Machine Learning in Health Care
Welcome to the AIM_AHEAD and PRIME Machine Learning in Health Care Course
Course Description
Machine Learning in Health Care
Course description
Introduces students to machine learning in healthcare, including the nature of clinical data and the use of machine learning for risk stratification, disease progression modeling, precision medicine, diagnosis, subtype discovery, and improving clinical workflows. Topics include causality, interpretability, algorithmic fairness, time-series analysis, graphical models, deep learning and transfer learning.
Note: this is a self-directed course. Materials have been adopted from the Institute for Medical Engineering & Science, the Computer Science and Artificial Intelligence Laboratory, and the J-Clinic for Machine Learning in Health at MIT.
LECTURE NOTES
READINGS
| SES # | REQUIRED READINGS | OPTIONAL READINGS |
|---|---|---|
1 | No required readings. | Bates, David, Suchi Saria, et al. “Big Data In Health Care: Using Analytics to Identify and Manage High-Risk and High-Cost Patients.” Health Affairs 33, no. 7 (July 2014): 1123–31. |
2 | No required readings. | No readings. |
3 | Agniel, Denis, Isaac Kohane, and Griffin Weber. “Biases in Electronic Health Record Data Due to Processes Within the Healthcare System: Retrospective Observational Study.” BMJ, 2018. | No readings. |
4 | Razavian, Narges, Saul Blecker, et al. “Population-Level Prediction of Type 2 Diabetes From Claims Data and Analysis of Risk Factors.” Big Data 3, no. 4 (2015): 277–87. Pozen, Michael, Ralph D’Agostino, et al. “A Predictive Instrument to Improve Coronary-Care-Unit Admission Practices in Acute Ischemic Heart Disease.” New England Journal of Medicine 310, no. 20 (1984): 1273–78. | No readings. |
5 | Futoma, Joseph, Sanjay Hariharan, et al. “An Improved Multi-Output Gaussian Process RNN With Real-Time Validation for Early Sepsis Detection.” arXiv preprint arXiv:1708.05894 (2017). Caruana, Rich, Yin Lou, et al. “Intelligible Models for HealthCare.” Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD 15, 2015. | Henry, Katharine, David Hager, et al. “A Targeted Real-Time Early Warning Score (TREWScore) for Septic Shock.” Science Translational Medicine 7, no. 299 (May 2015). Rodríguez, G. (2007). “Chapter 7: Survival Models.” In Lecture Notes on Generalized Linear Models. |
6 | Quinn, J.A., C.K.I. Williams, and N. Mcintosh. “Factorial Switching Linear Dynamical Systems Applied to Physiological Condition Monitoring.” IEEE Transactions on Pattern Analysis and Machine Intelligence 31, no. 9 (2009): 1537–51. Hannun, Awni, Pranav Rajpurkar, et al. “Cardiologist-Level Arrhythmia Detection and Classification in Ambulatory Electrocardiograms Using a Deep Neural Network.” Nature Medicine 25, no. 3 (2019): 65–69. | No readings. |
7 | Leaman, Robert, Ritu Khare, and Zhiyong Lu. “Challenges in Clinical Natural Language Processing for Automated Disorder Normalization.” Journal of Biomedical Informatics 57 (2015): 28–37. | Halpern, Yoni, Steven Horng, et al. “Electronic Medical Record Phenotyping Using the Anchor and Learn Framework.” Journal of the American Medical Informatics Association 23, no. 4 (2016): 731–40. Elhadad, N., and D. Demner-Fushman. “Aspiring to Unintended Consequences of Natural Language Processing: A Review of Recent Developments in Clinical and Consumer-Generated Text Processing.” Yearbook of Medical Informatics 25, no. 01 (2016): 224–33. |
8 | No required readings. | Vaswani, Ashish, Noam Shazeer, et al. “Attention Is All You Need.” In Advances in Neural Information Processing Systems, pp. 5998-6008. 2017. Devlin, Jacob, Ming-Wei Chang, et al. “Bert: Pre-Training of Deep Bidirectional Transformers for Language Understanding.” arXiv preprint arXiv:1810.04805 (2018). |
9 | No required readings. | Fihn, Stephan, Joseph Francis, et al. “Insights From Advanced Analytics at the Veterans Health Administration.” Health Affairs 33, no. 7 (2014): 1203–11. Amland, Robert C., and Kristin E. Hahn-Cover. “Clinical Decision Support for Early Recognition of Sepsis.” American Journal of Medical Quality 31, no. 2 (March 2016): 103–10. |
