Inspiration Behind Using Algorithms to Predict Stroke Risk: Michael Pencina, PhD
The vice dean for data science at Duke University School of Medicine talked about the main findings from his latest published study on stroke risk algorithms. [WATCH TIME: 3 minutes]
WATCH TIME: 3 minutes
“The study was motivated by the need to do better in prevention of stroke. We know that the incidence rates of stroke are much higher among Black adults as compared with White adults. We also know that there are a number of predictive algorithms that estimate the risk of stroke.”
Stroke, the fifth-highest cause of death in the United States, is also a leading cause of long-term serious disability in Black patients, a group known to be at a higher risk of stroke. One strategy that may assist with predicting and preventing stroke is the use of quality risk algorithms since they are free of bias.
In a recently published study in the Journal of American Medical Association, corresponding author Michael Pencina, PhD, and colleagues compared performance of stroke-specific algorithms with pooled cohort equations between different subgroups to determine the value of machine learning.1 All told, results suggested that specific risk prediction models and novel machine learning techniques did not significantly improve discriminative accuracy for new-onset stroke compared with the pooled cohort equations, while the REGARDS self-report model had the best calibration.
Pencina recently sat down in an interview with NeurologyLive® to talk about the highlights of the study from an investigator's perspective. Pencina, professor in the Department of Biostatistics and Bioinformatics and director of AI Health at Duke University School of Medicine, shared a brief summary of the methodology for the study as well as the main findings from the analysis.
