JCO Clinical Cancer Informatics最新文献

{"title":"Unsupervised Large Language Models to Identify Topics in Cancer Center Patient Portal Messages.","authors":"Ji Hyun Chang, Amir Ashraf-Ganjouei, Isabel Friesner, Ryzen Benson, Travis Zack, Sumi Sinha, Jason Chan, Steve Braunstein, Amy Lin, Lisa Singer, Julian C Hong","doi":"10.1200/CCI-25-00102","DOIUrl":"10.1200/CCI-25-00102","url":null,"abstract":"<p><strong>Purpose: </strong>The increasing use of patient portal messages has enhanced patient-provider communication. However, the high volume of these messages has also contributed to physician burnout.</p><p><strong>Methods: </strong>Patient-generated portal messages sent to a single cancer center from 2011 to 2023 were extracted. BERTopic, a natural language processing topic modeling technique based on large language models, was optimized. For further categorization, the topic words were labeled using GPT-4, followed by review by two oncologists. Uniform Manifold Approximation and Projection was used for dimensionality reduction and visualizing topics. Message volume changes over time were assessed using a Student's <i>t</i> test.</p><p><strong>Results: </strong>A total of 2,280,851 messages were analyzed. The monthly average number of messages increased from 2,071 in 2012 to 43,430 in 2022 (<i>P</i> < .001). There was a significant rise in message volume after the COVID-19 pandemic, with a posterior probability of a causal effect of 96.4% (<i>P</i> = .04). Scheduling-related messages were the most frequent across departments, whereas symptoms and health concerns were second or third most common topics. In medical oncology and surgical oncology, topics on prescriptions and medications were more common compared with radiation oncology and gynecologic oncology. Despite concurrent institutional changes in self-scheduling systems, scheduling-related messages did not decrease over time.</p><p><strong>Conclusion: </strong>The substantial increase in patient portal messages, particularly scheduling-related inquiries, underscores the need for streamlined communication to reduce the burden on health care providers. These findings highlight the need for strategies to manage message volume and mitigate physician burnout, laying groundwork for artificial intelligence-driven future triage systems to improve message management and patient care.</p>","PeriodicalId":51626,"journal":{"name":"JCO Clinical Cancer Informatics","volume":"9 ","pages":"e2500102"},"PeriodicalIF":2.8,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12490804/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145208048","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":"OncovigIA: Artificial Intelligence for Early Lung Cancer Detection and Referral in a Chilean Public Hospital.","authors":"Jose Peña, Sebastián Santana, Juan Cristobal Morales, Natalie Pinto, Mariano Suárez, Carola Sánchez, Juan Carlos Opazo, Rodrigo Villarroel, Claudio Montenegro, Bruno Nervi, Richard Weber","doi":"10.1200/CCI-25-00035","DOIUrl":"https://doi.org/10.1200/CCI-25-00035","url":null,"abstract":"<p><strong>Purpose: </strong>Lung cancer is a leading cause of death in Chile, where late-stage diagnoses and high mortality rates prevail. Here, we describe the development of <i>OncovigIA</i>, a novel digital tool powered by natural language processing that enhances the identification of potential lung cancer cases by surveilling computed tomography (CT) reports in a large public Hospital in Santiago, Chile.</p><p><strong>Materials and methods: </strong>We combined natural language processing and large language models with state-of-the-art machine learning techniques and approaches to treat unbalanced data sets and determine the best solution to implement in <i>OncovigIA</i>. Focusing on key sections of the reports and using various machine learning models, including a balanced Random Forest, the tool achieved high performance with 0.90 accuracy and 0.84 F1-score on the test set.</p><p><strong>Results: </strong>When applied to 13,326 CT chest reports from 2022, it successfully identified 377 CTs of patients with suspected lung cancer previously undetected and not managed by the multidisciplinary local lung cancer team.</p><p><strong>Conclusion: </strong>This study underscores the potential of artificial intelligence in early cancer detection and highlights the importance of its integration into local health care ecosystems. By promptly increasing the number of patients referred for specialized management, the tool <i>OncovigIA</i> offers a promising path toward improving lung cancer survival rates in Chile and beyond. Moreover, this article provides avenues for its broader implementation, extending it to other cancer types and/or health care-related texts for continuous surveillance, aiming at the early referral and treatment of cancer in low-resource settings.