Machine learning-based diagnosis and risk factor analysis of cardiocerebrovascular disease based on KNHANES.

The prevalence of cardiocerebrovascular disease (CVD) is continuously increasing, and it is the leading cause of human death. Since it is difficult for physicians to screen thousands of people, high-accuracy and interpretable methods need to be presented. We developed four machine learning-based CVD classifiers (i.e., multi-layer perceptron, support vector machine, random forest, and light gradient boosting) based on the Korea National Health and Nutrition Examination Survey. We resampled and rebalanced KNHANES data using complex sampling weights such that the rebalanced dataset mimics a uniformly sampled dataset from overall population. For clear risk factor analysis, we removed multicollinearity and CVD-irrelevant variables using VIF-based filtering and the Boruta algorithm. We applied synthetic minority oversampling technique and random undersampling before ML training. We demonstrated that the proposed classifiers achieved excellent performance with AUCs over 0.853. Using Shapley value-based risk factor analysis, we identified that the most significant risk factors of CVD were age, sex, and the prevalence of hypertension. Additionally, we identified that age, hypertension, and BMI were positively correlated with CVD prevalence, while sex (female), alcohol consumption and, monthly income were negative. The results showed that the feature selection and the class balancing technique effectively improve the interpretability of models.

Generation and analysis of end sequence database for T-DNA tagging lines in rice.

We analyzed 6749 lines tagged by the gene trap vector pGA2707. This resulted in the isolation of 3793 genomic sequences flanking the T-DNA. Among the insertions, 1846 T-DNAs were integrated into genic regions, and 1864 were located in intergenic regions. Frequencies were also higher at the beginning and end of the coding regions and upstream near the ATG start codon. The overall GC content at the insertion sites was close to that measured from the entire rice (Oryza sativa) genome. Functional classification of these 1846 tagged genes showed a distribution similar to that observed for all the genes in the rice chromosomes. This indicates that T-DNA insertion is not biased toward a particular class of genes. There were 764, 327, and 346 T-DNA insertions in chromosomes 1, 4 and 10, respectively. Insertions were not evenly distributed; frequencies were higher at the ends of the chromosomes and lower near the centromere. At certain sites, the frequency was higher than in the surrounding regions. This sequence database will be valuable in identifying knockout mutants for elucidating gene function in rice. This resource is available to the scientific community at http://www.postech.ac.kr/life/pfg/risd.