ESMO Real World Data and Digital Oncology最新文献

{"title":"Editoiral Board","authors":"","doi":"10.1016/S2949-8201(25)00561-2","DOIUrl":"10.1016/S2949-8201(25)00561-2","url":null,"abstract":"","PeriodicalId":100491,"journal":{"name":"ESMO Real World Data and Digital Oncology","volume":"10 ","pages":"Article 100672"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145789920","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Proof-of-concept: AI-assisted, natural-language-guided survival analysis achieves concordance with human-conducted results in glioblastoma","authors":"E. Omene ,&nbsp;C. Marsters ,&nbsp;J. Easaw ,&nbsp;K. Young ,&nbsp;C. Kolbeck ,&nbsp;O. Abdelsalem ,&nbsp;Y. Yuan","doi":"10.1016/j.esmorw.2025.100653","DOIUrl":"10.1016/j.esmorw.2025.100653","url":null,"abstract":"<div><h3>Background</h3><div>The use of large language models with natural-language prompting may simplify survival analysis but requires validation against standard analyses carried out by trained analysts. We compared a human-conducted SPSS survival analysis to the Replit cloud development platform for conversational statistical analysis using a fully observed cohort of 1265 glioblastoma patients.</div></div><div><h3>Patients and methods</h3><div>Two statistical procedures—Kaplan–Meier estimation and Cox proportional hazards regression—were implemented. The reference analysis was carried out by an experienced clinical researcher using SPSS; the Replit-based analysis by an oncologist with no graduate level statistical or programming training employed the lifelines package through Claude language model integration via conversational chatbox interface. Statistical results were reviewed by a data science professor. Artificial intelligence- (AI) generated code was reviewed by a machine learning engineer. All patients had died at last follow-up, so no censoring occurred. Concordance was defined as exact matches in median survival times and hazard ratios (HR), reflecting the scientific principle that identical datasets processed with identical statistical methods must produce identical results.</div></div><div><h3>Results</h3><div>Initial comparison of median survival across 12 molecular/age subgroups found exact concordance in 7 of 12 subgroups (58.3%). The remaining discrepancies represented preprocessing differences rather than acceptable analytical variation. Natural-language troubleshooting through Replit’s conversational interface identified three sources of discrepancy: patient inclusion differences, age-group boundary definitions, and inconsistent molecular encoding. After harmonizing these factors, median survival times and HRs were identical across both analyses, achieving 100% concordance. The Replit-based approach required 1 h 40 min total time compared with 8.5 h for traditional analysis, representing a 80% time reduction while maintaining statistical rigor.</div></div><div><h3>Conclusions</h3><div>This proof-of-concept demonstrates that the Replit platform can achieve exact replication of standard Kaplan–Meier and Cox analyses carried out by an experienced analyst when subgroup definitions and data preprocessing are aligned. Although our findings are limited to a single dataset and workflow, they suggest conversational AI interfaces could reduce barriers to statistical analysis for clinical researchers. Broader validation across varied analytical scenarios is essential before widespread clinical implementation. Statistical expertise remains essential for data quality assessment and model validation.</div></div>","PeriodicalId":100491,"journal":{"name":"ESMO Real World Data and Digital Oncology","volume":"10 ","pages":"Article 100653"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145684415","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Real-world effectiveness and safety of avelumab + axitinib combination in first-line treatment of UK patients with advanced renal cell carcinoma","authors":"P. Nathan ,&nbsp;N. Charnley ,&nbsp;R. Frazer ,&nbsp;J. McGrane ,&nbsp;I. Muazzam ,&nbsp;M. Pillai ,&nbsp;S. Rudman ,&nbsp;A. Sharma ,&nbsp;R. Stevenson ,&nbsp;B. Venugopal ,&nbsp;J. Hickey ,&nbsp;J. Hughes ,&nbsp;A.R. Ritchie ,&nbsp;Y. Shah","doi":"10.1016/j.esmorw.2025.100630","DOIUrl":"10.1016/j.esmorw.2025.100630","url":null,"abstract":"<div><h3>Background</h3><div>Avelumab + axitinib (A + Ax) combination use in patients with advanced renal cell carcinoma (aRCC) is growing in the United Kingdom, yet real-world evidence of its use remains limited.</div></div><div><h3>Methods</h3><div>This was a UK-based multicentre, retrospective noninterventional cohort study. Inclusion criteria were diagnosis of aRCC, A + Ax initiation on or after 1 August 2019, and aged ≥18 years at the date of initiation. Primary endpoints were overall survival (OS), progression-free survival (PFS), objective response rate (ORR), and best response at 36 months after initiation.