</p>","PeriodicalId":51626,"journal":{"name":"JCO Clinical Cancer Informatics","volume":"9 ","pages":"e2500035"},"PeriodicalIF":2.8,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145214463","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":"Mitigating Ethical Issues for Large Language Models in Oncology: A Systematic Review.","authors":"Shuang Zhou, Xingyi Liu, Zidu Xu, Zaifu Zhan, Meijia Song, Jun Wang, Shiao Liu, Hua Xu, Rui Zhang","doi":"10.1200/CCI-25-00076","DOIUrl":"10.1200/CCI-25-00076","url":null,"abstract":"<p><strong>Purpose: </strong>Large language models (LLMs) have demonstrated remarkable versatility in oncology applications, such as cancer staging and survival analysis. Despite their potential, ethical concerns such as data privacy breaches, bias in training data, lack of transparency, and risks associated with erroneous outputs pose significant challenges to their adoption in high-stakes oncology settings. Therefore, we aim to explore the ethical challenges associated with LLM-based applications in oncology and evaluate emerging techniques designed to address these issues.</p><p><strong>Methods: </strong>Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses framework, a systematic review was conducted to evaluate publications related to ethical issues of LLMs in oncology across eight academic databases (eg, PubMed, Web of Science, and Embase) between January 1, 2019, and December 31, 2024.</p><p><strong>Results: </strong>The search retrieved 4,319 published articles, of which 65 publications were preserved and included in our analysis. We identified six prevalent ethical challenges in oncology, including trust, equity, privacy, transparency, nonmaleficence, and accountability. We then evaluated emerging technical solutions to mitigate ethical challenges and summarized evaluation metrics used to assess these solutions' effectiveness.</p><p><strong>Conclusion: </strong>This review provides actionable recommendations for responsibly deploying LLMs in oncology, ensuring adherence to ethical guidelines, and fostering improved patient outcomes. By bridging technical and clinical perspectives, this review offers a foundational framework for advancing ethical artificial intelligence applications in oncology and highlights areas for future research.</p>","PeriodicalId":51626,"journal":{"name":"JCO Clinical Cancer Informatics","volume":"9 ","pages":"e2500076"},"PeriodicalIF":2.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145139554","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":"Enhancing Oncology-Specific Question Answering With Large Language Models Through Fine-Tuned Embeddings With Synthetic Data.","authors":"Kun-Han Lu, Sina Mehdinia, Kingson Man, Chi Wah Wong, Allen Mao, Zahra Eftekhari","doi":"10.1200/CCI-25-00011","DOIUrl":"https://doi.org/10.1200/CCI-25-00011","url":null,"abstract":"<p><strong>Purpose: </strong>The recent advancements of retrieval-augmented generation (RAG) and large language models (LLMs) have revolutionized the extraction of real-world evidence from unstructured electronic health records (EHRs) in oncology. This study aims to enhance RAG's effectiveness by implementing a retriever encoder specifically designed for oncology EHRs, with the goal of improving the precision and relevance of retrieved clinical notes for oncology-related queries.</p><p><strong>Methods: </strong>Our model was pretrained with more than six million oncology notes from 209,135 patients at City of Hope. The model was subsequently fine-tuned into a sentence transformer model using 12,371 query-passage training pairs. Specifically, the passages were obtained from actual patient notes, whereas the query was synthesized by an LLM. We evaluated the retrieval performance of our model by comparing it with six widely used embedding models on 50 oncology questions across 10 categories based on Normalized Discounted Cumulative Gain (NDCG), Precision, and Recall.</p><p><strong>Results: </strong>In our test data set comprising 53 patients, our model exceeded the performance of the runner-up model by 9% for NDCG (evaluated at the top 10 results), 7% for Precision (top 10), and 6% for Recall (top 10). Our model showed exceptional retrieval performance across all metrics for oncology-specific categories, including biomarkers assessed, current diagnosis, disease status, laboratory results, tumor characteristics, and tumor staging.