Machine Learning for Healthcare 2017
Northeastern University, August 18-19, 2017
Selected videos of talks may be found at: https://www.youtube.com/channel/UCt8n_CtkuWK2gdbDOijxnEg
Friday, August 18:
9:00: The BIDMC Explore IT Program, John Halamka, BIDMC
BIDMC has implemented Machine Learning functionality from Amazon and Google to support several use cases. In this presentation, the speaker will review the implementation experience and the outcomes achieved.
9:45: Deep Learning as an FDA-Cleared Product, Daniel Golden, Arterys
Radiological diagnosis and interpretation is ready for an overhaul. Radiologists spend countless hours on tasks that are onerous and error-prone, resulting in high costs and frequent misdiagnoses. Arterys is working to address these deficiencies, using deep learning to vastly improve the speed and consistency with which radiologists read cardiac MRI studies. Our first product, Arterys Cardio DL, is the first technology ever to be cleared by the FDA that leverages cloud computing and deep learning in a clinical setting. We discuss the technology behind the software and how we proved its safety and efficacy to secure FDA clearance in the United States and the CE Mark in Europe.
13:45: How Can NLP Help Cure Cancer?, Regina Barzilay, MIT
Majority of cancer research today takes place in biology and medicine. Computer science plays a minor supporting role in this process if at all. In this talk, I hope to convince you that NLP as a field has a chance to play a significant role in this battle. Indeed, free-form text remains the primary means by which physicians record their observations and clinical findings. Unfortunately, this rich source of textual information is severely underutilized by predictive models in oncology. In the first part of my talk, I will describe a number of tasks where NLP-based models can make a difference in clinical practice. For example, these include improving models of disease progression, preventing over-treatment, and narrowing down to the cure. This part of the talk draws on active collaborations with oncologists from MGH. In the second part of the talk, I will push beyond standard tools, introducing new functionalities and avoiding annotation-hungry training paradigms ill-suited for clinical practice. In particular, I will focus on interpretable neural models that provide rationales underlying their predictions, and semi-supervised methods for information extraction.
14:30: Tools for Interpretable Machine Learning with Healthcare Applications, Cynthia Rudin, Duke
How do patients and doctors know that they can trust predictions from a model that they cannot understand? Transparency in machine learning models is critical in high stakes decisions, like those made every day in healthcare. My lab creates machine learning algorithms for predictive models that are interpretable to human experts. As it turns out, by using modern optimization tools, one often does not need to sacrifice accuracy to gain interpretability. We will focus mainly on the problem of building medical scoring systems using data. We provide applications to ADHD diagnosis, sleep apnea screening, EEG monitoring for seizure prediction in ICU patients, and early detection of cognitive impairments. Then, we switch to creating logical models, and in particular, rule lists, which are a form of decision tree. Finally we will discuss how to model recovery curves that have realistic shapes and realistic uncertainty bands, and show an application to modeling recovery curves for prostatectomy patients.
I will focus on work of students Berk Ustun, Hima Lakkaraju, William Souillard-Mandar, and Fulton Wang. Other collaborators include Brandon Westover, Matt Bianchi, Randall Davis, Dana L. Penney, Tyler McCormick, and Ronald C. Kessler.
Saturday, August 19:
9:00 AM: The algorithm for precision medicine, Matt Might, Harvard/Utah
Precision medicine requires an algorithmic approach to the delivery of care, and it encounters a wide range of computational challenges. This talk will center on an in-depth case study in precision medicine, highlighting computational challenges at the forefront of the field.
9:45 AM: Opportunities to Apply Machine Learning in Neurocritical Care, Soojin Park, Columbia
The Neurocritical care patient is monitored for reversible secondary brain injury. Timely personalized assessments of subclinical or early state changes in the neuroICU currently rely on vigilance and constant availability of expert interpretation. Those at most risk are obtunded or comatose patients, but state changes in even conscious patients may be clinically asymptomatic or subtly evade detection. With the proliferation of multimodality neuro monitoring and advances in data acquisition and analytics, the field of neuro critical care has generated studies in signal processing and machine learning, advancing the science of detection, prediction, and goal setting. There is growing demand for the implementation of these findings.
13:30: Challenges in Developing Learning Algorithms to Personalize Treatment in Real Time, Susan Murphy, University of Michigan
A formidable challenge in designing sequential treatments is to determine when and in which context it is best to deliver treatments. Consider treatment for individuals struggling with chronic health conditions. Operationally designing the sequential treatments involves the construction of decision rules that input current context of an individual and output a recommended treatment. That is, the treatment is adapted to the individual's context; the context may include current health status, current level of social support and current level of adherence for example. Data sets on individuals with records of time-varying context and treatment delivery can be used to inform the construction of the decision rules. There is much interest in personalizing the decision rules, particularly in real time as the individual experiences sequences of treatment. Here we discuss our work in designing online "bandit" learning algorithms for use in personalizing mobile health interventions.
