Pemodelan Sistem Prediksi Evaluasi Keperawatan Dengan Pendekatan Adaptasi Roy Pada Pasien Dengan Gangguan Syaraf

Modeling of Nursing Evaluation Prediction System Using Roy Adaptation Approach in Patients with Neurological Disorders

Abstract

Introduction: Neurological disorders are health problems that affect physiological function, psychological responses, social roles, and patient independence. Comprehensive nursing evaluation is needed to determine patient adaptation responses; however, conventional evaluation methods are often subjective and require a long assessment process. The Roy Adaptation Model provides a structured framework for assessing patient adaptation through four adaptive modes. Objective: This study aimed to develop a prediction system model for nursing evaluation outcomes in patients with neurological disorders based on the Roy Adaptation Model approach. Methods: This quantitative study used a predictive modeling approach involving 120 neurological disorder patients. Data were collected based on physiological, self-concept, role function, and interdependence adaptation indicators. Several machine learning algorithms were tested, including logistic regression and random forest. Model performance was evaluated using accuracy, precision, recall, and F1-score. Results: The Random Forest model showed the highest performance with an accuracy of 91.7%, precision of 90.8%, recall of 92.1%, and F1-score of 91.4%. The physiological adaptation mode was the strongest predictor of nursing evaluation outcomes. Conclusion: The prediction system based on the Roy Adaptation Model can support nurses in evaluating patient adaptation responses and assist clinical decision-making for neurological disorder management.