</p><p><strong>Conclusion: </strong>Our findings highlight the effectiveness of pretrained contextual embeddings and sentence transformers in retrieving pertinent notes from oncology EHRs. The innovative use of LLM-synthesized query-passage pairs for data augmentation was proven to be effective. This fine-tuning approach holds significant promise in specialized fields like health care, where acquiring annotated data is challenging.</p>","PeriodicalId":51626,"journal":{"name":"JCO Clinical Cancer Informatics","volume":"9 ","pages":"e2500011"},"PeriodicalIF":2.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145006898","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":"Erratum: 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-25-00256","DOIUrl":"https://doi.org/10.1200/CCI-25-00256","url":null,"abstract":"","PeriodicalId":51626,"journal":{"name":"JCO Clinical Cancer Informatics","volume":"9 ","pages":"e2500256"},"PeriodicalIF":2.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145031163","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":"Hybrid ReGex and Natural Language Inference Model as a Zero-Shot Classifier for Extracting Data From Medical Reports.","authors":"Nicolas Wagneur, Olivier Capitain, Stéphane Supiot, Florent Le Borgne, François Bocquet, Mario Campone, Tanguy Perennec","doi":"10.1200/CCI-25-00130","DOIUrl":"https://doi.org/10.1200/CCI-25-00130","url":null,"abstract":"<p><strong>Purpose: </strong>This study presents a new method based on regular expressions (ReGex) and artificial intelligence for extracting relevant medical data from clinical reports. This hybrid approach is designed to address the limitations of each technique. The pipeline is evaluated for its effectiveness in extracting key clinical information from prostate cancer medical reports.</p><p><strong>Methods: </strong>We developed a hybrid pipeline that combines ReGex for initial data extraction with a Natural Language Inference model for classification. This approach was retrospectively applied to 1,000 reports randomly selected among all consultation reports of patients with prostate cancer treated at the institute, focusing on identifying key clinical information such as rectal bleeding, dysuria, pollakiuria, and hematuria. The model's performance was evaluated using precision, recall, accuracy, F1-score, and Cohen's kappa coefficient.</p><p><strong>Results: </strong>The pipeline demonstrated high performance, with precision scores ranging from 0.778 to 0.954 and recall consistently high at 0.920 to 1.00. F1-scores indicated balanced accuracy across symptoms, and Cohen's kappa values (0.871 to 0.951) reflected strong agreement with physician-labeled data.</p><p><strong>Conclusion: </strong>The proposed pipeline is both efficient and fast while being computationally lightweight. It achieves high accuracy in extracting medical data from clinical reports, making it an effective and practical tool for clinical research and health care applications.</p>","PeriodicalId":51626,"journal":{"name":"JCO Clinical Cancer Informatics","volume":"9 ","pages":"e2500130"},"PeriodicalIF":2.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145126390","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":"Enhancing Readability of Lay Abstracts and Summaries for Urologic Oncology Literature Using Generative Artificial Intelligence: BRIDGE-AI 6 Randomized Controlled Trial.","authors":"Conner Ganjavi, Ethan Layne, Francesco Cei, Karanvir Gill, Vasileios Magoulianitis, Andre Abreu, Mitchell Goldenberg, Mihir M Desai, Inderbir Gill, Giovanni E Cacciamani","doi":"10.1200/CCI-25-00042","DOIUrl":"10.1200/CCI-25-00042","url":null,"abstract":"<p><strong>Purpose: </strong>To evaluate a generative artificial intelligence (GAI) framework for creating readable lay abstracts and summaries (LASs) of urologic oncology research, while maintaining accuracy, completeness, and clarity, for the purpose of assessing their comprehension and perception among patients and caregivers.</p><p><strong>Methods: </strong>Forty original abstracts (OAs) on prostate, bladder, kidney, and testis cancers from leading journals were selected. LASs were generated using a free GAI tool, with three versions per abstract for consistency. Readability was compared with OAs using validated metrics. Two independent reviewers assessed accuracy, completeness, and clarity and identified AI hallucinations. A pilot study was conducted with 277 patients and caregivers randomly assigned to receive either OAs or LASs and complete comprehension and perception assessments.