Purpose: Accurate data collection and analysis are crucial in clinical research, particularly for extracting information from unstructured medical records in cancer research. Traditional methods often struggle with this task. Large language models (LLMs) specializing in natural language processing (NLP), like ChatGPT (OpenAI), show potential for automating this process. This study evaluated whether GPT-4 could accurately extract clinical stages of colorectal cancer (CRC) from imaging reports. Methods: Using specific prompts based on the American Joint Committee on Cancer TNM staging system, GPT-4 was tested on the unstructured abdominal imaging reports of 100 CRC patients. The results were evaluated by a colorectal surgical oncologist and compared with data manually extracted by a nonspecialist data manager. Results: GPT-4 demonstrated high accuracy in extracting lesion locations (96.0%) and T (89.0%), N (90.0%), and M (85.0%) stages, with an overall TNM stage extraction accuracy of 69.0%. The combined accuracy for TNM stage and lesion location was 67.0%. Human data managers had similar TNM stage accuracy but lower lesion-location accuracy (76.0%). Higher accuracy was observed when reports directly mentioned stages and were in English only. Conclusion This study confirms that LLM-based NLP, with proper prompt engineering, can accurately extract clinical stages from CRC imaging reports, particularly in English-only contexts.

The impact of age on the relationship between body mass index (BMI) and all-cause mortality in hemodialysis (HD) patients is not clearly understood. Using data from the Korean Renal Data System (2001–2022), we analyzed 66,129 HD patients, stratified into young (<65 years, n = 24,589), younger-old (65–74 years, n = 17,732), and older-old (≥75 years, n = 23,808) groups. Patients were categorized into BMI quartiles, and survival outcomes were evaluated using Kaplan-Meier curves and event time ratios for the relative change in the survival time. During the follow-up period, 14,360 of the patients (21.7%) died, with a median follow-up of 3.4 years. Kaplan-Meier curves revealed poorer outcomes in lower BMI quartiles across all age groups. The lowest BMI quartile was significantly associated with a shorter survival time compared to the highest BMI quartile, with a 15% reduction in the young group (p = 0.001) and a 12% reduction in the older-old group (p = 0.002). Predicted survival time increases with rising BMI in the young group, but the rate of increase slows in the younger-old group and plateaus in the older-old group after a BMI of 25 kg/m2. Lower BMI correlates with higher mortality, particularly in younger HD patients.

Patients with end-stage kidney disease (ESKD) are more susceptible to viral epidemics and are known to have higher incidence and death rates of coronavirus disease 2019 (COVID-19) compared to the general population. We determined COVID-19 incidence and mortality among chronic hemodialysis (HD), peritoneal dialysis (PD), and kidney transplantation (KT) patients in Korea. Methods: We conducted a retrospective cohort study and data regarding Korean ESKD adults (aged ≥18 years) were obtained from the National Health Insurance Service of Korea from October 2020 to December 2021. We examined and compared the incidence of COVID-19–related infections and deaths among the patients receiving HD, PD, and KT. Results: Of all ESKD patients, 85,018 (68.1%) were on HD, 8,399 (6.7%) on PD, and 31,343 (25.1%) on KT. The COVID-19 incidence was 1.3% for HD, 1.2% for PD, and 1.5% for KT. COVID-19 mortality was 16.3% for HD, 12.2% for PD, and 4.7% for KT. PD patients had a lower incidence of infection compared to HD patients (odds ratio [OR], 0.76; 95% confidence interval [CI], 0.607–0.93), but KT patients had a significantly higher risk of infection (OR, 1.28; 95% CI, 1.13–1.44). Compared with HD, the risk of COVID-19–related death was not different for PD patients but was significantly lower for KT patients (hazard ratio, 0.55; 95% CI, 0.35–0.88). Conclusion: COVID-19 incidence was lower in PD patients than in HD patients, but mortality was not different between them. KT was associated with a higher risk of COVID-19 infection but lower mortality compared to HD.

In the rapidly evolving healthcare environment, radiologists strive to establish their rightful place.Thus, there is a need for enhanced outpatient and clinical education within the Department of Radiology and exploration of its methodologies. Accordingly, the Korean Society of Radiology established a task force to investigate the clinical and outpatient practice status of radiologists overseas, current state of related education, involvement of other specialties in radiologic practices and education in Korea, and clinical and outpatient practice status among Korean radiologists. Furthermore, a survey on clinical competency enhancement was conducted among the members of the Korean Society of Radiology. These findings suggest the need for visibility and clinical competency enhancement in radiologists and methodologies for strengthening clinical competencies.

