce to the computer gaming community a recently proposed preconditioner, the incomplete Poisson preconditioner (IPP ), for conjugate gradient solvers. We show that IPP performs as well as the current state-of-the-art preconditioners, while being much more amenable to standard thread-level parallelism. We demonstrate our results on an 8-core Mac Pro and a 32-core Emerald Rigde system.