My primary research interests lie at the intersection of machine learning, data mining, and medicine. Within machine learning, I am particularly interested in time-series analysis, transfer/multitask learning, intelligible models, and causal inference. The overarching goal of my research is to develop the computational methods needed to help organize, process, and transform patient data into actionable knowledge.
My work has applications in modeling disease progression and predicting adverse outcomes. For several years now, I have been focused on developing accurate patient risk stratification approaches that leverage spatiotemporal data, with the ultimate goal of reducing the rate of healthcare-associated infections among patients admitted to hospitals in the US.
In addition to my research in the healthcare domain, I also spend a portion of my time developing new data mining techniques for analyzing player tracking data from the NBA. In general, I enjoy tackling the challenges that develop when working with large complex datasets.
- Heart Sound Classification Based on Temporal Alignment Techniques, Jose Javier Gonzalez Ortiz, Cheng Perng Phoo, and Jenna Wiens, Computing in Cardiology, September 2016.[Code: link]
- Method to their March Madness: Insights from Mining a Novel Large-Scale Dataset of Pool Brackets, Mason Wright and Jenna Wiens, KDD Workshop on Large-Scale Sports Analytics, August 2016.
- Patient Risk Stratification with Time-Varying Parameters: A Multitask Learning Approach, Jenna Wiens, John Guttag, and Eric Horvitz, JMLR, April 2016.
- Recognizing and Analyzing Ball Screen Defense in the NBA, Avery McIntyre, Joel Brooks, John Guttag, and Jenna Wiens, Sloan Sports Analytics Conference, March 2016.[Slides: pdf]
- Automated Feature Learning: Mining Unstructured Data for Useful Abstractions, Abhishek Bafna and Jenna Wiens, ICDM, November 2015.
- Learning Useful Abstractions from the Web , Abhishek Bafna and Jenna Wiens, AMIA [poster], November 2015.
- An LED Blink is Worth a Thousand Packets: Inferring a Networked Device's Activity from its LED Blinks, Sai R. Gouravajhala et al. USENIX Summit on Information Technologies for Health, August 2015.
- Predicting Disease Progression in Alzheimer's Disease, Devendra Goyal, Zeeshan Syed, and Jenna Wiens MUCMD, August 2015.
- Learning Data-Driven Patient Risk Stratification Models for Clostridium difficile, Jenna Wiens et al., Open Forum Infectious Diseases, July 2014.
- Learning to Prevent Healthcare-Associated Infections: Leveraging Data Across Time and Space to Improve Local Predictions, Jenna Wiens, PhD Thesis, MIT, May 2014.
- Automatically Recognizing On-Ball Screens, Jenna Wiens et al., Sloan Sports Analytics Conference, Feb 2014.
- A Study in Transfer Learning: Leveraging Data from Multiple Hospitals to Enhance Hospital-Specific Predictions, Jenna Wiens et al., Journal of the American Medical Informatics Association, Jan 2014.
- To Crash or Not to Crash: A quantitative look a the relationship between offensive rebounding and transition defense in the NBA, Jenna Wiens et al., Sloan Sports Analytics Conference, March 2013.
- Patient Risk Stratification for Hospital-Associated C. diff as a Time-Series Classification Task, Jenna Wiens et al., Neural Information Processing Systems (NIPS), Dec 2012. [Video]
- Learning Evolving Patient Risk Processes for C. diff Colonization, Jenna Wiens et al., ICML Workshop on Clinical Data Analysis, June 2012.[Slides: pdf]
- On the Promise of Topic Models for Abstracting Complex Medical Data: A Study of Patients and their Medications, Jenna Wiens et al., NIPS Workshop on Personalized Medicine, December 2011.
- Patient-Specific Ventricular Beat Classification without Patient-Specific Expert Knowledge: A Transfer Learning Approach, Jenna Wiens and John Guttag, IEEE EMBS Conference, September 2011.
- Active Learning Applied to Patient-Adaptive Heartbeat Classification, Jenna Wiens and John Guttag, Neural Information Processing Systems (NIPS), December 2010.
- Machine Learning for Ectopic Beat Classification, Jenna Wiens. Master's thesis, MIT, May 2010.
- Patient-Adaptive Ectopic Beat Classification using Active Learning. , Jenna Wiens and John Guttag, Computing in Cardiology (CinC) September 2010. [Slides: pptx]
Invited Talk at Wellesley College: Big Data's Impact in Medicine, Finance, and Sports | SSAC13: To Crash or not to Crash | ESPN TrueHoop TV: Interview with Henry Abbott | ESPN TrueHoop: Commentary | Grantland Interview | NIPS 2012 Spotlight | NIPS Workshops 2011 Spotlight