Background: Diabetes mellitus is a chronic metabolic disorder with an increasing global prevalence. Early detection and risk assessment are essential for preventing disease-related complications. In recent years, machine learning methods have been increasingly investigated for predicting disease status using medical data and supporting clinical decision-making. Aim: This study aimed to develop a predictive model for diabetes status using the Random Forest classification algorithm based on the PIMA Indians Diabetes Database and to evaluate its classification performance. Materials and Methods: The study used the PIMA dataset, comprising 768 observations, eight predictor variables, and one target variable. Zero values in selected measurements that were physiologically implausible were treated as missing values and imputed using the median. The dataset was split into training and test sets at an 80:20 ratio. Hyperparameters of the Random Forest model were optimized using 10-fold cross-validation on the training data. Model performance was evaluated using Accuracy, Sensitivity, Specificity, Balanced Accuracy, Cohen’s Kappa, and the area under the receiver operating characteristic curve (ROC-AUC). Variable importance was also assessed. All statistical analyses and machine learning procedures were performed in the R programming environment. Results: Cross-validation identified mtry=4 as the optimal configuration, achieving an Accuracy of 78.05% and a Cohen’s Kappa of 0.5062. On the test set, the model achieved an Accuracy of 72.55%, Sensitivity of 58.49%, Specificity of 80.00%, Balanced Accuracy of 69.25%, and Cohen’s Kappa of 0.3883. The area under the ROC curve (AUC) was 0.7802, indicating that the model could distinguish between individuals with and without diabetes better than random classification. Variable importance analysis identified blood glucose level as the most influential predictor, followed by body mass index (BMI), age, and number of pregnancies. Conclusion The Random Forest algorithm demonstrated the potential to predict diabetes status using the PIMA dataset; however, its sensitivity on the test set was relatively low. Therefore, the model should be considered a potential tool for preliminary risk assessment and supporting early detection rather than a replacement for clinical diagnosis. Further research is needed to improve sensitivity, compare the model with other machine learning algorithms, and validate its performance using larger and more diverse datasets.

Background: Globally, an estimated 13% of adolescents aged 10–19 are affected by mental disorders. As of 2020, the number of children under the age of 19 in Mongolia was reported to be 1,289,587, reflecting a 0.9% increase compared to 2015. A 2013 study on adolescents found that 60.5% were categorized as mentally healthy, 30.5% exhibited emotional and behavioral difficulties, and 9% were diagnosed with a mental disorder. A study conducted in Govi-Altai Province between 2018 and 2019 reported that 58.6% of adolescents were classified as healthy, 36.1% experienced psychological difficulties, and 5.2% were diagnosed with a mental disorder. Internationally, adolescent mental health has been widely assessed using the Strengths and Difficulties Questionnaire (SDQ), with an increasing number of studies employing artificial intelligence-based predictive models. However, in Mongolia, research utilizing artificial intelligence and machine learning for analyzing large-scale mental health data remains limited. This gap underscores the need for the present study. Aim: Machine learning models were compared to determine adolescent emotional and behavioral problems using the SDQ. Materials and Methods: Data was collected from teenagers, teachers, and parents in Govi-Altai Province, and the databases were created for each group. The teenager database was divided into 10 folds by cross-validation, and the models were developed using machine learning methods and evaluated using their performance measures. The results were mainly analyzed using the Bayes model. Results: The teenagers have emotional and behavioral problems due to emotional and peer interactions, but they are at risk of developing disorders due to hyperactivity and behavioral changes. Conclusion Comparing the model performance results with previous studies, Bayesian model accuracy decreased by 0.03, sensitivity decreased by 0.08, and specificity increased by 0.01. Also, the difference between the performance evaluation metrics of the C50 and Bayesian models is very small, between 0.01 and 0.02. This shows that the performance of the Bayesian method is good when the number of attributes in the database increases. Compared to the results of the knowledge generated by the research, the participants are more likely to develop emotional and behavioral disorders due to their peer relationship indicators, such as other children generally not liking them, getting on better with adults, and due to emotional symptoms such as being unhappy and depressed.