</div></div><div><h3>Results</h3><div>A total of 130 patients were included. Median age was 67.1 years; 74% (<em>n</em> = 96) were male. OS and PFS rates [95% confidence interval (95% CI)] at 36 months were 53% (45.2% to 62.9%) and 27% (20.3% to 36.0%), respectively. Median OS was not reached; median PFS was 13.5 months (95% CI 10.2-17.7 months). ORR (<em>n</em> = 127) at 36 months was 62% (95% CI 53.8% to 70.6%), including best response of complete response in 5% (<em>n</em> = 6) and partial response in 57% (<em>n</em> = 73).</div></div><div><h3>Conclusions</h3><div>In this UK-based real-world study of first-line A + Ax treatment in patients with aRCC, OS, PFS, ORR, and best response observed at 36 months were in line with findings from JAVELIN Renal 101 (NCT02684006) and other observational studies, with no newly emerging adverse events.</div></div>","PeriodicalId":100491,"journal":{"name":"ESMO Real World Data and Digital Oncology","volume":"10 ","pages":"Article 100630"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145465435","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"JAVEMACS: a real-world study of avelumab maintenance therapy for advanced urothelial carcinoma in Japan","authors":"H. Kitamura ,&nbsp;T. Kobayashi ,&nbsp;Y. Endo ,&nbsp;M. Ikeda ,&nbsp;K. Yonemori ,&nbsp;M. Nakayama ,&nbsp;A. Fujihara ,&nbsp;T. Abe ,&nbsp;F. Shimizu ,&nbsp;K. Fujimoto ,&nbsp;T. Nakagawa ,&nbsp;S. Hatakeyama ,&nbsp;K. Murakami ,&nbsp;K. Nishihara ,&nbsp;D. Ikarashi ,&nbsp;N. Masumori ,&nbsp;S. Naito ,&nbsp;K. Fujita ,&nbsp;N. Hayakawa ,&nbsp;T. Hara ,&nbsp;E. Kikuchi","doi":"10.1016/j.esmorw.2025.100646","DOIUrl":"10.1016/j.esmorw.2025.100646","url":null,"abstract":"<div><h3>Background</h3><div>Avelumab maintenance therapy was approved in Japan in February 2021 for patients with unresectable locally advanced or metastatic urothelial carcinoma (la/mUC) without disease progression after platinum-based chemotherapy (PBC). We report the primary analysis from the JAVEMACS chart review study of avelumab maintenance therapy in Japan.</div></div><div><h3>Materials and methods</h3><div>This multicenter, retrospective study collected data from medical charts of patients with la/mUC who received avelumab maintenance after first-line (1L) PBC.</div></div><div><h3>Results</h3><div>Between February 2021 and December 2023, 350 patients received avelumab maintenance; median age was 73 years and most were male (74.0%). Prior 1L PBC was cisplatin–gemcitabine in 56.0% and carboplatin–gemcitabine in 33.1%; 28.6% were cisplatin eligible and 52.9% were cisplatin ineligible/platinum eligible. At data cut-off (June 2024), 67 patients (19.1%) were still receiving avelumab. Among 283 patients who discontinued avelumab, 200 (70.7%) received second-line (2L) treatment. In the overall population, median overall survival (OS) from avelumab initiation was 31.8 months [95% confidence interval (CI) 24.6 months-not estimable (NE)]. In subgroups who received 2L enfortumab vedotin (EV) (<em>n</em> = 133), PBC (<em>n</em> = 41), or pembrolizumab (<em>n</em> = 17), median OS from the start of 2L treatment was 17.8 months (95% CI 11.9 months-NE), 15.1 months (95% CI 11.6 months-NE), and 15.6 months (95% CI 8.6-21.3 months), respectively. Limitations include the study’s retrospective nature.</div></div><div><h3>Conclusions</h3><div>Results from JAVEMACS confirm the effectiveness of avelumab maintenance in real-world clinical practice in Japan, supporting its recommendation for patients with la/mUC without disease progression following 1L PBC. This treatment sequence followed by 2L EV appeared to be associated with encouraging long-term outcomes in this real-world population.</div></div>","PeriodicalId":100491,"journal":{"name":"ESMO Real World Data and Digital Oncology","volume":"10 ","pages":"Article 100646"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145571603","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Barriers to career development and gender-related challenges in oncology: the results of the JSMO and JSCO surveys in Japan","authors":"M. Ono ,&nbsp;I. Takahashi ,&nbsp;T. Kudo ,&nbsp;N. Miyazaki ,&nbsp;T. Azuma ,&nbsp;H. Horinouchi ,&nbsp;I. Kinoshita ,&nbsp;T.E. Nakajima ,&nbsp;T. Yoshino ,&nbsp;H. Minami","doi":"10.1016/j.esmorw.2025.100186","DOIUrl":"10.1016/j.esmorw.2025.100186","url":null,"abstract":"<div><h3>Background</h3><div>As the number of female physicians in Japan increases, so does the number of female oncologists. This study investigates gender-related challenges and identifies factors influencing career progression among oncology professionals in Japan.</div></div><div><h3>Materials and methods</h3><div>A survey was distributed to members of the Japanese Society of Medical Oncology (JSMO) and the Japan Society of Clinical Oncology (JSCO), based on the European Society for Medical Oncology (ESMO) Women for Oncology questionnaire. It covered demographics, professional environment, work–life balance, personal choices, and career-related challenges.