Background: Routine electronic assessment of patient-reported outcomes (ePROs) can improve cancer care; yet, its implementation in routine practice and long-term sustainability remain unclear. Understanding these aspects is critical to advancing the field. Objective: To review and describe the past and current status, time trends, and long-term sustainability of clinical ePRO applications in routine oncology care. Methods: We conducted a systematic review of publications on ePRO use in oncology care up to December 31, 2023, searching PubMed and Web of Science and extracting data on clinical ePRO applications. We included peer-reviewed studies including patients with cancer using ePRO assessments in clinical practice, excluding research letters and conference abstracts. Data from the review were analyzed using descriptive statistics and univariate regression models to evaluate time trends, with year of publication as the predictor. A follow-up survey was sent to authors of published ePRO applications to assess their current use of the application or reasons for discontinuation. Responses from the follow-up survey were analyzed descriptively. Results: For the review, we screened 2933 references, and 303 met inclusion criteria. Results showed that Europe was the most common region (n=141, 46.5%), and study populations consisted mostly of adult patients (n=276, 91.1%) under chemotherapy treatment (n=124, 40.9%) assessed in an outpatient setting (n=261, 86.1%). The EORTC (European Organisation for Research and Treatment of Cancer; n=77, 25.4%) and PRO-CTCAE (Patient-Reported Outcomes Version of the Common Terminology Criteria for Adverse Events) questionnaires (n=65, 21.5%) were most frequently integrated into ePRO applications. In the univariate analysis, we found that publications increased significantly over time (2003-2023, P<.001). Trends showed a rise in mobile app use (odds ratio [OR] 1.211, P<.001), remote assessments (OR 1.094, P=.002), and feedback provided to patients (OR 1.060, P=.04). Of the 303 studies, 221 unique clinical ePRO applications were identified, merging publications at the application level. The follow-up survey had a 35.3% response rate (78/221), with 61.1% of ePRO applications still in use, lasting a median of 5 years. The most common reason for discontinuation was a lack of funding and resources (42.9%, 12/28). Conclusions: The field of ePRO assessment in oncology is rapidly evolving, with a shift toward remote, app-based tools and a growing emphasis on providing feedback to patients. We present, for the first time, data on the sustainability of ePRO use in routine care. While our findings offer valuable insights, they should be interpreted in light of potential response bias in the follow-up survey. Several ePRO applications remain in active use, highlighting potential for long-term integration into clinical practice. However, financial constraints, limited reimbursement models, and challenges with workflow integration continue to hinder broader and more sustainable adoption. Addressing these barriers will be essential to support the continued use of ePROs in clinical care.

Health related quality of life (HRQoL) is increasingly assessed in oncology research and routine care, which has led to the inclusion of HRQoL in prediction models. This review aims to describe the current state of oncological prediction models incorporating HRQoL. A systematic literature search for the inclusion of HRQoL in prediction models in oncology was conducted. Selection criteria were a longitudinal study design and inclusion of HRQoL data in prediction models as predictor, outcome, or both. Risk of bias was assessed using the PROBAST tool and quality of reporting was scored with an adapted TRIPOD reporting guideline. From 4747 abstracts, 98 records were included in this review. High risk of bias was found in 71% of the publications. HRQoL was mainly incorporated as predictor (78% (55% predictor only, 23% both predictor and outcome)), with physical functioning and symptom domains selected most frequently as predictor. Few models (23%) predicted HRQoL domains by other or baseline HRQoL domains. HRQoL was used as outcome in 21% of the publications, with a focus on predicting symptoms. There were no difference between AI-based (16%) and classical methods (84%) in model type selection or model performance when using HRQoL data. This review highlights the role of HRQoL as a tool in predicting disease outcomes. Prediction of and with HRQoL is still in its infancy as most of the models are not fully developed. Current models focus mostly on the physical aspects of HRQoL to predict clinical outcomes, and few utilize AI-based methods.

