Predictive value of seven scoring systems for 28-day mortality in ICU patients with Sleep apnea-hypopnea syndrome (SAHS) and clinical indicators.

Background and objective: Sleep apnea-hypopnea syndrome (SAHS) is a chronic condition linked to recurrent upper airway collapse during sleep and has been associated with lower in-hospital mortality in ICU patients. This study evaluates the predictive efficacy of seven ICU scoring systems (Sequential Organ Failure Assessment (SOFA), Acute Physiology Score III (APSIII), Systemic Inflammatory Response Syndrome (SIRS), Simplified Acute Physiology Score II (SAPSII), Oxford Acute Severity of Illness Score (OASIS), Glasgow Coma Scale (GCS), and Charlson Comorbidity Index (CCI)) for 28-day all-cause mortality in SAHS patients.

Methods: Data from first-time ICU admissions were extracted from the MIMIC-IV database and analyzed using R, SPSS, and GraphPad Prism. Univariate and multivariate regression analyses identified independent risk factors for mortality. We evaluated the predictive accuracy of the scoring systems using calibration curves and the Hosmer-Lemeshow test. Decision curve analysis (DCA) and receiver operating characteristic (ROC) curves assessed the predictive performance of scoring systems.

Results: The study showed that deceased patients had higher SOFA, APSIII, SIRS, SAPSII, OASIS, and CCI scores but lower GCS scores compared to survivors. SAPSII and APSIII demonstrated the highest net benefit and the area under the curve (AUC) values for predicting mortality, with APSIII showing the highest sensitivity and CCI the highest specificity. Kaplan-Meier analysis indicated lower mortality risk in low-risk subgroups of SAPSII and APSIII.

Conclusion: SAPSII score in this study demonstrated not only robust calibration but also showed high clinical net benefit and discriminative ability. APSIII demonstrated the highest sensitivity in predicting mortality outcomes. The CCI's specificity underscores the importance of addressing comorbidities.