</div></div><div><h3>Results</h3><div>A total of 612 responses (47.5% women, 52.5% men) were analyzed; 58.9% were &lt;50 years of age. Female respondents were significantly more likely to report that their careers impacted marital status, childbearing decisions, and time for childcare. Women also reported a greater influence of life choices—such as marriage, childbirth, and reduced working hours—on their careers than men. Notably, 66.4% of women perceived career barriers compared with 40.6% of men. Major obstacles included difficulty balancing work and life, limited opportunities for clinical research, and childcare responsibilities. Multivariate analysis showed that gender and age were significant predictors of perceived career barriers.</div></div><div><h3>Conclusions</h3><div>Gender disparities remain a major issue for female oncologists in Japan, rooted in societal expectations, unequal childcare burdens, and institutional limitations. Systemic changes—such as promoting task sharing, expanding mentorship, and implementing inclusive workplace policies—are essential to foster equitable career advancement in oncology.</div></div>","PeriodicalId":100491,"journal":{"name":"ESMO Real World Data and Digital Oncology","volume":"10 ","pages":"Article 100186"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145159279","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DIPSS and DIPSS Plus risk scoring in myelofibrosis utilizing automated, electronic health record-integrated decision system","authors":"A. Mervaala-Muroke ,&nbsp;M. Lehto ,&nbsp;K. Porkka ,&nbsp;O. Brück","doi":"10.1016/j.esmorw.2025.100196","DOIUrl":"10.1016/j.esmorw.2025.100196","url":null,"abstract":"<div><h3>Background</h3><div>Automated risk scoring could reduce human errors and enhance consistency. The aim of the study was to investigate whether automation of myelofibrosis Dynamic Prognostic Scoring System (DIPSS) and DIPSS Plus scores could improve their prognostic accuracy.</div></div><div><h3>Materials and methods</h3><div>We built an automated, electronic health record (EHR)-integrated decision system, extracting risk score covariates from tabular source databases and patient journals using text mining. Physician-defined scores were obtained through manual chart review (DIPSS 12%, DIPSS Plus 21%) or manual calculations (DIPSS 88%, DIPSS Plus 79%) using the reported risk score covariates. We compared automated scores with physician-defined scores by their ability to predict overall survival, using Cox regression, C-index, and time-dependent area under the receiver operating characteristic (AUROC) values.</div></div><div><h3>Results</h3><div>We included real-world data of patients with myelofibrosis (<em>n</em> = 251) from the Helsinki University Hospital district, Finland, at the time of their diagnosis. Cox regression analyses demonstrated C-indices of 0.72/0.72 (DIPSS/DIPSS Plus) for automated scoring and 0.69/0.71 for physician-defined scoring. Yearly time-dependent AUROC values for 10-year overall survival varied 0.75-0.82/0.74-0.84 for automated scoring and 0.71-0.79/0.74-0.82 for physician-defined scoring. We validated the feasibility and performance (C-indices: 0.68/70 for automated scoring versus 0.66/67 for physician-defined scoring, AUROC ranges: 0.67-0.76/0.67-0.87 for automated scoring versus 0.65-0.74/0.65-0.79 for physician-defined scoring) of the automated model in an external dataset (<em>n</em> = 120 patients).</div></div><div><h3>Conclusions</h3><div>We present the first automated, EHR-integrated decision system for calculating DIPSS and DIPSS Plus scores. The accuracy of the scores was aligned with the physician-defined scores, but the availability of the scores was significantly improved, highlighting the need for machine-assisted scoring.</div></div>","PeriodicalId":100491,"journal":{"name":"ESMO Real World Data and Digital Oncology","volume":"10 ","pages":"Article 100196"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145268342","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From Lindbergh’s cockpit to predictive, AI-driven health care: a roadmap for high-reliability medicine","authors":"B. Fuchs ,&nbsp;P. Heesen","doi":"10.1016/j.esmorw.2025.100650","DOIUrl":"10.1016/j.esmorw.2025.100650","url":null,"abstract":"<div><div>Modern health care remains largely intuition-driven, reactive, and fragmented, resulting in preventable errors and inefficiencies. In contrast, aviation has evolved into a highly structured, automated, and predictive safety system, achieving near-zero accident rates through standardization, automation, and artificial intelligence (AI)-assisted decision making. While medicine has incorporated certain aviation-inspired practices—such as checklists, crew resource management, and simulation training—it lacks the comprehensive data-driven framework and continuous oversight that underpins aviation’s safety culture. This