skip to main content
research-article
Open Access

Feasibility Study of Monitoring Deterioration of Outpatients Using Multimodal Data Collected by Wearables

Authors Info & Claims
Published:02 March 2020Publication History
Skip Abstract Section

Abstract

In the article, we explore the feasibility of monitoring outpatients using Fitbit Charge HR wristbands and the potential of machine learning models to predict clinical deterioration (readmissions and death) among outpatients discharged from the hospital. We developed and piloted a data collection system in a clinical study that involved 25 heart failure patients recently discharged. The results demonstrated the feasibility of continuously monitoring outpatients using wristbands. We observed high levels of patient compliance in wearing the wristbands regularly and satisfactory yield, latency, and reliability of data collection from the wristbands to a cloud-based database. Finally, we explored a set of machine learning models to predict deterioration based on the Fitbit data. Through fivefold cross-validation, K nearest neighbor achieved the highest accuracy of 0.8667 for identifying patients at risk of deterioration using the data collected from the beginning of the monitoring. Machine learning models based on multimodal data (step, sleep, and heart rate) significantly outperformed the traditional clinical approach based on LACE index. Moreover, our proposed Weighted Samples One-Class SVM model with estimated confidence can reach high accuracy (0.9635) for predicting the deterioration using data collected within a sliding window, which indicates the potential for allowing timely intervention.

