Reducing No-Show Rates through Digitalization: AI and SMS-Based Interventions for Better Patient Adherence
Year: 2025
Type: conference-paper
Abstract: Missed medical appointments and no-shows cause problems for healthcare systems. They drive up costs and reduce healthcare quality. This study introduces a practical approach that uses machine learning models combined with SMS reminders to identify and reach out to patients likely to miss appointments. Out of the four models tested, the CatBoost model performed best, with a 77% recall and a 75% F1 score. The key takeaways are: 1) Combining predictive models with focused digital outreach can noticeably cut down no-show rates from 32.1% to 18.5%. 2) These digital efforts work especially well for patients aged 20–40 and for those without chronic conditions. By improving how appointments are scheduled and helping patients stick to their visits, digital outreach gives healthcare providers a scalable and effective solution.
Authors: Yixin Zhang, Yisong Chen
Institutions: Columbia University, Georgia Institute of Technology
Language: English
Subfield: Emergency Medical Services
Field: Health Professions
Domain: Health Sciences
Open Access status: gold
Funder: Strong
OpenAlex ID: W4412822318