Development of a predictive model for prolonged length of stay in conservatively treated patients with spontaneous intracerebral hemorrhage: A retrospective study

Spontaneous intracerebral hemorrhage (ICH) is a major cause of stroke-related morbidity and mortality, with prolonged length of stay (PLOS) contributing significantly to patient outcomes and healthcare costs. This study aims to identify the independent risk factors associated with prolonged length of stay in conservatively treated patients with ICH and to develop a predictive model to assist in clinical decision-making. A retrospective analysis was conducted on 161 patients with spontaneous ICH admitted to the Second Affiliated Hospital of Wannan Medical College between January 2021 and December 2022. Demographic, clinical, and laboratory data were collected. Factors influencing prolonged length of stay were identified using multivariate logistic regression analysis. A nomogram was developed to predict PLOS, and its performance was evaluated using receiver operating characteristic (ROC) curves, and decision curve analysis. Patients in the PLOS group (n = 26, 16.1 %) had significantly higher NIHSS score, systolic blood pressure, rates of in-hospital pulmonary infections, and white blood cell counts, as well as lower ADL score, compared to those in the non-PLOS group (n = 135, 83.9 %). Multivariate logistic regression identified in-hospital pulmonary infection (OR = 4.548, 95 % CI: 1.529-13.530,P = 0.006), NIHSS score (OR = 1.106, 95 % CI: 1.017-1.203,P = 0.018), ADL score (OR =0.974, 95 % CI: 0.953-0.996,P = 0.022), and systolic blood pressure (OR = 1.019, 95 % CI: 1.000-1.038,P = 0.045) as independent risk factors for PLOS. The developed nomogram demonstrated strong discriminatory ability with an AUC of 0.845, outperforming individual factors. The model also showed good calibration and a higher net benefit, especially when the threshold probabilities were between 10 % and 80 %. A predictive nomogram incorporating NIHSS score, ADL score, systolic blood pressure, and in-hospital pulmonary infection can effectively identify patients at risk for prolonged length of stay after spontaneous ICH. This model can guide clinicians in early intervention strategies and resource allocation, ultimately reducing healthcare costs and improving patient outcomes.