Background: Trauma is one of the most critical public health issues worldwide, leading to death and disability and influencing all age groups. Therefore, there is great interest in models for predicting mortality in trauma patients admitted to the ICU. The main objective of the present study is to develop and evaluate SMOTE-based machine-learning tools for predicting hospital mortality in trauma patients with imbalanced data. Methods: This retrospective cohort study was conducted on 126 trauma patients admitted to an intensive care unit at Besat hospital in Hamadan Province, western Iran, from March 2020 to March 2021. Data were extracted from the medical information records of patients. According to the imbalanced property of the data, SMOTE techniques, namely SMOTE, Borderline-SMOTE1, Borderline-SMOTE2, SMOTE-NC, and SVM-SMOTE, were used for primary preprocessing. Then, the Decision Tree (DT), Random Forest (RF), Naive Bayes (NB), Artificial Neural Network (ANN), Support Vector Machine (SVM), and Extreme Gradient Boosting (XGBoost) methods were used to predict patients' hospital mortality with traumatic injuries. The performance of the methods used was evaluated by sensitivity, specificity, Positive Predictive Value (PPV), Negative Predictive Value (NPV), accuracy, Area Under the Curve (AUC), Geometric Mean (G-means), F1 score, and P-value of McNemar's test. Results: Of the 126 patients admitted to an ICU, 117 (92.9%) survived and 9 (7.1%) died. The mean follow-up time from the date of trauma to the date of outcome was 3.98 ± 4.65 days. The performance of ML algorithms is not good with imbalanced data, whereas the performance of SMOTE-based ML algorithms is significantly improved. The mean area under the ROC curve (AUC) of all SMOTE-based models was more than 91%. F1-score and G-means before balancing the dataset were below 70% for all ML models except ANN. In contrast, F1-score and G-means for the balanced datasets reached more than 90% for all SMOTE-based models. Among all SMOTE-based ML methods, RF and ANN based on SMOTE and XGBoost based on SMOTE-NC achieved the highest value for all evaluation criteria. Conclusions: This study has shown that SMOTE-based ML algorithms better predict outcomes in traumatic injuries than ML algorithms. They have the potential to assist ICU physicians in making clinical decisions.

Objective: Early diagnosis of many diseases is essential for their treatment. Furthermore, the existence of abundant and unknown variables makes more complicated decision making. For this reason, the diagnosis and classification of diseases using machine learning algorithms have attracted a lot of attention. Therefore, this study aimed to design a support vector machine (SVM) based decision-making support system to diagnosis various periodontal diseases. Data were collected from 300 patients referring to Periodontics department of Hamadan University of Medical Sciences, west of Iran. Among these patients, 160 were Gingivitis, 60 were localized periodontitis and 80 were generalized periodontitis. In the designed classification model, 11 variables such as age, sex, smoking, gingival index, plaque index and so on used as input and output variable show the individual’s status as a periodontal disease. Results: Using different kernel functions in the design of the SVM classification model showed that the radial kernel function with an overall correct classification accuracy of 88.7% and the overall hypervolume under the manifold (HUM) value was to 0.912 has the best performance. The results of the present study show that the designed classification model has an acceptable performance in predicting periodontitis.

Farhadian M, et al. Imaging Sci Dent. 2019 Mar;49(1):19-26. https://doi.org/10.5624/isd.2019.49.1.19

Background: Late-diagnosis of HIV is a major challenge for the control and prevention of AIDS in the world. The present study aimed to specify factors associated with the late diagnosis of HIV in Iran from 1987 to 2016. Methods: In this retrospective cohort study, data for 4402 diagnosed HIV/AIDS patients were extracted from 158 behavioral disease counseling centers of 31 Iranian provinces. We defined late diagnosis as having a CD4 count less than 350 within 3 months after diagnosis. Multiple logistic regression analysis was used to determine the factors influencing late diagnosis. Moreover, we used multivariate Cox regression to assess the association of these factors with the patients’ survival. Results: In this study, the prevalence of late diagnosis among the patients was 58.2%. People aged 50 years and over (adjusted OR = 3.55), transmission through blood transfusion (adjusted OR = 2.89), co-infection with tuberculosis (adjusted OR = 2.06), and male gender (adjusted OR = 1.38) were the strongest predictors for late diagnosis of HIV. On the other hand, baseline CD4 (adjusted HR = 2.21), people aged 50 and over (adjusted HR = 1.81), male gender (adjusted HR = 1.76), being a widow (adjusted HR = 1.68), people with unknown transmission way (adjusted HR = 18.24), people who inject drugs (adjusted HR = 1.87), diagnosis at previous years (adjusted HR = 2.45) and co-infection with tuberculosis (adjusted OR = 1.77) significantly associated with the survival of patients. Conclusion: The prevalence of late diagnosis is high among Iranian HIV/AIDS. The risk factors of late diagnoses include being males and aged 50 years and over, transmission through blood transfusion, and co-infection with tuberculosis. Therefore, implementation of screening programs for early diagnosis of HIV these high risk groups is recommended to Iranian health providers and policymakers.