JCO Clinical Cancer Informatics最新文献

{"title":"Safe and Responsible Use of Artificial Intelligence in Health Care: Current Regulatory Landscape and Considerations for Regulatory Policy.","authors":"Alaap Shah, Sekeithia Mitchell, Gary Coad, Dina Michels","doi":"10.1200/CCI-25-00123","DOIUrl":"https://doi.org/10.1200/CCI-25-00123","url":null,"abstract":"<p><p>The integration of artificial intelligence (AI) into health care promises transformative advancements in diagnostics, treatment, and operational efficiency. However, this transformation introduces significant clinical, technical, and socioethical risks. This article examines these emerging risks and analyzes a fragmented landscape of federal, state, and international regulations attempting to govern the development and deployment of AI in health care. It highlights the need for a multifaceted approach, combining robust regulatory frameworks with ethical considerations, and ongoing vigilance from AI developers, health care providers, and policymakers.</p>","PeriodicalId":51626,"journal":{"name":"JCO Clinical Cancer Informatics","volume":"9 ","pages":"e2500123"},"PeriodicalIF":2.8,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144978089","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":"Breast, Cervical, and Colorectal Cancer Screening Among New Jersey Medicaid Enrollees: 2017-2022.","authors":"Ann M Nguyen, Adriana Waldron-Corredor, Feng-Yi Liu, Xiaoling Yun, Jose Nova, Anita Y Kinney, Joel C Cantor, Jennifer Tsui","doi":"10.1200/CCI-25-00055","DOIUrl":"10.1200/CCI-25-00055","url":null,"abstract":"<p><strong>Purpose: </strong>The COVID-19 pandemic disrupted cancer screenings in the United States, with disproportionate impact on health disparity populations. The objective of this study was to examine the impact of the pandemic on routine screening for breast, cervical, and colorectal cancer among Medicaid enrollees.</p><p><strong>Materials and methods: </strong>This study is a retrospective, descriptive analysis to estimate the rate of breast, colorectal, and cervical cancer screenings among Medicaid enrollees age 50-75 years in New Jersey. Secondary enrollment and claims from the 2017-2022 Medicaid Management Information System were used. The results were stratified by screening type and socioeconomic factors. Bivariate analysis assessed between-group differences.</p><p><strong>Results: </strong>Although April 2020 had the lowest screening rates in the 6-year period, rates for all three cancer types rebounded to prepandemic levels by late summer 2020. In 2022, breast cancer screening rates exceeded previous peaks. However, cervical and colorectal screening rates did not resume their prepandemic trajectories. Key findings comparing 2022 with 2019 were (1) across all three cancer screening groups, the younger group (50-64 years) had a higher screening rate than the older group (65-75 years); (2) Hispanic enrollees consistently had the highest screening rates; (3) the screening rate among dually eligible enrollees increased throughout the pandemic; and (4) there was wide screening variation by geographic region.</p><p><strong>Conclusion: </strong>Multilevel, multisectoral approaches, including policy and health system strategies, are critical to addressing gaps in care for Medicaid enrollees. Future efforts should focus on bolstering cervical and colorectal cancer screening rates and ensuring equitable access to cancer screening and treatment.</p>","PeriodicalId":51626,"journal":{"name":"JCO Clinical Cancer Informatics","volume":"9 ","pages":"e2500055"},"PeriodicalIF":2.8,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144790703","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":"Feasibility and Implementation of a Digital Health Intervention Electronic Patient-Reported Outcomes-Based Platform for Telemonitoring Patients With Breast Cancer Undergoing Chemotherapy.","authors":"Daniela Donadon de Oliveira Rodrigues, Bianca Sakamoto Ribeiro Paiva, Domicio Carvalho Lacerda, Sérgio Vicente Serrano, Alessandra Menezes Morelle, Carlos Barrios, Matheus Soares Rocha, Paulo Alfredo Casanova Schulze, Carlos Eduardo Paiva","doi":"10.1200/CCI-25-00018","DOIUrl":"10.1200/CCI-25-00018","url":null,"abstract":"<p><strong>Purpose: </strong>Breast cancer (BC) is a leading cause of morbidity and mortality among women. Symptoms and treatment-related side effects often go undetected during routine follow-ups. Digital health interventions offer promising tools for real-time monitoring and personalized care. We aimed to implement and evaluate the feasibility of a mobile health electronic Patient-Reported Outcomes (ePRO)-based platform for telemonitoring patients with BC undergoing (neo)adjuvant chemotherapy.