Objective: To evaluate the adherence of large language model (LLM)-based healthcare research to the Minimum Reporting Items for Clear Evaluation of Accuracy Reports of Large Language Models in Healthcare (MI-CLEAR-LLM) checklist, a framework designed to enhance the transparency and reproducibility of studies on the accuracy of LLMs for medical applications. Materials and Methods: A systematic PubMed search was conducted to identify articles on LLM performance published in high-ranking clinical medicine journals (the top 10% in each of the 59 specialties according to the 2023 Journal Impact Factor) from November 30, 2022, through June 25, 2024. Data on the six MI-CLEAR-LLM checklist items: 1) identification and specification of the LLM used, 2) stochasticity handling, 3) prompt wording and syntax, 4) prompt structuring, 5) prompt testing and optimization, and 6) independence of the test data—were independently extracted by two reviewers, and adherence was calculated for each item. Results: Of 159 studies, 100% (159/159) reported the name of the LLM, 96.9% (154/159) reported the version, and 91.8% (146/159) reported the manufacturer. However, only 54.1% (86/159) reported the training data cutoff date, 6.3% (10/159) documented access to web-based information, and 50.9% (81/159) provided the date of the query attempts. Clear documentation regarding stochasticity management was provided in 15.1% (24/159) of the studies. Regarding prompt details, 49.1% (78/159) provided exact prompt wording and syntax but only 34.0% (54/159) documented prompt-structuring practices. While 46.5% (74/159) of the studies detailed prompt testing, only 15.7% (25/159) explained the rationale for specific word choices. Test data independence was reported for only 13.2% (21/159) of the studies, and 56.6% (43/76) provided URLs for internet-sourced test data. Conclusion Although basic LLM identification details were relatively well reported, other key aspects, including stochasticity, prompts, and test data, were frequently underreported. Enhancing adherence to the MI-CLEAR-LLM checklist will allow LLM research to achieve greater transparency and will foster more credible and reliable future studies.

The anticancer drugs have evolved significantly, spanning molecular targeted therapeutics (MTTs), immune checkpoint inhibitors (ICIs), chimeric antigen receptor T-cell (CAR-T) therapy, and antibody-drug conjugates (ADCs). Complications associated with these drugs vary widely based on their mechanisms of action. MTTs that target angiogenesis can often lead to complications related to ischemia or endothelial damage across various organs, whereas non-anti-angiogenic MTTs present unique complications derived from their specific pharmacological actions. ICIs are predominantly associated with immunerelated adverse events, such as pneumonitis, colitis, hepatitis, thyroid disorders, hypophysitis, and sarcoid-like reactions. CAR-T therapy causes unique and severe complications including cytokine release syndrome and immune effector cell-associated neurotoxicity syndrome. ADCs tend to cause complications associated with cytotoxic payloads. A comprehensive understanding of these drug-specific toxicities, particularly using medical imaging, is essential for providing optimal patient care. Based on this knowledge, radiologists can play a pivotal role in multidisciplinary teams. Therefore, radiologists must stay up-to-date on the imaging characteristics of these complications and the mechanisms underlying novel anticancer drugs.

Purpose: Thrombosis and bleeding significantly affect morbidity and mortality in myeloproliferative neoplasms (MPNs). The efficacy and safety of direct oral anticoagulants (DOACs) in MPN patients remain uncertain. Materials and Methods: We conducted a large, retrospective, nationwide cohort study using the Korean Health Insurance Review and Assessment Service database from 2010 to 2021. Results: Out of the 368 MPN patients included in the final analysis, 62.8% were treated with DOACs for atrial fibrillation (AF), and 37.2% for venous thromboembolism (VTE). The AF group was statistically older with higher CHA2DS2-VASc (congestive heart failure, hypertension, age ≥ 75 years, diabetes mellitus, prior stroke, transient ischemic attack, or thromboembolism, vascular disease, age 65-74 years, sex category [female]) scores compared to the VTE group. Antiplatelet agents were used in 51.1% of cases, and cytoreductive drugs in 79.3%, with hydroxyurea being the most common (64.9%). The median follow-up was 22.3 months, with 1-year cumulative incidence rates of thrombosis and bleeding at 11.1% and 3.7%, respectively. Multivariate analysis identified CHA2DS2-VASc scores ≥ 3 (hazard ratio [HR], 3.48), concomitant antiplatelet use (HR, 2.57), and cytoreduction (HR, 2.20) as significant thrombosis risk factors but found no significant predictors for major bleeding. Conclusion Despite the limitations of retrospective data, DOAC treatment in MPN patients seems effective and has an acceptable bleeding risk.

