Search

Background Many studies have evaluated stroke using claims data; most of these studies have defined ischemic stroke by using an operational definition following the rule-based method. Rule-based methods tend to overestimate the number of patients with ischemic stroke. Objective We aimed to identify an appropriate algorithm for phenotyping stroke by applying machine learning (ML) techniques to analyze the claims data. Methods We obtained the data from the Korean National Health Insurance Service database, which is linked to the Ilsan Hospital database (n = 30,897). The performance of prediction models (extreme gradient boosting [XGBoost] or long short-term memory [LSTM]) was evaluated using the area under the receiver operating characteristic curve (AUROC), the area under precision-recall curve (AUPRC), and calibration curve. Results In total, 30,897 patients were enrolled in this study, 3,145 of whom (10.18%) had ischemic stroke. XGBoost, a tree-based ML technique, had the AUROC was 93.63% and AUPRC was 64.05%. LSTM showed results similar to those of the rule-based method. The F1 score was 70.01%, while the AUROC was 97.10% and AUPRC was 85.70%, which was the highest. Conclusions We proposed recurrent neural network based deep learning techniques to improve stroke phenotyping. We anticipate the ability to produce rapid and accurate results.

Background This study aimed to examine the association between familial aggregation of chronic kidney disease (CKD) and risk of CKD development and its progression. Methods This nationwide family study comprised 881,453 cases with newly diagnosed CKD between 2004 and 2017 and 881,453 controls without CKD matched by age and sex, using data from the Korean National Health Insurance Service with linkage to the family tree database. The risks of CKD development and disease progression, defined as an incident end-stage renal disease (ESRD), were evaluated. Results The presence of any affected family member with CKD was associated with a significantly higher risk of CKD with adjusted ORs (95% CI) of 1.42 (1.38–1.45), 1.50 (1.46–1.55), 1.70 (1.64–1.77), and 1.30 (1.27–1.33) for individuals with affected parents, offspring, siblings, and spouses, respectively. In Cox models conducted on patients with predialysis CKD, risk of incident ESRD was significantly higher in those with affected family members with ESRD. The corresponding HRs (95% CI) were 1.10 (1.05–1.15), 1.38 (1.32–1.46), 1.57 (1.49–1.65), and 1.14 (1.08–1.19) for individuals listed above, respectively. Conclusions Familial aggregation of CKD was strongly associated with a higher risk of CKD development and disease progression to ESRD.

Background Almost all Koreans are covered by mandatory national health insurance and are required to undergo health screening at least once every 2 years. We aimed to develop a machine learning model to predict the risk of developing hepatocellular carcinoma (HCC) based on the screening results and insurance claim data. Methods The National Health Insurance Service-National Health Screening database was used for this study (NHIS-2020-2-146). Our study cohort consisted of 417,346 health screening examinees between 2004 and 2007 without cancer history, which was split into training and test cohorts by the examination date, before or after 2005. Robust predictors were selected using Cox proportional hazard regression with 1000 different bootstrapped datasets. Random forest and extreme gradient boosting algorithms were used to develop a prediction model for the 9-year risk of HCC development after screening. After optimizing a prediction model via cross validation in the training cohort, the model was validated in the test cohort. Results Of the total examinees, 0.5% (1799/331,694) and 0.4% (390/85,652) in the training cohort and the test cohort were diagnosed with HCC, respectively. Of the selected predictors, older age, male sex, obesity, abnormal liver function tests, the family history of chronic liver disease, and underlying chronic liver disease, chronic hepatitis virus or human immunodeficiency virus infection, and diabetes mellitus were associated with increased risk, whereas higher income, elevated total cholesterol, and underlying dyslipidemia or schizophrenic/delusional disorders were associated with decreased risk of HCC development (p C-index, AUC, and Brier skill score were 0.857, 0.873, and 0.078, respectively. Conclusions Machine learning-based model could be used to predict the risk of HCC development based on the health screening examination results and claim data.

Background: Diabetes mellitus (DM), one of the most common metabolic diseases worldwide, is associated with malignancies at many sites. The relationship between DM and bladder or kidney cancer is still controversial. We investigated the associations between DM and bladder or kidney cancer in a population-based exposure-control matched study.Method: Using the Korean National Health Insurance System sample cohort database, we identified patients who were diagnosed as having DM between January 2006 and December 2010. A control group was also selected from the database using propensity score matching to adjust for age and sex. An exposure-control matched study was conducted until December 2015. The two groups were compared for baseline characteristics and bladder or kidney cancer incidence. Cox’s proportional hazard regression analyses were performed to investigate associations between bladder or kidney cancer and each clinical variable.Results: In total, 132,570 patients with DM were identified. In addition, 132,570 patients without DM matched by age and sex (control group) were selected. The mean age was 54 years, and the male-to-female ratio was 1:1. During the follow-up period, 619 patients in the DM group and 511 in the control group were diagnosed as having bladder cancer. Of those diagnosed as having kidney cancer, 419 patients were in the DM group and 285 were in the control group. Adjusted Cox’s proportional hazard regression analysis revealed that DM is associated with bladder and kidney cancer.Conclusions: DM is associated with bladder and kidney cancer. Older men are at an increased risk for both cancers.