JNCI Cancer Spectrum最新文献

{"title":"Use of natural language processing to identify patients with inflammatory breast cancer across a health-care system.","authors":"Ramez Kouzy, Megumi Kai, Huong T Le-Petross, Sadia Saleem, Wendy A Woodward","doi":"10.1093/jncics/pkaf058","DOIUrl":"10.1093/jncics/pkaf058","url":null,"abstract":"<p><p>Early identification and referral of inflammatory breast cancer remains challenging within large health-care systems, limiting access to specialized care. We developed and evaluated an artificial intelligence-driven platform integrating natural language processing (NLP) with electronic health records to systematically identify potential inflammatory breast cancer patients across 5 campuses. Our platform analyzed 8 623 494 clinical notes, implementing a sequential review process: NLP screening followed by human validation and multidisciplinary confirmation. Initial NLP screening achieved 55.4% positive predictive value, improving to 78.4% with human-in-the-loop review. Notably, among 255 confirmed patients with inflammatory breast cancer, our system demonstrated 92.2% sensitivity, identifying 57 patients (22.4%) that traditional surveillance methods missed. Documentation patterns influenced system performance, with combined inflammatory breast cancer and T4d staging mentions showing the highest predictive value (98.2%). This proof-of-concept study demonstrates that lightweight NLP systems with targeted human review can identify rare cancer cases that may otherwise remain siloed within complex health-care networks, ultimately improving access to specialized care resources.</p>","PeriodicalId":14681,"journal":{"name":"JNCI Cancer Spectrum","volume":" ","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12205850/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144266191","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction to: Neighborhood-level social determinants of health burden among adolescent and young adult cancer patients and impact on overall survival.","authors":"","doi":"10.1093/jncics/pkaf063","DOIUrl":"10.1093/jncics/pkaf063","url":null,"abstract":"","PeriodicalId":14681,"journal":{"name":"JNCI Cancer Spectrum","volume":"9 3","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12204728/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144336586","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Risks of colorectal and extracolonic cancers following colorectal cancer: a systematic review and meta-analysis.","authors":"Ye Kyaw Aung, Ye Zhang, Mark A Jenkins, Aung Ko Win","doi":"10.1093/jncics/pkaf031","DOIUrl":"10.1093/jncics/pkaf031","url":null,"abstract":"<p><strong>Background: </strong>Colorectal cancer survivors face increased risks of developing new primary cancers in colorectum and other anatomical sites. This systematic review aimed to estimate primary colorectal and extracolonic cancers risks following colorectal cancer.</p><p><strong>Methods: </strong>Peer-reviewed articles published before January 2025 were screened across 4 databases to identify studies using population cancer registry reporting standardized incidence ratios (SIRs) of primary cancers following colorectal cancer, compared with the general population. A meta-analysis was conducted to summarize the SIRs, and age-specific cumulative risks of primary cancers following colorectal cancer were estimated using the summarized SIRs and age-, sex-, calendar-, region-, and cancer-specific incidence data.</p><p><strong>Results: </strong>Of 8254 articles identified, 57 were included in meta-analysis. The pooled SIRs (95% confidence interval) for any primary cancer, extracolonic cancer and colorectal cancer were 1.13 (1.06 to 1.20), 1.10 (1.03 to 1.17), and 1.55 (1.33 to 1.77), respectively. Increased risks were also observed for primary cancers of small intestine, ovary, uterus, testes, kidney, female breast, thyroid, and prostate overall, as well as for lung and urinary bladder cancer in recent studies. The cumulative risks of any primary cancer, extracolonic cancer, and colorectal cancer to age 75 years were 38.5%, 31.6%, and 8.24% in Australasia; 33.8%, 30.9%, and 4.77% in North America; 27.4%, 25.6%, and 8.01% in East Asia; and 33.4%, 28.8%, and 4.68% in Europe.</p><p><strong>Conclusion: </strong>Colorectal cancer survivors have an increased risk of subsequent primary cancers, both extracolonic and colorectal, when compared with the general population. These findings underscore the necessity for tailored surveillance and prevention strategies to effectively identify and manage subsequent primary cancers in this population.