Purpose Metastatic castration-resistant prostate cancer (mCRPC) shows marked clinical heterogeneity and poor long-term survival, highlighting the need for simple and reliable risk stratification tools beyond the limited usability of existing complex prognostic models. In this study, we developed and validated PROGRESS (Prostate Cancer Global Risk Evaluation and Stratification Score), a simplified prognostic score derived through machine learning‑guided feature selection distilled into a simple laboratory-based tool. Methods Baseline data from 2,035 patients with mCRPC (training set) were embedded into synthetic representations, reduced with UMAP, and clustered with DBSCAN to discover outcome-related subpopulations. Feature contribution analysis informed a multivariable model that yielded three independent predictors (prostate specific antigen [PSA], alkaline phosphatase [ALP], and AST) composing PROGRESS. External validation used two independent data sets (n = 1,239) across different therapeutic settings. Overall survival (OS) was analyzed with Kaplan-Meier and Cox regression; discrimination was assessed by ROC-AUC, AUC(t), and Harrel C-index. Results Unsupervised modeling identified two patient risk subpopulations with significantly different OS rates (median 27.4 v 17.7 months; hazard ratio [HR], 2.20 [95% CI, 1.91 to 2.54]; P < .00001). The three retained predictors (PSA, ALP, and AST) were combined into a composite score (PROGRESS) that showed strong discrimination in the training cohort (ROC-AUC 0.89; AUC(t) 0.60; Harrel C-index 0.69). Using a prespecified cutoff, patients classified by PROGRESS as increased risk had significantly shorter survival than low-risk patients (median 18.3 v 25.6 months; HR, 1.72 [95% CI, 1.50 to 1.97]; P < .0001). PROGRESS prognostic performance was consistent across all validation cohorts (all P < .0001). Conclusion By combining ML-based pattern discovery with classical modeling, PROGRESS provides a simple, objective, and readily implementable prognostic tool using three inexpensive routine laboratory measures. Its consistent performance across independent data sets supports clinical utility for individual risk stratification, trial enrichment, and early decision making. Prospective real-world validation is warranted.
Purpose Patients with cancer experience nutrition challenges, but access to registered dietitians (RDs) is limited. The purpose of this study was to determine whether a specialized Artificial Intelligence (AI) Nutrition Platform trained on curated high-quality evidence is equivalent in providing nutrition information to patients with cancer compared with oncology-credentialed RDs. Methods Twenty nutrition queries were developed by an expert panel, encompassing common cancer types, symptoms, and food allergies/preferences. These queries were administered to the AI Platform and to four nationally recruited human dietitians. Three expert reviewers with >10 years of cancer-specific nutrition experience blindly reviewed all query responses using a modified version of the Quality Assessment of Medical AI (mQAMAI) instrument, which assigns a score between 1 and 5 for accuracy, clarity, relevance, completeness, and usefulness (total quality score between 5 and 25). The primary outcome was mQAMAI total score. Equivalence was evaluated a priori using two one-sided tests (TOST). Secondary outcomes included readability and response time. Results The AI Nutrition Platform met equivalence criteria with human dietitians at ±3 to ±5 points (mean difference: 0.9 points; 90% CI, -0.27 to 2.15; TOST P < .05), while scoring higher on individual components: clarity (4.2 v 3.9; P = .001), relevance (4.1 v 3.9; P = .04), and usefulness (3.8 v 3.5; P = .02). AI responses were easier to read (Flesch-Kincaid grade level 7.2 v 9.8; P < .001) with faster response time (8.5 v 18.5 minutes per two queries; P < .001). Conclusion The AI Platform was equivalent to human dietitians for cancer nutrition information, delivering responses with greater clarity, relevance, usefulness, and readability in less time. This tool could broaden access to nutrition support for patients in settings where access to dietitians is limited.
Purpose Empowering and activating patients by means of digital tools is associated with increased utilization of health care services and reduced health care costs. The aim of this study was to assess the ability patients with cancer have to use digital tools and digitally mediated health information by means of the eHealth Literacy Questionnaire (eHLQ) survey tool. Methods This quantitative cross-sectional study included patients from three outpatient oncology departments in Central Norway between July 2023 and February 2024. Eligible participants were 18 years or older, currently or recently (<60 days) receiving chemotherapy, and Norwegian speaking. Data were collected using the eHLQ and supplementary questions on sociodemographic characteristics and patient portal use. Mean scale scores were calculated for the seven eHLQ scales. Analyses were performed in SPSS using general linear models. Results A total of 248 patients with cancer were recruited. Mean eHealth literacy (EHL) scores assessed by using eHLQ, ranged from 2.72 to 3.14 across the seven scales (standard deviation [SD], 0.42-0.62). The highest score was observed for scale 4 feel safe and in control (mean 3.14, SD, 0.45). Increasing age showed the strongest association with lower EHL. No statistically significant gender differences were observed, and associations of low education and income with lower EHL were attenuated after adjustment for age. Conclusion Our data indicate that EHL among patients with cancer does not differ substantially from what has been found in other populations in previous studies. This may indicate that having a severe disease or receiving chemotherapy does not affect overall EHL. Increasing age was the strongest factor associated with lower EHL.
PURPOSE Heterogeneity in cancer registries limits reuse of real-world data (RWD) alongside clinical trials to support regulatory decisions. Rituximab, gemcitabine, and oxaliplatin (R-GemOx) is commonly a comparator in large B-cell lymphoma (LBCL) trials and used in practice, but RWD are not structured for trial comparison. We developed a reusable pipeline to convert the Lymphoma Epidemiology of Outcomes Consortium for Real World Evidence (LEO CReWE) registry into Clinical Data Interchange Standards Consortium (CDISC)–compliant data sets by constructing a generalized, registry-wide Study Data Tabulation Model (SDTM) and deriving analysis-ready Analysis Data Model (ADaM) data sets. METHODS Using R 4.5.2 with the sdtm.oak, admiral, and admiralonco packages, we generated ADaM for 183 patients with relapsed/refractory LBCL treated with R-GemOx across the multicenter LEO cohort. RESULTS ADaM-derived summary statistics showed exact concordance with published results for this cohort: median age 68 years, complete response rate 29%, median overall survival 13.5 months, and median event-free survival 2.3 months. CDISC conformance was assessed using the CDISC Open Rules Engine (CORE); no finding represented rejection-level structural nonconformance. The generalized SDTM enabled rapid regeneration of ADaM as cohort definitions changed, including a separate cohort treated with axicabtagene ciloleucel (a chimeric antigen receptor T-cell), and supports federated analyses in which sites retain control of patient-level data. CONCLUSION This work demonstrates a practical, reusable pipeline for CDISC-standardized RWD in lymphoma.
