JNCI Cancer Spectrum最新文献

{"title":"Prevalence of symptomatic toxicities for novel therapies in adult oncology trials: a scoping review.","authors":"Amanda L King, Tamara Vasilj, Diane Cooper, Elizabeth Vera, Sefanit Berhanu, Morgan Johnson, Ciara Locke, Bennett Mciver, Ethan Basch, Joseph C Cappelleri, Amylou Dueck, Mark R Gilbert, Lee Jones, Yuelin Li, Lori M Minasian, Bryce B Reeve, Terri S Armstrong, Tito Mendoza","doi":"10.1093/jncics/pkaf036","DOIUrl":"10.1093/jncics/pkaf036","url":null,"abstract":"<p><strong>Background: </strong>Patients' self-report of their symptoms can provide important data for the evaluation of treatment benefit and tolerability of oncology drugs. Contemporary treatment approaches, including immunotherapy and molecular targeted therapies, have unique toxicities based on their novel mechanisms of action. This scoping review aimed to summarize evidence from existing reviews and clinical practice guidelines to examine the type and prevalence of toxicities including symptomatic adverse events (sympAEs) for adult cancer patients to inform clinical care and therapeutic trials.</p><p><strong>Methods: </strong>A systematic search of PubMed, Web of Science, and Embase was performed using predefined eligibility criteria. Thirty-one literature reviews and 3 clinical practice guidelines met inclusion criteria and were selected for review and data abstraction.</p><p><strong>Results: </strong>Findings from this scoping review demonstrated several leading sympAEs that were reported across immunotherapy and targeted therapy drugs, including fatigue, diarrhea, and rash. In addition to these more prevalent sympAEs, there were some less frequently reported class-specific sympAEs, which had potential for significant harm or disability to the patient if not properly identified and treated. Many studies reported toxicities as AEs or syndromes solely using data reported by clinicians without additional self-report from patients.</p><p><strong>Conclusion: </strong>We identified several core sympAEs experienced by patients participating in oncology trials using immunotherapy and targeted therapy agents, which has implications for future trial design and drug labeling. Future cancer trials should assess patient-reported sympAEs based on the identified drug mechanism to inform the tolerability of these newer agents and enhance patient safety during trial participation and clinical care.</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/PMC12092082/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143730149","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":"Ending nuclear weapons, before they end us†.","authors":"Kamran Abbasi, Parveen Ali, Virginia Barbour, Marion Birch, Inga Blum, Peter Doherty, Andy Haines, Ira Helfand, Richard Horton, Kati Juva, Jose F Lapena, Robert Mash, Olga Mironova, Arun Mitra, Carlos Monteiro, Elena N Naumova, David Onazi, Tilman Ruff, Peush Sahni, James Tumwine, Carlos Umaña, Paul Yonga, Chris Zielinski","doi":"10.1093/jncics/pkaf044","DOIUrl":"10.1093/jncics/pkaf044","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/PMC12085997/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144093861","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":"Treatment strategies for triple-negative primary breast cancer in older women: a systematic review.","authors":"Buraq Ahmed, Qutaiba Al-Khames Aga, Kwok-Leung Cheung, Jana de Boniface, Michael Gnant, Maria-Joao Cardoso, Emad Rakha, Thiraviyam Elumalai, Nadia Harbeck, Orit Kaidar-Person, Amit Agrawal","doi":"10.1093/jncics/pkaf049","DOIUrl":"10.1093/jncics/pkaf049","url":null,"abstract":"<p><strong>Background: </strong>Although the relative proportion of triple-negative breast cancer decreases with age, its prevalence is rising with an aging population. This study examined real-world treatment practices, whether age in older women with triple-negative breast cancer affects therapy and outcomes, focusing on the potentially curable nature of early-stage triple-negative breast cancer.</p><p><strong>Methods: </strong>A Preferred Reporting Items for Systematic Reviews and Meta-Analyses, PRISMA-compliant search using population, intervention, comparison, outcomes criteria identified literature from 2014 to 2023 across 5 databases (MEDLINE, Embase, PubMed, Web of Science, and Scopus), focusing on women aged 65 years and older with early-stage triple-negative breast cancer.