Clinical & Translational Oncology最新文献

{"title":"Management of late toxicities and specific follow-up needs of adolescent and young adult cancer survivors: recommendations from scientific societies in Spain.","authors":"Alejandro Pérez Fidalgo, Pilar Alonso, Maitane Andión, Adela Cañete, Erica Collado, Carmen Garrido Colino, José Gómez Codina, Xavier Díaz Carrasco, Ramón García Sanz, Sergio Hernández Expósito, Teresa Lopez-Fernandez, Gabriela Medin, Antonio Molinés, Alberto Moreno Vega, Mónica Ramos, Iñigo San Miguel, Joaquín Sánchez García, Fátima Santolaya","doi":"10.1007/s12094-025-04047-0","DOIUrl":"https://doi.org/10.1007/s12094-025-04047-0","url":null,"abstract":"<p><p>Adolescent and young adult cancer survivors (AYACS) represent a specific cancer patient population with unique chronic health issues difficult to identify in early, reversible phases with standard monitoring protocols. This review, conducted by a group of Spanish experts, provides recommendations for managing AYACS, focusing on key areas, such as cardiac toxicities, neurotoxicity and neurocognitive disorders, metabolic syndrome, secondary primary malignancies, bone toxicities, sexuality and fertility, psychosocial aspects, and other treatment-related toxicities.</p>","PeriodicalId":50685,"journal":{"name":"Clinical & Translational Oncology","volume":" ","pages":""},"PeriodicalIF":2.5,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145001833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparison of clinical characteristics and survival between HER2-zero and HER2-low in early breast cancer: a retrospective observational study.","authors":"Violeta Núñez Álvarez, Belén González Castilla, Belén Fernández Rivero, María Hernández Carrasco, Jaime Lluch Gómez, Irene Sánchez Lobón, María Ángeles Ocaña de la Rosa, Yulema Menguiano Romero, Eduardo Perdomo Zaldívar, Lourdes Rodríguez Pérez, Encarnación Benítez Rodríguez, José Manuel Baena Cañada","doi":"10.1007/s12094-025-04053-2","DOIUrl":"https://doi.org/10.1007/s12094-025-04053-2","url":null,"abstract":"<p><strong>Purpose: </strong>Human epidermal growth factor receptor 2 (HER2)-negative breast cancer includes HER2-zero and HER2-low tumors. Whether their clinical features and survival are different is not fully clarified. The objective was to explore their clinicopathologic differences and survival.</p><p><strong>Methods/patients: </strong>Retrospective analysis of HER2-negative, stage I-III breast cancer patients from 2006 to 2016 at a single site. Clinicopathological variables, events and survival are analyzed, comparing HER2-low and HER2-zero cases.</p><p><strong>Results: </strong>Of 535 patients, 351 (65.61%) were HER2-zero and 184 (34.39%) HER2-low (154 (83.70%) score 1 + and 30 (16.30%) score 2 +). The proportion of premenopausal women was higher in the HER2-low subgroup (50.50% vs 39.40%, p = 0.016). For those with HER2-zero tumors, 15.70% were estrogen receptor (ER) negative, whereas only 9.20% (p = 0.045) of HER2-low tumors were ER negative. In HER2-low/ER negative tumors, tumor size, histologic grade, and Ki67 levels were higher. Patients with HER2-zero/ER-negative tumors were younger, had fewer comorbidities, less nodal involvement, a higher frequency of ductal histopathology, and, again, higher histologic grade and Ki67 levels. There were no differences in the events. The overall survival probability at 11.50 years in the HER2-zero subgroup was 0.51 (95% confidence interval (CI 95%) 0.28-0.74) and in the HER2-low subgroup 0.67 (95% CI 0.56-0.77) (p = 0.52).</p><p><strong>Conclusions: </strong>HER2-zero and HER2-low breast cancers are not distinct clinicopathologic entities. The differences detected in some variables seem to depend on ER status. No prognostic differences were observed.</p>","PeriodicalId":50685,"journal":{"name":"Clinical & Translational Oncology","volume":" ","pages":""},"PeriodicalIF":2.5,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144994285","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MRI-based deep learning radiomics in predicting histological differentiation of oropharyngeal cancer: a multicenter cohort study.","authors":"Zhaoyu Pan, Wei Lu, Changyun Yu, Sen Fu, Hang Ling, Yong Liu, Xin Zhang, Liang Gong","doi":"10.1007/s12094-025-04042-5","DOIUrl":"https://doi.org/10.1007/s12094-025-04042-5","url":null,"abstract":"<p><strong>Background: </strong>The primary aim of this research was to create and rigorously assess a deep learning radiomics (DLR) framework utilizing magnetic resonance imaging (MRI) to forecast the histological differentiation grades of oropharyngeal cancer.