References

  1. Raghad Abdulmajeed. 2016. The Use of Continuous Monitoring of Heart Rate as a Prognosticator of Readmission in Heart Failure Patients. Master’s thesis. University of Toronto, Canada.Google ScholarGoogle Scholar
  2. Mennatallah Amer, Markus Goldstein, and Slim Abdennadher. 2013. Enhancing one-class support vector machines for unsupervised anomaly detection. In Proceedings of the ACM SIGKDD Workshop on Outlier Detection and Description (ODD’13). ACM, 8--15. DOI:https://doi.org/10.1145/2500853.2500857Google ScholarGoogle ScholarDigital LibraryDigital Library
  3. Roxanne M. Andrews and Anne Elixhauser. 2007. The national hospital bill: Growth trends and 2005 update on the most expensive conditions by payer. In Healthcare Cost and Utilization Project (HCUP) Statistical Briefs [Internet]. Retrieved from https://www.ncbi.nlm.nih.gov/books/NBK56314/.Google ScholarGoogle Scholar
  4. Geoff Appelboom, Blake E. Taylor, Eliza Bruce, Clare C. Bassile, Corinna Malakidis, Annie Yang, Brett Youngerman, Randy D’Amico, Sam Bruce, Olivier Bruyère, Jean-Yves Reginster, Emmanuel P.L. Dumont, and E. Sander Connolly Jr. 2015. Mobile phone-connected wearable motion sensors to assess postoperative mobilization. JMIR mHealth uHealth 3, 3 (July 28, 2015), e78. DOI:https://doi.org/10.2196/mhealth.3785Google ScholarGoogle Scholar
  5. Sangwon Bae, Anind K. Dey, and Carissa A. Low. 2016. Using passively collected sedentary behavior to predict hospital readmission. In Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp’16). ACM, 616--621. DOI:https://doi.org/10.1145/2971648.2971750Google ScholarGoogle Scholar
  6. Claudia Beleites and Reiner Salzer. 2008. Assessing and improving the stability of chemometric models in small sample size situations. Analytical and Bioanalytical Chemistry 390, 5 (March 1, 2008), 1261--1271. DOI:https://doi.org/10.1007/s00216-007-1818-6Google ScholarGoogle Scholar
  7. Jason P. Burnham, Chenyang Lu, Lauren H. Yaeger, Thomas C. Bailey, and Marin H. Kollef. 2018. Using wearable technology to predict health outcomes: A literature review. Journal of the American Medical Informatics Association 25, 9 (2018), 1221--1227. DOI:https://doi.org/10.1093/jamia/ocy082Google ScholarGoogle ScholarCross RefCross Ref
  8. Lisa Cadmus-Bertram, Bess H. Marcus, Ruth E. Patterson, Barbara A. Parker, and Brittany L. Morey. 2015. Use of the Fitbit to measure adherence to a physical activity intervention among overweight or obese, postmenopausal women: Self-monitoring trajectory during 16 weeks. JMIR mHealth uHealth 3, 4 (Nov. 19, 2015), e96. DOI:https://doi.org/10.2196/mhealth.4229Google ScholarGoogle Scholar
  9. Octav Chipara, Chenyang Lu, Thomas C. Bailey, and Gruia-Catalin Roman. 2010. Reliable clinical monitoring using wireless sensor networks: Experiences in a step-down hospital unit. In Proceedings of the 8th ACM Conference on Embedded Networked Sensor Systems (SenSys’10). ACM, 14. DOI:https://doi.org/10.1145/1869983.1869999Google ScholarGoogle Scholar
  10. Paul E. Cotter, Vikas K. Bhalla, Stephen J. Wallis, and Richard W. S. Biram. 2012. Predicting readmissions: Poor performance of the LACE index in an older UK population. Age and Ageing 41, 6 (2012), 784--789. DOI:https://doi.org/10.1093/ageing/afs073Google ScholarGoogle Scholar
  11. Massimiliano de Zambotti, Aimee Goldstone, Stephanie Claudatos, Ian M. Colrain, and Fiona C. Baker. 2018. A validation study of Fitbit Charge 2 compared with polysomnography in adults. Chronobiology International 35, 4 (2018), 465--476. DOI:https://doi.org/10.1080/07420528.2017.1413578Google ScholarGoogle ScholarCross RefCross Ref
  12. Kumar Dharmarajan, Angela F. Hsieh, Zhenqiu Lin, Héctor Bueno, Joseph S. Ross, Leora I. Horwitz, José Augusto Barreto-Filho, Nancy Kim, Susannah M. Bernheim, Lisa G. Suter, Elizabeth E. Drye, and Harlan M. Krumholz. 2013. Diagnoses and timing of 30-day readmissions after hospitalization for heart failure, acute myocardial infarction, or pneumonia. JAMA Internal Medicine 309, 4 (2013), 355--363.DOI:https://doi.org/10.1001/jama.2012.216476Google ScholarGoogle Scholar
