OAR@UM Collection:

Global readiness for AI and digital health in infection prevention and control

Thu, 01 Jan 2026 00:00:00 GMT

Title: Global readiness for AI and digital health in infection prevention and control Authors: Tartari, Ermira; Gastaldi, S. Abstract: Digital transformation is reshaping infection prevention and control (IPC), with artificial intelligence (AI) and digital health tools offering new opportunities for surveillance, decision-making, and work force training. However, their effective use depends on the digital competencies of the health workforce. Evidence on global readiness, particularly skills, training, and capacity gaps among IPC professionals, remains limited.

Diagnostic accuracy of automated systems for detection of hand hygiene compliance among healthcare workers : a systematic review and meta-analysis

Thu, 01 Jan 2026 00:00:00 GMT

Title: Diagnostic accuracy of automated systems for detection of hand hygiene compliance among healthcare workers : a systematic review and meta-analysis Authors: Lotfinejad, Nasim; Tartari, Ermira; Timurkaynak, Funda; Pittet, Didier Abstract: Background: Hand hygiene compliance is essential for preventing healthcare-associated infections and limiting the spread of antimicrobial resistance. Automated electronic monitoring systems have been proposed as possible alternatives to direct observation; however, their diagnostic accuracy remains uncertain. The aim of this system- atic review was to evaluate the diagnostic performance of automated systems in detecting hand hygiene compli- ance among healthcare workers (HCWs). Method: We searched PubMed, EMBASE, Cochrane Library, and Web of Science for studies published from January 2000 through May 2026. Studies were eligible if they compared the accuracy of automated hand hygiene monitoring systems with that of direct observation. A bivariate random-effects model was used to pool sensitivity and specificity. The review followed PRISMA guidelines and was registered in PROSPERO (CRD42022338607). Results: Twenty studies were included in the review, of which seven were eligible for meta-analysis. The included studies evaluated different types of automated electronic hand hygiene monitoring systems, most commonly using room entry and exit events as proxies for hand hygiene opportunities. In terms of diagnostic performance for identifying hand hygiene compliance among HCWs, the pooled sensitivity and specificity were 86% (95%CI: 52–97%) and 98% (95%CI: 83–100%), respectively. Severe between-study heterogeneity was observed in the univariate analyses. Therefore, pooled diagnostic accuracy estimates should be interpreted cautiously. Conclusion: Automated hand hygiene monitoring systems may offer a promising approach for assessing hand hygiene compliance; however, current diagnostic accuracy estimates remain uncertain with substantial between- study heterogeneity. Further well-designed studies using standardized validation methods and transparent report- ing of diagnostic accuracy outcomes are needed to clarify how accurately automated systems capture specific elements of hand hygiene compliance.

Explainable machine learning predictive models for surgical site infections : scoping review