</p><p><strong>Methods: </strong>This retrospective analysis encompassed 122 patients diagnosed with oropharyngeal cancer across three medical institutions in China. The participants were divided at random into two groups: a training cohort comprising 85 individuals and a test cohort of 37. Radiomics features derived from MRI scans, along with deep learning (DL) features, were meticulously extracted and carefully refined. These two sets of features were then integrated to build the DLR model, designed to assess the histological differentiation of oropharyngeal cancer. The model's predictive efficacy was gaged through the area under the receiver operating characteristic curve (AUC) and decision curve analysis (DCA).</p><p><strong>Results: </strong>The DLR model demonstrated impressive performance, achieving strong AUC scores of 0.871 on the training cohort and 0.803 on the test cohort, outperforming both the standalone radiomics and DL models. Additionally, the DCA curve highlighted the significance of the DLR model in forecasting the histological differentiation of oropharyngeal cancer.</p><p><strong>Conclusions: </strong>The MRI-based DLR model demonstrated high predictive ability for histological differentiation of oropharyngeal cancer, which might be important for accurate preoperative diagnosis and clinical decision-making.</p>","PeriodicalId":50685,"journal":{"name":"Clinical & Translational Oncology","volume":" ","pages":""},"PeriodicalIF":2.5,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144994371","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Safety and pharmacokinetics evaluation of oroxylin A in Chinese healthy volunteers: a phase I, double-blind, placebo-controlled, single ascending dose, multiple dose, and food effect study.","authors":"Fan Yang, Xianmin Meng, Shukui Qin, Qinglong Guo, Libin Wei, Di Zhao","doi":"10.1007/s12094-025-04017-6","DOIUrl":"https://doi.org/10.1007/s12094-025-04017-6","url":null,"abstract":"<p><strong>Purpose: </strong>Oroxylin A (OA) is a flavonoid, obtained from the root of Scutellaria baicalensis Georgi which is a traditional Chinese herbal, with antitumor and other pharmacological activities. OA tablets are an innovative drug, and a formal single ascending and multiple dose pharmacokinetic (PK) trial was conducted in humans to evaluate the required to determine the safety and tolerability of OA as well as the effect of food on its PK parameters profile.</p><p><strong>Methods: </strong>This clinical study consisted of three parts: single ascending dose (400[n = 3], 800, 1600 and 2400 mg OA [n = 8/group] and placebo [n = 6]), multiple dose (1600 or 2400 mg OA [n = 8 / group] and placebo [n = 4] once daily), and food effects (1600 mg OA single dose [n = 12]).</p><p><strong>Results: </strong>No dose-limiting toxic events (DLT), no serious adverse events (SAEs) or death occurred, and incidence of gastrointestinal AEs were higher in multiple doses than in single dose. OA appeared rapidly in plasma; t_max was approximately 0.17 ~ 5.0 h. The C_max of OA approximately increased in dose-proportional manner (C_max slope 1.114), and the AUC_0-t increased less than dose increasing (AUC_0-t slope 0.7513). After 10 days of continuous administration, OA presented a moderate cumulative effect (1.51-1.73-fold). High-fat diet can increase the C_max of OA (1.6-fold), and its metabolites increased more significantly (p < 0.05), there was no effect of food on t_max or terminal half-life.</p><p><strong>Conclusions: </strong>The safety and PK profile support once-daily administration of OA, and considering the effects of food, it is recommended to administrate OA tablet after meals in further clinical studies.</p><p><strong>Trial registration number: </strong>ChiCTR2100051434 http://www.chictr.org/cn/ ; Date of registration: 23 Sep., 2021.