perspective proposes a four-phase roadmap for integrating AI into health care, drawing on lessons from aviation’s transformation over the past century. Phase I emphasizes the standardization of clinical data and interoperability, mirroring aviation’s shift from handwritten logs to digital flight recorders. Phase II introduces AI-assisted decision support, paralleling the emergence of autopilot and early flight control systems. Phase III highlights real-time predictive monitoring, analogous to continuous flight data monitoring, while phase IV envisions autonomous health care systems, reflecting modern aircraft’s capacity for automated flight. However, aviation’s experience also reveals the perils of over-reliance on technology, including automation bias and deskilling, underscoring the need for regulatory adaptation, transparent error reporting, and robust human–AI collaboration. By integrating these safeguards, medicine can carefully integrate AI’s transformative potential to reduce errors, improve efficiency, and enhance patient outcomes, thereby shifting from an intuition-driven model to one of precision and reliability.</div></div>","PeriodicalId":100491,"journal":{"name":"ESMO Real World Data and Digital Oncology","volume":"10 ","pages":"Article 100650"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145571523","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prognostic role of Ki-67 in high-risk estrogen receptor-positive/HER2-negative early breast cancer: a population-based cohort study","authors":"E. Tegnelius ,&nbsp;J. Ahlgren ,&nbsp;A. Valachis","doi":"10.1016/j.esmorw.2025.100647","DOIUrl":"10.1016/j.esmorw.2025.100647","url":null,"abstract":"<div><h3>Background and purpose</h3><div>Abemaciclib is a CDK4/6-inhibitor approved for adjuvant use in estrogen receptor (ER)-positive/human epidermal growth factor receptor 2 (HER2)-negative breast cancer with high risk of relapse, defined as N2-N3 disease or high-risk N1 disease. The MonarchE study also included high Ki-67 in combination with N1 disease as a separate study cohort. We investigated the prognostic value of MonarchE risk group criteria, with or without the addition of Ki-67, when applied to a large set of real-world data (RWD).</div></div><div><h3>Materials and methods</h3><div>We carried out a retrospective cohort study using Breast Cancer Data Base Sweden (BCBaSe) 3.0, a research database including all Swedish breast cancer patients from 2008 to 2020. The cohort included 21 110 ER-positive/HER2-negative breast cancer patients, whereof 12 983 had available Ki-67 data.</div></div><div><h3>Results</h3><div>Risk groups were defined as N1 low risk, N1 high risk and N2-N3 very high risk, based on MonarchE criteria. Survival analyses showed an increasingly worse prognosis across the three groups for three outcomes including distant disease-free survival (DDFS), breast cancer-specific survival (BCSS), and overall survival (OS). Ki-67 ≥20% was associated with statistically significant worse DDFS, BCSS, and OS in the overall N1 group, but when comparing 5-year survival rates in the N1 group with and without Ki-67 stratification, no clinically meaningful absolute difference in OS was seen.</div></div><div><h3>Conclusions</h3><div>Our nationwide RWD results support the use of MonarchE's risk group criteria for selection of high-risk ER-positive/HER2-negative breast cancer patients who might derive benefit from adjuvant abemaciclib. The role of Ki-67 in risk stratification seems to be limited and without clear clinical significance.</div></div>","PeriodicalId":100491,"journal":{"name":"ESMO Real World Data and Digital Oncology","volume":"10 ","pages":"Article 100647"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145571605","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"9P Benchmarking instance segmentation architectures for whole-cell segmentation in IHC-stained images: A multi-cancer study","authors":"F.J. Segerer,&nbsp;S. Sathya Narayanan,&nbsp;T. Falck,&nbsp;G. Vivar,&nbsp;N. Brieu,&nbsp;M. Bui","doi":"10.1016/j.esmorw.2025.100208","DOIUrl":"10.1016/j.esmorw.2025.100208","url":null,"abstract":"","PeriodicalId":100491,"journal":{"name":"ESMO Real World Data and Digital Oncology","volume":"10 ","pages":"Article 100208"},"PeriodicalIF":0.0,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145610119","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"82P Edge-native artificial intelligence for automated anamnesis, real-time documentation, and multilingual communication in oncology practice","authors":"L. Luo ,&nbsp;J.C. Murillo Rojas","doi":"10.1016/j.esmorw.2025.100280","DOIUrl":"10.1016/j.esmorw.2025.100280","url":null,"abstract":"","PeriodicalId":100491,"journal":{"name":"ESMO Real World Data and Digital Oncology","volume":"10 ","pages":"Article 100280"},"PeriodicalIF":0.0,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145610210","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}