AP Model: A Simple Tool to Predict Poor Long‐Term PAP Adherence in Obstructive Sleep Apnea

Abstract Objective To identify clinical and polysomnographic factors predicting poor long‐term positive airway pressure (PAP) compliance in patients with obstructive sleep apnea (OSA) in a Southeast Asian population and to develop a simple risk model applicable in routine practice. Study Design Retrospective cohort study. Setting Songklanagarind Hospital, Thailand, from January 2012 to December 2022. Methods Adult OSA patients aged 18 to 65 years prescribed PAP therapy were included. Adherence was objectively recorded from device downloads. Good adherence was defined as ≥4 hours per night on ≥70% of nights at 12 months. Logistic regression identified predictors of poor long‐term adherence. Results A total of 343 patients were enrolled; 253 had follow‐up data at 12 months. Good adherence was observed in 47.8% of patients. In multivariate analysis, age < 50 years (odds ratio [OR] 1.92; 95% CI 1.01‐3.67; P = .046) and poor short‐term adherence (OR 4.47; 95% CI 2.33‐8.72; P < .001) independently predicted poor long‐term adherence. The resulting “AP” model (Age and Poor early adherence) achieved an area under the curve of 0.73 (95% CI 0.66‐0.79), with a high specificity of 94%. Conclusion Although predictors of PAP adherence have been described in Western populations, this study provides the first large data set from Thailand. The AP model, while simple, is pragmatic and easily applied in resource‐limited settings. Prospective, multicenter validation across Southeast Asia is warranted to enhance its generalizability and incorporate modifiable predictors.