10 | Ranschaert, Erik, Sergey Morozov, and Paul Algra. “Chapter 13: Artificial Intelligence and Computer-Assisted Evaluation of Chest Pathology.” In Artificial Intelligence in Medical Imaging: Opportunities, Applications and Risks. Cham, Switzerland: Springer, 2019. ISBN: 9783319948775. | Zhang, Jeffrey, Sravani Gajjala, et al. “Fully Automated Echocardiogram Interpretation in Clinical Practice: Feasibility and Diagnostic Accuracy.” Circulation 138, no. 16 (2018): 1623-1635. Lieman-Sifry, Jesse, Matthieu Le, et al. “FastVentricle: Cardiac Segmentation with ENet.” Functional Imaging and Modelling of the Heart Lecture Notes in Computer Science (2017): 127–38. |
11 | Rotmensch, Maya, Yoni Halpern, et al. “Learning a Health Knowledge Graph from Electronic Medical Records.” Scientific Reports 7, no. 1 (2017): 5994. | Shwe, M. A., D. E. Heckerman, et al. “Probabilistic Diagnosis Using a Reformulation of the INTERNIST-1/QMR Knowledge Base.” Methods of Information in Medicine 30, no. 04 (1991): 241–55. Pople, H. E., Jr. “Heuristic Methods for Imposing Structure on Ill-Structured Problems: The Structuring of Medical Diagnostics.” In Szolovits, P. (Ed.) Artificial Intelligence in Medicine. 1982. |
12 | Wang, Dayong, Aditya Khosla, et al. “Deep Learning for Identifying Metastatic Breast Cancer.” arXiv preprint arXiv:1606.05718 (2016). | Oakden-Rayner, Luke. “Exploring the ChestXray14 Dataset: Problems.” Rayner, December 18, 2017. |
13 | Ranschaert, Erik, Sergey Morozov, and Paul Algra. “Chapter 14: Deep Learning in Breast Cancer Screening.” In Artificial Intelligence in Medical Imaging: Opportunities, Applications and Risks. Cham, Switzerland: Springer, 2019. ISBN: 9783319948775. | Lehman, Constance, Adam Yala, et al. “Mammographic Breast Density Assessment Using Deep Learning: Clinical Implementation.” Radiology 290, no. 1 (2019): 52–58. |
14 | Hernán MA, Robins JM. Causal Inference: What If. Boca Raton: Chapman & Hall/CRC, forthcoming. Chapter 1. 2019. | Brat, Gabriel, Denis Agniel, et al. “Postsurgical Prescriptions for Opioid Naive Patients and Association with Overdose and Misuse: Retrospective Cohort Study.” BMJ, 2018. Bertsimas, Dimitris, Nathan Kallus, et al. “Personalized Diabetes Management Using Electronic Medical Records.” Diabetes Care 40, no. 2 (Feb 2017): 210–17. Huszar, Ferenc. “Causal Inference 3: Counterfactuals.” inFERENCe. January 24, 2019. |
15 | No required readings. | Rosenbaum, Paul R. “From Association to Causation in Observational Studies: The Role of Tests of Strongly Ignorable Treatment Assignment.” Journal of the American Statistical Association 79, no. 385 (1984): 41. Kallus, Nathan, and Angela Zhou. “Confounding-Robust Policy Improvement.” In Advances in Neural Information Processing Systems, pp. 9269-9279. 2018. Louizos, Christos, Uri Shalit, et al “Causal Effect Inference with Deep Latent-Variable Models.” In Advances in Neural Information Processing Systems, pp. 6446-6456. 2017. |
16 | Prasad, Niranjani, Li-Fang Cheng, et al. “A Reinforcement Learning Approach to Weaning of Mechanical Ventilation in Intensive Care Units.” arXiv preprint arXiv:1704.06300 (2017). | Chakraborty, Bibhas, and Erica Moodie. Statistical Methods for Dynamic Treatment Regimes. Section 2.1, 2.2, and Chapter 3. Springer, 2013. ISBN: 9781461474272. Gottesman, Omer, Fredrik Johansson, et al. “Guidelines for Reinforcement Learning in Healthcare.” Nature Medicine 25, no. 1 (2019): 16–18. |
17 | Komorowski, Matthieu, Leo Celi, et al. “The Artificial Intelligence Clinician learns optimal treatment strategies for sepsis in intensive care.” Nature Medicine 24, no. 11 (2018): 1716. | Dickerman, Barbra, Edward Giovannucci, et al. “Guideline-Based Physical Activity and Survival Among US Men With Nonmetastatic Prostate Cancer.” American Journal of Epidemiology 188, no. 3 (2018): 579–86. |
18 | Schulam, Peter, and Suchi Saria. “Integrative Analysis Using Coupled Latent Variable Models for Individualizing Prognoses.” The Journal of Machine Learning Research 17, no. 232 (2016): 1–35. | No readings. |
19 | Young, Alexandra, Razvan Marinescu, et al. “Uncovering the Heterogeneity and Temporal Complexity of Neurodegenerative Diseases with Subtype and Stage Inference.” Nature Communications 9, no. 1 (2018): 4273. | Wang, Xiang, David Sontag, and Fei Wang. “Unsupervised Learning of Disease Progression Models.” In Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 85-94. ACM, 2014. Pierson, Emma, Pang Wei Koh, et al. “Inferring Multi-Dimensional Rates of Aging from Cross-Sectional Data.” arXiv preprint arXiv:1807.04709 (2018). Saelens, Wouter, Robrecht Cannoodt, et al. “A Comparison of Single-Cell Trajectory Inference Methods.” Nature Biotechnology 37, no. 5 (2019): 547–54. Campbell, Kieran R., and Christopher Yau. “Order Under Uncertainty: Robust Differential Expression Analysis Using Probabilistic Models for Pseudotime Inference.” PLOS Computational Biology 12, no. 11 (2016). |