</p><p><strong>Methods: </strong>This prospective observational study enrolled patients with BC (TNM stages I to III) initiating chemotherapy at Barretos Cancer Hospital in Brazil. Participants were telemonitored using the <i>ThummiOnco</i> platform for 4-6 months, following a standardized protocol. Feasibility was assessed through platform usage, resolution of patient-reported symptoms (according to Common Terminology Criteria for Adverse Events) within 48-72 hours, and health care outcomes, including additional consultations, dose reductions, treatment interruptions/discontinuations, hospitalizations, and mortality. Statistical analysis was performed using descriptive statistics.</p><p><strong>Results: </strong>Between October 2022 and June 2023, 67 eligible patients (median age 51 years) were included, with 62% receiving neoadjuvant chemotherapy. The median number of app accesses per patient was 38, with 6.65 daily symptom reports and 94% adherence. At 48 hours, 67% of patient-reported symptoms were fully resolved, whereas at 72 hours the resolution rate was 75.4%. Regarding resolution by grade, 83% of grade 1, 69.5% of grade 2, and 54.8% of grade 3 symptoms were fully resolved. Complementary consultations were needed for 34 patients. Dose reductions occurred in 10 (14.9%), treatment interruptions/discontinuations in 35 (52.2%), and hospitalizations in seven (10.4%). One patient died from progressive disease.</p><p><strong>Conclusion: </strong>Telemonitoring facilitated early symptom identification and management. Most reports were resolved through the platform, with minimal additional demands on the health care team. Future studies should assess cost-effectiveness and scalability across diverse populations.</p>","PeriodicalId":51626,"journal":{"name":"JCO Clinical Cancer Informatics","volume":"9 ","pages":"e2500018"},"PeriodicalIF":2.8,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144849591","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":"Pragmatic Use of Minimal Common Oncology Data Elements and Observational Medical Outcomes Partnership at an Academic Medical Center.","authors":"Tatyana Sandler, Sarah Manglicmot, Katelyn M Mullen, Neil Shah, John Philip","doi":"10.1200/CCI-25-00231","DOIUrl":"https://doi.org/10.1200/CCI-25-00231","url":null,"abstract":"","PeriodicalId":51626,"journal":{"name":"JCO Clinical Cancer Informatics","volume":"9 ","pages":"e2500231"},"PeriodicalIF":2.8,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144978117","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":"Automated Extraction of Imaging and Pathology Data From Diverse Prostate Cancer Electronic Records.","authors":"John M Culnan, Sergey D Goryachev, John R Bihn, Grace Lee, Daniel C R Chen, Oleg Soloviev, Robert Zwolinski, Karlynn N Dulberger, Nhan V Do, Channing J Paller, Matthew R Cooperberg, Nathanael R Fillmore","doi":"10.1200/CCI-25-00085","DOIUrl":"10.1200/CCI-25-00085","url":null,"abstract":"<p><strong>Purpose: </strong>To develop and validate an algorithm to extract clinically relevant data elements for prostate cancer (PCa) from prostate biopsy reports and magnetic resonance imaging (MRI) reports.</p><p><strong>Patients and methods: </strong>MRI reports and biopsy pathology reports were extracted from a cohort of 1,360,866 patients with PCa in the VA Cancer Registry System or the VA Corporate Data Warehouse, with 155,570 patients having the relevant reports for inclusion. We hand-annotated a sample of these reports, which were used to develop a rule-based natural language processing (NLP) algorithm for extracting Gleason score, positive cores, and total cores taken during biopsy from biopsy pathology reports and Prostate Imaging Reporting and Data System (PI-RADS) score, prostate-specific antigen (PSA) density, prostate volume, and prostate dimensions from MRI reports. Our algorithm was validated on a set of 250 biopsy reports and 250 MRI reports representing 378 patients at 78 VA centers with procedures between 2004 and 2024.