Background: Since OpenAI released ChatGPT, with its strong capability in handling natural tasks and its user-friendly interface, it has garnered significant attention. Objective: A prospective analysis is required to evaluate the accuracy and appropriateness of medication consultation responses generated by ChatGPT. Methods: A prospective cross-sectional study was conducted by the pharmacy department of a medical center in Taiwan. The test data set comprised retrospective medication consultation questions collected from February 1, 2023, to February 28, 2023, along with common questions about drug-herb interactions. Two distinct sets of questions were tested: real-world medication consultation questions and common questions about interactions between traditional Chinese and Western medicines. We used the conventional double-review mechanism. The appropriateness of each response from ChatGPT was assessed by 2 experienced pharmacists. In the event of a discrepancy between the assessments, a third pharmacist stepped in to make the final decision. Results: Of 293 real-world medication consultation questions, a random selection of 80 was used to evaluate ChatGPT’s performance. ChatGPT exhibited a higher appropriateness rate in responding to public medication consultation questions compared to those asked by health care providers in a hospital setting (31/51, 61% vs 20/51, 39%; P=.01). Conclusions: The findings from this study suggest that ChatGPT could potentially be used for answering basic medication consultation questions. Our analysis of the erroneous information allowed us to identify potential medical risks associated with certain questions; this problem deserves our close attention.

A genome-wide association study (GWAS) can be conducted to systematically analyze the contributions of genetic factors to a wide variety of complex diseases. Nevertheless, existing GWASs have provided highly ethnic specific data. Accordingly, to provide data specific to Taiwan, we established a large-scale genetic database in a single medical institution at the China Medical University Hospital. With current technological limitations, microarray analysis can detect only a limited number of single-nucleotide polymorphisms (SNPs) with a minor allele frequency of >1%. Nevertheless, imputation represents a useful alternative means of expanding data. In this study, we compared four imputation algorithms in terms of various metrics. We observed that among the compared algorithms, Beagle5.2 achieved the fastest calculation speed, smallest storage space, highest specificity, and highest number of high-quality variants. We obtained 15,277,414 high-quality variants in 175,871 people by using Beagle5.2. In our internal verification process, Beagle5.2 exhibited an accuracy rate of up to 98.75%. We also conducted external verification. Our imputed variants had a 79.91% mapping rate and 90.41% accuracy. These results will be combined with clinical data in future research. We have made the results available for researchers to use in formulating imputation algorithms, in addition to establishing a complete SNP database for GWAS and PRS researchers. We believe that these data can help improve overall medical capabilities, particularly precision medicine, in Taiwan.

Large-artery atherosclerosis (LAA) is a leading cause of cerebrovascular disease. However, LAA diagnosis is costly and needs professional identification. Many metabolites have been identified as biomarkers of specific traits. However, there are inconsistent findings regarding suitable biomarkers for the prediction of LAA. In this study, we propose a new method integrates multiple machine learning algorithms and feature selection method to handle multidimensional data. Among the six machine learning models, logistic regression (LR) model exhibited the best prediction performance. The value of area under the receiver operating characteristic curve (AUC) was 0.92 when 62 features were incorporated in the external validation set for the LR model. In this model, LAA could be well predicted by clinical risk factors including body mass index, smoking, and medications for controlling diabetes, hypertension, and hyperlipidemia as well as metabolites involved in aminoacyl-tRNA biosynthesis and lipid metabolism. In addition, we found that 27 features were present among the five adopted models that could provide good results. If these 27 features were used in the LR model, an AUC value of 0.93 could be achieved. Our study has demonstrated the effectiveness of combining machine learning algorithms with recursive feature elimination and cross-validation methods for biomarker identification. Moreover, we have shown that using shared features can yield more reliable correlations than either model, which can be valuable for future identification of LAA.

We addressed the underrepresentation of non-European populations in genome-wide association studies (GWASs) by building HiGenome, a large-scale genetic resource for the Taiwanese Han population. Using a custom genotyping array, we integrated deidentified electronic medical records (2003 to 2021) with genomic data to enable GWASs, phenome-wide association studies, and polygenic risk score (PRS) analysis. Among 413,000 participants, 323,397 passed ancestry and quality control filtering. GWASs covered 1085 traits, focusing on diseases prevalent in Taiwan such as type 2 diabetes, chronic kidney disease, gout, and alcoholic liver damage. PRSs were calculated for 238 traits, with the strongest associations observed in musculoskeletal disorders. Incorporating PRS into clinical practice supports early risk prediction and personalized prevention. To further expand translational value, we also conducted pharmacogenomic analysis and human leukocyte antigen typing. HiGenome offers a large-scale genetic and clinical dataset from the Taiwanese Han population, supporting population-specific analyses and precision medicine development in East Asia. The hospital-based design enables continuous follow-up and longitudinal data expansion.

Motivation: Mathematical modeling and optimization have been used for detecting enzyme targets in human metabolic disorders. Such optimal drug design methods are generally differentiated as two stages, identification and decision-making, to find optimal targets. We developed a unified method named fuzzy equal metabolic adjustment to formulate an optimal enzyme target design problem for drug discovery. The optimization framework combines the identification of enzyme targets and a decision-making strategy simultaneously. The objectives of this algorithm include evaluations of the therapeutic effect of target enzymes, the adverse effects of drugs and the minimum effective dose (MED). Results: An existing generalized mass action system model of human uric acid (UA) metabolism was used to formulate the fuzzy optimization method for detecting two types of enzymopathies: hyperuricemia caused by phosphoribosylpyrophosphate synthetase (PRPPS) overactivity and Lesch–Nyhan syndrome. The fuzzy objectives were set so that the concentrations of the metabolites were as close as possible to the healthy levels. The target design included a diet control of ribose-5-phospahate (R5P). The diet control of R5P served as an extra remedy to reduce phosphate uptake entering the purine metabolic pathway, so that we could obtain a more satisfactory treatment than obtained for those without a diet control. Moreover, enhancing UA excretion resulted in an effective treatment of hyperuricemia caused by PRPPS overactivity. This result correlates with using probenecid and benbromazone, which are uricosuric agents present in current clinical medications. By contrast, the Lesch–Nyhan syndrome required at least three enzyme targets to cure hyperuricemia. Contact:chmfsw@ccu.edu.tw Supplementary information: Supplementary data are available at Bioinformatics online.