Log In(current)

An evaluation of physician predictions of discharge on a general medicine service.

View / Download32.11 KB

Date

2015-12

Authors

Journal Title

Journal ISSN

Volume Title

Citation Stats

Attention Stats

Abstract

The goal of this study was to evaluate general medicine physicians' ability to predict hospital discharge. We prospectively asked study subjects to predict whether each patient under their care would be discharged on the next day, on the same day, or neither. Discharge predictions were recorded at 3 time points: mornings (7-9 am), midday (12-2 pm), or afternoons (5-7 pm), for a total of 2641 predictions. For predictions of next-day discharge, the sensitivity (SN) and positive predictive value (PPV) were lowest in the morning (27% and 33%, respectively), but increased by the afternoon (SN 67%, PPV 69%). Similarly, for same-day discharge predictions, SN and PPV were highest at midday (88% and 79%, respectively). We found that although physicians have difficulty predicting next-day discharges in the morning prior to the day of expected discharge, their ability to correctly predict discharges continually improved as the time to actual discharge decreased. Journal of Hospital Medicine 2015;10:808-810. © 2015 Society of Hospital Medicine.

Type

Journal article

Department

Description

Provenance

Subjects

Clinical Competence, Forecasting, General Practice, Humans, Patient Discharge, Physicians, Prospective Studies

Citation

Permalink

https://hdl.handle.net/10161/12041

Published Version (Please cite this version)

10.1002/jhm.2439

Publication Info

Sullivan, B, D Ming, JC Boggan, RD Schulteis, S Thomas, J Choi and J Bae (2015). An evaluation of physician predictions of discharge on a general medicine service. J Hosp Med, 10(12). pp. 808–810. 10.1002/jhm.2439 Retrieved from https://hdl.handle.net/10161/12041.

This is constructed from limited available data and may be imprecise. To cite this article, please review & use the official citation provided by the journal.

Collections

Scholarly Articles

Endorsement

Review

Supplemented By

Referenced By

Full item page

Scholars@Duke

Sullivan

Brian Sullivan

Assistant Professor of Medicine

I am a Physician Scientist in Gastroenterology, with a research focus in optimizing colorectal cancer (CRC) screening and surveillance recommendations, including colonoscopy and other non-invasive screening modalities. Specifically, we are evaluating current and evolving CRC screening strategies, as well as identifying people at high risk for underlying hereditary/genetic CRC syndromes. 

Ming

David Yung Ming

Associate Professor of Pediatrics

I am a med-peds hospitalist and researcher with interests in improving systems of care of patients with complex health needs. My research focus areas include implementation science, population health sciences, community-engaged research, and digital health. My vision is to design, implement, evaluate, and scale programs and interventions that will simplify the delivery of complex care. By doing so, we can equitably improve the health outcomes that matter most to children and adults with complex health needs and their families.

Boggan

Joel Boggan

Associate Professor of Medicine
I am a hospital medicine physician and educator working at the intersection of healthcare quality, medical education, and artificial intelligence. I serve as Executive Director for Artificial Intelligence in Medical and Health Professions Education in the Duke University School of Medicine, where I lead institutional efforts to develop and implement an integrated strategy for AI-enabled teaching, learning, assessment, and educational operations across our MD and other health professions programs.
 
I also serve in leadership roles within the Duke Internal Medicine Residency Program and the Durham VA Health Care System, having been an Associate Program Director for Quality Improvement and Patient Safety and Lead Mentor for the Chief Residency in Quality and Safety roles until transitioning to the Executive Director role, and continuing as Core Faculty for AI for the Residency Program and an Associate Investigator for the national VA Hospital Medicine Analytics Team. My scholarly work focuses on health system performance, inpatient care, and the development of future clinical leaders, as well as the responsible implementation of artificial intelligence in health education across disciplines. 
Thomas

Samantha Thomas

Biostatistician, Principal

Samantha is the manager of the Duke Cancer Institute (DCI) Biostatistics Shared Resource. Collaboratively, she primarily works with physicians in DCI, specifically in research of Endocrine Neoplasia and Breast Cancer. She is also the director of the Biostatistics, Epidemiology, Research, and Design Methods (BERD) Core Training and Internship Program (BCTIP). Her professional experience involves study design, analysis, and reporting of clinical trials and observational studies. Her specific areas of interest include training of collaborative biostatisticians, modeling of non-linear associations, and application of partitioning analyses to identify homogeneous patient groups.

Bae

Jonathan Gregory Bae

Associate Professor of Medicine

Patient safety and quality improvement, hospital based performance improvement, care transitions and hospital readmissions, general internal medicine hospital care, resident and medical student education.

Unless otherwise indicated, scholarly articles published by Duke faculty members are made available here with a CC-BY-NC (Creative Commons Attribution Non-Commercial) license, as enabled by the Duke Open Access Policy. If you wish to use the materials in ways not already permitted under CC-BY-NC, please consult the copyright owner. Other materials are made available here through the author’s grant of a non-exclusive license to make their work openly accessible.