kHealth : Proactive Personalized Actionable Information for Better Healthcare

Mobile devices and sensors are profoundly changing the way we create, consume, and share information. Health aficionados and patients with chronic conditions are increasingly using sensors and mobile devices to track sleep, food, activity, and other physiological observations (e.g., weight, heart rate, blood pressure). This trend is leading to a paradigm shift from reactive medicine to predictive, preventative, personalized, and participatory medicine. This is also empowering an individual to more fully participate in health related decision making. To facilitate this transformation, there is a dearth of research in understanding the richness and nuances of health care data. There are many healthcare applications that utilize mobile devices and sensors to monitor the health of an individual. With increased instrumentation such as use of smart phones and social media provides a fine-grained access to the activities of a person and population in general. Majority of analytics is focused on finding discrepancies in a single stream of observations without much insight into the problem and actionable information. kHealth analyzes observations from passive (no human involvement in data collection) and active (human input involved in data collection) sensors to provide explanations that are intelligible to individuals and when needed their clinicians for well-informed decision making.

[1]  Nir Friedman,et al.  Probabilistic Graphical Models - Principles and Techniques , 2009 .

[2]  Amit P. Sheth,et al.  Predicting Parkinson's Disease Progression with Smartphone Data , 2013 .

[3]  David Maxwell Chickering,et al.  Learning Bayesian Networks: The Combination of Knowledge and Statistical Data , 1994, Machine Learning.

[4]  Instantiation to Support the Integration of Logical and Probabilistic Knowledge , 2011 .

[5]  Amit P. Sheth,et al.  Physical-Cyber-Social Computing: An Early 21st Century Approach , 2013, IEEE Intelligent Systems.

[6]  Olivia R. Liu Sheng,et al.  Examining the Technology Acceptance Model Using Physician Acceptance of Telemedicine Technology , 1999, J. Manag. Inf. Syst..

[7]  Xin Ming,et al.  The Quantified Self Self-knowledge Through Numbers ? , 2016 .

[8]  Dean Allemang,et al.  Semantic Web for the Working Ontologist - Effective Modeling in RDFS and OWL, Second Edition , 2011 .

[9]  Nir Friedman,et al.  Learning Bayesian Networks with Local Structure , 1996, UAI.

[10]  J. Tenenbaum,et al.  Special issue on “Probabilistic models of cognition , 2022 .

[11]  Amit P. Sheth,et al.  An ontological approach to focusing attention and enhancing machine perception on the Web , 2011, Appl. Ontology.

[12]  Cory Andrew Henson,et al.  A Semantics-based Approach to Machine Perception , 2013 .

[13]  Amit P. Sheth,et al.  An Efficient Bit Vector Approach to Semantics-Based Machine Perception in Resource-Constrained Devices , 2012, SEMWEB.

[14]  Andrew McCallum,et al.  Introduction to Statistical Relational Learning , 2007 .

[15]  A. Allen,et al.  Telemedicine technology and clinical applications. , 1995, JAMA.

[16]  Amit P. Sheth,et al.  Semantic Perception: Converting Sensory Observations to Abstractions , 2012, IEEE Internet Computing.

[17]  Qiang Ji,et al.  Learning Bayesian network parameters under incomplete data with domain knowledge , 2009, Pattern Recognit..

[18]  Thomas D. Nielsen,et al.  Fusion of Domain Knowledge with Data for Structural Learning in Object Oriented Domains , 2003, J. Mach. Learn. Res..

[19]  Marek J. Druzdzel,et al.  Combining Knowledge from Different Sources in Causal Probabilistic Models , 2003, J. Mach. Learn. Res..