Machine Learning for the Prediction of New-Onset Diabetes Mellitus during 5-Year Follow-up in Non-Diabetic Patients with Cardiovascular Risks

PURPOSE: Many studies have proposed predictive models for type 2 diabetes mellitus (T2DM). However, these predictive models have several limitations, such as user convenience and reproducibility. The purpose of this study was to develop a T2DM predictive model using electronic medical records (EMRs) and machine learning and to compare the performance of this model with traditional statistical methods. MATERIALS AND METHODS: In this study, a total of available 8454 patients who had no history of diabetes and were treated at the cardiovascular center of Korea University Guro Hospital were enrolled. All subjects completed 5 years of follow up. The prevalence of T2DM during follow up was 4.78% (404/8454). A total of 28 variables were extracted from the EMRs. In order to verify the cross-validation test according to the prediction model, logistic regression (LR), linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), and K-nearest neighbor (KNN) algorithm models were generated. The LR model was considered as the existing statistical analysis method. RESULTS: All predictive models maintained a change within the standard deviation of area under the curve (AUC) < 0.01 in the analysis after a 10-fold cross-validation test. Among all predictive models, the LR learning model showed the highest prediction performance, with an AUC of 0.78. However, compared to the LR model, the LDA, QDA, and KNN models did not show a statistically significant difference. CONCLUSION: We successfully developed and verified a T2DM prediction system using machine learning and an EMR database, and it predicted the 5-year occurrence of T2DM similarly to with a traditional prediction model. In further study, it is necessary to apply and verify the prediction model through clinical research.

Identification of Differentially Expressed Genes by Gabapentin in Cultured Dorsal Root Ganglion in a Rat Neuropathic Pain Model

Neuropathic pain is a chronic pain disorder caused by nervous system lesions as a direct consequence of a lesion or by disease of the portions of the nervous system that normally signal pain. The spinal nerve ligation (SNL) model in rats that reflect some components of clinical pain have played a crucial role in the understanding of neuropathic pain. To investigate the direct effects of gabapentin on differential gene expression in cultured dorsal root ganglion (DRG) cells of SNL model rats, we performed a differential display reverse transcription-polymerase chain reaction analysis with random priming approach using annealing control primer. Genes encoding metallothionein 1a, transforming growth factor-beta1 and palmitoyl-protein thioesterase-2 were up-regulated in gabapentin-treated DRG cells of SNL model rats. The functional roles of these differentially expressed genes were previously suggested as neuroprotective genes. Further study of these genes is expected to reveal potential targets of gabapentin.

Rapid ABO Genotyping Using Whole Blood without DNA Purification / 대한진단검사의학회지

BACKGROUND: ABO genotyping is commonly used in cases of an ABO discrepancy between cell typing and serum typing, as well as in forensic practice for personal identification and paternity testing. We evaluated ABO genotyping via multiplex allele-specific PCR (ASPCR) amplification using whole blood samples without DNA purification. METHODS: A four-reaction multiplex ASPCR genotyping assay was designed to detect specific nucleotide sequence differences between the six ABO alleles A101, A102, B101, O01, O02, and cis-AB01. The ABO genotypes of 127 randomly chosen samples were determined using the new multiplex ASPCR method. RESULTS: The genotypes of the 127 samples were found to be A101/A102 (n=1), A102/A102 (n=9), A101/O01 (n=3), A102/O01 (n=12), A102/O02 (n=14), B101/B101 (n=5), B101/O01 (n=18), B101/O02 (n=15), O01/O01 (n=14), O02/O02 (n=8), O01/O02 (n=14) and A102/B101 (n=14), from which phenotypes were calculated to be A (n=39), B (n=38), O (n=36) and AB (n=14). The multiplex ASPCR assay results were compared with the serologically determined blood group phenotypes and genotypes determined by DNA sequencing, and there were no discrepancies. CONCLUSIONS: This convenient multiplex ASPCR assay, performed using whole blood samples, provides a supplement to routine serological ABO typing and might also be useful in other genotyping applications.