  13. Jacques D. Donzé, Mark V. Williams, Edmondo J. Robinson, Eyal Zimlichman, Drahomir Aujesky, Eduard E. Vasilevskis, Sunil Kripalani, Joshua P. Metlay, Tamara Wallington, Grant S. Fletcher, Andrew D. Auerbach, and Jeffrey L. Schnipper. 2016. International validity of the “HOSPITAL” score to predict 30-day potentially avoidable readmissions in medical patients. JAMA Internal Medicine 176, 4 (April 2016), 496--502. DOI:https://doi.org/10.1001/jamainternmed.2015.8462Google ScholarGoogle Scholar
  14. Barbara J. Drew, Patricia Harris, Jessica K. Zègre-Hemsey, Tina Mammone, Daniel Schindler, Rebeca Salas-Boni, Yong Bai, Adelita Tinoco, Quan Ding, and Xiao Hu. 2014. Insights into the problem of alarm fatigue with physiologic monitor devices: A comprehensive observational study of consecutive intensive care unit patients. PloS One 9, 10 (Oct. 22, 2014), 1--23. DOI:https://doi.org/10.1371/journal.pone.0110274Google ScholarGoogle Scholar
  15. Christo El Morr, Liane Ginsburg, Seungree Nam, and Susan Woollard. 2017. Assessing the performance of a modified LACE index (LACE-rt) to predict unplanned readmission after discharge in a community teaching hospital. Interactive Journal of Medical Research 6, 1 (March 8, 2017), e2--e2. DOI:https://doi.org/10.2196/ijmr.7183Google ScholarGoogle Scholar
  16. Steve R. Fisher, Yong-Fang Kuo, Gulshan Sharma, Mukaila A. Raji, Amit Kumar, James S. Goodwin, Glenn V. Ostir, and Kenneth J. Ottenbacher. 2013. Mobility after hospital discharge as a marker for 30-day readmission. Journals of Gerontology. Series A, Biological Sciences and Medical Sciences 68, 7 (July 19, 2013), 805--810. DOI:https://doi.org/10.1093/gerona/gls252Google ScholarGoogle Scholar
  17. Margaret Hall, Carol DeFrances, Sonja N. Williams, Aleksandr Golosinskiy, and Alexander Schwartzman. 2010. National hospital discharge survey: 2007 summary. National Health Statistics Reports 29 (2010), 1--20, 24. DOI:https://doi.org/10.3886/ICPSR28162.v1Google ScholarGoogle Scholar
  18. Margaret Hall, Shaleah Levant, and Carol DeFrances. 2012. Hospitalization for congestive heart failure: United States, 2000-2010. NCHS Data Brief 108 (2012), 1--8.Google ScholarGoogle Scholar
  19. Danning He, Simon C. Mathews, Anthony N. Kalloo, and Susan Hutfless. 2014. Mining high-dimensional administrative claims data to predict early hospital readmissions. Journal of the American Medical Informatics Association 21, 2 (2014), 272--279. DOI:https://doi.org/10.1136/amiajnl-2013-002151Google ScholarGoogle ScholarCross RefCross Ref
  20. Arian Hosseinzadeh, Masoumeh T. Izadi, Aman Verma, Doina Precup, and David L. Buckeridge. 2013. Assessing the predictability of hospital readmission using machine learning. In Proceedings of the 27th AAAI Conference on Artificial Intelligence (AAAI’13). AAAI Press, 1532--1538.Google ScholarGoogle Scholar
  21. Kun Hu, Plamen Ivanov, Zhi Chen, Pedro Carpena, and H. Stanley. 2001. Effect of trends on detrended fluctuation analysis. Physical Review. E, Statistical, Nonlinear, and Soft Matter Physics 64, 1 (June 2001), 011114. DOI:https://doi.org/10.1103/PhysRevE.64.011114Google ScholarGoogle Scholar
  22. Kanitthika Kaewkannate and Soochan Kim. 2016. A comparison of wearable fitness devices. BMC Public Health 16, 1 (May 24, 2016), 433. DOI:https://doi.org/10.1186/s12889-016-3059-0Google ScholarGoogle Scholar
  23. Devan Kansagara, Honora Englander, Amanda Salanitro, David Kagen, Cecelia Theobald, Michele Freeman, and Sunil Kripalani. 2011. Risk prediction models for hospital readmission: A systematic review. JAMA 306, 15 (2011), 1688--1698. DOI:https://doi.org/10.1001/jama.2011.1515Google ScholarGoogle ScholarCross RefCross Ref
  24. Lian Leng Low, Kheng Hock Lee, Marcus Eng Hock Ong, Sijia Wang, Shu Yun Tan, Julian Thumboo, and Nan Liu. 2015. Predicting 30-day readmissions: Performance of the LACE index compared with a regression model among general medicine patients in Singapore. Biomedical Research International 2015 (Nov. 23, 2015), 169870. DOI:https://doi.org/10.1155/2015/169870Google ScholarGoogle Scholar
  25. Yi Mao, Wenlin Chen, Yixin Chen, Chenyang Lu, Marin Kollef, and Thomas Bailey. 2012. An integrated data mining approach to real-time clinical monitoring and deterioration warning. In Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’12). ACM, 1140--1148. DOI:https://doi.org/10.1145/2339530.2339709Google ScholarGoogle ScholarDigital LibraryDigital Library