</p>","PeriodicalId":50685,"journal":{"name":"Clinical & Translational Oncology","volume":" ","pages":""},"PeriodicalIF":2.5,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144994418","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Applications of single-cell transcriptomics: updated insights in endometrial cancer.","authors":"Shuyue Xiao, Huixin Li, Jianyao Liu, Xinyi Xie, Hanzi Xu, Zhen Gong, Shanliang Zhong","doi":"10.1007/s12094-025-04032-7","DOIUrl":"https://doi.org/10.1007/s12094-025-04032-7","url":null,"abstract":"<p><p>Endometrial cancer (EC) presents a major global health challenge due to its heterogeneity and complex pathophysiology. The tumor microenvironment (TME), comprising stromal cells, immune cells, endothelial cells, and non-cellular components, critically influences EC progression. Single-cell RNA sequencing (scRNA-seq) has revolutionized our understanding of EC by revealing TME cellular heterogeneity and interactions. This review synthesizes recent scRNA-seq applications in EC, focusing on two key areas: ① Mapping transcriptional heterogeneity across major cellular components (epithelial, stromal, endothelial, and immune cells); ② Elucidating the factors driving tumor evolution, immune evasion, and differential immunotherapy response. Collectively, these scRNA-seq-derived insights into the dynamic TME ecosystem provide the foundation for translating basic discoveries toward clinical applications. Such advances could thereby promote TME-based personalized therapies and more accurate prognostic predictions.</p>","PeriodicalId":50685,"journal":{"name":"Clinical & Translational Oncology","volume":" ","pages":""},"PeriodicalIF":2.5,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144994345","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Implementation of the precision oncology program in catalonia's public health system: results, lessons learned, and future prospects.","authors":"Pilar Mur, Anna Pozuelo, Josep Tabernero, Joan Albanell, Beatriz Bellosillo, Francesc Bosch, Javier Briones, Joan Brunet, Dolors Colomer, Montserrat Domènech, Joan Manel Fontanet, Xavier Matias-Guiu, Ramon Salazar, Rosa Maria Vivanco-Hidalgo, Meritxell Mollà, Lucas Moreno, Aleix Prat, Josep Maria Ribera, Ramón Clèries, Alex Guarga, Josep A Espinàs, Josep Maria Borras","doi":"10.1007/s12094-025-04022-9","DOIUrl":"https://doi.org/10.1007/s12094-025-04022-9","url":null,"abstract":"<p><strong>Purpose: </strong>The Precision Oncology Program (POP) in Catalonia aims to provide equitable access to molecular testing for individuals with cancer, integrating Next-Generation Sequencing (NGS) into clinical practice to inform diagnosis, prognosis, and treatment decisions for both adult and pediatric patients with solid and hematologic malignancies, including somatic and germline alterations. This study evaluates the program's outcomes and impact.</p><p><strong>Methods: </strong>This evaluation covers the period from the program's implementation in July 2021 through December 2023, with a more detailed analysis focusing on 2022-2023. The program involved 12 reference centers utilizing NGS technology for cancer genetic analysis, coordinated by CatSalut, the regional public health service payer. Data collected from each reference laboratory included the number of tests performed, types of tumor panels used, clinical indications, and associated outcomes.</p><p><strong>Results: </strong>Between July 2021 and December 2023, a total of 23,135 molecular tests were performed on 22,501 patients. The most frequently analyzed panels were for solid tumors (38.1%), hematologic cancers (17.3%), and germline mutations (42.2%). Pediatric patients accounted for 2.4% of the total. Notably, 24.7% of patients underwent a change in clinical management, contributing to more targeted treatment strategies, particularly in solid tumors (58.7%). Reports were delivered within an average of four weeks, meeting program benchmarks and facilitating timely decision-making. Sample submission compliance was high, reaching 98.5%.</p><p><strong>Conclusions: </strong>This POP successfully addressed operational, financial, and logistic challenges, ensuring equitable access to molecular testing. This program led to more efficient and personalized clinical management, with growing impact on cancer care and patient outcomes.</p>","PeriodicalId":50685,"journal":{"name":"Clinical & Translational Oncology","volume":" ","pages":""},"PeriodicalIF":2.5,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144976555","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CDK4/6 inhibitors for metastatic breast cancer in routine clinical practice in Spain: survey of patterns of use and oncologists' perceptions.","authors":"F Moreno, V Iranzo, I Álvarez, A Antón, J I Chacón, J Gavilá, M Martín, P Sánchez Rovira, P Gratal, M J Fernández González, R López","doi":"10.1007/s12094-025-03896-z","DOIUrl":"10.1007/s12094-025-03896-z","url":null,"abstract":"<p><strong>Purpose: </strong>To assess the use of cyclin-dependent kinase 4/6 (CDK4/6) inhibitors in routine clinical practice in Spain, as well as the perceptions from oncologists.