Objective To explore independent risk factors affecting the prognosis of patients with heat stroke and construct a nomogram prediction model. Methods A retrospective analysis was conducted on 80 patients with heat stroke who were hospitalized in Emergency Department of Southwest Medical University Affiliated Hospital and Emergency Department of Zigong Fourth People’s Hospital from July 2022 to August 2023. Based on the outcomes at discharge, patients were classified into a survival group and a death group. Collection of the first clinical data within 24 hours of patient admission. Univariate and multivariate logistic regression analyses were performed to identify independent risk factors affecting prognosis in heat stroke patients. A nomogram prediction model was constructed, and its discrimination, consistency, and clinical utility were validated using the receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA). Results Univariate analysis revealed that the prognosis of heat stroke patients was significantly associated with the Sequential Organ Failure Assessment (SOFA) score, lymphocyte count, D-Dimer, and oxygenation index (P<0.05), while no significant associations were found with activated partial thromboplastin time, glomerular filtration rate, creatine kinase, lactate dehydrogenase, brain natriuretic peptide, acid-base balance, partial pressure of oxygen, oxygen concentration, and blood potassium (P>0.05). Multivariate analysis indicated that the oxygenation index and D-Dimer were independent risk factors for the prognosis of heat stroke patients (P<0.05). The nomogram prediction model based on these independent risk factors demonstrated good discrimination (area under the ROC curve=0.956), consistency (Hosmer-Lemeshow goodness-of-fit test χ2=7.641, P = 0.469), and clinical utility. Conclusion An oxygenation index of less than 263.1 mmHg and a D-dimer level greater than 13.31 μg/ml are independent risk factors for mortality in patients with heat stroke. The combination of these two parameters into a nomogram for predicting the risk of death in heat stroke patients demonstrates enhanced predictive performance. This model provides significant prognostic value, allowing for a simple and accurate assessment of the severity of the condition and precise guidance for subsequent treatment, thereby improving patient outcomes