</p><p><strong>Results: </strong>From 7171 records, 37 studies were included. Older women with triple-negative breast cancer exhibited less aggressive features, including lower Ki67, higher androgen receptor, and higher Bcl2 expression. Breast-conserving surgery with radiation therapy (RT) was associated with improved overall survival and breast cancer-specific survival, with fewer recurrences compared with mastectomy with or without RT. Older women with triple-negative breast cancer were more likely to receive RT than systemic therapy, and the lack of RT correlated with worse outcomes. Multivariate analyses showed that systemic treatment improved 5-year overall survival and breast cancer-specific survival. Overall, outcomes did not show significant differences between women aged 70 years and older and women younger than 70 years at a median follow-up of 46 months.</p><p><strong>Conclusions: </strong>The lack of overall outcome improvements for older women with triple-negative breast cancer following treatment may not solely be due to absent targetable receptors because the intrinsic biology in older patients may be relatively favorable. Instead, treatment selection biases against active treatment due to age-related factors may contribute substantially. Treatment decisions should be biology based and guided by a multidisciplinary, holistic, and patient-centered approach that carefully considers comorbidities, functional status, social support, and patient preferences.</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/PMC12199755/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144078182","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":"Accuracy of self-reported exam indications for breast cancer screening.","authors":"Erin J Aiello Bowles, Hongyuan Gao, Lynn E Fleckenstein, Perla Bravo, Michael G Nash, Bryan Comstock, Chris Neslund-Dudas, Jin Mou, Larry G Kessler","doi":"10.1093/jncics/pkaf046","DOIUrl":"10.1093/jncics/pkaf046","url":null,"abstract":"<p><p>We validated updated National Health Interview Survey questions on mammography indications compared with electronic health records (EHRs). We asked 244 Kaiser Permanente Washington members ages 40-74 years and eligible for breast cancer screening to self-report their most recent mammogram reason by using a series of new hierarchical yes/no questions. We first asked if they had the mammogram because of a health problem, then as a follow-up test, and last for screening. We compared self-reported reasons with 2 EHR datasets: procedure/diagnostic codes and radiologist-defined indications. Self-reported exams for a health problem had 89.2% agreement with codes and 92.2% agreement with radiologist-defined indications. Self-reported exams for follow-up had 87.5% agreement with codes and 89.3% agreement with radiologist-defined indications. Self-reported exams for screening had 91.4% agreement with codes and 95.7% agreement with radiologist-defined indications. Self-reported mammogram indications have good agreement with procedure/diagnostic codes and radiologist-reported indications, when asked using this novel hierarchical approach.</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/PMC12124912/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143967156","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":"Persistent prescription opioid use and all-cause mortality following the first-year breast cancer survivorship.","authors":"Rulin C Hechter, Lie Hong Chen, Jiaxiao Shi, Zheng Gu, Moira Brady-Rogers, Rowan T Chlebowski, Reina Haque","doi":"10.1093/jncics/pkaf060","DOIUrl":"10.1093/jncics/pkaf060","url":null,"abstract":"<p><strong>Background: </strong>Harm associated with persistent opioid use beyond the first-year intensive cancer treatment is underinvestigated in cancer survivors. We examined rates and risk factors for persistent opioid use and all-cause mortality after the first-year breast cancer survivorship.