JCO Clinical Cancer Informatics最新文献

Purpose: Analyzing complex medical data sets is specialized and time-consuming. This study aimed to develop and evaluate a novel multiagent artificial intelligence (AI) framework for automating medical data analysis workflows and to compare its performance against nonagent-based approaches using large language models (LLMs).

Methods: A six-party AI agent system was developed using the AutoGen platform, with specialized agents for planning, data retrieval, cleaning, statistical analysis, and review, powered by OpenAI gpt-4o. This framework was applied to deidentified single patient-level data sets from 20 recent studies in the field of bone marrow transplantation (2021-2023). The primary objective was to evaluate its accuracy in replicating published primary outcomes, benchmarked against direct use of the Web site-based ChatGPT 4o.

Results: The multiagent framework successfully replicated 53.3% (95% CI, 40.7 to 66.0) of primary outcomes, significantly outperforming ChatGPT 4o (35.0% [95% CI, 22.9 to 47.1]; P = .04). The agent framework's failures were predominantly due to data transformation issues (46.4%) and analysis code errors (21.4%). In contrast, ChatGPT 4o failures largely stemmed from incorrect statistical method application (38.4%) and data transformation (45.6%), often attempting to resolve code errors by switching to alternative, incorrect statistical methods. Hallucinations of variables or results were not observed in the multiagent approach.

Conclusion: Our multiagent AI framework demonstrated superior accuracy and robustness in automating biomedical data analysis compared with a generalized LLM.

Purpose: The rapid expansion of scientific literature has made it increasingly challenging for clinicians and researchers to efficiently identify relevant evidence. While large language models (LLMs) offer promising solutions for automating literature review tasks, few tools support integrated workflows that enable trend analysis as well. This study aimed to develop and evaluate Rapid Clinical Evidence eXplorer (RaCE-X), a Generative Pre-trained Transformer (GPT)-based automated pipeline designed to streamline abstract screening, extract structured information, and visualize key trends in clinical research.

Methods: We used GPT-4.1 mini to screen 865 PubMed abstracts based on predefined screening criteria. Structured information was then extracted from the 87 relevant abstracts based on a predefined information model covering nine fields. A gold standard data set was created through expert review to assess model performance. The extracted information was visualized through an interactive dashboard. Usability was evaluated using the Post-Study System Usability Questionnaire (PSSUQ) and open-ended feedback from five clinical research coordinators.

Results: RaCE-X demonstrated high screening performance (precision = 0.954, recall = 0.988, F1 = 0.971) and achieved strong average performance in information extraction (precision = 0.977, recall = 0.989, F1 = 0.983), with no hallucinations identified. Usability testing indicated generally positive feedback (overall PSSUQ score = 2.8), with users noting that RaCE-X was intuitive and effective for data interpretation.

Conclusion: RaCE-X enables efficient GPT-based abstract screening, structured information extraction, and research trend exploration, thereby facilitating the summary of clinically relevant evidence from the biomedical literature. This study demonstrates the feasibility of using LLMs to reduce manual workload and accelerate evidence-based research practices.

Purpose: Electronic patient portals can promote patient-centered care, but determinants of engagement remain underexplored in oncology. This study examines sociodemographic and clinical factors associated with engagement with four portal features, including invitations to complete patient-reported outcome (PRO) measures before appointments.

Methods: Secondary analysis of the Northwestern University IMproving the Management of symPtoms during and following Cancer Treatment study, a stepped-wedge cluster randomized trial to promote symptom management using PROs in adult oncology care was performed. For each enrolled participant, we examined portal usage across 1 year.

Results: A total of 3,457 patients were enrolled between April 2020 and April 2023 from 30 Northwestern Medicine ambulatory oncology clinics. Patients were 65% female, 85% White, and 85% non-Hispanic/Latino, with a mean age of 60.8 years. Cancer diagnoses were 30% breast, 12% lymphoma, and all other types accounted for <10% of the sample. Patients accessed laboratory results most frequently (median 23 days in the year), followed by messaging (median 11 days) and physician notes (median 2 days). A total of 62.6% of patients completed at least one invited PRO. Controlling for sociodemographic factors, patient characteristics that were associated with greater engagement across three or more features included more oncology appointments, high health literacy, high anxiety, one or more severe physical symptoms, and high shared decision making with their health care team. Black race, Hispanic/Latino ethnicity, and Medicaid insurance were associated with lower portal engagement. Patients who used any other portal features were more likely to complete PROs. In contrast to other portal features, patients with at least one severe physical symptom were less likely to complete PROs (incidence rate ratio, 0.87 [95% CI, 0.81 to 0.93]; P < .001).

