BMI Journal Club

Overview

Welcome to the journal club for the Department of Biomedical Informatics at UCSD.

We present and critique literature on machine learning, signal processing, and computation in biomedicine.

Sessions are moderated by Professor Shamim Nemati.

Where

Altman Clinical and Translational Research Institute (ACTRI)
9452 Medical Center Drive
La Jolla, CA - 92093
(For room number, see below)
—

Schedule & Papers

Date	Time	Room	Presenter	PDFs of Papers & Slides ( )
05/06	10:30am	-	Jonathan	Early detection of sepsis utilizing deep learning on electronic health record event sequences
04/22	10:30am	-	Nancy	Multimodal fusion with deep neural networks for leveraging CT imaging and electronic health record: a case‑study in pulmonary embolism detection
04/08	10:30am	-	Severine	Directions for Explainable Knowledge-Enabled Systems
03/24	10:30am	-	Supreeth	Assessment of Machine Learning to Estimate the Individual Treatment Effect of Corticosteroids in Septic Shock
03/04	10:30am	-	Aaron	Improving the delivery of palliative care through predictive modeling and healthcare informatics
02/19	10:30am	-	-	From Data to Optimal Decision Making: A Data-Driven, Probabilistic Machine Learning Approach to Decision Support for Patients With Sepsis
02/11	10:30am	-	Dr. Sally Baxter	Development and validation of the ISARIC 4C Deterioration model for adults hospitalised with COVID-19: a prospective cohort study
01/28	10:30am	-	Supreeth	Learning Representations of Missing Data for Predicting Patient Outcomes
01/14	10:30am	-	Supreeth	Second opinion needed: communicating uncertainty in medical machine learning
01/07	10:30am	-	Fatemeh	Deep Learning for Improved Risk Prediction in Surgical Outcomes
10/29	10:30am	-	-	Deep-learning-based real-time prediction of acute kidney injury outperforms human predictive performance
10/15	10:30am	-	Supreeth	Controlling Level of Unconsciousness by Titrating Propofol with Deep Reinforcement Learning
10/15	10:30am	-	-	Reinforcement Learning for Closed-Loop Propofol Anesthesia: A Study in Human Volunteers
2020	-	-	-	Contrastive Learning of Medical Visual Representations from Paired Images and Text
2020	-	-	-	A generalizable 29-mRNA neural-network classifier for acute bacterial and viral infections
2020	-	-	Supreeth	Predictive modeling of bacterial infections and antibiotic therapy needs in critically ill adults
2020	-	-	Nancy	Machine Learning Characterization of COPD Subtypes: Insights From the COPDGene Study
2020	-	-	Nancy	A multidimensional precision medicine approach identifies an autism subtype characterized by dyslipidemia
2020	-	-	Nancy	Predicting Severe Chronic Obstructive Pulmonary Disease Exacerbations. Developing a Population Surveillance Approach with Administrative Data
2020	-	-	Nancy	Machine Learning and Prediction of All-Cause Mortality in COPD
2020	-	-	Heqi	Explainable artificial intelligence model to predict acute critical illness from electronic health records

SEPSIS Grand Rounds

Date	Time	Presenter	PDFs of Papers & Slides ( )
09/23	11am	Chris	Control of Confounding and Reporting of Results in Causal Inference Studies Examples of DAG Strobe Statement Strobe Paper

Join our JC

Reminder emails are sent out via the BMIJC googlegroup listserv.

Please enter your name and E-mail address in this spreadsheet to receive notifications regarding BMIJC.

Please spread the word to colleagues; anyone is welcome to attend.

Note this website is the gold standard for meeting locations, times, and dates.

ML method papers

Overcoming catastrophic forgetting in neural networks Blog post

Exponentially Weighted Imitation Learning for Batched Historical Data

Previous presentations

Date	Presenter	PDFs of Papers & Slides ( )
04/13	-	1) PROBAST: A Tool to Assess Risk of Bias and Applicability of Prediction Model Studies: Explanation and Elaboration 2) A Harmonized Data Quality Assessment Terminology and Framework for the Secondary Use of Electronic Health Record Data
09/12	Supreeth	On the interpretability of machine learningbased model for predicting hypertension Extra: Blog post on LIME, Blog post on Shapley Values
08/15	Jejo Koola	A clinically applicable approach to continuous prediction of future acute kidney injury
07/12	Gabe Wardi	Personal clinical history predicts antibiotic resistance of urinary tract infections
07/02	Supreeth	Derivation, Validation, and Potential Treatment Implications of Novel Clinical Phenotypes for Sepsis - Continued
06/20	Supreeth	Derivation, Validation, and Potential Treatment Implications of Novel Clinical Phenotypes for Sepsis and Supplementary Material
05/17	Supreeth	Electronic health record-based clinical decision support alert for severe sepsis: a randomised evaluation and Objecting to experiments that compare two unobjectionable policies or treatments
02/25	Matt	Temporal Convolutional Networks and Dynamic Time Warping can Drastically Improve the Early Prediction of Sepsis
02/11	Russell	Sepsis as a model for improving diagnosis and Evaluating the impact of a computerized surveillance algorithm and decision support system on sepsis mortality
01/09	Russell	Evaluating a New Marker for Risk Prediction Using the Test Tradeoff: An Update Decision Analysis for the Evaluation of Diagnostic Tests, Prediction Models, and Molecular Markers Decision Analysis
12/05/18	Russell	The challenge of implementing AI models in the ICU To Trust Or Not To Trust A Classifier Supplement
11/16/18	Russell/Supreeth	Relational inductive biases, deep learning, and graph networks
10/24/18	Russell	The Artificial Intelligence Clinician learns optimal treatment strategies for sepsis in intensive care Supplementary Materials
10/03/18	Supreeth	Addressing Appearance Change in Outdoor Robotics with Adversarial Domain Adaptation
09/28/18	Supreeth	Estimating attributable fraction of mortality from sepsis to inform clinical trials Supplementary Materials
09/12/18	Russell	The reusable holdout: Preserving validity in adaptive data analysis Supplementary Materials
03/07/18	Supreeth	Scalable and accurate deep learning for Electronic Health Records
01/31/19	Supreeth	Learning to cluster in order to transfer across domains and tasks
01/24/18	Azade	Maximum Likelihood Estimation, Weibull cox proportional hazards model
12/14/17	Supreeth	Neural Network based clustering using pair-wise constraints
07/13/17	Erik Reinertsen	Transfer Entropy Estimation and Directional Coupling Change Detection in Biomedical Time Series
07/06/17	Supreeth	Doubly Robust Policy Evaluation and Learning
06/29/17	Supreeth	Doubly Robust Estimation of Causal Effects
06/22/17	Supreeth	Nonlinear Inverse Reinforcement Learning with Gaussian Processes
06/07/17	Supreeth	Doctor AI: Predicting Clinical Events via Recurrent Neural Networks
06/22/16	Mark Connolly	The Automatic Neuroscientist: A framework for optimizing experimental design with closed-loop real-time fMRI
05/18/16	Sahar Harati	Speech Emotion Recognition Using Deep Neural Network and Extreme Learning Machine
04/27/16	Jitesh Punjabi	Using Anchors to Estimate Clinical State without Labelee Data
04/13/16	Supreeth Prajwal	OrderRex: clinical order decision support and outcome predictions by data-mining electronic medical records
03/30/16	Ziyi Li	Using generalized estimating equations for longitudinal data analysis
03/02/16	Erik Reinertsen	Major depressive disorder subtypes to predict long-term course
02/17/16	Myles McCrary	Real-time prediction of mortality, readmission, and length of stay