</p><p><strong>Methods: </strong>This retrospective cohort study used electronic health record data from Kaiser Permanente Southern California for women diagnosed with a nonmetastatic breast cancer between 2009 and 2019 who filled 2 or more opioid prescriptions. Rates of persistent opioid use were estimated from first-year survivorship through December 31, 2021. Rate ratios (RRs) and 95% confidence intervals (CIs) for factors associated with persistent use were estimated using a multivariable Poisson regression model. Hazard ratios (HRs) for all-cause mortality associated with persistent opioid use were estimated using multivariable Cox regression models.</p><p><strong>Results: </strong>Of 14 347 eligible individuals (mean [SD] age = 61.9 [12.5]), 2285 (15.9%) developed persistent opioid use, with an incident rate of 25.5 per 1000 person-years. Risk factors included older age (≥65 vs < 65 years: RR = 1.63, 95% CI = 1.24 to 2.14), smoking (current: 1.89, 1.68 to 2.13; former: 1.30, 1.20 to 1.41), baseline comorbidities (Elixhauser Comorbidity Index 5+ vs 0: 1.70, 1.29 to 2.24), and substance use disorders (1.58, 1.43 to 1.74). All-cause mortality was doubled among individuals with persistent use (51.6, 48.0 to 55.6 per 1000 person-years) than in those without (25.3, 24.2 to 26.4). Persistent use was associated with an increased all-cause mortality (adjusted HR = 1.84, 1.66 to 2.04).</p><p><strong>Conclusions: </strong>Persistent opioid use was common in breast cancer survivors and associated with increased mortality. Further research is needed to explore factors that may be contributing to increased mortality.</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/PMC12205851/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144274852","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":"Associations between early tumor shrinkage/depth of response and survival from the ARCAD database.","authors":"Hideaki Bando, Yuriko Takeda, Toshihiro Misumi, Tomomi Nishikawa, Masashi Wakabayashi, Kentaro Yamazaki, Eiji Oki, Jean-Yves Douillard, Cornelis J A Punt, Miriam Koopman, Eric Van Cutsem, Carsten Bokemeyer, Alan P Venook, Heinz-Josef Lenz, Yoshihiko Maehara, Thierry Andre, Qian Shi, Aimery de Gramont, Takayuki Yoshino","doi":"10.1093/jncics/pkaf042","DOIUrl":"10.1093/jncics/pkaf042","url":null,"abstract":"<p><strong>Background: </strong>Early tumor shrinkage and depth of response have emerged as potential prognostic indicators in metastatic colorectal cancer (CRC). However, their associations with overall survival, progression-free survival (PFS), and postprogression survival in patients receiving anti-epidermal growth factor receptor (EGFR) antibodies or bevacizumab remain unclear.</p><p><strong>Methods: </strong>We analyzed 3219 treatment-naive patients with RAS wild-type metastatic CRC from 8 randomized studies (CRYSTAL, OPUS, PRIME, CAIRO2, CALGB80405, WJOG4407G, ATOM, PARADIGM) in the Aid and Research in Digestive Cancerology database. Early tumor shrinkage was defined as a 20% or more reduction in tumor size at 8 ± 2 weeks, whereas depth of response was assessed by maximum tumor shrinkage at nadir. Cox regression models evaluated the associations of early tumor shrinkage and depth of response with overall survival, PFS, and postprogression survival, adjusting for confounders. A 2-sided test was conducted with a significance level of .05.</p><p><strong>Results: </strong>Early tumor shrinkage and depth of response substantially stratified overall survival, PFS, and postprogression survival outcomes across all treatment groups. Early tumor shrinkage positivity was associated with improved overall survival, PFS, and postprogression survival in anti-EGFR and bevacizumab-based therapies, with a trend toward better outcomes in the anti-EGFR group. The depth of response analysis revealed optimal cutoff values of 0.55 for anti-EGFR-based therapy and 0.47 for bevacizumab-based therapy to achieve a median overall survival of approximately 32 months.</p><p><strong>Conclusions: </strong>Early tumor shrinkage and depth of response serve as valuable prognostic markers in RAS wild-type metastatic CRC, particularly for patients treated with anti-EGFR antibodies. These findings highlight the potential role of early tumor shrinkage and depth of response in guiding treatment strategies and improving outcomes for patients with CRC.