</p><p><strong>Methods: </strong>A survey was developed by nine oncologists, experts in breast cancer, practising in Spain. Survey responses were collected between July 2022 and April 2023.</p><p><strong>Results: </strong>Fifty-one survey responses were obtained. Most oncologists used CDK4/6 inhibitors in the first line. The first-line endocrine therapy most frequently used was an aromatase inhibitor (endocrine-sensitive disease) and fulvestrant (endocrine-resistant disease). CDK4/6 inhibitors were used for primary or secondary resistance, or visceral disease without visceral crisis. A lower-than-standard starting dose was considered (57% of respondents) for specific profiles. Strategies to manage toxicity included switching to another CDK4/6 inhibitor or delaying the next dose. CDK4/6 inhibitors were mostly considered to improve quality of life.</p><p><strong>Conclusions: </strong>Use of CDK4/6 inhibitors in Spain follows current recommendations and aligns with the evidence.</p>","PeriodicalId":50685,"journal":{"name":"Clinical & Translational Oncology","volume":" ","pages":"3819-3826"},"PeriodicalIF":2.5,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143722570","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Treatment patterns and survival outcomes in patients with small-cell lung cancer following failure of first-line platinum-based chemotherapy.","authors":"Chi-Lu Chiang, Ying-Ting Liao, Ruei-Lin Sun, Hsu-Ching Huang, Chia-I Shen, Yen-Han Tseng, Yung-Hung Luo, Yuh-Min Chen","doi":"10.1007/s12094-025-03918-w","DOIUrl":"10.1007/s12094-025-03918-w","url":null,"abstract":"<p><strong>Purpose: </strong>Small-cell lung cancer (SCLC) is an aggressive malignancy with limited treatment options, especially after the failure of first-line (1L) platinum-based chemotherapy. This study evaluated the treatment patterns and survival outcomes of Taiwanese patients with SCLC following 1L treatment failure, focusing on the effects of treatment-free interval (TFI).</p><p><strong>Methods: </strong>This retrospective study enrolled 287 patients with SCLC from 2012 to 2021. Data on clinical characteristics, systemic treatments after 1L failure, and survival status were collected. Progression-free survival (PFS) and overall survival (OS) were examined in analyses stratified by TFI. TFI < 90 days and ≥ 90 days denoted resistant relapse and sensitive relapse, respectively.</p><p><strong>Results: </strong>Second-line (2L) and third-line (3L) chemotherapy was administered to 76% and 54.1% of patients, respectively. Topotecan was administered to 25.4% of patients, primarily those with TFI 90-179 days. Platinum rechallenge was administered to 8.4% of patients, primarily those with TFI ≥ 180 days. The median PFS of patients with 2L treatment was 2.3 months (95% CI 2.2-2.6), and the median OS was 5.1 months (95% CI 4.3-6.2). Patients with TFI ≥ 90 days had significantly longer PFS (2.6 vs 2.2 months, P = 0.011) and OS (9.6 vs 4.0 months, P < 0.0001) than did those with TFI < 90 days. Platinum rechallenge showed similar efficacy to topotecan in patients with sensitive relapse (3.0 vs 2.7 months, P = 0.61).</p><p><strong>Conclusions: </strong>Survival outcomes in patients with relapsed SCLC remain poor, particularly in those with platinum-resistant relapse. Our findings highlight the importance of optimizing 1L treatment for delaying disease progression. More effective 2L therapies should be developed to improve survival outcomes in patients with relapsed SCLC.</p>","PeriodicalId":50685,"journal":{"name":"Clinical & Translational Oncology","volume":" ","pages":"3664-3671"},"PeriodicalIF":2.5,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144055507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Sex-related differences in the efficacy and toxicity of cancer treatments.","authors":"Ana Santaballa Bertrán, José Antonio Marcos Rodríguez, Ana Cardeña-Gutiérrez, Virginia Martinez-Callejo, Oliver Higuera, Beatriz Bernardez, Maria-Estela Moreno-Martínez, Margarita Majem","doi":"10.1007/s12094-025-03893-2","DOIUrl":"10.1007/s12094-025-03893-2","url":null,"abstract":"<p><p>Differences between the biological sexes have long been observed in cancer