Deployment of a Robust and Explainable Mortality Prediction Model: The COVID-19 Pandemic and Beyond

no code implementations • 28 Nov 2023 • Jacob R. Epifano, Stephen Glass, Ravi P. Ramachandran, Sharad Patel, Aaron J. Masino, Ghulam Rasool

This study investigated the performance, explainability, and robustness of deployed artificial intelligence (AI) models in predicting mortality during the COVID-19 pandemic and beyond.

Mortality Prediction

Revisiting the Fragility of Influence Functions

1 code implementation • 22 Mar 2023 • Jacob R. Epifano, Ravi P. Ramachandran, Aaron J. Masino, Ghulam Rasool

In the last few years, many works have tried to explain the predictions of deep learning models.

Machine learning models for early sepsis recognition in the neonatal intensive care unit using readily available electronic health record data

1 code implementation • PLOS ONE 2019 • Aaron J. Masino, Mary Catherine Harris, Daniel Forsyth, Svetlana Ostapenko, Lakshmi Srinivasan, Christopher P. Bonafide, Fran Balamuth, Melissa Schmatz, Robert W. Grundmeier

Including both culture and clinically positive cases, the same 6 models achieved an AUC between 0. 85–0. 87, again with no significant differences.

Cultural Vocal Bursts Intensity Prediction

Unsupervised learning with GLRM feature selection reveals novel traumatic brain injury phenotypes

no code implementations • 30 Nov 2018 • Aaron J. Masino, Kaitlin A. Folweiler

Baseline injury categorization is important to traumatic brain injury (TBI) research and treatment.

Clustering feature selection

A Framework for Developing and Evaluating Word Embeddings of Drug-named Entity

no code implementations • WS 2018 • Mengnan Zhao, Aaron J. Masino, Christopher C. Yang

We investigate the quality of task specific word embeddings created with relatively small, targeted corpora.

Named Entity Recognition (NER) Outlier Detection +3