</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/PMC12159729/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144024309","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":"Accelerometer-measured physical activity, sedentary behavior, and mortality among cancer survivors: the Women's Health Accelerometry Collaboration.","authors":"Eric T Hyde, Kelly R Evenson, Gretchen E Bandoli, Jingjing Zou, Noe C Crespo, Humberto Parada, Michael J LaMonte, Annie Green Howard, Steve Nguyen, Meghan B Skiba, Tracy E Crane, Marcia L Stefanick, I-Min Lee, Andrea Z LaCroix","doi":"10.1093/jncics/pkaf034","DOIUrl":"10.1093/jncics/pkaf034","url":null,"abstract":"<p><strong>Background: </strong>Data on prospective associations of accelerometer-measured physical activity, sedentary behavior, and mortality among cancer survivors are lacking. Our study examined accelerometer-measured daily physical activity (including light, moderate to vigorous, total, and steps), sedentary behavior (sitting time and mean bout duration), and mortality among cancer survivors in the Women's Health Accelerometry Collaboration.</p><p><strong>Methods: </strong>Postmenopausal women in the Collaboration who reported a cancer diagnosis at least 1 year prior to wearing an ActiGraph GT3X+ device on the hip for at least 4 of 7 days from 2011 to 2015 were included. Outcomes included all-cause, cancer-related, and cardiovascular disease (CVD)-related mortality. Covariate-adjusted Cox regression estimated hazard ratios (HRs) and 95% CIs for each physical activity and sedentary behavior measure in association with mortality.</p><p><strong>Results: </strong>Overall, 2479 cancer survivors (mean [SD] age, 74.2 [6.7] years) were followed up for 8.3 years. For all-cause mortality (n = 594 cases), every 78.1 minutes per day in light physical activity, 96.5 minutes per day in total physical activity, 102.2 minutes per day in sitting time, and 4.8 minutes in a sitting bout duration had hazard ratios of 0.92 (95% CI = 0.84 to 1.01), 0.89 (95% CI = 0.80 to 0.98), 1.12 (95% CI = 1.02 to 1.24), and 1.04 (95% CI = 0.96 to 1.12), respectively. Linear associations for cancer mortality (n = 168) and CVD mortality (n = 109) were not statistically significant, except for steps (hazard ratio per 2469 steps/d = 0.66, 95% CI = 0.45 to 0.96) and sitting time (hazard ratio = 1.30, 95% CI = 1.02 to 1.67) for CVD mortality. Nonlinear associations showed benefits of moderate to vigorous physical activity (for all-cause and CVD mortality) and steps (all-cause mortality only) maximized at approximately 60 minutes per day and 5000-6000 steps per day, respectively.</p><p><strong>Conclusions: </strong>Among postmenopausal cancer survivors, higher physical activity and lower sedentary behavior was associated with reduced hazards of all-cause and CVD mortality.</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/PMC12062960/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143730145","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 mediating role of physical activity on cognitive disparities in cancer survivors.","authors":"Jaimi L Allen, Laura Q Rogers, Michelle Y Martin, Benjamin C Amick","doi":"10.1093/jncics/pkaf023","DOIUrl":"10.1093/jncics/pkaf023","url":null,"abstract":"<p><p>This study examined the association of physical activity (PA) with cognitive difficulties (CD) and education, income, poverty, and age among cancer survivors (CS) using data from the 2020 National Health Interview Survey. Causal mediation analysis was tested using the bootstrapping method to examine associations between PA, cognitive difficulties, and other sociodemographic characteristics. Results showed statistically significant disparities in both CD and physical inactivity among CS with low education, low income, high poverty, and certain age categories. Health disparities related to CD based on race/ethnicity, sex, and age were also identified. Physical activity mediated the relationship between CD and education, income, poverty, and age. Future research is needed to gain deeper insight into the mechanisms of PA-induced health benefits and to develop specific PA prescription guidelines in the subgroups at risk for CD.