</p><p><strong>Results: </strong>Our algorithm performed well across all data elements, demonstrating high F1 scores: Gleason (96.9), PI-RADS (93.7), PSA density (99.5), prostate volume (95.7), and prostate dimensions (93.2), with the percentage of positive cores being greater than or less than 34% (88.4). Error analysis demonstrated that items missed by our algorithm were often explained by unusual or vague wording within the notes or especially complex language.</p><p><strong>Conclusion: </strong>We developed an NLP algorithm and validated that it successfully captures salient information about data elements of interest in PCa research. Reliable extraction of these key data elements will have numerous uses for downstream research in this field.</p>","PeriodicalId":51626,"journal":{"name":"JCO Clinical Cancer Informatics","volume":"9 ","pages":"e2500085"},"PeriodicalIF":2.8,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12352557/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144800884","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":"Step Count, Step Aside: Newer Physical Activity Metrics to Predict Survival in Oncology.","authors":"Sanjit Paturi, Rahul Banerjee","doi":"10.1200/CCI-25-00197","DOIUrl":"10.1200/CCI-25-00197","url":null,"abstract":"","PeriodicalId":51626,"journal":{"name":"JCO Clinical Cancer Informatics","volume":"9 ","pages":"e2500197"},"PeriodicalIF":2.8,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144838566","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":"Elucidating Celecoxib's Preventive Effect in Capecitabine-Induced Hand-Foot Syndrome Using Medical Natural Language Processing.","authors":"Masami Tsuchiya, Yoshimasa Kawazoe, Kiminori Shimamoto, Tomohisa Seki, Shungo Imai, Hayato Kizaki, Emiko Shinohara, Shuntaro Yada, Shoko Wakamiya, Eiji Aramaki, Satoko Hori","doi":"10.1200/CCI-25-00096","DOIUrl":"10.1200/CCI-25-00096","url":null,"abstract":"<p><strong>Purpose: </strong>Capecitabine, an oral anticancer agent, frequently causes hand-foot syndrome (HFS), affecting patients' quality of life and treatment adherence. However, such symptomatic toxicities are often difficult to detect in structured electronic health record (EHR) data. This study primarily aimed to validate a natural language processing (NLP) approach to identifying capecitabine-induced HFS from unstructured clinical text and demonstrate its application in evaluating medication-associated adverse event trends in real-world settings.</p><p><strong>Methods: </strong>We conducted a retrospective cohort study using EHRs from the University of Tokyo Hospital (2004-2021). HFS cases were identified using the MedNERN-CR-JA NLP model. After propensity score matching, we compared capecitabine users with and without celecoxib and assessed time to HFS onset using Cox proportional hazards models. NLP-based HFS detection was validated through manual annotation of aggregated clinical notes. Negative control and sensitivity analyses ensured robustness.</p><p><strong>Results: </strong>Among 44,502 patients with cancer, 669 capecitabine users were analyzed. HFS incidence was significantly higher among capecitabine users (hazard ratio [HR], 1.93 [95% CI, 1.48 to 2.52]; <i>P</i> < .001) compared with nonusers. Celecoxib use showed a suggestive association with a reduced HFS risk (HR, 0.51 [95% CI, 0.24 to 1.07]; <i>P</i> = .073). The NLP model demonstrated high accuracy in identifying HFS, achieving a precision of 0.875, recall of 1.000, and F₁ score of 0.933, based on manual annotation of patient-level clinical notes. Outcome trends remained consistent when using manually annotated HFS case labels instead of NLP-detected events, supporting the method's robustness.</p><p><strong>Conclusion: </strong>These findings demonstrate the effectiveness of NLP in detecting HFS from real-world clinical records. The application to celecoxib-HFS detection illustrates the potential utility of this approach for retrospective safety analysis. Further work is needed to evaluate generalizability across diverse clinical settings.