</p>","PeriodicalId":14681,"journal":{"name":"JNCI Cancer Spectrum","volume":" ","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12086680/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143669867","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Trends in stage-specific prostate cancer incidence by neighborhood socioeconomic status.","authors":"Meenakshi Davuluri, Faith Morley, Michael Tzeng, Bashir Al Hussein Al Awamlh, Jialin Mao, Kevin H Kensler","doi":"10.1093/jncics/pkaf050","DOIUrl":"10.1093/jncics/pkaf050","url":null,"abstract":"<p><p>Changes in screening guidelines have influenced stage at diagnosis for prostate cancer, but it remains unclear whether these trends differ by neighborhood socioeconomic status (SES). Using cancer registry data from the Surveillance, Epidemiology, and End Results program from 2011 to 2020, we estimated age-standardized stage-specific incidence rates and annual percent changes for localized and distant prostate cancer incidence by neighborhood SES quintile and age group. Incidence of localized prostate cancer was highest in higher neighborhood SES areas, while distant prostate cancer rates were highest in areas with lowest neighborhood SES. Annual percent changes in localized prostate cancer incidence were similar by neighborhood SES over the decade, whereas the differences in distant prostate cancer incidence by neighborhood SES diminished over this period. The differing trends in localized and distant prostate cancer incidence by neighborhood SES highlight the importance of equitable access to screening among younger high-risk individuals and improved personalized screening strategies among older men based on health status.</p>","PeriodicalId":14681,"journal":{"name":"JNCI Cancer Spectrum","volume":" ","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12161447/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144110721","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AI meets informed consent: a new era for clinical trial communication.","authors":"Michael Waters","doi":"10.1093/jncics/pkaf028","DOIUrl":"10.1093/jncics/pkaf028","url":null,"abstract":"<p><p>Clinical trials are fundamental to evidence-based medicine, providing patients with access to novel therapeutics and advancing scientific knowledge. However, patient comprehension of trial information remains a critical challenge, as registries like ClinicalTrials.gov often present complex medical jargon that is difficult for the general public to understand. While initiatives such as plain-language summaries and multimedia interventions have attempted to improve accessibility, scalable and personalized solutions remain elusive. This study explores the potential of Large Language Models (LLMs), specifically GPT-4, to enhance patient education regarding cancer clinical trials. By leveraging informed consent forms from ClinicalTrials.gov, the researchers evaluated 2 artificial intelligence (AI)-driven approaches-direct summarization and sequential summarization-to generate patient-friendly summaries. Additionally, the study assessed the capability of LLMs to create multiple-choice question-answer pairs (MCQAs) to gauge patient understanding. Findings demonstrate that AI-generated summaries significantly improved readability, with sequential summarization yielding higher accuracy and completeness. MCQAs showed high concordance with human-annotated responses, and over 80% of surveyed participants reported enhanced understanding of the author's in-house BROADBAND trial. While LLMs hold promise in transforming patient engagement through improved accessibility of clinical trial information, concerns regarding AI hallucinations, accuracy, and ethical considerations remain. Future research should focus on refining AI-driven workflows, integrating patient feedback, and ensuring regulatory oversight. Addressing these challenges could enable LLMs to play a pivotal role in bridging gaps in clinical trial communication, ultimately improving patient comprehension and participation.</p>","PeriodicalId":14681,"journal":{"name":"JNCI Cancer Spectrum","volume":" ","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11964292/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143657178","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The use of large language models to enhance cancer clinical trial educational materials.","authors":"Mingye Gao, Aman Varshney, Shan Chen, Vikram Goddla, Jack Gallifant, Patrick Doyle, Claire Novack, Maeve Dillon-Martin, Teresia Perkins, Xinrong Correia, Erik Duhaime, Howard Isenstein, Elad Sharon, Lisa Soleymani Lehmann, David Kozono, Brian Anthony, Dmitriy Dligach, Danielle S Bitterman","doi":"10.1093/jncics/pkaf021","DOIUrl":"10.1093/jncics/pkaf021","url":null,"abstract":"<p><strong>Background: </strong>Adequate patient awareness and understanding of cancer clinical trials is essential for trial recruitment, informed decision making, and protocol adherence. Although large language models (LLMs) have shown promise for patient education, their role in enhancing patient awareness of clinical trials remains unexplored. This study explored the performance and risks of LLMs in generating trial-specific educational content for potential participants.</p><p><strong>Methods: </strong>Generative Pretrained Transformer 4 (GPT4) was prompted to generate short clinical trial summaries and multiple-choice question-answer pairs from informed consent forms from ClinicalTrials.gov. Zero-shot learning was used for summaries, using a direct summarization, sequential extraction, and summarization approach. One-shot learning was used for question-answer pairs development. We evaluated performance through patient surveys of summary effectiveness and crowdsourced annotation of question-answer pair accuracy, using held-out cancer trial informed consent forms not used in prompt development.