Patients with breast cancer often experience health-related quality of life (HRQoL) impairments that remain difficult to predict on an individual level. Prediction models can aid in understanding individual survivorship trajectories. However, current prognostic models are based on fixed intervals, limiting their utility in clinical follow-up schedules. This study aimed to develop and externally validate time-dynamic machine learning (ML) models that predict clinically relevant HRQoL impairments in nonmetastatic patients with breast cancer. Using the pooled multicohort EORTC (European Organisation for Research and Treatment of Cancer) BALANCE (big data in patients with breast cancer) dataset (n=6316) containing repeated HRQoL measurements (EORTC QLQ [Quality of Life Core Questionnaire]-C30), we constructed over 70,000 patient assessment pairs. ML algorithms were trained using the earlier HRQoL assessment and clinical data to predict dichotomized impairments in QLQ-C30 domains at the later assessment between 2 weeks and 5 years ahead, reflecting the range of follow-up intervals available in the dataset. The best performing model was determined via the area under the receiver operating characteristic curve in the internal validation, and externally validated in an independent cohort of the BALANCE dataset, in which the calibration and predictive performance in risk groups (patients: postmenopause, with financial difficulties, with obesity, with 2 or more comorbidities, with lower educational status, and with frailty) were also evaluated. ML models showed good discrimination (area under the receiver operating characteristic curve 0.64-0.84) across most domains, especially for persistent symptoms such as fatigue, financial difficulties, or functioning scales. Gradient boosting models performed best, but tended to be overconfident, with poor calibration for low-prevalence symptoms such as diarrhea or constipation. Model performance varied by risk group (eg, lower education and frailty), though no group consistently performed poorly. Performance remained stable across time windows, with prior HRQoL being the strongest predictor at the respective scale level, while clinical variables such as the type of treatment were less important for prediction. Time-dynamic ML models can support personalized HRQoL prediction in breast cancer care. Future improvements should focus on calibration and fairness to enable equitable, clinically meaningful implementation.

Health-related quality of life (HRQoL) is a crucial outcome for cancer patients, providing a comprehensive measure of patient well-being beyond traditional clinical endpoints. While HRQoL data are increasingly available from real-world data (RWD), randomized controlled trials (RCTs), and observational studies, they remain fragmented, limiting their utility for large-scale analysis. The European Organisation for Research and Treatment of Cancer (EORTC) Quality of Life Group’s BALANCE project aims to address this by pooling and harmonizing international HRQoL datasets for breast cancer patients. This article describes the challenges of pooling international HRQoL datasets, including the process of dataset identification, acquisition, and harmonization within the BALANCE project. We successfully pooled and harmonized six datasets, representing 6500 patients and over 30 000 observations from diverse RCTs, observational studies, and RWD sources. The resulting database includes 142 variables across demographic, clinical, and HRQoL domains. Challenges included various interpretations of the General Data Protection Regulation across Europe, related to data protection and ownership. Furthermore, inconsistent data collection and resource limitations (e.g. funding or personnel) required iterative negotiations and customized harmonization. This led to the exclusion of 17 datasets containing an estimated number of 20 000-22 500 patients. The BALANCE project demonstrates the feasibility of pooling international HRQoL data by overcoming key barriers and creating one of the largest HRQoL datasets for breast cancer. It lays the groundwork for upcoming publications focused on developing and validating prediction models. Future research should focus on adopting standardized data models, including secondary use clauses in consent forms, and establishing RWD registries to facilitate data sharing.

