Background: This study aims to address the gap in understanding clinicians’ attitudes toward explainable AI (XAI) methods applied to machine learning models using tabular data, commonly found in clinical settings. It specifically explores clinicians’ perceptions of different XAI methods from the ALFABETO project, which predicts COVID-19 patient hospitalization based on clinical, laboratory, and chest X-ray at time of presentation to the Emergency Department. The focus is on two cognitive dimensions: understandability and actionability of the explanations provided by explainable-by-design and post-hoc methods. Methods: A questionnaire-based experiment was conducted with 10 clinicians from the IRCCS Policlinico San Matteo Foundation in Pavia, Italy. Each clinician evaluated 10 real-world cases, rating predictions and explanations from three XAI tools: Bayesian networks, SHapley Additive exPlanations (SHAP), and AraucanaXAI. Two cognitive statements for each method were rated on a Likert scale, as well as the agreement with the prediction. Two clinicians answered the survey during think-aloud interviews. Results: Clinicians demonstrated generally positive attitudes toward AI, but high compliance rates (86% on average) indicate a risk of automation bias. Understandability and actionability are positively correlated, with SHAP being the preferred method due to its simplicity. However, the perception of methods varies according to specialty and expertise. Conclusions: The findings suggest that SHAP and AraucanaXAI are promising candidates for improving the use of XAI in clinical decision support systems (DSSs), highlighting the importance of clinicians’ expertise, specialty, and setting on the selection and development of supportive XAI advice. Finally, the study provides valuable insights into the design of future XAI DSSs.

Rib fractures are common conditions often associated with significant complications, including respiratory failure, pneumonia, prolonged hospitalisation, and chronic pain. Adequate pain management is crucial to improve outcomes and reduce morbidity in these patients. Despite the wide adoption of multimodal analgesia, the optimal combination of analgesic strategies remains uncertain. To review and synthesize current evidence on analgesic strategies for acute pain management in patients with rib fractures. We conducted a narrative review by searching scientific literature on PubMed and Scopus to identify randomised controlled trials (RCTs) on analgesia for rib fractures from blunt trauma. Included studies assessed pharmacologic, non-pharmacologic and regional anaesthesia interventions. Studies describing surgical treatment of multiple rib fractures or addressing analgesia for non-traumatic causes of rib fractures (e.g. neoplasms) or study design other than RCTs were excluded. Forty-seven RCTs met the inclusion criteria. Opioids remain the most studied class of analgesics in the context of rib fracture. While effective for acute pain relief, they pose significant risks, especially in the elderly population. Non-opioid agents - especially non-steroidal anti-inflammatory drugs (NSAIDs) and paracetamol -are effective components of opioid-sparing strategies. Thoracic epidural and paravertebral blocks offer superior analgesia and respiratory benefits but are associated with a steep learning curve, are time-consuming, and carry a significant risk of procedural complications. Emerging regional anaesthesia techniques, such as the erector spinae plane (ESP) and serratus anterior plane (SAP) blocks, demonstrated promising results due to their ease of administration and favourable safety profiles. Non-pharmacologic approaches, including cryotherapy, transcutaneous electrical nerve stimulation (TENS), and kinesiotaping, represent additional pain relief options, although evidence remains limited. Multimodal analgesia - combining pharmacologic, non-pharmacologic and regional anaesthesia approaches -is considered the most effective strategy to guarantee pain relief in patients with multiple rib fractures. However, substantial heterogeneity remains in the regimens employed. Further research is needed to standardize multimodal analgesic protocols and to assess their impact on long-term, patient-centred outcomes.

Background: COVID-19 is an emerging infectious disease, that is heavily challenging health systems worldwide. Admission Arterial Blood Gas (ABG) and Lung Ultrasound (LUS) can be of great help in clinical decision making, especially during the current pandemic and the consequent overcrowding of the Emergency Department (ED). The aim of the study was to demonstrate the capability of alveolar-to-arterial oxygen difference (AaDO₂) in predicting the need for subsequent oxygen support and survival in patients with COVID-19 infection, especially in the presence of baseline normal PaO₂/FiO₂ ratio (P/F) values. Methods: A cohort of 223 swab-confirmed COVID-19 patients underwent clinical evaluation, blood tests, ABG and LUS in the ED. LUS score was derived from 12 ultrasound lung windows. AaDO₂ was derived as AaDO₂ = ((FiO₂) (Atmospheric pressure − H₂O pressure) − (PaCO₂/R)) − PaO₂. Endpoints were subsequent oxygen support need and survival. Results: A close relationship between AaDO₂ and P/F and between AaDO₂ and LUS score was observed (R² = 0.88 and R² = 0.67, respectively; p < 0.001 for both). In the subgroup of patients with P/F between 300 and 400, 94.7% (n = 107) had high AaDO₂ values, and 51.4% (n = 55) received oxygen support, with 2 ICU admissions and 10 deaths. According to ROC analysis, AaDO₂ > 39.4 had 83.6% sensitivity and 90.5% specificity (AUC 0.936; p < 0.001) in predicting subsequent oxygen support, whereas a LUS score > 6 showed 89.7% sensitivity and 75.0% specificity (AUC 0.896; p < 0.001). Kaplan–Meier curves showed different mortality in the AaDO₂ subgroups (p = 0.0025). Conclusions: LUS and AaDO₂ are easy and effective tools, which allow bedside risk stratification in patients with COVID-19, especially when P/F values, signs, and symptoms are not indicative of severe lung dysfunction.

