June 05, 2019 | Bill Seiler
Machine Learning Score Predicts Hospital Returns Better Than Standard Methods
A University of Maryland School of Medicine study suggests that a novel machine learning model developed at the University of Maryland Medical System (UMMS), called the Baltimore score (B score), may help hospitals better predict which discharged patients are likely to be readmitted.
The research was led by Daniel Morgan, MD, MS, Associate Professor of Epidemiology and Public Health at the University of Maryland School of Medicine (UMSOM). Dr. Morgan analyzed data on more than 14,000 patients from three UMMS hospitals using this special predictive score to determine the likelihood these patients would be readmitted.
The research, published in the journal JAMA Network Open, could help set the stage toward improving patient care and avoiding returns to the hospital... Full Story >
Read the full story at: https://www.umms.org/ummc/news/2019/computer-analytics-may-solve-readmission
Contact
Department of Anesthesiology
(410) 328-6120 (phone)
(410) 328-5531 (fax)
newsletter@som.umaryland.edu
Bill Seiler
Media Relations Assistant Director
University of Maryland Medical Center – Transplant, Heart and Vascular, Surgery
410-328-8919
bseiler@umm.edu
Related stories
Monday, August 07, 2023
AI Transformation of Medicine: Why Doctors Are Not Prepared
As artificial intelligence systems like ChatGPT find their way into everyday use, physicians will start to see these tools incorporated into their clinical practice to help them make important decisions on diagnosis and treatment of common medical conditions. These tools, called clinical decision support (CDS) algorithms, can be enormously helpful in helping guide health care providers in determining, for example, which antibiotics to prescribe or whether to recommend a risky heart surgery.
Tuesday, June 06, 2023
Hospital Infection Control Experts Question Validity of Public Reporting Metrics, New Study Finds
Infections spread in hospitals and other healthcare settings cause over 680,000 infections and 72,000 patient deaths in the U.S. every year. Surveillance and reporting of these infections to government entities has become a key part of hospital infection control programs, yet infection control experts question the effectiveness of these measures at protecting public health. That is the finding of a new survey led by researchers at the University of Maryland School of Medicine. Results were published last week in the journal JAMA Network Open.