2 March 2022 in JMIR Formative Research
Background: Chronic pain affects approximately 30% of the general population, severely degrades quality of life (especially in older adults) and professional life (inability or reduction in the ability to work and loss of employment), and leads to billions in additional health care costs. Moreover, available painkillers are old, with limited efficacy and can cause significant adverse effects. Thus, there is a need for innovation in the management of chronic pain. Better characterization of patients could help to identify the predictors of successful treatments, and thus, guide physicians in the initial choice of treatment and in the follow-up of their patients. Nevertheless, current assessments of patients with chronic pain provide only fragmentary data on painful daily experiences. Real-life monitoring of subjective and objective markers of chronic pain using mobile health (mHealth) programs can address this issue. Objective: We hypothesized that regular patient self-monitoring using an mHealth app would lead physicians to obtain deeper understanding and new insight into patients with chronic pain and that, for patients, regular self-monitoring using an mHealth app would play a positive therapeutic role and improve adherence to treatment. We aimed to evaluate the feasibility and acceptability of a new mHealth app called eDOL. Methods: We conducted an observational study to assess the feasibility and acceptability of the eDOL tool. Patients completed several questionnaires using the tool over a period of 2 weeks and repeated assessments weekly over a period of 3 months. Physicians saw their patients at a follow-up visit that took place at least 3 months after the inclusion visit. A composite criterion of the acceptability and feasibility of the eDOL tool was calculated after the completion of study using satisfaction surveys from both patients and physicians. Results: Data from 105 patients (of 133 who were included) were analyzed. The rate of adherence was 61.9% (65/105) after 3 months. The median acceptability score was 7 (out of 10) for both patients and physicians. There was a high rate of completion of the baseline questionnaires and assessments (mean 89.3%), and a low rate of completion of the follow-up questionnaires and assessments (63.8% (67/105) and 61.9% (65/105) respectively). We were also able to characterize subgroups of patients and determine a profile of those who adhered to eDOL. We obtained 4 clusters that differ from each other in their biopsychosocial characteristics. Cluster 4 corresponds to patients with more disabling chronic pain (daily impact and comorbidities) and vice versa for cluster 1. Conclusions: This work demonstrates that eDOL is highly feasible and acceptable for both patients with chronic pain and their physicians. It also shows that such a tool can integrate many parameters to ensure the detailed characterization of patients for future research works and pain management. Trial Registration: ClinicalTrial.gov NCT03931694; http://clinicaltrials.gov/ct2/show/NCT03931694
23 February 2026 in JMIR Cancer
Background: Screening for clinical trials is challenging for clinicians due to its time-consuming and repetitive nature. The rise of artificial intelligence (AI) offers an opportunity to improve screening productivity and reproducibility. Pancreatic cancer is characterized by increasing incidence, poor survival outcomes, and an urgent need for improved management strategies. Objective: This study aimed to assess the performance of AI in evaluating clinical trial inclusion and exclusion criteria, compared to a double-blind human gold standard, using a retrospective cohort. Methods: In the PANCR-AI (Pancreatic Cancer Retrospective Screening with Artificial Intelligence) pilot study, we retrospectively reviewed cases from our institutional database of patients with advanced pancreatic cancer presented at tumor board meetings between January 2018 and December 2023. Each patient was screened for clinical trials open for inclusion at the time of the multidisciplinary meeting. Manual screening of eligibility criteria for each patient-trial pair was performed by 2 blinded oncologists to determine potential eligibility (gold standard), with a third oncologist resolving discrepancies. Potential eligibility was also assessed using 3 large language models (ie, GPT-4.5, Claude 3.7 Sonnet, and Mistral-7B-Instruct v0.3). Their performance was compared to the human gold standard using standard evaluation metrics (eg, sensitivity, specificity, precision, recall, and F 1 -score). Correlations between the risk of failure and the number of words and characters in the criteria were analyzed. The time required to complete the screening was recorded for both human and AI assessments. The number of trials open for enrollment at the time of the tumor board meeting was also recorded as a variable for analysis. Results: Across 341 patient-trial pairs, the AI models demonstrated high sensitivity, ranging from 83.3% to 92.2%. Analysis of the criteria showed a correlation between the risk of failure and the number of words and the number of characters in the criteria. Overall screening time for manual assessment was significantly longer for the human gold standard (44.70 hours) assessment than for AI (2.53-3.15 hours). Patients were more likely to have been included in a clinical trial if the number of trials open for enrollment was higher at the time of the tumor board meeting ( P =.02). Conclusions: Our study highlights the promising performance of AI in clinical trial screening. Future work should explore integration with structured clinical data, such as laboratory values or radiological findings, to improve multimodal comprehension. Expanding the evaluation to a broader range of tumor types and multicenter datasets would improve generalizability. Finally, real-time prospective validation and workflow integration with electronic health records will be critical to assess the feasibility and clinical impact of large language model–assisted screening in daily oncology practice. Addressing these challenges will be essential to move from proof of concept to scalable clinical implementation.