no code implementations • 24 Mar 2023 • David Benrimoh, Akiva Kleinerman, Toshi A. Furukawa, Charles F. Reynolds III, Eric Lenze, Jordan Karp, Benoit Mulsant, Caitrin Armstrong, Joseph Mehltretter, Robert Fratila, Kelly Perlman, Sonia Israel, Myriam Tanguay-Sela, Christina Popescu, Grace Golden, Sabrina Qassim, Alexandra Anacleto, Adam Kapelner, Ariel Rosenfeld, Gustavo Turecki
We analyzed data from six clinical trials of pharmacological treatment for depression (total n = 5438) using the Differential Prototypes Neural Network (DPNN), a neural network model that derives patient prototypes which can be used to derive treatment-relevant patient clusters while learning to generate probabilities for differential treatment response.
no code implementations • 6 Dec 2020 • Abba M. Krieger, David Azriel, Adam Kapelner
This rate benefits from the greedy switching heuristic which is $O_p(n^{-3})$ and the rate of matching which is $O_p(n^{-1})$.
Methodology
1 code implementation • 30 Apr 2014 • Adam Kapelner, Justin Bleich, Alina Levine, Zachary D. Cohen, Robert J. DeRubeis, Richard Berk
We demonstrate our method's promise on simulated data as well as on data from a randomized trial investigating two treatments for depression.
Methodology
no code implementations • 8 Dec 2013 • Adam Kapelner, Justin Bleich
We present a new package in R implementing Bayesian additive regression trees (BART).
6 code implementations • 25 Sep 2013 • Alex Goldstein, Adam Kapelner, Justin Bleich, Emil Pitkin
This article presents Individual Conditional Expectation (ICE) plots, a tool for visualizing the model estimated by any supervised learning algorithm.
Applications
no code implementations • 3 Jun 2013 • Adam Kapelner, Justin Bleich
We present a method for incorporating missing data in non-parametric statistical learning without the need for imputation.