incidence and prevalence, and in treatment outcomes including efficacy and toxicity. Ideally, there should be sufficient information to improve the individualization of cancer treatment by incorporating sex into treatment decisions. Necessary information should include: the nature and source of these differences; whether inherent to the specific cancer (such as molecular profiles, metabolic behaviors, and immune responses); the pathophysiological mechanisms of the specific cancer; or the pharmacokinetic and pharmacodynamic profiles of different cancer drugs. The influence of gender, which is defined as the sociocultural construct that determines societal norms for males and females, should also be included in personalized decision-making. This review aimed to describe the current evidence on the impact of sex and gender on treatment effects, outcomes, and toxicity profiles in cancer patients. Data for the influence of gender were negligible, whereas clinical studies and meta-analyses in different cancer types have identified differences between males and females in the effectiveness on survival outcomes of immunotherapy, chemotherapy, targeted therapy, and radiotherapy. Similarly, toxicity profiles of different cancer treatments varied between sexes. Based on these observed differences, it seems clear that sex should be included as an important variable when individualizing treatment; however, more research into sex- and gender-related differences in cancer treatment efficacy and toxicity, and the causes for these differences, is required before this can be fully incorporated into individualized treatment programs in real-world clinical practice.</p>","PeriodicalId":50685,"journal":{"name":"Clinical & Translational Oncology","volume":" ","pages":"3636-3646"},"PeriodicalIF":2.5,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12399714/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143736173","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessing the accuracy of the GPT-4 model in multidisciplinary tumor board decision prediction.","authors":"Efe Cem Erdat, Merih Yalçıner, Mehmet Berk Örüncü, Yüksel Ürün, Filiz Çay Şenler","doi":"10.1007/s12094-025-03905-1","DOIUrl":"10.1007/s12094-025-03905-1","url":null,"abstract":"<p><strong>Purpose: </strong>Artificial intelligence models like GPT-4 (OpenAI) have the potential to support clinical decision-making in oncology. This study aimed to assess the consistency between multidisciplinary tumor board (MTB) decisions and GPT-4 model predictions in cancer patient management.</p><p><strong>Patients and methods: </strong>A cross-sectional study was conducted involving patients aged ≥ 18 years with definite or suspicious cancer diagnoses presented at MTBs in Ankara University Hospitals, Türkiye, from February 2021 to June 2023. GPT-4 was utilized to generate treatment recommendations based on case summaries. Three independent raters evaluated the compatibility between MTB decisions and GPT-4 predictions using a 4-point Likert scale. Cases with mean compatibility scores equal to or below 2 were reviewed by two expert oncologists for appropriateness.</p><p><strong>Results: </strong>A total of 610 patients were included. The mean compatibility score across raters was 3.59 (SD = 0.81), indicating high agreement between GPT-4 predictions and MTB decisions. Cronbach's alpha was 0.950 (95% CI 0.935-0.960), demonstrating excellent interrater reliability. Sixty-two cases (10.2%) had mean compatibility scores below the threshold of 2. The first expert oncologist deemed GPT-4's predictions inappropriate in 8 of these cases (12.9%), while the second deemed them inappropriate in 16 cases (25.8%). Cohen's kappa showed moderate agreement (κ = 0.50, 95% CI 0.25-0.75, p < 0.001). Discrepancies were often due to rare cases lacking guideline information or misunderstandings of case presentations.</p><p><strong>Conclusion: </strong>GPT-4 exhibited high compatibility with MTB decisions in cancer patient management, suggesting its potential as a supportive tool in clinical oncology. However, limitations exist, especially in rare or complex cases.</p>","PeriodicalId":50685,"journal":{"name":"Clinical & Translational Oncology","volume":" ","pages":"3793-3802"},"PeriodicalIF":2.5,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12399707/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143711925","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}