Predicting Patient Hospitalisation: PCPs vs. Algorithms

A new study shows that primary care physicians (PCPs) were as effective as commonly used predictive algorithms in identifying patients at high risk for hospitalisation. According to the study, published in American Journal of Managed Care, PCPs know the clinical and psychosocial needs of patients, enabling them to help identify factors missed by predictive algorithms.

See Also: Patient Engagement and Profit Improvement

Researchers asked primary care doctors managing a panel of at least 100 patients to review a list of randomly selected patients. They were asked: “Would you be surprised if this patient was admitted to the hospital in the next year?” Patients were categorised as high or low admission risk based on the doctors’ answers. Of 9,594 patients, doctors classified 21.2 percent as high admission risk and 78.6 percent as low risk.

When compared with commonly used risk stratification instruments, doctors did just as well at predicting which patients would need hospitalisation in the subsequent year, the researchers said.

“Given the predictive accuracy of PCPs’ clinical assessment, efforts to identify patients at high risk for future hospitalisation should aim to incorporate the unique insight that PCPs have about predisposing biopsychosocial factors,” the researchers concluded.

Identifying patients at increased risk for hospitalisation is key to designing interventions to prevent avoidable admissions. And the better PCPs know patients, the more they can reduce hospital admissions and lower costs. Greater continuity in primary care makes a difference, according to a previous study, which found patients who met with the same doctor most frequently had about 12 percent fewer admissions compared to those with lower continuity of care.

Source: Fierce Healthcare
Image Credit: Pixabay