BACKGROUND Routine electronic assessment of patient-reported outcomes (ePROs) can improve cancer care; yet, its implementation in routine practice and long-term sustainability remain unclear. Understanding these aspects is critical to advancing the field. OBJECTIVE To review and describe the past and current status, time trends, and long-term sustainability of clinical ePRO applications in routine oncology care. METHODS We conducted a systematic review of publications on ePRO use in oncology care up to December 31, 2023, searching PubMed and Web of Science and extracting data on clinical ePRO applications. We included peer-reviewed studies including patients with cancer using ePRO assessments in clinical practice, excluding research letters and conference abstracts. Data from the review were analyzed using descriptive statistics and univariate regression models to evaluate time trends, with year of publication as the predictor. A follow-up survey was sent to authors of published ePRO applications to assess their current use of the application or reasons for discontinuation. Responses from the follow-up survey were analyzed descriptively. RESULTS For the review, we screened 2933 references, and 303 met inclusion criteria. Results showed that Europe was the most common region (n=141, 46.5%), and study populations consisted mostly of adult patients (n=276, 91.1%) under chemotherapy treatment (n=124, 40.9%) assessed in an outpatient setting (n=261, 86.1%). The EORTC (European Organisation for Research and Treatment of Cancer; n=77, 25.4%) and PRO-CTCAE (Patient-Reported Outcomes Version of the Common Terminology Criteria for Adverse Events) questionnaires (n=65, 21.5%) were most frequently integrated into ePRO applications. In the univariate analysis, we found that publications increased significantly over time (2003-2023, P<.001). Trends showed a rise in mobile app use (odds ratio [OR] 1.211, P<.001), remote assessments (OR 1.094, P=.002), and feedback provided to patients (OR 1.060, P=.04). Of the 303 studies, 221 unique clinical ePRO applications were identified, merging publications at the application level. The follow-up survey had a 35.3% response rate (78/221), with 61.1% of ePRO applications still in use, lasting a median of 5 years. The most common reason for discontinuation was a lack of funding and resources (42.9%, 12/28). CONCLUSIONS The field of ePRO assessment in oncology is rapidly evolving, with a shift toward remote, app-based tools and a growing emphasis on providing feedback to patients. We present, for the first time, data on the sustainability of ePRO use in routine care. While our findings offer valuable insights, they should be interpreted in light of potential response bias in the follow-up survey. Several ePRO applications remain in active use, highlighting potential for long-term integration into clinical practice. However, financial constraints, limited reimbursement models, and challenges with workflow integration continue to hinder broader and more sustainable adoption. Addressing these barriers will be essential to support the continued use of ePROs in clinical care. CLINICALTRIAL

Background: Head and neck cancer (HNC) and its multimodal treatment substantially impair speech, swallowing, breathing, appearance, and psychosocial well-being. Patient-reported outcome measures (PROMs) improve symptom monitoring and quality of life in oncology, yet their integration into routine HNC care remains inconsistent. This study assessed patterns of PROM use, perceived value, and barriers to implementation among healthcare professionals (HCPs) involved in HNC care. Methods: A 30-item cross-sectional survey was distributed to HCPs treating HNC patients between June 2024 and April 2025. The questionnaire explored PROM use in clinical practice and trials, perceived relevance across care phases, and implementation barriers. Respondents were classified as non-users, occasional users, or regular users. Data were analyzed descriptively with comparisons between groups. Results: Among 133 respondents, 33.8% were non-users, 29.3% occasional users, and 36.8% regular users of PROMs. Users reported inviting half of patients to complete PROMs, predominantly via paper-based questionnaires (67.8%). PROMs were mainly applied during active treatment and early follow-up to monitor symptoms, overall health, and emotional well-being, and were less frequently used to guide treatment decisions. The EORTC QLQ-C30 and HNC-specific tools were most commonly reported. Compared with users, non-users more often cited lack of time, limited training in interpreting PROM data, insufficient institutional support, resource constraints, and lack of appropriate instruments (all p < 0.05). PROM use in clinical trials was associated with routine use (p < 0.001). Conclusions: Although PROMs are widely valued in HNC care, their integration into clinical decision-making remains limited. Addressing organizational, educational, and digital barriers is essential to support sustainable implementation.