Carl Victor Asche

Introduction: This systematic literature review (SLR) provides an analytical framework for clinical trials evaluating clinical outcomes of artificial intelligence-based digital health interventions (AI-DHI). Methods: The SLR was conducted in accordance with the PRISMA guidelines. Search was conducted (September 2025) in PubMed and Embase. Population included patients using AI-DHI. Only clinical trials exploring clinical outcomes, written in English, were considered. NICE checklist was used to assess studies’ quality. Results were analyzed descriptively. Results: Final sample had 84 studies, with metabolic (28.6%), musculoskeletal (20.2%), and mental health disorders (19.0%) as the most common indications. Most studies (75.0%) were controlled, parallel-group trials with 2+ arms, mostly comparing AI-DHI with standard-of-care or waitlist. Although type of intervention often precludes blinding (64.3% were open-label), a double-blinding is strongly recommended (only 6.0%). Only 9.5% of studies were conducted at multiple sites across different countries. Dropout rates in the total sample and each study arm should be <20% at all endpoints (64.3%). Statistical tests were used based on the outcome measures. The small sample sizes and limited generalizability of findings were reported as the main limitations. Conclusions: This SLR emphasized current methodological gaps and an urgent need for unified global guidelines. Standard SLR limitations apply to this research.

Trends of first-line treatment received by patients with DTs across time. Note: 30 patients received no active treatment, of which 26 had DT-related encounters of at least 6-month intervals during the study period. Overall first-line treatment patterns significantly changed over time (P = 0.003) based on Jonckheere–Terpstra tests for trend. Specifically, significant changes were observed for surgery (P < 0.001), cryoablation (P < 0.001), and TKIs (P < 0.001) but not for radiation (P = 0.15), chemotherapy (P = 0.18), and other systemic therapy (P = 0.94) based on Cochran–Armitage tests for trend.

Patient flow diagram showing how the study cohort was identified from the data source

List of ICD-CM codes used to identify patients with potential misdiagnoses

Treatment patterns of patients with DT during the entire disease course and up to the fourth line of therapy.

Additional data showing the baseline characteristics of patients stratified by the type of first line treatment received

Baseline demographics and clinical characteristics of patients at DT diagnosis.

List of terms used in the study to infer disease progression among study participants from documentation in clinical notes