HealthSense: classification of health-related sensor data through user-assisted machine learning

ABSTRACT

Remote patient monitoring generates much more data than healthcare professionals are able to manually interpret. Automated detection of events of interest is therefore critical so that these points in the data can be marked for later review. However, for some important chronic health conditions, such as pain and depression, automated detection is only partially achievable. To assist with this problem we developed HealthSense, a framework for real-time tagging of health-related sensor data. HealthSense transmits sensor data from the patient to a server for analysis via machine learning techniques. The system uses patient input to assist with classification of interesting events (e.g., pain or itching). Due to variations between patients, sensors, and condition types, we presume that our initial classification is imperfect and accommodate this by incorporating user feedback into the machine learning process. This is done by occasionally asking the patient whether they are experiencing the condition being monitored. Their response is used to confirm or reject the classification made by the server and continually improve the accuracy of the classifier's decisions on what data is of interest to the health-care provider.

REFERENCES

• 1: Daniele Apiletti , Elena Baralis , Giulia Bruno , Tania Cerquitelli, SAPhyRA: Stream Analysis for Physiological Risk Assessment, Proceedings of the Twentieth IEEE International Symposium on Computer-Based Medical Systems, p.193-198, June 20-22, 2007 [doi>10.1109/CBMS.2007.95]
• 2: Marion Blount , Virinder M. Batra , Andrew N. Capella , Maria R. Ebling , William F. Jerome , Sherri M. Martin , Michael Nidd , Michael R. Niemi , Steven P. Wright, Remote health-care monitoring using personal care connect, IBM Systems Journal, v.46 n.1, p.95-113, January 2007
• 3: Marion Blount , John Davis , Maria Ebling , Ji Hyun Kim , Kyun Hyun Kim , KangYoon Lee , Archan Misra , SeHun Park , Daby Sow , Young Ju Tak , Min Wang , Karen Witting, Century: Automated Aspects of Patient Care, Proceedings of the 13th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications, p.504-509, August 21-24, 2007 [doi>10.1109/RTCSA.2007.26]
• 4: A. Cárdenas, R. Pon, and R. Cameron, "Management of Streaming Body Sensor Data for Medical Information Systems," Proceedings of METMBS 2003, Las Vegas, NV, pp. 186--191, 2003.
• 5: Jon Froehlich , Mike Y. Chen , Sunny Consolvo , Beverly Harrison , James A. Landay, MyExperience: a system for in situ tracing and capturing of user feedback on mobile phones, Proceedings of the 5th international conference on Mobile systems, applications and services, June 11-13, 2007, San Juan, Puerto Rico [doi>10.1145/1247660.1247670]
• 6: Stephen S. Intille , Ling Bao , Emmanuel Munguia Tapia , John Rondoni, Acquiring in situ training data for context-aware ubiquitous computing applications, Proceedings of the SIGCHI conference on Human factors in computing systems, p.1-8, April 24-29, 2004, Vienna, Austria [doi>10.1145/985692.985693]
• 7: Stephen S. Intille , John Rondoni , Charles Kukla , Isabel Ancona , Ling Bao, A context-aware experience sampling tool, CHI '03 extended abstracts on Human factors in computing systems, April 05-10, 2003, Ft. Lauderdale, Florida, USA [doi>10.1145/765891.766101]
• 8: J. Lester, T. Choudhury and B. Borriello, "A Practical Approach to Recognizing Physical Activities," Pervasive 2006, LNCS 3968, pp. 1--16, 2006.
• 9: J. Lester, T. Choudhury, N. Kern, G. Borriello and B. Hannaford, "A Hybrid Discriminative/Generative Approach for Modeling Human Activities," Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, pp. 766--722, Edinburgh, Scotland, 2005.
• 10: E. Tapia, S. Intille, and K. Larson, "Activity Recognition in the Home Using Simple and Ubiquitous Sensors," Pervasive 2004, LNCS 3001, pp. 158--175, 2004.
• 11: Tracy Westeyn , Kristin Vadas , Xuehai Bian , Thad Starner , Gregory D. Abowd, Recognizing Mimicked Autistic Self-Stimulatory Behaviors Using HMMs, Proceedings of the Ninth IEEE International Symposium on Wearable Computers, p.164-169, October 18-21, 2005 [doi>10.1109/ISWC.2005.45]
• 12: http://www.cancer.gov/cancertopics/pdq/supportivecare
• 13: http://www.medpagetoday.com/Psychiatry/Depression-/tb/6617
• 14: http://www.cdc.gov/arthritis/data_statistics
• 15: http://www.wrongdiagnosis.com/e/eczema/stats.htm
• 16: http://ptolemy.berkeley.edu/java/ptplot/
• 17: http://www.bodymedia.com

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.1 Content Analysis and Indexing
          Subjects: Indexing methods

Additional Classification:
  J. Computer Applications
  J.3 LIFE AND MEDICAL SCIENCES

General Terms:
Design, Experimentation, Management, Measurement

Keywords:
healthcare, indexing, sensor data analysis