Michal Pruski, Jasmine Rollings, Kathleen L. Withers
Building on a previous Wales-wide survey, this study aimed to provide more in-depth exploration of the barriers and facilitators to healthcare artificial intelligence adoption in Wales. The study aimed to explore these barriers and facilitators among various social groups, to inform policy development in Wales. Four focus groups were conducted with a group of members of the public and a group of healthcare professionals (both groups recruited from a previous survey), as well as a group Sixth Form students and a group of retired adults. Inductive thematic analysis was used to generate themes and to compare the issues raised by the various groups. Contiguity-based analysis was undertaken to underscore how themes related with each other. A total of 21 individuals participated in the focus groups (healthcare professionals=6, members of the public=6, sixth-form students=5, retirees=4). Seven thematic networks were identified. Across groups, seven themes were identified in the healthcare professional group, six in the general members of the public group, seven in the sixth form student group, and seven in the retiree group. All groups voiced concerns about data privacy and highlighted the importance of human oversight of AI and human contact during the clinical encounter as they expressed more trust in human practitioners. There were though differences between groups, such as greater trust in black-box systems by healthcare professionals, and between individual participants in regard to trust in private organisations developing AI for healthcare organisations. All groups were concerned with information security and expressed a preference for human contact during the clinical encounter and a human-in-the-loop approach. There were differences between the groups, such as in attitudes towards black-box AI technologies and trust in clinicians. No additional barriers or facilitators were identified for proxy consent.
Rebecca K. Kelly, Amy Hanus, Janet Calhoun, Jonathan P. Bonnet, Ron Stout
Nutrition counseling is often limited by time, staffing, and resources. Full Plate Living (FPL) is a free, self-guided digital nutrition program that encourages a whole food, plant predominant, fiber-rich eating pattern. This study examined baseline-to-follow-up changes in diet quality, body mass index (BMI), dietary fiber intake, and participant-reported health measures among adults with eligible paired Diet ID/FPL assessments. This secondary analysis used de-identified observational records from July 2023 through January 2026. Baseline was the first available record, and follow-up was the first subsequent record at least 60 days later. Baseline characteristics were compared between participants with and without eligible paired records. Within-participant changes were evaluated using paired analyses, with Bonferroni-adjusted sensitivity analyses for multiple outcomes. Regression analyses examined whether follow-up interval was associated with outcome change. Among 4,359 participants with 7,077 records, 392 (9.0%) had eligible paired records. The paired-assessment cohort was predominantly female (87.5%), White (81.1%), mean age was 57.7 years. Compared with participants without eligible follow-up records, paired-assessment participants were older and had higher diet quality and dietary fiber intake and lower estimated energy intake. Among participants with paired data, Diet ID Quality Score increased from 7.20 to 7.91 (Cohen d=0.26), Healthy Eating Index-2015 increased from 73.87 to 80.24 (d=0.27), BMI decreased from 31.62 to 31.03 kg/m² (d=−0.17), and dietary fiber intake increased by 5.0 g/d (d=0.28). After Bonferroni adjustment, improvements in diet quality, healthy food choice confidence, weight-loss confidence, energy level, general health, dietary fiber intake, and food group measures remained significant, along with the modest BMI reduction; sleep duration category did not remain significant. Longer follow-up interval was weakly associated with smaller improvements in Healthy Eating Index-2015 and dietary fiber intake and was not associated with BMI change. DISCUSSION: Among participants with eligible paired assessments, baseline-to-follow-up improvements were observed in diet quality, dietary fiber intake, participant-reported health measures, food group measures, and BMI; effect sizes were small. These findings should be interpreted as exploratory repeated-observation changes rather than causal evidence of program effectiveness. These findings may guide evaluation of FPL as a no-cost digital nutrition resource for individuals, clinics, and communities.
Lennart Ocker-Serger, Elisabeth Livingstone, Georg Lodde, Eggert Stockfleth, Nessr Abu Rached, Dirk Schadendorf, Stephan Nüesch
Artificial intelligence (AI) has demonstrated high diagnostic performance in skin cancer detection and is increasingly being integrated into clinical workflows. However, whether these advances translate into meaningful patient-relevant and healthcare system outcomes remains unclear. Evidence on value-oriented outcomes has not been systematically synthesized. We conducted a PRISMA-ScR–guided scoping review of studies published between January 2015 and October 2025 identified through PubMed/MEDLINE, Scopus, and Web of Science. Studies evaluating AI-based technologies for skin cancer diagnosis, triage, risk stratification, or management were included if they reported outcomes beyond technical performance metrics. Reported outcomes were mapped to three value-oriented domains: clinical and prognostic, process and experiential, and system-level and economic outcomes. Of 4,021 records identified, 33 studies met the inclusion criteria, whereas 389 publications were excluded because they reported only technical performance metrics without value-oriented outcomes. Reported outcomes were predominantly process and experiential (28/33 studies), including diagnostic confidence, workflow efficiency, and user acceptance. Clinical and prognostic outcomes were reported in only five studies, with four studies focussing on prognostic utility and one study focussing on patient management, while system-level and economic outcomes were identified in three studies. Most evaluations were conducted in controlled experimental settings, whereas prospective real-world implementation studies were less common. Overall, the available evidence predominantly focused on process-level benefits, with limited evidence for clinical and prognostic or system-level and economic outcomes. Current evaluation strategies for AI-based skin cancer diagnostics remain predominantly performance-oriented and are largely focused on process and experiential outcomes. From a value-based healthcare perspective, current evidence remains largely confined to intermediate stages of the diagnostic value chain: although AI-assisted systems may improve diagnostic workflows, clinician confidence, and clinical decision making, few studies have evaluated their impact on downstream patient-relevant clinical and prognostic, or system-level and economic outcomes. Future research should prioritize prospective real-world studies, outcome-driven evaluation frameworks, and economic assessments that examine the impact of AI-supported decision-making on clinical outcomes and healthcare systems. Despite promising effects on diagnostic processes, evidence for the clinical and system-level value of AI-based skin cancer diagnostics remains limited. Outcome-driven evaluation frameworks are needed to bridge the gap between algorithmic performance and meaningful healthcare impact.
