Using AI to Improve Clinical Outcomes
Clinical Data Science
We are a team of data scientists and engineers that leverage the power of ML and AI at Mount Sinai Hospital.
Clinical Conditions
Data science, machine learning (ML) and artificial intelligence (AI) have the potential to transform the delivery of clinical care and improve early recognition and diagnosis of clinical conditions
Hospital Operations
AI allows us to gain new insights and continuously improve over time as the platform learns from our patients and clinicians to enhance hospital operations
Awareness and Intervention
We have built a powerful real-time streaming clinical data platform that brings the power of ML and AI to improve provider awareness and timely intervention
Development and validation of a machine learning-based prediction model for near-term in-hospital mortality among patients with COVID-19
This paper was published in BMJ Supportive and Palliative Care 2022;12:e424-e431. Parchure P, Joshi H, Dharmarajan K, et al. Development and validation of a machine learning-based prediction model for near-term in-hospital mortality among patients with COVID-19. BMJ...
MUST-Plus: A Machine Learning Classifier That Improves Malnutrition Screening in Acute Care Facilities
The paper below was published in the Journal of the American College of Nutrition, 40:1,3-12. Prem Timsina, Himanshu N. Joshi, Fu-Yuan Cheng, Ilana Kersch, Sara Wilson, Claudia Colgan, Robert Freeman, David L. Reich, Jeffrey Mechanick, Madhu Mazumdar, Matthew A. Levin...
Using Machine Learning to Predict ICU Transfer in Hospitalized COVID-19 Patients
The paper below was published in the Journal of Clinical Medicine. 2020, 9(6), 1668; Cheng F-Y, Joshi H, Tandon P, Freeman R, Reich DL, Mazumdar M, Kohli-Seth R, Levin MA, Timsina P, Kia A. Using Machine Learning to Predict ICU Transfer in Hospitalized COVID-19...
Using Electronic Health Records to Enhance Predictions of Fall Risk in Inpatient Settings
Using Electronic Health Records to Enhance Predictions of Fall Risk in Inpatient Settings (research paper) NOTE: The research paper below was published in The Joint Commission Journal on Quality and Patient Safety, Volume 46, pages 199-206. Gil Moskowitz,...
MEWS++: Enhancing the Prediction of Clinical Deterioration in Admitted Patients through a Machine Learning Model
The research paper below was published in Journal of Clinical Medicine. 2020; 9(2):343. Kia A, Timsina P, Joshi HN, Klang E, Gupta RR, Freeman RM, Reich DL, Tomlinson MS, Dudley JT, Kohli-Seth R, Mazumdar M, Levin MA. MEWS++: Enhancing the Prediction of Clinical...
48hr Discharge (Length of Stay) MSH
The 48Hr Discharge (aka Length of Stay) streaming engine was created to predict the probability of patient discharge (by 2pm and midnight daily) and therefore help automate the RTDC system and assist in the prioritization of remaining tasks at Mount Sinai Hospital....
How to Use Data to Improve Patient Safety
Avoiding patient harm is intrinsic to the work of healthcare professionals. Hippocrates (ca.460–377 BCE), known as the Father of Modern Medicine, helped set this precedent when he said, “The physician must…have two special objects in view with regard to disease,
namely, to do good or to do no harm.” Data can help.
Pipeline Debt
Interesting new open source project, designed to clear one particular form of technical debt in backend systems: pipeline debt.
Getting Buy-In for Predictive Analytics in Health Care
Because putting together a streaming, real-time, machine-learning, predictive analytics infrastructure is the easy part. https://hbr.org/2017/06/getting-buy-in-for-predictive-analytics-in-health-care