Machine Learning

Generalizing an Antibiotic Recommendation Algorithm for Treatment of Urinary Tract Infections to an Urban Academic Medical Center

An AI-based system for UTI antibiotic selection generalized fairly well to data from NYU Langone Health. However, utility in practice unclear due to a concerning trend of disparities against non-white patients. The tradeoff between inappropriate antibiotic treatment (IAT; how often the prescribed antiobiotic is ineffective) and broad-spectum usage (BSU; how often a stronger, more broad antibiotic is prescribed) is improved by the AI but white patients benefit significantly whereas non-white groups continue to receive ineffective and aggressive treatment.

Garrett Yoon, Richard S. Matulewicz, Vincent J. Major

Evaluating the Effect of a COVID-19 Predictive Model to Facilitate Discharge: A Randomized Controlled Trial

Background We previously developed and validated a predictive model to help clinicians identify hospitalized adults with coronavirus …

Vincent J. Major, Simon A. Jones, Narges Razavian, Ashley Bagheri, Felicia Mendoza, Jay Stadelman, Leora Horwitz, Jonathan Austrian, Yindalon Aphinyanaphongs

Probing Automated Treatment of Urinary Tract Infections for Bias: A Case-Study Where Machine Learning Perpetuates Structural Differences and Racial Disparities

Urinary tract infections (UTI) are a common indication for antibiotic treatment worldwide. Fluoroquinolone antibiotics are widely …

Garrett Yoon, Vincent J. Major

Clinical Trial of an AI COVID-19 Model to Identify Patients Ready for Discharge

We previously developed a predictive model to help clinicians identify adults with COVID-19 who may be ready for discharge given their …

Vincent J. Major, Simon Jones, Ashley Bagheri, Felicia Mendoza, Jay Stadelman, Vuthy Nguy, Michael Quinn, Peter Stella, Narges Razavian, Leora Horwitz, Jonathan Austrian, Yindalon Aphinyanaphongs

Expanding the Reach of Structured EHR Data with Clinical Notes: Improving End-of-Life Prediction

Appropriate treatment decisions and end-of-life planning for patients with serious, life-limiting disease rely on accurate prognosis …

Seda Bilaloglu, Vincent J. Major, Himanshu Grover, Isabel Metzger, Yindalon Aphinyanaphongs

Supporting Acute Advance Care Planning with Precise, Timely Mortality Risk Predictions

Patients with serious, life-limiting disease benefit from end-of-life conversations, goal setting, and palliative care. Hospitalized …

Erwin Wang, Vincent J. Major, Nicole Adler, Kevin Hauck, Jonathan Austrian, Yindalon Aphinyanaphongs, Leora Horwitz

A Validated, Real-Time Prediction Model for Favorable Outcomes in Hospitalized COVID-19 Patients

The COVID-19 pandemic has challenged front-line clinical decision-making, leading to numerous published prognostic tools. However, few …

Narges Razavian, Vincent J. Major, Mukund Sudarshan, Jesse Burk-Rafel, Peter Stella, Hardev Randhawa, Seda Bilaloglu, Ji Chen, Vuthy Nguy, Walter Wang, Hao Zhang, Ilan Reinstein, David Kudlowitz, Cameron Zenger, Meng Cao, Ruina Zhang, Siddhant Dogra, Keerthi Harish, Brian Bosworth, Fritz Francois, Leora Horwitz, Rajesh Ranganath, Jonathan Austrian, Yindalon Aphinyanaphongs

Development, Implementation, and Prospective Validation of a Model to Predict 60-Day End-of-Life in Hospitalized Adults Upon Admission at Three Sites

Background: Automated systems that use machine learning to estimate a patient’s risk of death are being developed to influence care. …

Vincent J. Major, Yindalon Aphinyanaphongs

Estimating Real World Performance of a Predictive Model: A Case-Study in Predicting End-of-Life

Objective: One primary consideration when developing predictive models is downstream effects on future model performance. We conduct …

Vincent J. Major, Neil Jethani, Yindalon Aphinyanaphongs