Le-le Li, Rui-feng Xu, Liang-liang Huang, Bing-ru Lu, Shu-ting Zhang, Ya Tuo, Hui-qing Liu, Rui Ren, Shu-fang Wang, Ming-xia Sun, Xiao-tong Zhang, Jian-rong Zhao, Lei Yu, Yan Meng
Kt/V is a widely used indicator for assessing hemodialysis (HD) adequacy, but conventional measurement methods require blood sampling and are impractical for large-scale or real-time use. This study aimed to develop and validate predictive models for Kt/V using multiple linear regression (MLR) and machine learning algorithms, enabling clinicians to estimate dialysis adequacy before a session begins using simple, non-invasive parameters. A total of 1,017 eligible patients were enrolled from seven HD centers in Hohhot City, China, and divided into training (n = 677), internal (n = 220), and external validation (n = 120) sets. From 26 candidate variables, eight clinically meaningful derived features were constructed, and a multi-algorithm fusion strategy integrating F test, Mutual Information, Random Forest importance, XGBoost importance, LASSO coefficients, Permutation Importance, Recursive Feature Elimination, and Boruta was employed for feature selection. Five final features (body surface area, pre-dialysis weight, standardized blood flow, sex, and circulating blood volume) were selected. Eight point-prediction models (MLR, XGBoost, LightGBM, Random Forest, Gradient Boosting, KNN, SVM, and BPNN), a simple average ensemble of the three top-performing models, and two probabilistic prediction methods (LightGBM Quantile Regression and NGBoost) were developed. Hyperparameter tuning was performed using GridSearchCV with 5-fold cross-validation. Model performance was evaluated using R 2, RMSE, and MAE on internal and external validation sets. On external validation, the SVM model achieved the highest R 2 (0.5931) and lowest RMSE (0.1633) and MAE (0.1214) among individual models, followed by Gradient Boosting (R 2 = 0.5748, RMSE = 0.1670, MAE = 0.1276) and XGBoost (R 2 = 0.5681, RMSE = 0.1683, MAE = 0.1288). The ensemble model achieved the best overall performance (R 2 = 0.5911, RMSE = 0.1637, MAE = 0.1240). Calibration assessment revealed all models were well-calibrated without requiring post-hoc adjustment. For probabilistic prediction, NGBoost provided well-calibrated 80% prediction intervals (PICP = 82.27%) with narrower intervals than LightGBM Quantile Regression. SHAP analysis identified BSA, standardized blood flow, and gender as the most influential predictors. Machine learning models, particularly SVM, the ensemble model, and NGBoost, can provide accurate, interpretable, and uncertainty-aware predictions of Kt/V using non-invasive, readily available parameters. The development of a local standalone executable application further facilitates clinical translation, enabling pre-dialysis prediction and real-time prescription adjustment. Prospective validation in diverse populations is warranted to confirm generalizability.
Reham Aldakhil, Geva Greenfield, Albandari Alharbi, Ahmed Alboksmaty, Benedict Hayhoe, Azeem Majeed, Ana Luisa Neves
Although virtual consultations (VCs) have become a routine component of type 2 diabetes (T2D) care, evidence regarding patient experiences remains limited. We investigated VC use among UK adults with T2D, factors associated with both current and intended use, and perceived quality of care. A weighted national cross-sectional survey of 373 UK adults with self-reported T2D was conducted via the YouGov panel. The questionnaire included digital adoption factors based on the UTAUT2 framework, and perceived impacts of virtual consultations across IOM quality domains. Weighted logistic regression identified predictors of use and satisfaction. About one in three respondents (31.0%) had used virtual consultations, almost always by telephone (91.3%) and infrequently. After adjustment, younger age (18–44 vs. ≥65: OR 7.76, 95% CI 2.22–27.16) and a bachelor's undergraduate education (OR 2.05, 95% CI 1.06–3.96) were the only independent factors associated with use, and the same profile predicted intention to use. In the acceptance framework UTAUT2, effort expectancy and facilitating conditions were the strongest constructs and social influence the weakest. Across the full sample, efficiency was perceived as the quality domain most positively impacted by virtual consultations (62.4%), whereas patient-centredness was rated least favourably (34.5%). Perceived equity was also limited, with only 40.2% of respondents agreeing that different groups benefit equally from virtual consultations. Users rated the five parallel quality domains more positively than non-users anticipated; the equity item, asked of all respondents, did not differ significantly between groups. Findings suggest that equitable and sustained uptake of virtual consultations requires attention to both digital inclusion and usability. Policies should support tailored interventions for populations at risk of exclusion, alongside investment in digital infrastructure and support resources. As perceived benefits vary across dimensions of care quality, virtual consultations are likely to be most effective when integrated within flexible hybrid models that align with patient preferences and care needs.
