Application of SVM to Speed Up and Accurate Nursing Decisions for Mentally Disordered Patients

Abstract

This study aims to evaluate the application of the Support Vector Machine (SVM) algorithm in increasing the speed and accuracy of nursing decision making in patients with mental health disorders. Fast and accurate decision making is very important in the nursing context, especially in treating patients with complex mental disorders. In this research, patient medical record data is used to train an SVM model, which is then used to predict the severity of the patient's mental disorder, such as Mild, Moderate, or Severe. The model is trained using features such as the patient's age, gender, diagnosis, psychological test scores, and physical condition. The evaluation results show that the SVM model has 100% accuracy, which means the model succeeded in classifying the severity of the patient's mental disorder very accurately. In addition, implementing this model also reduces the time required for decision making, allowing nurses to provide faster and more precise decisions. These results indicate that SVM can be a very useful tool in supporting nursing decision making, increasing the efficiency and quality of care, and reducing diagnostic errors. This research provides important insights into the potential use of artificial intelligence algorithms in clinical decision support systems in the mental health field.