</p><p><strong>Results: </strong>For summaries, both prompting approaches achieved comparable results for readability and core content. Patients found summaries to be understandable and to improve clinical trial comprehension and interest in learning more about trials. The generated multiple-choice questions achieved high accuracy and agreement with crowdsourced annotators. For both summaries and multiple-choice questions, GPT4 was most likely to include inaccurate information when prompted to provide information that was not adequately described in the informed consent forms.</p><p><strong>Conclusions: </strong>LLMs such as GPT4 show promise in generating patient-friendly educational content for clinical trials with minimal trial-specific engineering. The findings serve as a proof of concept for the role of LLMs in improving patient education and engagement in clinical trials, as well as the need for ongoing human oversight.</p>","PeriodicalId":14681,"journal":{"name":"JNCI Cancer Spectrum","volume":" ","pages":""},"PeriodicalIF":4.1,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12362247/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143373978","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Re: Structural racism and inequity in cancer clinical trial participation: time for solutions.","authors":"Craig Underhill, Sabe Sabesan, Monica Green","doi":"10.1093/jncics/pkaf013","DOIUrl":"https://doi.org/10.1093/jncics/pkaf013","url":null,"abstract":"","PeriodicalId":14681,"journal":{"name":"JNCI Cancer Spectrum","volume":"9 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12020723/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144002995","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluating patient diversity in early phase clinical trials in Australia through a prospective multicenter nonrandomized cohort study.","authors":"Udit Nindra, Joanne Tang, Jun Hee Hong, Martin Hong, Christina Teng, Joe Wei, Andrew Killen, Adam Cooper, Kate Wilkinson, Weng Ng, Charlotte Lemech, Wei Chua, Abhijit Pal","doi":"10.1093/jncics/pkaf035","DOIUrl":"10.1093/jncics/pkaf035","url":null,"abstract":"<p><strong>Background: </strong>Early phase clinical trials continue to have difficulty with enrolling real-world populations with many minorities being underrepresented. Reasons for this include patient or clinician perception as well as cultural, linguistic, or social barriers. In Australia, there is currently no prospective data in the early phase clinical trial space regarding recruitment of priority populations.</p><p><strong>Methods: </strong>Patient Diversity in Early Phase Clinical Trials was a multicenter, prospective, cohort study involving 2 major early phase clinical trial centers in Sydney, Australia. All participants who were consented to an early phase clinical trial between August 2023 and August 2024 were enrolled. Participants completed a baseline demographic survey, which included cultural and linguistic status, sexual orientation, socioeconomic status, and regional diversity.</p><p><strong>Results: </strong>A total of 114 participants were recruited. Median age was 63 years (range = 25-83 years) with predominance for female participants (52%). No participant reported a nonbinary gender. All participants reported their sexuality as heterosexual, with no LGBTQIA+ participants recruited. A total of 34 (30%) participants were identified as culturally diverse, while 28 (25%) were linguistically diverse. One patient identified as Indigenous Australian. Of the participants, 26% were born overseas, with 44% having at least 1 parent born overseas. The majority were living in households with family members, with 8% of participants living alone.</p><p><strong>Conclusion: </strong>Patient Diversity in Early Phase Clinical Trials is the first prospective study that provides granular description of social, cultural, linguistic, economic, and sexual diversity among early phase clinical trial participants. Certain subgroups are underrepresented, including those with sexual diversity, gender diversity, and Indigenous backgrounds. Ongoing efforts to monitor and promote inclusion of diverse populations in clinical trials are vital.</p>","PeriodicalId":14681,"journal":{"name":"JNCI Cancer Spectrum","volume":" ","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12020725/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143730147","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Tumor localization strategies of multicancer early detection tests: a quantitative assessment.","authors":"Christopher Tyson, Kevin H Li, Xiting Cao, James M O'Brien, Elliot K Fishman, Elizabeth K O'Donnell, Carlos Duran, Vijay Parthasarathy, Seema P Rego, Omair A Choudhry, Tomasz M Beer","doi":"10.1093/jncics/pkaf011","DOIUrl":"10.1093/jncics/pkaf011","url":null,"abstract":"<p><strong>Background: </strong>Multicancer early detection tests may expand cancer screening. Characterizing diagnostic resolution approaches following positive multicancer early detection tests is critical. Two trials employed distinct resolution approaches: a molecular signal to predict tissue of origin and an imaging-based diagnostic strategy. This modeling study characterizes diagnostic journeys and impact in a hypothetical population of average-risk multicancer early detection-eligible patients.