</p>","PeriodicalId":51626,"journal":{"name":"JCO Clinical Cancer Informatics","volume":"9 ","pages":"e2500096"},"PeriodicalIF":2.8,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12341754/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144838565","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":"Assessment of Functional Status of Human Leukocyte Antigen Class I Genes in Cancer Tissues in the Context of Personalized Neoantigen Peptide Vaccine Immunotherapy.","authors":"Vijay G Padul, Nupur Biswas, Mini Gill, Jesus A Perez, Javier J Lopez, Santosh Kesari, Shashanka Ashili","doi":"10.1200/CCI-24-00174","DOIUrl":"10.1200/CCI-24-00174","url":null,"abstract":"<p><strong>Purpose: </strong>Accurate human leukocyte antigen (HLA) typing is an essential step for designing peptide vaccines used in the personalized neoantigen peptide vaccine immunotherapy (PNPVT) in patients with cancer. The reasons for variation in the patient response to PNPVT are yet unknown. One of the reasons could be the somatic changes in the HLA genes in the cancer cells. The objective of the present research was to analyze the somatic status of HLA class I genes in cancer tissue through integrative genomic analysis and to identify high-confidence subset of potentially functional cancer somatic HLA class I genotype relevant to PNPVT.</p><p><strong>Patients and methods: </strong>Whole-exome (paired tumor-normal) and RNAseq (tumor) paired-end sequencing data from 24 patients with cancer were used for the analysis. The genotyping of HLA class I was performed using four HLA typing software tools. To assess the functional status of HLA class I genes in the cancer tissue, we analyzed somatic mutation, HLA gene loss of heterozygosity, and chromosome 6 copy loss status in cancer exome data.</p><p><strong>Results: </strong>Somatic mutations in HLA genes were detected in the tumor data of five patients, and somatic HLA gene loss of heterozygosity was identified in the tumor data of five patients. Complete or partial chromosome 6 copy loss was detected in eight patient samples.</p><p><strong>Conclusion: </strong>The results indicate that HLA class I genes may get affected by somatic changes in cancer tissue, and assessment of the somatic status of the HLA genotype should be performed in the cancer tissues. The results provide robust rational for removal of mutated or lost HLAs from the personalized neoantigen peptide prediction pipeline to potentially increase the efficacy of the PNPVT. Further functional studies are needed to assess the impact of HLA gene mutations/loss on PNPVT outcomes.</p>","PeriodicalId":51626,"journal":{"name":"JCO Clinical Cancer Informatics","volume":"9 ","pages":"e2400174"},"PeriodicalIF":3.3,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12233180/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144555616","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":"Automatic Abstraction of Computed Tomography Imaging Indication Using Natural Language Processing for Evaluation of Surveillance Patterns in Long-Term Lung Cancer Survivors.","authors":"Aparajita Khan, Eunji Choi, Chloe Su, Anna Graber-Naidich, Solomon Henry, Mina L Satoyoshi, Archana Bhat, Allison W Kurian, Su-Ying Liang, Joel Neal, Michael Gould, Ann Leung, Heather A Wakelee, Leah M Backhus, Curtis Langlotz, Julie Wu, Summer S Han","doi":"10.1200/CCI-24-00279","DOIUrl":"10.1200/CCI-24-00279","url":null,"abstract":"<p><strong>Purpose: </strong>Despite its routine use to monitor patients with lung cancer (LC), real-world evaluations of the impact of computed tomography (CT) surveillance on overall survival (OS) have been inconsistent. A major confounder is the absence of imaging indications because patients undergo CT scans for purposes beyond surveillance, like symptom evaluations (eg, cough) linked to poor survival. We propose a novel natural language processing model to predict CT imaging indications (surveillance <i>v</i> others).