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.

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.

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.

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.

Purpose: This study aimed to assess prognostic factors associated with combined hepatocellular-cholangiocarcinoma (cHCC-CCA) and to predict 5-year survival based on these factors. Materials and Methods: Patients who underwent definitive hepatectomy from 2006 to 2022 at a single institution was retrospectively analyzed. Inclusion criteria involved a pathologically confirmed diagnosis of cHCC-CCA. Results: A total of 80 patients with diagnosed cHCC-CCA were included in the analysis. The median progression-free survival was 15.6 months, while distant metastasis-free survival (DMFS), hepatic progression-free survival, and overall survival (OS) were 50.8, 21.5, and 85.1 months, respectively. In 52 cases of recurrence, intrahepatic recurrence was the most common initial recurrence (34/52), with distant metastasis in 17 cases. Factors associated with poor DMFS included tumor necrosis, lymphovascular invasion (LVI), perineural invasion, and histologic compact type. Postoperative carbohydrate antigen 19-9, tumor necrosis, LVI, and close/positive margin were associated with poor OS. LVI emerged as a key factor affecting both DMFS and OS, with a 5-year OS of 93.3% for patients without LVI compared to 35.8% with LVI. Based on these factors, a nomogram predicting 3-year and 5-year DMFS and OS was developed, demonstrating high concordance with actual survival in the cohort (Harrell C-index 0.809 for OS, 0.801 for DMFS, respectively). Conclusion The prognosis of cHCC-CCA is notably poor when combined with LVI. Given the significant impact of adverse features, accurate outcome prediction is crucial. Moreover, consideration of adjuvant therapy may be warranted for patients exhibiting poor survival and increased risk of local recurrence or distant metastasis.

Objectives: . A substantial proportion of patients with head and neck cancer (HNC) require emergency room (ER) visits or unplanned hospitalizations during or after treatment with various modalities. We investigated HNC cases that necessitated ER visitation after cancer treatment, aiming to identify potential risk factors in the context of the Korean healthcare system. Methods: . This single-center cohort study examined patients with HNC who received cancer treatments at Samsung Medical Center in 2019 (n=566). Treatment modalities included surgery alone (n=184), surgery and adjuvant therapy (n=138), curative non-surgical treatment such as radiation or chemoradiation (n=209), and palliative treatments (n=35). We followed these cases for up to 3 years, focusing on those who visited the ER during or after cancer treatment, and analyzed the primary reasons and risk factors associated with these visits. Results: . The ER visitation rate was 8.0% (n=45) among patients with HNC, with a total of 70 ER visits (12.4%; mean, 1.56; range, 1–4). The rate of treatment-related ER visitation was 4.6%. Common reasons for ER visits included surgical site or wound complications (31.1% of patients visiting the ER, 22.9% of ER visits) and issues with oral intake or feeding (22.2% of patients, 31.4% of visits). Significant risk factors for ER visits included tumor subsite (with hypopharyngeal cancer associated with a 17.9% rate of treatment-related ER visits), tumor stage (T2–4, 8.6%–12.2%; N+ status, 6.7%), and treatment modality (surgery with adjuvant chemoradiation, 19.4%). Patient age and comorbidities did not represent significant factors. Conclusion . The most frequent reasons for ER visits among patients with HNC included complications with wounds and feeding. Additionally, tumor characteristics and treatment modality were independent risk factors for ER visits. Adequate planning and management to address these issues could potentially decrease the number of ER visits, lower costs, and improve patient care.

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.

Purpose: This study aimed to assess prognostic factors associated with combined hepatocellular-cholangiocarcinoma (cHCC-CCA) and to predict 5-year survival based on these factors. Materials and Methods: Patients who underwent definitive hepatectomy from 2006 to 2022 at a single institution was retrospectively analyzed. Inclusion criteria involved a pathologically confirmed diagnosis of cHCC-CCA. Results: A total of 80 patients with diagnosed cHCC-CCA were included in the analysis. The median progression-free survival was 15.6 months, while distant metastasis-free survival (DMFS), hepatic progression-free survival, and overall survival (OS) were 50.8, 21.5, and 85.1 months, respectively. In 52 cases of recurrence, intrahepatic recurrence was the most common initial recurrence (34/52), with distant metastasis in 17 cases. Factors associated with poor DMFS included tumor necrosis, lymphovascular invasion (LVI), perineural invasion, and histologic compact type. Postoperative carbohydrate antigen 19-9, tumor necrosis, LVI, and close/positive margin were associated with poor OS. LVI emerged as a key factor affecting both DMFS and OS, with a 5-year OS of 93.3% for patients without LVI compared to 35.8% with LVI. Based on these factors, a nomogram predicting 3-year and 5-year DMFS and OS was developed, demonstrating high concordance with actual survival in the cohort (Harrell C-index 0.809 for OS, 0.801 for DMFS, respectively). Conclusion The prognosis of cHCC-CCA is notably poor when combined with LVI. Given the significant impact of adverse features, accurate outcome prediction is crucial. Moreover, consideration of adjuvant therapy may be warranted for patients exhibiting poor survival and increased risk of local recurrence or distant metastasis.

Objectives: . A substantial proportion of patients with head and neck cancer (HNC) require emergency room (ER) visits or unplanned hospitalizations during or after treatment with various modalities. We investigated HNC cases that necessitated ER visitation after cancer treatment, aiming to identify potential risk factors in the context of the Korean healthcare system. Methods: . This single-center cohort study examined patients with HNC who received cancer treatments at Samsung Medical Center in 2019 (n=566). Treatment modalities included surgery alone (n=184), surgery and adjuvant therapy (n=138), curative non-surgical treatment such as radiation or chemoradiation (n=209), and palliative treatments (n=35). We followed these cases for up to 3 years, focusing on those who visited the ER during or after cancer treatment, and analyzed the primary reasons and risk factors associated with these visits. Results: . The ER visitation rate was 8.0% (n=45) among patients with HNC, with a total of 70 ER visits (12.4%; mean, 1.56; range, 1–4). The rate of treatment-related ER visitation was 4.6%. Common reasons for ER visits included surgical site or wound complications (31.1% of patients visiting the ER, 22.9% of ER visits) and issues with oral intake or feeding (22.2% of patients, 31.4% of visits). Significant risk factors for ER visits included tumor subsite (with hypopharyngeal cancer associated with a 17.9% rate of treatment-related ER visits), tumor stage (T2–4, 8.6%–12.2%; N+ status, 6.7%), and treatment modality (surgery with adjuvant chemoradiation, 19.4%). Patient age and comorbidities did not represent significant factors. Conclusion . The most frequent reasons for ER visits among patients with HNC included complications with wounds and feeding. Additionally, tumor characteristics and treatment modality were independent risk factors for ER visits. Adequate planning and management to address these issues could potentially decrease the number of ER visits, lower costs, and improve patient care.

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.