Purpose: Some studies suggest that TP53 mutations are associated with the response to immune checkpoint inhibitors (ICI) in patients with non–small cell lung cancer (NSCLC) and also contribute to sex disparities in several cancers. Thus, we hypothesized that TP53 mutations might serve as sex-dependent genomic biomarkers of ICI treatment response in patients with NSCLC. Materials and Methods: Clinical data of 100 patients with metastatic NSCLC treated with ICI monotherapy at Seoul National University Bundang Hospital (SNUBH) were retrospectively reviewed. Genomic and clinical datasets of The Cancer Genome Atlas and an ICI-treated lung cancer cohort (cBioPortal) were also analyzed. Results: In SNUBH cohort, no statistically significant difference was observed in the median progression-free survival (PFS) according to TP53 mutation status (p=0.930); however, female patients with TP53 mutations (MT) had a significantly prolonged median PFS compared to wild-type (WT) (6.1 months in TP53 MT vs. 2.6 months in TP53 WT; p=0.021). Programmed death-ligand 1 (PD-L1) high (≥ 50%) expression was significantly enriched in female patients with TP53 MT (p=0.005). The analysis from publicly available dataset also revealed that females with NSCLC with TP53 MT showed significantly longer PFS than those with TP53 WT (p < 0.001). In The Cancer Genome Atlas analysis, expression of immune-related genes, and tumor mutation burden score in TP53 MT females were higher than in males without TP53 MT. Conclusion Female patients with NSCLC with TP53 mutations had high PD-L1 expression and showed favorable clinical outcomes following ICI therapy, suggesting a need for further research to explore the role of TP53 mutations for sex disparities in response to ICI therapy.

Background/Aims: Hepatocellular carcinoma (HCC) exhibits high de novo recurrence rates post-resection. Current post-surgery recurrence prediction methods are limited, emphasizing the need for reliable biomarkers to assess recurrence risk. We aimed to develop methylation-based markers for classifying HCC patients and predicting their risk of de novo recurrence post-surgery. Methods: In this retrospective cohort study, we analyzed data from HCC patients who underwent surgical resection in Korea, excluding those with recurrence within one year post-surgery. Using the Infinium Methylation EPIC array on 140 samples in the discovery cohort, we classified patients into low- and high-risk groups based on methylation profiles. Distinctive markers were identified through random forest analysis. These markers were validated in the cancer genome atlas (n=217), Validation cohort 1 (n=63) and experimental Validation using a methylation-sensitive high-resolution melting (MS-HRM) assay in Validation cohort 1 and Validation cohort 2 (n=63). Results: The low-risk recurrence group (methylation group 1; MG1) showed a methylation average of 0.73 (95% confidence interval [CI] 0.69–0.77) with a 23.5% recurrence rate, while the high-risk group (MG2) had an average of 0.17 (95% CI 0.14–0.20) with a 44.1% recurrence rate (P<0.03). Validation confirmed the applicability of methylation markers across diverse populations, showing high accuracy in predicting the probability of HCC recurrence risk (area under the curve 96.8%). The MS-HRM assay confirmed its effectiveness in predicting de novo recurrence with 95.5% sensitivity, 89.7% specificity, and 92.2% accuracy. Conclusions Methylation markers effectively classified HCC patients by de novo recurrence risk, enhancing prediction accuracy and potentially offering personalized management strategies.