20 | Udler, Miriam S., Jaegil Kim, et al. “Type 2 Diabetes Genetic Loci Informed by Multi-Trait Associations Point to Disease Mechanisms and Subtypes: A Soft Clustering Analysis.” PLoS Medicine 15, no. 9 (2018): e1002654. | Denny, Joshua, Marylyn Ritchie, et al. “PheWAS: Demonstrating the Feasibility of a Phenome-Wide Scan to Discover Gene–Disease Associations.” Bioinformatics 26, no. 9 (2010): 1205-1210. |
21 | No required readings. | Zhang, Yiye, Rema Padman, and Nirav Patel. “Paving the COWpath: Learning and Visualizing Clinical Pathways from Electronic Health Record Data.” Journal of Biomedical Informatics 58 (2015): 186–97. Gawande, Atul. “A Life-Saving Checklist.” The New Yorker. The New Yorker, December 3, 2007. |
22 | US Food and Drug Administration. “Proposed Regulatory Framework for Modifications to Artificial Intelligence/Machine Learning (AI/ML)-Based Software as a Medical Device (SaMD)-Discussion Paper and Request for Feedback.” (2019). | Coravos, Andy. “The Doctor Prescribes Video Games and Virtual Reality Rehab.” Wired. Conde Nast, November 20, 2018. Coravos, Andy, Irene Chen, et al. “We Should Treat Algorithms like Prescription Drugs.” Quartz. Quartz, February 19, 2019. “Want to Create Meaningful Change in the US Healthcare System? Serve a ‘Tour of Duty’ in the Government.” Rock Health. March 25, 2019. Hsiang, Mina. “If You Want to Make Government Programs Work Better, Submit a Public Comment.” Medium. Medium, March 23, 2019. |
23–25 | No required readings. | No readings. |
Course Faculty and Instructors:
David Sontag Professor of Electrical Engineering and Computer Science at MIT, part of the Institute for Medical Engineering & Science, the Computer Science and Artificial Intelligence Laboratory, and the J-Clinic for Machine Learning in Health. His research focuses on advancing machine learning and artificial intelligence and using these to transform health care.
Peter Szolovits Professor of Computer Science and Engineering and Professor of Health Sciences and Technology, Department of Electrical Engineering and Computer Science
Guest lecturers:
Rahul Deo completed medical school at the Weill Medical College of Cornell University (as part of the Tri-Institutional MD/PhD Program) and then trained in Internal Medicine at Brigham and Women’s Hospital and in Cardiology at the Massachusetts General Hospital. He earned a doctorate in Molecular Biophysics from the Rockefeller University, and completed postdoctoral research at Harvard Medical School in human genetics and computational biology.
Andy Beck earned his MD from Brown Medical School and completed residency and fellowship training in Anatomic Pathology and Molecular Genetic Pathology from Stanford University. He completed a PhD in Biomedical Informatics from Stanford University, where he developed one of the first machine-learning based systems for cancer pathology.
Adam Yala Assistant Professor of Computational Precision Health at UC Berkeley and UCSF. His interests lie in the intersection of Machine Learning and Precision Medicine. He believe that algorithmic innovation can create more precise and equitable healthcare.
Fredrik D. Johansson, PhD Assistant professor of Computer Science & Engineering DSAI.se at Chalmers University of Technology, Sweden Machine Learning for Causal Inference & Healthare, CV (July, 2022)
Andy Coravos is the CEO/Co-Founder of Elektra Labs, building a digital medicine platform focusing on digital biomarkers for decentralized clinical trials. She serves as a research collaborator at the Harvard-MIT Center for Regulatory Sciences. Formerly, she served as an Entrepreneur in Residence at the FDA working in the Digital Health Unit (DHU), focusing on the Pre-Cert program and policies around software-as-a-medical-device and AI/ML. Previously, Andy worked as a software engineer at Akili Interactive Labs, a leading digital therapeutic company.
Mark Shervey Data Engineer @ Institute for Next Generation Healthcare Icahn School of Medicine at Mount Sinai.
- https://ocw.mit.edu/
- https://ocw.mit.edu/courses/6-s897-machine-learning-for-healthcare-spring-2019/
- https://mlhc17mit.github.io/
- https://mlhcmit.github.io/