Purpose: Unnecessary prostate biopsies for detecting prostate cancer (PCa) should be minimized. Therefore, this study developed a machine learning (ML) model to predict PCa in Korean men and evaluated its usability. Materials and Methods: We retrospectively analyzed clinical data from 928 patients who underwent prostate biopsies at Kangwon National University Hospital between May 2013 and May 2023. Of these, 377 (41.6%) were diagnosed with PCa, and 551 (59.4%) did not have cancer. For external validation, clinical data from 385 patients aged 48–89 years who underwent prostate biopsies from September 2005 to September 2023 at Wonju Severance Christian Hospital were also included. Twenty-two clinical features were used to develop an ML model to predict PCa. Features were selected based on their contributions to model performance, leading to the inclusion of 15 features. A meta-learner was constructed using logistic regression to predict the probability of PCa, and the classifier was trained and validated on randomly extracted training and test sets at an 8:2 ratio. Results: The prostate health index, prostate volume, age, nodule on digital rectal examination, and prostate-specific antigen were the top 5 features for predicting PCa. The area under the receiver operating characteristic curve (AUC) of the meta-learner logistic regression model was 0.89, and the accuracy, sensitivity, and specificity were 0.828, 0.711, and 0.909, respectively. Our model also showed excellent prediction performance for high-grade PCa, with a Gleason score of 7 or higher and an AUC of 0.903. Furthermore, we evaluated the performance of the model using external cohort clinical data and achieved an AUC of 0.863. Conclusions Our ML model excelled in predicting PCa, specifically clinically significant PCa. Although extensive cross-validation in other clinical cohorts is needed, this ML model is a promising option for future diagnostics.

Background: Late-onset hypogonadism (LOH) is associated with reduced testosterone levels and an increase in various physical, mental, and emotional changes in men with age. Several lifestyle factors, including smoking, are reported to be related to LOH; however, very few studies have sufficiently investigated the relationships between smoking and the symptoms of LOH. This study aimed to use the Androgen Deficiency in Aging Males (ADAM) questionnaire to assess the associations between smoking and LOH symptoms in Korean men. Methods: Men who underwent medical check-ups and transrectal ultrasonography at a university hospital between January 1, 2018 and March 31, 2021 (n=793) were included in this study. Multiple logistic regression was used to assess the risk of LOH symptoms among non-smokers, exsmokers, and current smokers, with adjustments for age, body mass index, alcohol consumption, and exercise and education levels. Results: There were significant correlations between LOH symptoms, as assessed using the ADAM questionnaire, and smoking status. The results of the multivariate logistic regression analysis adjusted for confounding factors indicated that the risk of LOH symptoms was higher in the ex-smokers (odds ratio, 2.446; 95% confidential interval, 1.511–3.962) and current smokers (odds ratio, 6.664; 95% confidential interval, 3.485–12.74) groups. Conclusion These results indicate a positive correlation between smoking and LOH symptoms in Korean men. Nevertheless, large-scale studies are required to further validate these findings.

Purpose: We sought to evaluate the time-dependent efficacy and safety of eplerenone for central serous chorioretinopathy. Methods: A systematic search was performed from inception to May 2023 in the Medline, EMBASE, and Cochrane literature databases to find randomized controlled trials that have administered oral eplerenone therapy to central serous chorioretinopathy patients. Results: Five randomized controlled trials were included in the final analysis. Among a total of 252 central serous chorioretinopathy patients, 134 were included in the eplerenone group and 118 were included in the control group. The best-corrected visual acuity was statistically significantly improved in the eplerenone group compared to the control group (95% confidence interval [CI], -0.08 to -0.02; p = 0.001). After meta-analysis was performed at each follow-up point, it was found that eplerenone statistically significantly improved the best-corrected visual acuity compared to the control group at 2 and 3 months after starting oral eplerenone therapy, but there was no statistically significant difference at 6 months. Subretinal fluid, chorioretinal thickness, central macular thickness, and complications showed no statistically significant differences between the eplerenone and control groups (p = 0.43, 0.67, 0.64, and 0.12, respectively). The difference in the risk of complications occurring between the eplerenone and control groups also didn’t show statistical significance (p = 0.12). Conclusions Although eplerenone is not superior to a control protocol when considering anatomical improvements, the best-corrected visual acuity seems to improve up to 3 months superiorly compared to in the control group when oral eplerenone therapy is administered for central serous chorioretinopathy. In addition, the complications of eplerenone are tolerable. Therefore, clinically short-term use of eplerenone up to 3 months in central serous chorioretinopathy patients can be considered.