14:15: Optimized risk stratification and treatment decisions with machine learning, Collin Stultz, MIT
The accurate assessment of a patient’s risk of adverse events remains a mainstay of clinical care for patients with cardiovascular disease. Sophisticated methods, such as those based on machine learning, form an attractive platform to build improved risk metrics because they can easily incorporate disparate pieces of data, yielding classifiers with improved performance. Using data from more than 5200 patients admitted with a non-ST segment elevation acute coronary syndrome we constructed an artificial neural network that identifies patients at high risk of cardiovascular death 1-year after the index event. We further demonstrate how q-learning can be used to find optimal treatment strategies for patients at high risk of death after an acute coronary syndrome.
List of accepted papers
Piecewise-constant parametric approximations for survival learning: Jeremy Weiss*, Carnegie Mellon University
Spatially-Continuous Plantar Pressure Reconstruction Using Compressive Sensing: Amirreza Farnoosh, Northeastern University; Mehrdad Nourani, University of Texas at Dallas; Sarah Ostadabbas*, Northeastern University
Classifying Lung Cancer Severity with Ensemble Machine Learning in Health Care Claims Data: Savannah Bergquist*, Harvard University; Gabriel Brooks, Dartmouth-Hitchcock Medical Center; Nancy Keating, Harvard Medical School, Brigham and Women's Hospital; Mary Beth Landrum, Harvard Medical School; Sherri Rose, Harvard Medical School
Predicting long-term mortality with first week post-operative data after Coronary Artery Bypass Grafting using Machine Learning models: José Forte*, University of Groningen; Marco Wiering, University of Groningen; Hjalmar Bouma, University Medical Center Groningen; Fred de Geus, University Medical Center Groningen; Anne Epema, University Medical Center Groningen
ShortFuse: Biomedical Time Series Representations in the Presence of Structured Information: Madalina Fiterau*, Stanford University; Suvrat Bhooshan, Stanford University; Jason Fries, Stanford University; Charles Bournhonesque, Stanford University; Jennifer Hicks, Stanford University; Eni Halilaj, Stanford University; Christopher Re, Stanford University; Scott Delp, Stanford University
Towards Vision-based Smart Hospitals: A System for Tracking and Monitoring Hand Hygiene Compliance: Albert Haque*, Stanford University; Michelle Guo, Stanford University; Alexandre Alahi, Stanford University; Amit Singh, Lucile Packard Children's Hospital; Serena Yeung, Stanford University; N. Lance Downing, Stanford; Terry Platchek, Lucile Packard Children's Hospital; Li Fei-Fei, Stanford University
Surgeon Technical Skill Assessment using Computer Vision based Analysis: Hei Law*, University of Michigan; Jia Deng, University of Michigan, Ann Arbor; Khurshid Ghani, University of Michigan
Predicting Surgery Duration with Neural Heteroscedastic Regression: Zachary Lipton*, UCSD; Nathan Ng, UCSD; Rodney Gabriel , UCSD; Charles Elkan, UCSD; Julian McAuley, UC San Diego
Temporal prediction of multiple sclerosis evolution from patient-centered outcomes: Samuele Fiorini, University of Genoa; Andrea Tacchino, Italian Multiple Sclerosis Foundation - Scientific Research Area; Giampaolo Brichetto, Italian Multiple Sclerosis Foundation - Scientific Research Area; Alessandro Verri, University of Genova, Italy; Annalisa Barla*, Università degli Studi di Genova
Clustering Patients with Tensor Decomposition: Matteo Ruffini*, UPC; Ricard Gavaldà, UPC; Esther Limón, Institut Català de la Salut
Continuous State-Space Models for Optimal Sepsis Treatment - a Deep Reinforcement Learning Approach: Aniruddh Raghu*, MIT; Marzyeh Ghassemi, MIT; Matthieu Komorowski, Imperial College London; Leo Celi, MIT; Pete Szolovits, MIT
Modeling Progression Free Survival in Breast Cancer with Tensorized Recurrent Neural Networks and Accelerated Failure Time Model: Yinchong Yang*, Siemens AG, LMU München; Volker Tresp, Siemens AG and Ludwig Maximilian University of Munich ; Peter Fasching, Department of Gynecology and Obstetrics, University Hospital Erlangen
