Curbside Consults Podcast
Patients who clinically deteriorate on medical and surgical wards suffer substantial morbidity and mortality. Identifying patients who are at risk for clinical deterioration provides an opportunity for early intervention. Complex automated models that use the vast data available in electronic medical records have been developed and integrated into healthcare systems. In this episode of Curbside Consults, I am joined by the authors of a recently published study in NEJM of such a program, entitled “Automated Identification of Adults at Risk for In-Hospital Clinical Deterioration.”
Dr. Gabriel Escobar is a research scientist at the Kaiser Permanente Northern California Division of Research, Director of the Division of Research Systems Research Initiative, and Regional Director for Hospital Operations Research for Kaiser Permanente Northern California.
Dr. Vincent Liu is a research scientist at the Kaiser Permanente Northern California Division of Research and Regional Director of Hospital Advanced Analytics for Kaiser Permanente Northern California.
0:06 – Introduction
1:56 – Limitations of existing early warning scores and rapid-response teams
2:59 – Explanation of machine learning
4:26 – Background literature: predictive models, machine learning, and electronic healthcare records
5:54 – Study background: Automated Identification of Adults at Risk for In-Hospital Clinical Deterioration Study background
6:42 – Automated predictive model description
7:11 – Study outcomes
7:29 – Challenges in implementing an integrated healthcare delivery system
9:52 – End
Resources and articles discussed in this episode:
1. Pencina MJ et al. Prediction Models — Development, Evaluation, and Clinical Application. N Engl J Med 2020.
2. Rajkomar A et al. Machine Learning in Medicine. N Engl J Med 2019.
3. Horwitz LI et al. Creating a Learning Health System through Rapid-Cycle, Randomized Testing. N Engl J Med 2019.
The Curbside Consults series complements the foundational information in Rotation Prep by taking a deep dive into key clinical topics with expert clinicians and educators. These podcasts explore and critique the evidence behind clinical practice and break down statistical concepts for the busy clinical trainee.