Patient no-shows are common and costly. A study published in BMC Health Services Research found that patients don’t show up to their scheduled appointments 18.8% of the time. In 2008, no-shows cost $196 per patient on average.
Lost revenue isn’t the only issue: patient no-shows cost time. Even with effective time management strategies in place, no-shows can prevent clinicians from shortening the day or filling the gaps with other patients.
A team of researchers at Johns Hopkins University Malone Center for Engineering in Healthcare set out to address the problem. The investigators developed a machine-learning algorithm that predicts the likelihood of a patient showing up for his or her appointment. The model takes into account various predictors including economic status, medical history, and demographics; it then assigns a “no-show” score for each patient.
The researchers also examined how clinicians can more efficiently fill these appointment slots. They determined that individual practices are best equipped to use the data provided by the model to either increase outreach to “high-risk” patients or fill those slots with patients who urgently need to be seen.
The model has been piloted at several clinics affiliated with the university. The plan is to eventually expand it to hospitals across the nation.
To learn more about the study, visit JHU.edu.
Kheirkhah P, Feng Q, Travis LM, Tavakoli-Tabasi S, Sharafkhaneh A. Prevalence, predictors and economic consequences of no-shows. BMC Health Serv Res. 2016;16:13.