Conclusion: Portal use among patients with cancer varies by sociodemographic and clinical characteristics. Findings suggest a need for targeted interventions to promote equitable use among under-represented groups and promote portal-based PRO completion for patients with higher symptom burden.

Purpose: The objective of this study was to develop a flexible risk stratification strategy for AML that is specific for venetoclax plus azacitidine (ven/aza), addresses real-world data (RWD) issues, and is also adaptable to different use cases.

Methods: A series of tunable risk models (RMs) were generated from a dynamic counterfactual machine learning (ML) strategy. These used a range of features from diagnostic AML samples and were tested using objective metrics on a single-institution cohort of 316 newly diagnosed patients treated with ven/aza. RM performance was tested using various model assumptions, data elements, and end points and with applications to an external AML real-world cohort (RWC).

Results: Favorable, intermediate, and adverse risk groups were identified in a series of ML-based RMs using different assumptions, for genetic-only or genetic-plus-phenotypic data elements and with overall survival and event-free survival as end points. Most RMs demonstrated equitable patient distribution (approximately 20%-40% in each risk group), significant separation between risk strata (log-rank-based P values <0.001), and predictability computed by time-dependent survival AUC values of 0.60-0.70. Similar performance was observed when the proposed RM strategy was adapted and compared with the European Leukemia Net 2022 using the external RWC.

Conclusion: The proposed ML strategy addresses a variety of RWD considerations and is readily tunable through coding and parameter updates for different contexts and use case needs. This strategy represents a novel approach to developing more effective RMs for AML and possibly other diseases.

Purpose: Breast cancer is a leading cause of cancer incidence and mortality among women globally, with significant disparities in screening uptake. Technology-based tools are emerging and show the potential to promote breast cancer screening (BCS), especially for underserved populations.

Methods: This review follows the Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines and the population, intervention, comparison, and outcome framework. We reviewed 24 peer-reviewed articles from databases including ProQuest Central, Scopus, ScienceDirect, PubMed, Web of Science, and IEEE Xplore published before February 21, 2025, which explore the efficacy of technology use in promotion of BCS.

Results: The included studies used diverse technologies, including videos, mobile health, websites, and sensor-based tools. The tools covered a variety of aspects for BCS promotion, including patient education, reminders, risk assessment, and competency building. Video-based interventions showed mixed results on BCS knowledge enhancement and screening rate promotion. Culturally tailored programs were effective in increasing screening rates among immigrant populations. Short messaging service reminders and web-based decision aids were associated with higher adherence and less decisional conflict. Challenges included technical barriers, limited digital access, and low engagement, which hinder the efficacy of the tools.

Conclusion: Technology-based interventions are promising to improve BCS uptake, especially when tailored to cultural and linguistic needs. However, addressing barriers such as digital literacy and accessibility is critical for equitable implementation. Future research should focus on longitudinal studies and diverse populations to optimize these interventions and reduce disparities in screening adherence.

Purpose: Selecting an optimal first-line chemotherapy regimen for advanced or metastatic pancreatic cancer is challenging because of varying efficacy and toxicity profiles of fluorouracil, leucovorin, irinotecan, and oxaliplatin (FOLFIRINOX) and gemcitabine/nab-paclitaxel (GnP). This study aimed to develop machine learning (ML) models that predict survival outcomes and guide treatment selection using routinely available clinical data.

Methods: We retrospectively analyzed 191 patients who received systemic chemotherapy for advanced or metastatic pancreatic cancer at Gangneung Asan Hospital and the Asan Medical Center between 2014 and 2023. Seventeen demographic and clinical variables, along with survival outcomes, were collected. The data set was stratified and split into training and test sets (4:1). CatBoost-based ML models were trained to predict 12-month overall survival (OS) for each regimen. A minimal subset of variables was selected using 5-fold cross-validation to optimize receiver operating characteristic (ROC)-AUC. Patients were classified as high or low risk based on model-derived thresholds.

Results: The median age of the cohort was 62 years, and 64% was male. The ML models achieved ROC-AUCs of 0.81 for FOLFIRINOX and 0.82 for GnP. Predictive accuracies on test data were 0.77 and 0.80, respectively. Median OS differed significantly between predicted high- and low-risk groups: 9 v 15 months for FOLFIRINOX (hazard ratio [HR], 2.8; P < .0001) and 9 v 18 months for GnP (HR, 2.5; P < .01). In addition, 27% of patients predicted to be high risk for FOLFIRINOX were classified as low risk for GnP, and 32% vice versa.

Conclusion: ML models trained on multicenter data can effectively predict early mortality risk and help personalize chemotherapy selection in advanced or metastatic pancreatic cancer, potentially improving clinical outcomes.