Patient Similarity Using Population Statistics and Multiple Kernel Learning: Bryan Conroy*, Philips Research North America; Minnan Xu-Wilson, Philips Research North America; Asif Rahman, Philips Research
A Video-Based Method for Automatically Rating Ataxia: Ronnachai Jaroensri*, MIT CSAIL; Amy Zhao, MIT; Fredo Durand, MIT; John Guttag, MIT; Jeremy Schmahmann, Massachusetts General Hospital; Guha Balakrishnan, MIT; Derek Lo, Yale University
Visualizing Clinical Significance with Prediction and Tolerance Regions: Maria Jahja*, North Carolina State University; Daniel Lizotte, UWO
Predictive Hierarchical Clustering: Learning clusters of CPT codes for improving surgical outcomes: Elizabeth C. Lorenzi, Stephanie L. Brown, Zhifei Sun, and Katherine Heller
An Improved Multi-Output Gaussian Process RNN with Real-Time Validation for Early Sepsis Detection: Joseph Futoma, Sanjay Hariharan, Katherine Heller, Mark Sendak, Nathan Brajer, Meredith Clement, Armando Bedoya, and Cara O'Brien
Marked Point Process for Severity of Illness Assessment Kazi Islam*, UC Riverside; Christian Shelton, UC Riverside
Diagnostic Inferencing via Improving Clinical Concept Extraction with Deep Reinforcement Learning: A Preliminary Study: Yuan Ling, Philips Research North America; Sadid A. Hasan*, Philips Research North America; Vivek Datla, Philips Research North America; Ashequl Qadir, Philips Research North America; Kathy Lee, Philips Research North America; Joey Liu, Philips Research North America; Oladimeji Farri, Philips Research North America
Generating Multi-label Discrete Patient Records using Generative Adversarial Networks: Edward Choi*, Georgia Institute of Technology; Siddharth Biswal, Georgia Institute of Technology; Bradley Malin, Vanderbilt University; Jon Duke, Georgia Institute of Technology; Walter Stewart, Sutter Health; Jimeng Sun, CS
Quantifying Mental Health from Social Media using Learned User Embeddings: Silvio Moreira*, INESC-ID; Glen Copperfield, qntfy.io; Paula Carvalho, INESC-ID; M‡rio Silva, INESC-ID; Byron Wallace, Northeastern
Clinical Intervention Prediction and Understanding using Deep Networks: Nathan Hunt*, MIT; Marzyeh Ghassemi, MIT; Harini Suresh, MIT; Pete Szolovits, MIT; Leo Celi, MIT; Alistair Johnson, MIT
Understanding Coagulopathy using Multi-view Data in the Presence of Sub-Cohorts: A Hierarchical Subspace Approach: Arya Pourzanjani*, UCSB; Tie Bo Wu, UCSB; Richard M. Jiang, UCSB; Mitchell J. Cohen, Denver Health Medical Center; Linda R. Petzold, UCSB
Towards a directory of rare disease specialists: Identifying experts from publication history: Zihan Wang*, University of Toronto; Michael Brudno, U Turonto; Orion Buske, Centre for Computational Medicine, SickKids Hospital
Reproducibility in critical care: a mortality prediction case study: Alistair Johnson*, MIT; Tom Pollard, MIT; Roger Mark, MIT
Accepted clinical abstracts
Extracting Information from Electronic Health Records Using Natural Language Processing – Knowledge Discovery from Unstructured Information: Vasua Chandrasekaran, Jinghua He, Monica Reed Chase, Aman Bhandari, Christopher Frederick, and Paul Dexter
Using Machine Learning to Recommend Oncology Clinical Trials: Anasuya Das, Leifur Thorbergsson, Aleksandr Grigorenko, David Sontag, Iker Huerga
Accounting for diagnostic uncertainty when training a Machine Learning algorithm to detect patients with the Acute Respiratory Distress Syndrome: Narathip Reamaroon, Michael W. Sjoding, Kayvan Najarian
Visual Supervision of Unsupervised Clustering of Patients with Clustervision: Adam Perer*, IBM Research; Bum Chul Kwon, IBM Research; Janu Verma, IBM Research; Kenney Ng, IBM Research; Ben Eysenbach, MIT; Christopher deFilippi, INOVA; Walter Stewart, Sutter Health
Light Field Otoscope 3D Imaging of Diseased Ears in an Alaska Native Population: Manuel Martinello, Harshavardhan Binnamangalam, Philip Hofstetter, John Kokesh, Samantha Kleindienst, Tiffany Romain, Noah Bedard, and Ivana Tosic