Data Driven Analytics for Personalized Healthcare
The concept of Learning Health Systems (LHS) is gaining momentum as more and more electronic healthcare data becomes increasingly accessible. The core idea is to enable learning from the collective experience of a care delivery network as recorded in the observational data, to iteratively improve care quality as care is being provided in a real world setting. In line with this vision, much recent research effort has been devoted to exploring machine learning, data mining and data visualization methodologies that can be used to derive real world evidence from diverse sources of healthcare data to provide personalized decision support for care delivery and care management. In this chapter, we will give an overview of a wide range of analytics and visualization components we have developed, examples of clinical insights reached from these components, and some new directions we are taking.
KeywordsData driven healthcare analytics Learning health system Practice based evidence Real world evidence Clinical decision support Machine learning Data mining Data visualization
- 4.Gawande A. The hot spotters. New Yorker, Jan 2011.Google Scholar
- 5.Global Initiative for Chronic Obstructive Lung Disease. Global strategy for the diagnosis, management, and prevention of COPD. 2014. http://www.goldcopd.org/guidelines-global-strategy-for-diagnosis-management.html. Accessed 21 Apr 2015.
- 6.Gotz D, Starvropoulos H, Sun J, Wang F. ICDA: a platform for intelligent care delivery analytics. Am Med Inform Assoc Annu Symp AMIA. 2012;2012:264–73.Google Scholar
- 7.Halpern Y, Sontag D. Unsupervised learning of noisy-or bayesian networks. In: Proceedings of the twenty-ninth conference on uncertainty in artificial intelligence (UAI2013). Bellevue, WA, USA. 2013. p. 272–81. arXiv:1309.6834 [cs.LG].
- 8.Hu J, Wang F, Sun J, Sorrentino R, Ebadollahi S. A healthcare utilization analysis framework for hot spotting and contextual anomaly detection. Am Med Inform Assoc Annu Symp (AMIA 2012). 2012;2012:360–9.Google Scholar
- 9.Krause J, Perer A, Bertini E. INFUSE: interactive feature selection for predictive modelling of high dimensional data. Paris: IEEE Visual Analytics Science and Technology (VAST 2014); 2014.Google Scholar
- 11.LHS. Institute of Medicine Report: best care at lower cost: the path to continuously learning health care in America, released on 6 Sept 2012. 2013. http://www.iom.edu/Reports/2012/Best-Care-at-Lower-Cost-The-Path-to-Continuously-Learning-Health-Care-in-America.aspx.
- 12.Luo D, Wang F, Sun J, Markatou M, Hu J, Ebadollahi S. SOR: scalable orthogonal regression for non redundant feature selection and its healthcare applications. SIAM Data Mining. 2012. http://www.research.ibm.com/healthcare/papers/sorSDM2012.pdf.
- 14.Mitsa T, editor. Temporal data mining. 1st ed. Boca Raton: Chapman & Hall/CRC; 2010.Google Scholar
- 16.Partners Healthcare. i2b2. 2014. https://www.i2b2.org/.
- 18.Perer A, Sun J. MatrixFlow: temporal network visual analytics to track symptom evolution during disease progression. Am Med Inform Assoc Annu Symp (AMIA 2012). 2012;2012:716–25.Google Scholar
- 20.Plaisant C, Mushlin R, Snyder A, Li J, Heller D, Shneiderman B. Lifelines: using visualization to enhance navigation and analysis of patient records. In American Medical Informatics Association Annual Symposium (AMIA), AMIA 1998 (1998), 7680.Google Scholar
- 23.Sun J, Sow DM, Hu J, Ebadollahi S. A system for mining temporal physiological data streams for advanced prognostic decision support. In: IEEE international conference on data mining. 2010. p. 1061–66. http://www.research.ibm.com/healthcare/papers/05694085.pdf.
- 24.Sun J, Sow DM, Hu J, Ebadollahi S. Localized supervised metric learning on temporal physiological data. In: International conference on pattern recognition. 2010. p. 4149–52. http://www.research.ibm.com/healthcare/papers/05597728.pdf.
- 26.Wang X, Sontag D, Wang F. Unsupervised learning of disease progression models. In: Proceedings of the 20th ACM SIGKDD international conference on knowledge discovery and data mining. New York: ACM; 2014. p. 85–94.
- 27.Wang F, Sun J, Hu J, Ebadollahi S. iMet: interactive metric learning in healthcare applications. In: SIAM Data Mining Conference. 2011. pp. 944–55. http://www.research.ibm.com/healthcare/papers/304.pdf.
- 28.Wang F, Sun J, Ebadollahi S. Integrating distance metrics learned from multiple experts and its application in inter-patient similarity assessment. In: SIAM Data Mining Conference. 2011. p. 59–70. http://www.research.ibm.com/healthcare/papers/113.pdf.
- 29.Wang X, Wang F, Wang J, Qian B, Hu J. Exploring patient risk groups with incomplete knowledge. 2013 IEEE 13th international conference on data mining (ICDM). New York: IEEE; 2013. p. 1223–28.
- 30.Wang F, Zhang C. Feature extraction by maximizing the average neighborhood margin. In: Computer Vision and Pattern Recognition, New York: IEEE; 2007. p. 1–8.
- 31.Wang F, Zhang C. Label propagation through linear neighborhoods. In: Proceedings of the 23rd international conference on machine learning, Pittsburgh, 2006, p. 985–92. http://www.autonlab.org/icml_documents/camera-ready/124_Label_Propagation_th.pdf.
- 32.WDA. What is Watson? 2014. http://www.ibm.com/smarterplanet/us/en/ibmwatson/discovery-advisor.html.
- 35.Zhang Z, Gotz D, Perer A. Iterative cohort analysis and exploration. Journal of Information Visualization, March 19, 2014. doi: 10.1177/1473871614526077. http://ivi.sagepub.com/content/early/2014/03/19/1473871614526077.abstract
- 36.Zhang P, Wang F, Hu J, Sorrentino R. Towards personalized medicine: leveraging patient similarity and drug similarity analytics. Am Med Inform Assoc (AMIA) Jt Summit Transl Sci Transl Bioinforma (TBI). 2014;2014:132–6.Google Scholar
- 37.Zhou J, Wang F, Hu J, Ye J. From micro to macro: data driven phenotyping by densification of longitudinal electronic medical records Proceedings of the 20th ACM SIGKDD international conference on knowledge discovery and data mining. New York: ACM; 2014. p. 135–44.Google Scholar