Background: Posttransplant diabetes mellitus (PTDM) complicates kidney transplant recipients (KTRs) in morbidity and mortality. This study aimed to predict PTDM risk in KTRs using machine learning and deep learning models. Methods: Data were obtained from the Korea Organ Transplantation Registry, a nationwide cohort study of KTRs. Four machine learning algorithms, including eXtreme Gradient Boosting (XGBoost), CatBoost, light gradient boosting machine and logistic regression, and deep learning were implemented on 41 pretransplant and 31 posttransplant variables to predict PTDM. Model performance was assessed using the area under the curve (AUC) of the receiver operating characteristic curve, accuracy, precision, recall, and F1 score. Results: Among 3,213 KTRs, 497 patients (15.5%) developed PTDM within 1 year. The PTDM group had higher age, body mass index (BMI), triglyceride level, and prevalence of hypertension and cardiovascular disease, and lower total cholesterol level at baseline than the No-PTDM group. The XGBoost model showed the highest AUC (0.738) and F1 score (0.42), and modest accuracy (0.86), while the CatBoost model exhibited the highest accuracy (0.87) and precision (0.79). Feature importance in XGBoost was highest for recipient age, followed by baseline BMI, triglyceride level at posttransplant 6 months, baseline glycated hemoglobin and high-density lipoprotein cholesterol level, white blood cell (WBC) count and serum uric acid level at 6 months, baseline WBC count, and tacrolimus trough level at discharge. Conclusion The XGBoost model demonstrated the best performance for predicting PTDM within 1 year, offering an accurate tool for early identification and personalized care of high-risk KTRs for PTDM.

BACKGROUND: The number of migrant workers, especially undocumented, has been increasing in Korea since late 1997. This study was conducted to evaluate the health status of those in Korea. METHODS: In June to November 2000, general health examinations and medical check-up were provided freely to undocumented migrant workers in Gyeonggi province. Total 580 migrant workers participated in this examination. RESULTS: 1. The number of examinee with abnormal results was 176 (30.3%), and hypertension (29.2%), abnormal liver function (13.4%) and abnormal chest X-ray finding (4.3%). 2. The prevalence rate of symptom is 77.2% and the most common symptom was back pain, followed by epigastric pain and joint pain. 3. The frequency of clinical diagnosis classified by physician was most common in hypertension (29.2%), followed by low back sprain/strain (7.4%), gastritis or peptic ulcer (7.4%), myofascial pain syndrome (6.4%). 4. The frequency of abnormal results in undocumented migrant workers was, compared with documented migrant industrial trainees significantly higher in HIV-Ab (+), hypertension and anemia, and compared with domestic workers, higher in hypertension, anemia and pulmonary disease. CONCLUSIONS: This study suggested that when compared with domestic workers, the number of undocumented migrant workers with abnormal results was not significantly higher, except for hypertension, anemia and pulmonary disease. But measures for infectious disease (including AIDS) transmission and development of work-related or chronic diseases by poor working condition and increased length of stay must be considered, including health management system such as periodical health examination.
Anemia ; Arthralgia ; Back Pain ; Chronic Disease ; Communicable Diseases ; Diagnosis ; Gastritis ; Gyeonggi-do* ; Humans ; Hypertension ; Korea ; Length of Stay ; Liver ; Lung Diseases ; Myofascial Pain Syndromes ; Peptic Ulcer ; Prevalence ; Thorax ; Transients and Migrants*