  26. Eric Marks. 2013. Complexity science and the readmission dilemma: Comment on “potentially avoidable 30-day hospital readmissions in medical patients” and “association of self-reported hospital discharge handoffs with 30-day readmissions.” JAMA Internal Medicine 173, 8 (2013), 629--631. DOI:https://doi.org/10.1001/jamainternmed.2013.4065Google ScholarGoogle Scholar
  27. Kenneth McDonald, Mark Ledwidge, John Cahill, Jean Kelly, Peter Quigley, Brian Maurer, Fiona Begley, Mary Ryder, Bronagh Travers, Lorna Timmons, and Teresa Burke. 2001. Elimination of early rehospitalization in a randomized, controlled trial of multidisciplinary care in a high-risk, elderly heart failure population: The potential contributions of specialist care, clinical stability and optimal angiotensin-converting enzyme inhibitor dose at discharge. European Journal of Heart Failure 3, 2 (2001), 209--215. DOI:https://doi.org/10.1016/S1388-9842(00)00134-3Google ScholarGoogle Scholar
  28. U.S. National Library of Medicine. 2019. Heart Failure. Retrieved June 3, 2019, from http://medlineplus.gov/heartfailure.html.Google ScholarGoogle Scholar
  29. Chung-Kang Peng, Sergey Buldyrev, Shlomo Havlin, M. Simons, H. Stanley, and Ary Goldberger. 1994. Mosaic organization of DNA nucleotides. Physical Review E 49, 2 (Feb. 1994), 1685--1689. DOI:https://doi.org/10.1103/PhysRevE.49.1685Google ScholarGoogle Scholar
  30. John C. Platt. 1999. Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. In Advances in Large Margin Classifiers. MIT Press, 61--74.Google ScholarGoogle Scholar
  31. Robert Robinson and Tamer Hudali. 2017. The HOSPITAL score and LACE index as predictors of 30 day readmission in a retrospective study at a university-affiliated community hospital. PeerJ 5 (Jan. 9, 2017), e3137--e3137. DOI:https://doi.org/10.7717/peerj.3137Google ScholarGoogle Scholar
  32. Véronique L. Roger. 2013. Epidemiology of heart failure. Circulation Research 113, 6 (Aug. 30, 2013), 646--659. DOI:https://doi.org/10.1161/CIRCRESAHA.113.300268Google ScholarGoogle Scholar
  33. Khader Shameer, Kipp W. Johnson, Alexandre Yahi, Riccardo Miotto, L. I. Li, Doran Ricks, Jebakumar Jebakaran, Patricia Kovatch, Partho P. Sengupta, Sengupta Gelijns, Alan Moskovitz, Bruce Darrow, David L. David, Andrew Kasarskis, Nicholas P. Tatonetti, Sean Pinney, and Joel T. Dudley. 2016. Predictive Modeling of Hospital Readmission Rates Using Electronic Medical Record-wide Machine Learning: A Case-study Using Mount Sinai Heart Failure Cohort. Vol. 22. 276--287. DOI:https://doi.org/10.1142/9789813207813_0027Google ScholarGoogle Scholar
  34. Anna Shcherbina, C. Mikael Mattsson, Daryl Waggott, Heidi Salisbury, Jeffrey W. Christle, Trevor Hastie, Matthew T. Wheeler, and Euan A. Ashley. 2017. Accuracy in wrist-worn, sensor-based measurements of heart rate and energy expenditure in a diverse cohort. Journal of Personalized Medicine 7, 2, Article 3 (2017), 1--12. DOI:https://doi.org/10.3390/jpm7020003Google ScholarGoogle Scholar
  35. Shanu Sushmita, Garima Khulbe, Aftab Hasan, Stacey Newman, Padmashree Ravindra, Senjuti Basu Roy, Martine De Cock, and Ankur Teredesai. 2016. Predicting 30-day risk and cost of “all-cause” hospital readmissions. In AAAI Workshop: Expanding the Boundaries of Health Informatics Using AI.Google ScholarGoogle Scholar
  36. Tetsuya Takahashi, Megumi Kumamaru, Sue Jenkins, Masakazu Saitoh, Tomoyuki Morisawa, and Hikaru Matsuda. 2015. In-patient step count predicts re-hospitalization after cardiac surgery. Journal of Cardiology 66, 4 (2015), 286--291. DOI:https://doi.org/10.1016/j.jjcc.2015.01.006Google ScholarGoogle Scholar
  37. Carl van Walraven, Irfan A. Dhalla, Chaim Bell, Edward Etchells, Ian G. Stiell, Kelly Zarnke, Peter C. Austin, and Alan J. Forster. 2010. Derivation and validation of an index to predict early death or unplanned readmission after discharge from hospital to the community. Canadian Medical Association Journal 182, 6 (2010), 551--557. DOI:https://doi.org/10.1503/cmaj.091117Google ScholarGoogle ScholarCross RefCross Ref