Objective: To evaluate the adherence of large language model (LLM)-based healthcare research to the Minimum Reporting Items for Clear Evaluation of Accuracy Reports of Large Language Models in Healthcare (MI-CLEAR-LLM) checklist, a framework designed to enhance the transparency and reproducibility of studies on the accuracy of LLMs for medical applications. Materials and Methods: A systematic PubMed search was conducted to identify articles on LLM performance published in high-ranking clinical medicine journals (the top 10% in each of the 59 specialties according to the 2023 Journal Impact Factor) from November 30, 2022, through June 25, 2024. Data on the six MI-CLEAR-LLM checklist items: 1) identification and specification of the LLM used, 2) stochasticity handling, 3) prompt wording and syntax, 4) prompt structuring, 5) prompt testing and optimization, and 6) independence of the test data—were independently extracted by two reviewers, and adherence was calculated for each item. Results: Of 159 studies, 100% (159/159) reported the name of the LLM, 96.9% (154/159) reported the version, and 91.8% (146/159) reported the manufacturer. However, only 54.1% (86/159) reported the training data cutoff date, 6.3% (10/159) documented access to web-based information, and 50.9% (81/159) provided the date of the query attempts. Clear documentation regarding stochasticity management was provided in 15.1% (24/159) of the studies. Regarding prompt details, 49.1% (78/159) provided exact prompt wording and syntax but only 34.0% (54/159) documented prompt-structuring practices. While 46.5% (74/159) of the studies detailed prompt testing, only 15.7% (25/159) explained the rationale for specific word choices. Test data independence was reported for only 13.2% (21/159) of the studies, and 56.6% (43/76) provided URLs for internet-sourced test data. Conclusion Although basic LLM identification details were relatively well reported, other key aspects, including stochasticity, prompts, and test data, were frequently underreported. Enhancing adherence to the MI-CLEAR-LLM checklist will allow LLM research to achieve greater transparency and will foster more credible and reliable future studies.

The anticancer drugs have evolved significantly, spanning molecular targeted therapeutics (MTTs), immune checkpoint inhibitors (ICIs), chimeric antigen receptor T-cell (CAR-T) therapy, and antibody-drug conjugates (ADCs). Complications associated with these drugs vary widely based on their mechanisms of action. MTTs that target angiogenesis can often lead to complications related to ischemia or endothelial damage across various organs, whereas non-anti-angiogenic MTTs present unique complications derived from their specific pharmacological actions. ICIs are predominantly associated with immunerelated adverse events, such as pneumonitis, colitis, hepatitis, thyroid disorders, hypophysitis, and sarcoid-like reactions. CAR-T therapy causes unique and severe complications including cytokine release syndrome and immune effector cell-associated neurotoxicity syndrome. ADCs tend to cause complications associated with cytotoxic payloads. A comprehensive understanding of these drug-specific toxicities, particularly using medical imaging, is essential for providing optimal patient care. Based on this knowledge, radiologists can play a pivotal role in multidisciplinary teams. Therefore, radiologists must stay up-to-date on the imaging characteristics of these complications and the mechanisms underlying novel anticancer drugs.

