Background: 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. Methods: 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. Results: 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. Conclusions: 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.
Purpose: To investigate whether quantitative nuclear morphology from routine H&E images can be used as a biomarker for glioblastoma (GBM) biology and prognosis. Methods: Nuclear eccentricity, circularity, density, and heterogeneity were measured from H&E whole-slide images in the TCGA-GBM cohort and independently validated in the CPTAC-GBM cohort. A multivariable Cox model was used to test the survival associations in both cohorts, and transcriptome-wide and gene set enrichment analyses were conducted in TCGA RNA data and validated using CPTAC RNA and proteomic data. Results: In TCGA-GBM, greater nuclear eccentricity was associated with better survival (HR, 0.85; 95% CI, 0.71–1.02; p = 0.089), with the same favorable association independently observed in CPTAC-GBM (HR, 0.74; 95% CI, 0.60–0.90; p = 0.003). No individual gene association with eccentricity was statistically significant in the TCGA cohort, but pathway analysis identified its association with epithelial–mesenchymal transition (EMT), inflammatory, hypoxic, and stress-related programs. Across the TCGA RNA, CPTAC RNA and proteomic datasets, greater eccentricity was consistently associated with increased NF-κB signaling, collagen biosynthesis, and ER-to-Golgi transport and decreased L1CAM-related and neuronal-projection programs, with EMT showing the strongest cross-cohort consistency. Conclusions: Nuclear eccentricity from patient H&E slide images is a potential biomarker associated with survival and transcriptional/translational programs in GBM. Integrating quantitative pathology with RNA and proteomic data may provide an accessible approach for GBM prognosis and tumor biology characterization.
Purpose: To investigate whether quantitative nuclear morphology from routine H&E images can be used as a biomarker for glioblastoma (GBM) biology and prognosis. Methods: Nuclear eccentricity, circularity, density, and heterogeneity were measured from H&E whole-slide images in the TCGA-GBM cohort and independently validated in the CPTAC-GBM cohort. A multivariable Cox model was used to test the survival associations in both cohorts, and transcriptome-wide and gene set enrichment analyses were conducted in TCGA and validated using CPTAC RNA and proteomic data. Results: In TCGA-GBM, greater nuclear eccentricity was associated with better survival (HR 0.85; 95% CI, 0.71–1.02; P=0.089), with the same favorable association independently observed in CPTAC-GBM (HR, 0.74; 95% CI, 0.60–0.90; P=0.003). No individual gene association with eccentricity was statistically significant in the TCGA cohort, but pathway analysis identified its association with epithelial-mesenchymal transition (EMT), inflammatory, hypoxic, and stress-related programs. Across TCGA RNA, CPTAC RNA, and proteomic dataset, greater eccentricity was consistently associated with increased NF-κB signaling, collagen biosynthesis, and ER-to-Golgi transport and decreased L1CAM-related and neuronal-projection programs, with EMT showing the strongest cross-cohort consistency. Conclusion: Nuclear eccentricity from patient H&E slide images is a potential biomarker associated with survival and transcriptional/translational programs in GBM. Integrating quantitative pathology with RNA and proteomic data may provide an accessible approach for GBM prognosis and tumor biology characterization.