Search Results (359)

Background: Identifying high-grade strictures (HGS) in patients with primary sclerosing cholangitis (PSC) relies upon subjective assessments of magnetic resonance cholangiopancreatography (MRCP). Quantitative MRCP (MRCP+) provides objective evaluation of MRCP examinations, which may help make these assessments more consistent and improve patient management and selection for intervention. We evaluated the impact of MRCP+ on clinicians’ confidence in diagnosing HGS in patients with PSC. Methods: Three expert abdominal radiologists independently assessed 28 patients with PSC. Radiological reads of MRCPs were performed twice, in a random order, three weeks apart, then a third time with MRCP+. HGS presence was recorded on semi-quantitative confidence scales. The cases where readers definitively agreed on presence/absence of HGS were used to assess inter- and intra-reader agreement and confidence. Results: When using MRCP alone, high intra-reader agreement was observed in identifying HGS within both intra- and extrahepatic ducts (64.3% and 70.8%, respectively), while inter-reader agreement was significantly lower for intrahepatic ducts (42.9%) than extrahepatic ducts (66.1%) (p < 0.01). Using MRCP+ in the third read significantly improved inter-reader agreement for intrahepatic HGS detection to 67.9% versus baseline reads (p = 0.02) and was comparable with extrahepatic ducts. Reader confidence tended to increase when supplemented with MRCP+, and inter-reader variability decreased. MRCP+ metrics had good performance in identifying HGS in both extra-hepatic (AUC:0.85) and intra-hepatic ducts (AUC:0.75). Conclusions: MRCP evaluation supported by quantitative metrics tended to increase individual reader confidence and reduce inter-reader variability for detecting HGS. Our results indicate that MRCP+ might help standardize MRCP assessment and subsequent management for patients with PSC. Full article

Background/Objectives: Chronic pain and eating disorders are two prevalent and disabling pediatric health concerns, with serious, life-threatening consequences. These conditions can co-occur, yet little is known about best practices addressing comorbid pain and eating disorders. Delayed intervention for eating disorders may have grave implications, as eating disorders have one of the highest mortality rates among psychological disorders. Moreover, chronic pain not only persists but worsens into adulthood when left untreated. This study aimed to understand pediatric clinicians’ experiences with adolescents with chronic pain and eating disorders. Methods: Semi-structured interviews were conducted with hospital-based physicians (N = 10; 70% female; M years of experience = 15.3) and psychologists (N = 10; 80% female; M years of experience = 10.2) specializing in anesthesiology/pain, adolescent medicine/eating disorders, and gastroenterology across the United States. Audio transcripts were coded, and thematic analysis was used to identify key themes. Results: Clinicians described frequently encountering adolescents with chronic pain and eating disorders. Clinicians described low confidence in diagnosing comorbid eating disorders and chronic pain, which they attributed to lack of screening tools and limited training. Clinicians collaborated with and consulted clinicians who encountered adolescents with chronic pain and/or eating disorders. Conclusions: Results reflect clinicians’ desire for additional resources, training, and collaboration to address the needs of this population. Targets for future research efforts in comorbid pain and eating disorders were highlighted. Specifically, results support the development of screening tools, program development to improve training in complex medical and psychiatric presentations, and methods to facilitate more collaboration and consultation across health care settings, disciplines, and specialties. Full article

Background: Artificial intelligence (AI) is being increasingly promoted as a means to enhance diagnostic accuracy, to streamline workflows, and to improve overall care quality in primary care. However, empirical evidence on how primary care physicians (PCPs) perceive, engage with, and emotionally respond to AI technologies in everyday clinical settings remains limited. Concerns persist regarding AI’s usability, transparency, and potential impact on professional identity, workload, and the physician–patient relationship. Methods: This qualitative study investigated the lived experiences and perceptions of 28 PCPs practicing in diverse outpatient settings across Germany. Participants were purposively sampled to ensure variation in age, practice characteristics, and digital proficiency. Data were collected through in-depth, semi-structured interviews, which were audio-recorded, transcribed verbatim, and subjected to rigorous thematic analysis employing Mayring’s qualitative content analysis framework. Results: Participants demonstrated a fundamentally ambivalent stance toward AI integration in primary care. Perceived advantages included enhanced diagnostic support, relief from administrative burdens, and facilitation of preventive care. Conversely, physicians reported concerns about workflow disruption due to excessive system prompts, lack of algorithmic transparency, increased cognitive and emotional strain, and perceived threats to clinical autonomy and accountability. The implications for the physician–patient relationship were seen as double-edged: while some believed AI could foster trust through transparent use, others feared depersonalization of care. Crucial prerequisites for successful implementation included transparent and explainable systems, structured training opportunities, clinician involvement in design processes, and seamless integration into clinical routines. Conclusions: Primary care physicians’ engagement with AI is marked by cautious optimism, shaped by both perceived utility and significant concerns. Effective and ethically sound implementation requires co-design approaches that embed clinical expertise, ensure algorithmic transparency, and align AI applications with the realities of primary care workflows. Moreover, foundational AI literacy should be incorporated into undergraduate health professional curricula to equip future clinicians with the competencies necessary for responsible and confident use. These strategies are essential to safeguard professional integrity, support clinician well-being, and maintain the humanistic core of primary care. Full article