</p><p><strong>Methods: </strong>A mathematical expression for diagnostic burden was derived using positive predictive value (PPV), molecular tissue of origin localization accuracy, and numbers of procedures associated with each diagnostic outcome. Imaging-based and molecular tissue of origin-informed strategies were compared. Excess lifetime cancer risk due to futile radiation exposure was estimated using organ-specific diagnostic imaging radiation doses.</p><p><strong>Results: </strong>Across all PPVs and localization performances, a molecular tissue of origin strategy resulted in a higher diagnostic burden (mean = 3.6 [0.445] procedures vs mean = 2.6 [0.100] procedures) for the imaging strategy. Estimated diagnostic burden was higher for molecular tissue of origin in 95.5% of all PPV and tissue of origin accuracy combinations; at least 79% PPV and 90% accuracy would be required for a molecular tissue of origin-informed strategy to be less burdensome than imaging. The maximum rate of excess cancer incidence from radiation exposure for multicancer early detection false-positive results (individuals aged 50-84 years) was 64.6 of 100 000 (annual testing, 99% specificity), 48.5 of 100 000 (biennial testing, 98.5% specificity), and 64.6 of 100 000 (biennial testing, 98% specificity).</p><p><strong>Conclusions: </strong>An imaging-based diagnostic strategy is more efficient than a molecular tissue of origin-informed approach across almost all PPV and tissue of origin accuracy combinations. The use of an imaging-based approach for cancer localization can be efficient and low-risk compared with a molecular-informed approach.</p>","PeriodicalId":14681,"journal":{"name":"JNCI Cancer Spectrum","volume":" ","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11897890/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143032964","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Parental loss at age birth to 21 years and daughters' breast cancer and tumor characteristics.","authors":"Corinna Keeler, Nickilou Y Krigbaum, Barbara Cohn, Piera Cirillo","doi":"10.1093/jncics/pkaf004","DOIUrl":"10.1093/jncics/pkaf004","url":null,"abstract":"<p><strong>Background: </strong>Adverse events in childhood are linked to cancer risk across the life course, but evidence is lacking regarding parental death during childhood and breast cancer characteristics. We investigated whether women who experienced parental loss in childhood have a higher incidence of breast cancer and are at higher risk of aggressive disease.</p><p><strong>Methods: </strong>The Child Health and Development Studies (CHDS) consists of more than 15 000 families that enrolled during mothers' pregnancies between 1959 and 1967; family members were followed for cancer incidence and cause-specific mortality. We constructed an analytical cohort of all live-born CHDS daughters (N = 9169) linked to their parents' cause and date of death. We estimated adjusted hazard ratios of incident breast cancer, disease stage at diagnosis, and tumor hormone receptor expression for parental loss in Cox models adjusted for race, maternal breast cancer, and paternal age. Generalized linear models estimated associations between breast density and parental loss among a subsample of CHDS daughters (n = 610) with available mammography reports.</p><p><strong>Results: </strong>In total, 137 CHDS daughters were diagnosed with breast cancer by age 52 years, and 654 daughters had lost 1 or both parents when they were 21 years of age or younger. Loss of both parents was associated with breast cancer incidence (adjusted hazard ratio =  4.69, 95% CI = 1.68 to 13.04); late-stage disease at diagnosis (adjusted hazard ratio =  9.47, 95% CI = 1.38 to 64.84); and ERBB2 (formerly HER2)-positive, progesterone receptor-negative, and estrogen receptor-negative tumors. Loss of mother or father was associated with ERBB2-positive tumors. Breast density in the premenopause window was associated with loss of a mother or both parents.</p><p><strong>Conclusion: </strong>In a multigenerational cohort with well-defined cancer outcomes and validated cause-of-death data, life-course risk of breast cancer was 4.69 times higher among participants who had lost both parents during childhood. Subanalyses showed that parental loss was associated with late stage at diagnosis and tumor hormone markers of aggressive disease. Parental death during childhood could be added to medical histories to indicate a need for counseling on prevention and early detection of breast cancer.</p>","PeriodicalId":14681,"journal":{"name":"JNCI Cancer Spectrum","volume":" ","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11892429/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143005554","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}