The COVID-19 pandemic highlighted an urgent need for reliable diagnostic tools to minimize viral spreading. It is mandatory to avoid cross-contamination between patients and detect COVID-19 positive individuals to cluster people by prognosis and manage the emergency department’s resources. Fondazione IRCCS Policlinico San Matteo Hospital’s Emergency Department (ED) of Pavia let us evaluate the exploitation of machine learning algorithms on a clinical dataset gathered from laboratory-confirmed rRT-PCR test patients, collected from 1 March to 30 June 2020. Physicians examined routine blood tests, clinical history, symptoms, arterial blood gas (ABG) analysis, and lung ultrasound quantitative examination. We developed two diagnostic tools for COVID-19 detection and oxygen therapy prediction, namely, the need for ventilation support due to lung involvement. We obtained promising classification results with F1 score levels meeting 92%, and we also engineered a user-friendly interface for healthcare providers during daily screening operations. This research proved machine learning models as a potential screening methodology during contingency times.

Artificial intelligence is increasingly used to support clinical decision making, yet concerns remain regarding algorithmic aversion, automation bias and the preservation of meaningful human oversight; while explainable AI aims to improve transparency, less attention has been devoted to the design of human–AI interaction protocols. This study investigates Frictional AI, an interaction paradigm that introduces cognitive friction to encourage critical engagement with AI recommendations. First, semi-structured interviews were conducted with a legal expert and a psychologist and analyzed through thematic analysis to identify legal, ethical, and cognitive requirements for AI-assisted decision support. Second, a user study involving 96 medical residents compared three interaction protocols: a conventional explainable AI-first design (XAI) and two friction-based protocols, namely a judicial protocol based on juxtaposed explanations (Judicial AI, JAI) and an adjunct protocol requiring an initial unsupported decision before AI exposure (AAI). Diagnostic accuracy and confidence, perceived usefulness, completion time, and reliance patterns were evaluated. The interviews highlighted the importance of human-centered explanations, contrastive reasoning, preservation of professional responsibility, and the role of user studies in evaluating human–AI interaction. The quantitative results showed that none of the AI-assisted conditions improved diagnostic accuracy relative to the no-support baseline. However, JAI achieved performance comparable to the baseline, outperforming XAI and AAI, and exhibited the lowest level of over-reliance. Overall findings suggest that the effectiveness of decision-support systems depends not only on model performance and explanation quality but also on interaction design. In conclusion, while preserving diagnostic performance, judicial protocols showed promise in mitigating automation bias and promoting active cognitive engagement in clinical decision support.

Background/Objectives: Sustained ventricular tachycardia (VT) is a potentially life-threatening arrhythmia requiring prompt Emergency Department (ED) assessment and management. However, data on its frequency, real-world treatment, and prognosis in the ED remain limited. We aimed to describe the clinical characteristics, acute management, and short- and long-term outcomes of patients presenting with VT. Methods: We retrospectively included consecutive patients presenting to the ED between January 2018 and December 2024 with a primary diagnosis of sustained VT with a pulse. We collected baseline characteristics, hemodynamic status, underlying cardiac disease, and acute treatment. In-hospital events and 30-day and 1-year outcomes were assessed. Results: A total of 103 patients were identified, accounting for approximately 0.025% of all ED visits during the study period; 84.5% were male. Chest pain (31.1%) and palpitations (25.2%) were the most common presenting symptoms. Structural heart disease was present in 90% of the cases, predominantly of ischemic origin (61%). Nearly half of the patients (49.5%) had a prior history of VT. Electrical cardioversion was performed in 28.2% of the cases. The majority of the patients (95/103; 92%) required hospitalization. Mortality was 4.9% at 30 days and 17% at 1 year. After adjustment for age, a left ventricular ejection fraction ≤ 30% and in-hospital arrhythmic recurrence were independently associated with 1-year mortality. Conclusions: Sustained VT is an uncommon but high-risk ED presentation, mainly affecting patients with ischemic structural heart disease. A discrepancy was observed between real-world clinical practice and guideline recommendations. The substantial mortality observed, particularly among patients with impaired left ventricular function or in-hospital arrhythmic recurrence, highlights the need for prompt risk stratification and optimized, guideline-concordant acute management.