Objective: To evaluate the adherence of large language model (LLM)-based healthcare research to the Minimum Reporting Items for Clear Evaluation of Accuracy Reports of Large Language Models in Healthcare (MI-CLEAR-LLM) checklist, a framework designed to enhance the transparency and reproducibility of studies on the accuracy of LLMs for medical applications. Materials and Methods: A systematic PubMed search was conducted to identify articles on LLM performance published in high-ranking clinical medicine journals (the top 10% in each of the 59 specialties according to the 2023 Journal Impact Factor) from November 30, 2022, through June 25, 2024. Data on the six MI-CLEAR-LLM checklist items: 1) identification and specification of the LLM used, 2) stochasticity handling, 3) prompt wording and syntax, 4) prompt structuring, 5) prompt testing and optimization, and 6) independence of the test data—were independently extracted by two reviewers, and adherence was calculated for each item. Results: Of 159 studies, 100% (159/159) reported the name of the LLM, 96.9% (154/159) reported the version, and 91.8% (146/159) reported the manufacturer. However, only 54.1% (86/159) reported the training data cutoff date, 6.3% (10/159) documented access to web-based information, and 50.9% (81/159) provided the date of the query attempts. Clear documentation regarding stochasticity management was provided in 15.1% (24/159) of the studies. Regarding prompt details, 49.1% (78/159) provided exact prompt wording and syntax but only 34.0% (54/159) documented prompt-structuring practices. While 46.5% (74/159) of the studies detailed prompt testing, only 15.7% (25/159) explained the rationale for specific word choices. Test data independence was reported for only 13.2% (21/159) of the studies, and 56.6% (43/76) provided URLs for internet-sourced test data. Conclusion Although basic LLM identification details were relatively well reported, other key aspects, including stochasticity, prompts, and test data, were frequently underreported. Enhancing adherence to the MI-CLEAR-LLM checklist will allow LLM research to achieve greater transparency and will foster more credible and reliable future studies.

The anticancer drugs have evolved significantly, spanning molecular targeted therapeutics (MTTs), immune checkpoint inhibitors (ICIs), chimeric antigen receptor T-cell (CAR-T) therapy, and antibody-drug conjugates (ADCs). Complications associated with these drugs vary widely based on their mechanisms of action. MTTs that target angiogenesis can often lead to complications related to ischemia or endothelial damage across various organs, whereas non-anti-angiogenic MTTs present unique complications derived from their specific pharmacological actions. ICIs are predominantly associated with immunerelated adverse events, such as pneumonitis, colitis, hepatitis, thyroid disorders, hypophysitis, and sarcoid-like reactions. CAR-T therapy causes unique and severe complications including cytokine release syndrome and immune effector cell-associated neurotoxicity syndrome. ADCs tend to cause complications associated with cytotoxic payloads. A comprehensive understanding of these drug-specific toxicities, particularly using medical imaging, is essential for providing optimal patient care. Based on this knowledge, radiologists can play a pivotal role in multidisciplinary teams. Therefore, radiologists must stay up-to-date on the imaging characteristics of these complications and the mechanisms underlying novel anticancer drugs.

Background: and Purpose The National Brain Biobank of Korea (NBBK) is a brain bank consortium supported by the Korea Disease Control and Prevention Agency and the Korea National Institute of Health, and was launched in 2015 to support research into neurodegenerative disease dementia (NDD). This study aimed to introduce the NBBK and describes clinicopathological correlations based on analyses of data collected from the NBBK. Methods: Four hospital-based brain banks have been established in South Korea: Samsung Medical Center Brain Bank (SMCBB), Seoul National University Hospital Brain Bank (SNUHBB), Pusan National University Hospital Brain Bank (PNUHBB), and Myongji Hospital Brain Bank (MJHBB). Clinical and pathological data were collected from these brain banks using standardized protocols. The prevalence rates of clinical and pathological diagnoses were analyzed in order to characterize the clinicopathological correlations. Results: Between August 2016 and December 2023, 185 brain specimens were collected and pathologically evaluated (SNUHBB: 117; PNUHBB: 27; SMCBB: 34; MJHBB: 7). The age at consent was 70.8±12.6 years, and the age at autopsy was 71.7±12.4 years. The four-most-common clinical diagnoses were Alzheimer’s disease (AD) dementia (20.0%), idiopathic Parkinson’s disease (15.1%), unspecified dementia (11.9%), and cognitively unimpaired (CU) (11.4%).Most cases of unspecified dementia had a pathological diagnosis of central nervous system (CNS) vasculopathy (31.8%) or AD (31.8%). Remarkably, only 14.2% of CU cases had normal pathological findings. The three-most-common pathological diagnoses were AD (26.5%), CNS vasculopathy (14.1%), and Lewy body disease (13.5%). Conclusions These clinical and neuropathological findings provide a deeper understanding of the mechanisms underlying NDD in South Korea.