</p><p><strong>Results: </strong>Mean GAI-generated LAS generation time was <10 seconds. Across 600 sections generated, readability and quality metrics were consistent (<i>P</i> > .05). Quality scores ranged from 85% to 100%, with hallucinations in 1% of sections. The best test showed significantly better readability (68.9 <i>v</i> 25.3; <i>P</i> < .001), grade level, and text metrics compared with the OA. Methods sections had slightly lower accuracy (85% <i>v</i> 100%; <i>P</i> = .03) and trifecta achievement (82.5% <i>v</i> 100%; <i>P</i> = .01), but other sections retained high quality (≥92.5%; <i>P</i> > .05). GAI-generated LAS recipients scored significantly better in comprehension and most perception-based questions (<i>P</i> < .001) with LAS being the only consistently significant predictor (<i>P</i> < .001).</p><p><strong>Conclusion: </strong>GAI-generated LASs for urologic oncology research are highly readable and generally preserve the quality of the OAs. Patients and caregivers demonstrated improved comprehension and more favorable perceptions of LASs compared with OAs. Human oversight remains essential to ensure the accurate, complete, and clear representations of the original research.</p>","PeriodicalId":51626,"journal":{"name":"JCO Clinical Cancer Informatics","volume":"9 ","pages":"e2500042"},"PeriodicalIF":2.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145034690","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":"Clinician's Artificial Intelligence Checklist and Evaluation Questionnaire: Tools for Oncologists to Assess Artificial Intelligence and Machine Learning Models.","authors":"Nadia S Siddiqui, Yazan Bouchi, Syed Jawad Hussain Shah, Saeed Alqarni, Suraj Sood, Yugyung Lee, John Park, John Kang","doi":"10.1200/CCI-25-00067","DOIUrl":"https://doi.org/10.1200/CCI-25-00067","url":null,"abstract":"<p><p>Advancements in oncology are accelerating in the fields of artificial intelligence (AI) and machine learning. The complexity and multidisciplinary nature of oncology necessitate a cautious approach to evaluating AI models. The surge in development of AI tools highlights a need for organized evaluation methods. Currently, widely accepted guidelines are aimed at developers and do not provide necessary technical background for clinicians. Additionally, published guides introducing clinicians to AI in medicine often lack user-friendly evaluation tools or lack specificity to oncology. This paper provides background on model development and proposes a yes/no checklist and questionnaire designed to help oncologists effectively assess AI models. The yes/no checklist is intended to be used as a more efficient scan of whether the model conforms to published best standards. The open-ended questionnaire is intended for a more in-depth survey. The checklist and the questionnaire were developed by clinical and AI researchers. Initial discussions identified broad domains, gradually narrowing to model development points relevant to clinical practice. The development process included two literature searches to align with current best practices. Insights from 24 articles were integrated to refine the questionnaire and the checklist. The developed tools are intended for use by clinicians in the field of oncology looking to evaluate AI models. Cases of four AI applications in oncology are analyzed, demonstrating utility in real-world scenarios and enhancing case-based learning for clinicians. These tools highlight the interdisciplinary nature of effective AI integration in oncology.</p>","PeriodicalId":51626,"journal":{"name":"JCO Clinical Cancer Informatics","volume":"9 ","pages":"e2500067"},"PeriodicalIF":2.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145082288","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":"Artificial Intelligence-Based Model Exploiting Hematoxylin and Eosin Images to Predict Rare Gene Mutations in Patients With Lung Adenocarcinoma.","authors":"Peiling Yu, Weixing Chen, Nan Liu, Yang Yu, Hongyu Guo, Yinan Yuan, Weilin Guo, Yini Alatan, Jinming Zhao, Hongbo Su, Siru Nie, Xiaoyu Cui, Yuan Miao","doi":"10.1200/CCI-25-00093","DOIUrl":"10.1200/CCI-25-00093","url":null,"abstract":"<p><strong>Purpose: </strong>Accurately identifying gene mutations in lung cancer is crucial for treatment, while molecular diagnostic methods are time-consuming and complex. This study aims to develop an advanced deep learning model to address this issue.