Thu, 01 Jan 2026 00:00:00 GMT

Title: Explainable machine learning predictive models for surgical site infections : scoping review Authors: Sun, Rui; Liu, Yao; Lu, Shuya; Tartari, Ermira; Birgand, Gabriel; Yang, Lin; Zhou, Lei Abstract: Background: Surgical site infections (SSIs) remain a major cause of health care–associated infections, and early prediction is essential for improving patient outcomes. Machine learning (ML) has shown potential for SSI prediction; however, clinical implementation requires models that are both accurate and explainable. Despite recent progress in explainable ML, its clinical application to SSI prediction remains limited.; Objective: This study aimed to map explainable ML models for SSI prediction from a clinical perspective and examine their use of structured and unstructured data across the dimensions of data, methodology, and explanation output.; Methods: We conducted a scoping review following PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) and Joanna Briggs Institute (JBI) guidance, and registered the protocol in PROSPERO. Six databases were searched for eligible studies published from January 2010 onward, without language restrictions. The search was conducted on August 9, 2025, and updated on July 14, 2026. We included studies that developed or validated an explainable ML model for predicting SSI in adults. Two reviewers (RS and YL) independently screened studies and extracted data. Findings were narratively synthesized and presented in evidence maps. Methodological quality was assessed using the PROBAST+AI (Prediction model Risk Of Bias Assessment Tool for prediction models using regression or artificial intelligence) methods.; Results: Overall, 77 studies reporting 98 ML models were included. Most models were prognostic (72/98, 73.5%), whereas 26 focused on postoperative SSI diagnosis. A total of 81.8% (63/77) of studies addressed a single surgical specialty, most commonly gastrointestinal surgery (27/63, 42.9%). Overall, 51.9% (40/77) of studies addressed composite SSI predictions. Among all models, % (40/98) were black-box models explained by post hoc methods; SHAP combined with ensemble learning was the leading approach (18/40, 45%). Regression models accounted for half of the inherently interpretable models, interpreted using coefficients. Prognostic models commonly included health and lifestyle (60/72, 83.3%), individual characteristics, and surgical process details (both 57/72, 79.2%); health and lifestyle factors were most frequently important across SSI types.Diagnostic models commonly included surgical process details (13/26, 50%), administrative codes, and individual characteristics (both 10/26, 38.5%). Key diagnostic predictors varied by SSI types: postoperative clinical interventions predominated for composite SSI; vital signs, postoperative interventions, and administrative codes for superficial SSI; postoperative recovery status for deep SSI; and vital signs for organ-space SSI.; Conclusions: Extending previous reviews focusing on model performance, this review mapped explainability methods and important features in SSI prediction, identifying recurring predictor patterns and substantial methodological heterogeneity across prognostic and diagnostic settings. Incomplete reporting of feature definitions and explanatory rationale, together with limited clinical relevance, constrained clinical interpretation and actionability. Clinician-informed reporting frameworks and validation of explanation fidelity and clinical relevance are needed to improve the trustworthiness and utility of SSI prediction models.

Public awareness and knowledge of antibiotic use and antimicrobial resistance in Malta

Thu, 01 Jan 2026 00:00:00 GMT

Title: Public awareness and knowledge of antibiotic use and antimicrobial resistance in Malta Authors: Schranz, Gavin; Camilleri, Vanessa; Sciortino, Monique; Borg, Michael Angelo; Tartari, Ermira Abstract: Introduction Antimicrobial resistance (AMR) is a major global threat, driven partly by inappropriate antibiotic use. Understanding public knowledge, awareness, and behaviours is critical for designing effective interventions. This study assessed these dimensions within the Maltese population to inform national AMR awareness and stewardship strategies.; Method A cross-sectional online survey was conducted between 9 and 29 April 2024 among Maltese residents using a questionnaire adapted from the World Health Organization (WHO) Antibiotic Resistance Multi-Coun try Public Awareness Survey. A convenience sampling approach with active demographic monitoring was used across gender, age, and education groups, using census-derived targets as benchmarks. The survey, available in English and Maltese, assessed knowledge of appropriate antibiotic use, awareness of AMR-related terminology, and attitudes towards antibiotic use and resistance. Data were analysed using descriptive statistics and non-para metric tests (Mann-Whitney U, Kruskal-Wallis H, Chi-Square, Likelihood Ratio) to explore associations between demographic factors and knowledge or behavioural outcomes.; Results A total of 476 eligible respondents completed the survey and were included in the analysis. Among respondents, 59.9% were female and the largest age group was 25–34 years (31.9%). Awareness of “antibiotic resistance” was high (88%) yet understanding of “antimicrobial resistance” (48%) and its abbreviation “AMR” (21%) was lower. Most participants (97%) agreed that antibiotics should only be used when prescribed, but mis conceptions persisted: 16.6% believed antibiotics treat colds and flu, 33.6% for fever, and 39.9% for sore throats. Three-quarters (75%) incorrectly attributed resistance to the body becoming resistant rather than bacteria. Older and more educated respondents showed significantly better knowledge and more appropriate attitudes (p < 0.05), whereas younger adults and males were more likely to hold misconceptions. While nearly all respondents (96.7%) agreed that individuals should use antibiotics responsibly, fewer (53.4%) viewed AMR as a major global chal lenge or expressed personal concern (67.2%) about its impact, and one-third believed they were not at risk if they used antibiotics correctly. Findings indicate general awareness but persistent conceptual and demographic gaps.; Conclusion Despite high awareness of appropriate antibiotic use, misconceptions about treatment indications and the mechanisms of AMR remain, particularly among younger adults and those with lower education. Improving public understanding of when antibiotics are needed and how resistance develops will be critical to promoting responsible use. These findings provide locally generated evidence to inform targeted public health communication and support AMR prevention efforts in Malta.