</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/PMC12042741/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143556891","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":"Gut microbiome in colorectal cancer: metagenomics from bench to bedside.","authors":"Amir Torshizi Esfahani, Nikta Zafarjafarzadeh, Fatemeh Vakili, Anahita Bizhanpour, Amirhesam Mashaollahi, Bita Karimi Kordestani, Mahdieh Baratinamin, Somayeh Mohammadpour","doi":"10.1093/jncics/pkaf026","DOIUrl":"10.1093/jncics/pkaf026","url":null,"abstract":"<p><p>Colorectal cancer (CRC) is a major global health challenge. Emerging research highlights the pivotal role of the gut microbiota in influencing CRC risk, progression, and treatment response. Metagenomic approaches, especially high-throughput shotgun sequencing, have provided unprecedented insights into the intricate connections between the gut microbiome and CRC. By enabling comprehensive taxonomic and functional profiling, metagenomics has revealed microbial signatures, activities, and biomarkers associated with colorectal tumorigenesis. Furthermore, metagenomics has shown a potential to guide patient stratification, predict treatment outcomes, and inform microbiome-targeted interventions. Despite remaining challenges in multi-omics data integration, taxonomic gaps, and validation across diverse cohorts, metagenomics has propelled our comprehension of the intricate gut microbiome-CRC interplay. This review underscores the clinical relevance of microbial signatures as potential diagnostic and prognostic tools in CRC. Furthermore, it discusses personalized treatment strategies guided by this omics' approach.</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/PMC12105612/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143567148","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":"Deep learning analysis of hematoxylin and eosin-stained benign breast biopsies to predict future invasive breast cancer.","authors":"Monjoy Saha, Mustapha Abubakar, Ruth M Pfeiffer, Thomas E Rohan, Máire A Duggan, Kathryn Richert-Boe, Jonas S Almeida, Gretchen L Gierach","doi":"10.1093/jncics/pkaf037","DOIUrl":"10.1093/jncics/pkaf037","url":null,"abstract":"<p><strong>Background: </strong>Benign breast disease is an important risk factor for breast cancer development. In this study, we analyzed hematoxylin and eosin-stained whole-slide images from diagnostic benign breast disease biopsies using different deep learning approaches to predict which individuals would subsequently developed breast cancer (cases) or would not (controls).</p><p><strong>Methods: </strong>We randomly divided cases and controls from a nested case-control study of 946 women with benign breast disease into training (331 cases, 331 control individuals) and test (142 cases, 142 control individuals) groups. We employed customized VGG-16 and AutoML machine learning models for image-only classification using whole-slide images, logistic regression for classification using only clinicopathological characteristics, and a multimodal network combining whole-slide images and clinicopathological characteristics for classification.</p><p><strong>Results: </strong>Both image-only (area under the receiver operating characteristic curve [AUROC] = 0.83 [SE = 0.001] and 0.78 [SE = 0.001] for customized VGG-16 and AutoML models, respectively) and multimodal (AUROC = 0.89 [SE = 0.03]) networks had high discriminatory accuracy for breast cancer. The clinicopathological-characteristics-only model had the lowest AUROC (0.54 [SE = 0.03]). In addition, compared with the customized VGG-16 model, which performed better than the AutoML model, the multimodal network had improved accuracy (AUROC = 0.89 [SE = 0.03] vs 0.83 [SE = 0.02]), sensitivity (AUROC = 0.93 [SE = 0.04] vs 0.83 [SE = 0.003]), and specificity (AUROC = 0.86 [SE = 0.03] vs 0.84 [SE = 0.003]).</p><p><strong>Conclusion: </strong>This study opens promising avenues for breast cancer risk assessment in women with benign breast disease. Integrating whole-slide images and clinicopathological characteristics through a multimodal approach substantially improved predictive model performance. Future research will explore deep learning techniques to understand benign breast disease progression to invasive breast cancer.</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/PMC12105608/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143803171","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}