Performance of Nursing Activities Score in intensive care units of a teaching hospital in a low-middle-income country: An observational study.

Nursing workload in intensive care units (ICUs) is a key determinant of patient outcomes, quality of care, and efficient resource utilization. The Nursing Activities Score (NAS) is a validated instrument for quantifying nursing workload; however, evidence regarding its use in low- and middle-income countries remains limited. This observational study assessed nursing workload using the NAS and evaluated its ability to predict patient outcomes among 501 adult patients admitted to the ICU of a teaching hospital between 7 March 2022 and 27 February 2023. NAS was recorded for each patient, and outcomes were classified as survivors and non-survivors. The predictive performance of NAS was evaluated using receiver operating characteristic (ROC) curve analysis, model calibration was assessed with the Hosmer-Lemeshow goodness-of-fit test, and logistic regression was used to examine the association between NAS and mortality. Differences in NAS scores between survivors and non-survivors were compared using the Mann-Whitney U test. The median NAS was 83.40 (IQR: 68.30-101.10; range: 39.2-134.4), indicating a high nursing workload. NAS demonstrated good discriminative ability for predicting patient outcomes (AUROC = 0.838, p < 0.001), with an optimal cut-off value of 90.40, yielding 73.5% sensitivity and 73.1% specificity. The model showed good calibration (Hosmer-Lemeshow p = 0.422). Higher NAS scores were significantly associated with mortality (Exp(B) = 0.937, p < 0.001), and non-survivors had significantly higher NAS scores than survivors (110.70 vs. 76.20, p < 0.001). These findings demonstrate that the NAS is a reliable tool for measuring ICU nursing workload and predicting patient outcomes, supporting its use to optimize nurse staffing, workload allocation, and critical care resource planning in resource-limited settings.