Observational Data and Machine Learning

I work on prediction and analysis of electronic health record data using existing and novel probabilistic methods.

I am interested in developing methods that combine disparate sources of data, such as clinical notes, laboratory values, medications, procedures, and billing codes to predict things such as chronic kidney disease progression or analyze data to identify side-effects that were previously unknown.

Wearable Medical Diagnostics and Sensors

As an extention of my work in analyzing electronic health record data, I am also interested in developing new sources of data to improve our ability to predict and analyze.

I am interested in developing methods that leverage data from mass spectrometry and light spectroscopy to better characterize an individual's current state of health and predict their future state of health.

Fall 2018-present: Computational Methods (BINF G4002)

This course is targeted to biomedical scientists developing a broad understanding of computational methods applicable in biomedicine. This is a fast-paced, technical course covering a broad range of topics including: Density estimation, regression, classification, deep learning, probabilistic graphical models, clustering, dimensionality reduction, time series models, statistical NLP, networks, hypothesis testing, causal inference, imputation, and association rule mining. Students are expected to read technical texts carefully, participate actively in lecture discussion, and develop hands-on skills in labs involving real-world biomedical and health datasets.

Spring 2016: Readings in Biomedical Informatics - Probabilistic Graphical Models for Biomedical Informatics (BINF 8001)

This course is a reading course targeted towards biomedical scientists interested in developing in-depth knowledge of Bayesian statistics and the graphical modeling framework. This is a fast-paced course covering the fundamentals of probabilistic graphical modeling theory, exponential families, model design, latent variable models, the expectation maximization algorithm, and various methods for inference including Markov chain Monte Carlo methods and variational methods. This course will involve several programming assignments and a final project.

Fall 2016-Fall 2019: Biomedical Informatics Seminar Series (BINF 4099)

Weekly seminar series with invited speakers, student research talks, and journal clubs. View the seminar schedule here.

For a PDF version, please click here.

For links to my publications, please see my Google Scholar page.

Adler Perotte

Department of Biomedical Informatics
Columbia University Medical Center
622 West 168th Street. PH20
New York, New York 10032

http://people.dbmi.columbia.edu/~ajp9009/

Current

Amelia Averitt - PhD Candidate

Shreyas Bhave - PhD Student

Victor Rodriguez - PhD Student

Katherine Schlosser - Masters

Aurnov Chattopadhyay - Undergraduate

Francesco Grechi - Undergraduate

Jason Ping - High School

Affiliated

Pierre Elias - Clinical Fellow

Past

Peter Bullen - PhD Candidate, Applied Math and Applied Physics

Joongheum (PJ) Park - Clinical Informatics Fellow

Guillaume David - Postdoctoral Research Scientist

Anando Sen - Postdoctoral Research Scientist

Natnicha (Numfah) Vanitchanant - Masters

Liana Tascau - Masters

Aras Curukcu - High School Intern