  38. Michael A. Vedomske, Donald E. Brown, and James H. Harrison. 2013. Random forests on ubiquitous data for heart failure 30-day readmissions prediction. In 2013 12th International Conference on Machine Learning and Applications, Vol. 2. 415--421. DOI:https://doi.org/10.1109/ICMLA.2013.158Google ScholarGoogle Scholar
  39. Martijn Vooijs, Laurence L. Alpay, Jiska B. Snoeck-Stroband, Thijs Beerthuizen, Petra C. Siemonsma, Jannie J. Abbink, Jacob K. Sont, and Ton A. Rövekamp. 2014. Validity and usability of low-cost accelerometers for internet-based self-monitoring of physical activity in patients with chronic obstructive pulmonary disease. Interactive Journal of Medical Research 3, 4 (Oct. 27, 2014), e14. DOI:https://doi.org/10.2196/ijmr.3056Google ScholarGoogle Scholar
  40. Haishuai Wang, Zhicheng Cui, Yixin Chen, Michael Avidan, Arbi Ben Abdallah, and Alexander Kronzer. 2017. Cost-sensitive deep learning for early readmission prediction at a major hospital. 16th SIGKDD Workshop on Data Mining in Bioinformatics.Google ScholarGoogle Scholar
  41. Hao Wang, Richard D. Robinson, Carlos Johnson, Nestor R. Zenarosa, Rani D. Jayswal, Joshua Keithley, and Kathleen A. Delaney. 2014. Using the LACE index to predict hospital readmissions in congestive heart failure patients. BMC Cardiovascular Disorders 14, 1 (Aug. 7, 2014), 97. DOI:https://doi.org/10.1186/1471-2261-14-97Google ScholarGoogle Scholar
  42. Rui Wang, Weichen Wang, Min S. H. Aung, Dror Ben-Zeev, Rachel Brian, Andrew T. Campbell, Tanzeem Choudhury, Marta Hauser, John Kane, Emily A. Scherer, and Megan Walsh. 2017. Predicting symptom trajectories of Schizophrenia using mobile sensing. Proceedings of ACM Interactive Mobile Wearable Ubiquitous Technology 1, 3 (Sept. 2017), 110:1--110:24. DOI:https://doi.org/10.1145/3130976Google ScholarGoogle ScholarDigital LibraryDigital Library
  43. Linli Xu, Koby Crammer, and Dale Schuurmans. 2006. Robust support vector machine training via convex outlier ablation. In Proceedings of the 21st National Conference on Artificial Intelligence - Vol. 1 (AAAI’06). AAAI Press, 536--542.Google ScholarGoogle Scholar
  44. Tong Zhang. 2009. Multi-stage convex relaxation for learning with sparse regularization. In Advances in Neural Information Processing Systems 21. Curran Associates Inc., 1929--1936.Google ScholarGoogle Scholar
  45. Bichen Zheng, Jinghe Zhang, Sang Won Yoon, Sarah S. Lam, Mohammad Khasawneh, and Srikanth Poranki. 2015. Predictive modeling of hospital readmissions using metaheuristics and data mining. Expert Systems with Applications 42, 20 (2015), 7110--7120. DOI:https://doi.org/10.1016/j.eswa.2015.04.066Google ScholarGoogle ScholarDigital LibraryDigital Library
  46. Xi-chuan Zhou, Hai-bin Shen, and Jie-ping Ye. 2011. Integrating outlier filtering in large margin training. Journal of Zhejiang University Science C 12, 5 (May 4, 2011), 362. DOI:https://doi.org/10.1631/jzus.C1000361Google ScholarGoogle Scholar
  47. Boback Ziaeian and Gregg C. Fonarow. 2015. The prevention of hospital readmissions in heart failure. Progress in Cardiovascular Diseases 58, 4 (2015), 379--385. DOI:https://doi.org/10.1016/j.pcad.2015.09.004Google ScholarGoogle Scholar
  48. Kiyana Zolfaghar, Naren Meadem, Ankur Teredesai, Senjuti Basu Roy, Si-Chi Chin, and Brian Muckian. 2013. Big data solutions for predicting risk-of-readmission for congestive heart failure patients. In 2013 IEEE International Conference on Big Data. 64--71. DOI:https://doi.org/10.1109/BigData.2013.6691760Google ScholarGoogle ScholarCross RefCross Ref

Index Terms

  1. Feasibility Study of Monitoring Deterioration of Outpatients Using Multimodal Data Collected by Wearables

      Recommendations

      Comments

      Login options

      Check if you have access through your login credentials or your institution to get full access on this article.

      Sign in

      Full Access

      PDF Format

      View or Download as a PDF file.

      PDF

      eReader

      View online with eReader.

      eReader

      HTML Format

      View this article in HTML Format .

      View HTML Format
      About Cookies On This Site

      We use cookies to ensure that we give you the best experience on our website.

      Learn more

      Got it!