</p><p><strong>Methods: </strong>We used electronic health records of 585 long-term LC survivors (≥5 years) at Stanford, followed for up to 22 years. Their 3,362 post-5-year CT reports (including 1,672 manually annotated) were used for modeling by integrating structured variables (eg, CT intervals) with key-phrase analysis of radiology reports. Naïve analysis compared OS in patients with CT for any indications (including symptoms) versus those without post-5-year CT, as in previous studies. Using model-predicted indications, we conducted exploratory analyses to compare OS between those with post-5-year surveillance CT and those without.</p><p><strong>Results: </strong>The model showed high discrimination (AUC, 0.86), with key predictors including a longer interval (≥6-month) from the previous CT (odds ratios [OR], 5.50; <i>P</i> < .001) and surveillance-related key phrases (OR, 1.37; <i>P</i> = .03). Propensity-adjusted survival analysis indicated better OS for patients with any post-5-year surveillance CT versus those without (adjusted hazard ratio, 0.60; <i>P</i> = .016). By contrast, no significant survival difference was found (<i>P</i> = .53) between patients with any CT versus those without post-5-year CT.</p><p><strong>Conclusion: </strong>Our model abstracted CT indications from real-world data with high discrimination. Exploratory analyses revealed the obscured imaging-OS association when considering indications, highlighting the model's potential for future real-world studies.</p>","PeriodicalId":51626,"journal":{"name":"JCO Clinical Cancer Informatics","volume":"9 ","pages":"e2400279"},"PeriodicalIF":2.8,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12309515/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144700322","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":"Disparities in Patient Portal Messaging Among Oncology Patients Enrolled in the Patient Portal.","authors":"Jes Alexander, Alexis L Beatty","doi":"10.1200/CCI-24-00234","DOIUrl":"https://doi.org/10.1200/CCI-24-00234","url":null,"abstract":"<p><strong>Purpose: </strong>Previous studies have consistently reported disparities in electronic health record portal enrollment. Among patients enrolled in a portal, it is less clear whether there are disparities in usage. We investigated whether disparities existed in portal usage among enrolled oncology patients regarding both sending portal messages to and receiving messages from oncology providers.</p><p><strong>Methods: </strong>This retrospective cohort study included patients ≥18 years old with cancer who were seen at an urban academic cancer center between January 2011 and February 2025 and enrolled in the patient portal. We developed Cox proportional hazards models for the outcomes of patients sending portal messages to and receiving messages from oncology providers as the first message in a thread. Time measurement began with the first cancer center visit or portal enrollment, whichever was later. Models were adjusted for demographic, socioeconomic, disease, and administrative visit variables.</p><p><strong>Results: </strong>Among 101,678 patients, the median age was 62 years (IQR, 51-71), and 68,527 sent and 42,242 received messages. After adjustment, age ≥50 versus 18-29 years, Latinx and Pacific Islander versus White, single and widowed versus partnered, non-English preferred language, and Medicaid and Medicare versus private insurance were associated with reduced likelihood of sending and receiving messages. Black and American Indian/Alaska Native were associated with reduced likelihood of sending messages. Female provider was associated with increased likelihood of sending and receiving messages. Women were more likely to send messages.</p><p><strong>Conclusion: </strong>Among oncology patients enrolled in the patient portal, disparities existed in sending and receiving portal messages. Given the association of messaging with better survival among oncology patients in previous studies, future studies should determine how best to minimize messaging disparities beyond just addressing disparities in portal enrollment.</p>","PeriodicalId":51626,"journal":{"name":"JCO Clinical Cancer Informatics","volume":"9 ","pages":"e2400234"},"PeriodicalIF":3.3,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144602237","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}