</p><p><strong>Methods: </strong>In this study, the ResNeXt101 model framework was established to predict the gene mutation status in lung adenocarcinoma. The model was trained and validated using data from two cohorts: cohort 1, comprising 144 patients from the First Affiliated Hospital of China Medical University, and cohort 2, which includes 69 patients from the The Cancer Genome Atlas-Lung Adenocarcinoma public database. The model was trained and validated on the two data sets, respectively, and they served as external test sets for each other to further verify the performance of the model. Additionally, we tested the trained model on a metastatic cancer data set, which included metastases to organs outside the lungs. The performance of the model was evaluated using the AUC, accuracy, precision, recall, and F1 score.</p><p><strong>Results: </strong>In cohort 1, the model achieved an AUC ranging from 0.93 to 1. In the external test on cohort 2, it performed well in predicting five of the six genes (AUC = 0.85-1). When tested on the metastatic cancer data set, it successfully predicted mutations of three of the six genes (AUC = 0.72-0.80).</p><p><strong>Conclusion: </strong>The artificial intelligence model developed in this study has a high accuracy in predicting gene mutations in lung adenocarcinoma, which is conducive to improving the management of patients with lung adenocarcinoma and promoting precision medicine.</p>","PeriodicalId":51626,"journal":{"name":"JCO Clinical Cancer Informatics","volume":"9 ","pages":"e2500093"},"PeriodicalIF":2.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12487657/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145180005","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":"Development of Machine Learning Systems to Predict Cancer-Related Symptoms With Validation Across a Health Care System.","authors":"Baijiang Yuan, Muammar Kabir, Jiang Chen He, Yuchen Li, Benjamin Grant, Sharon Narine, Mattea Welch, Sho Podolsky, Ning Liu, Rami Ajaj, Luna Jia Zhan, Aly Fawzy, Janine Xu, Yuhua Zhang, Vivien Yu, Wei Xu, Rahul G Krishnan, Steven Gallinger, Kelvin K W Chan, Monika K Krzyzanowska, Tran Truong, Geoffrey Liu, Robert C Grant","doi":"10.1200/CCI-25-00073","DOIUrl":"10.1200/CCI-25-00073","url":null,"abstract":"<p><strong>Purpose: </strong>Cancer and its treatment cause symptoms. In this study, we aimed to develop machine learning (ML) systems that predict future symptom deterioration among people receiving treatment for cancer and then validate the systems in a simulated deployment across an entire health care system.</p><p><strong>Methods: </strong>We trained and tested ML systems that predict a deterioration in nine patient-reported symptoms within 30 days after treatments for aerodigestive cancers, using internal electronic health record (EHR) data at Princess Margaret Cancer Centre (3,229 patients; 20,267 treatments). The primary performance metric was the area under the receiver operating characteristic curve (AUROC). The best-performing systems in the held-out internal test set were then externally validated across 82 cancer centers in Ontario (12,079 patients; 77,003 treatments) by adapting techniques from meta-analysis.</p><p><strong>Results: </strong>The best ML systems predicted symptom deterioration with AUROCs ranging from 0.66 (95% CI, 0.63 to 0.69) for dyspnea to 0.73 (95% CI, 0.71 to 0.75) for drowsiness in the internal test cohort. Treatments flagged as high-risk were significantly associated with future symptom deterioration (odds ratios [ORs], 2.53-6.56; all <i>P</i> < .001) and emergency department visits for dyspnea (OR, 1.85; <i>P</i> = .008), depression (OR, 1.84; <i>P</i> = .04), and anxiety (OR, 2.66; <i>P</i> < .001). In the external validation cohort, the AUROCs for different symptoms meta-analyzed across centers ranged from 0.67 (95% CI, 0.66 to 0.68) to 0.73 (95% CI, 0.72 to 0.74). Performance across centers displayed significant heterogeneity for six of nine symptoms (I², 46.4%-66.9%; <i>P</i> = .004 for dyspnea, <i>P</i> < .001 for the rest).</p><p><strong>Conclusion: </strong>ML can predict future symptoms among people with cancer from routine EHR data, which could guide personalized interventions. Heterogeneous performance across centers must be considered when systems are deployed across a health care system.</p>","PeriodicalId":51626,"journal":{"name":"JCO Clinical Cancer Informatics","volume":"9 ","pages":"e2500073"},"PeriodicalIF":2.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12487662/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145151821","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}