Objectives: The objective of this study was to assess the effect of aerobic exercise on depressive symptoms and to determine the optimal exercise prescription for Parkinson’s disease (PD) patients. Methods: A comprehensive search was conducted across PubMed, Web of Science, Cochrane, Scopus, and Embase databases. A meta-analysis was conducted to determine the standardized mean difference (SMD) and 95% confidence interval. Results: Aerobic exercise significantly alleviated depressive symptoms in PD patients (SMD, −0.68, p = 0.002). Subgroup analyses revealed that moderate intensity aerobic exercise (SMD, −0.72, p = 0.0006), interventions conducted for ≥12 weeks (SMD, −0.85, p = 0.04), ≥3 times per week (SMD, −0.68, p = 0.002), ≥60 min per session (SMD, −0.57, p < 0.0001), and ≥180 min per week (SMD, −0.87, p = 0.0002) were more effective in improving depressive symptoms in PD patients, especially in PD patients with a disease duration of ≤6 years (SMD, −1.00, p = 0.04). Conclusions: Integrating the available data, it is clear that aerobic exercise is a proven method for alleviating depressive symptoms in PD patients. This meta-analysis provides empirical support for clinicians to recommend that PD patients engage in aerobic exercise regimens of no less than 12 weeks’ duration, performed at a minimum frequency of three sessions per week, with each session lasting in excess of 60 min and a cumulative weekly duration of at least 180 min, to effectively attenuate depressive symptomatology. Earlier implementation of aerobic exercise interventions is recommended, as PD patients in the early stages of the disease (up to 6 years post-diagnosis) may derive the greatest benefit in terms of depression symptom improvement from such programs. Full article

Background: To assess the accuracy of ChatGPT-4o and OpenAI-o1 in answering refractive surgery questions from the AAO BCSC Self-Assessment Program and to evaluate whether their performance could meaningfully support clinical decision making, we compared the models with 1983 ophthalmology residents and clinicians. Methods: A randomized, questionnaire-based study was conducted with 228 text-only questions from the Refractive Surgery section of the BCSC Self-Assessment Program. Each model received the prompt, “Please provide an answer to the following questions.” Accuracy was measured as the proportion of correct answers and reported with 95 percent confidence intervals. Differences between groups were assessed with the chi-squared test for independence and pairwise comparisons. Results: OpenAI-o1 achieved the highest score (91.2%, 95% CI 87.6–95.0%), followed by ChatGPT-4o (86.4%, 95% CI 81.9–90.9%) and the average score from 1983 users of the Refractive Surgery section of the BCSC Self-Assessment Program (77%, 95% CI 75.2–78.8%). Both language models significantly outperformed human users. The five-point margin of OpenAI-o1 over ChatGPT-4o did not reach statistical significance (p = 0.1045) but could represent one additional correct decision in twenty clinically relevant scenarios. Conclusions: Both ChatGPT-4o and OpenAI-o1 significantly outperformed BCSC Program users, demonstrating a level of accuracy that could augment medical decision making. Although OpenAI-o1 scored higher than ChatGPT-4o, the difference did not reach statistical significance. These findings indicate that the “advanced reasoning” architecture of OpenAI-o1 offers only incremental gains and underscores the need for prospective studies linking LLM recommendations to concrete clinical outcomes before routine deployment in refractive-surgery practice. Full article

Objectives: To employ artificial intelligence (AI) to automatically measure bone mineral density (BMD) and intramuscular fat in computed tomography (CT) images of patients with fractures and explore the association between these parameters and fracture healing. Methods: This retrospective study included patients who underwent baseline CT scans for rib fracture diagnosis and follow-up CT scans for fracture healing assessment at our hospital between 2012 and 2023. The volumetric BMD of the entire first lumbar vertebra (L1) and the paraspinal intramuscular fat area (PIFA) at the midsection of L1 in the baseline CT were extracted using AI. The primary outcomes, including callus formation, volume increase, and poor healing, and logistic regression were used to analyze the relationships between BMD and PIFA with primary outcomes. Results: Overall, 297 fractures from 53 patients (24 males; mean age: 53.83 ± 10.86 years) were included in this study. In multivariate regression analysis, a 1 standard deviation (SD) decrease in BMD was identified as an independent prognostic factor for reduced callus formation (odds ratio [OR] = 0.70, 95% confidence interval [CI] = 0.50–0.97), diminished volume increase (OR = 0.70, 95% CI = 0.51–0.96), and elevated poor fracture healing at follow-up (OR = 2.08, 95% CI = 1.38–3.13). Similarly, a 1 SD increase in PIFA was an independent prognostic factor for reduced callus formation (OR = 0.24, 95% CI = 0.16–0.37), diminished volume increase (OR = 0.33, 95% CI = 0.23–0.49), and elevated poor fracture healing at follow-up (OR = 2.09, 95% CI = 1.50–2.93). Therefore, a model combining BMD, PIFA, and clinical characteristics significantly outperformed a model that included only clinical characteristics in predicting callus formation, volume increase, and poor fracture healing, with areas under the curve of 0.790, 0.749, and 0.701, respectively (all p < 0.001). Conclusions: BMD and PIFA can be used as early predictors of fracture healing outcomes and can help clinicians select appropriate interventions to prevent poor healing. Full article

Background and Objectives: Nausea and vomiting (NV) are common and distressing adverse effects among cancer patients undergoing treatment. Despite the widespread use of pharmacological antiemetics, these medications are often insufficient for controlling nausea and may cause medication interactions and side effects. Acupuncture has been proposed as a complementary therapy; however, the comprehensive analysis of its effects on NV across all emetogenic cancer treatments remains limited. This systematic review and meta-analysis aimed to evaluate the effectiveness and safety of acupuncture in managing NV in cancer patients undergoing chemotherapy, radiotherapy, or surgery. Materials and Methods: We conducted a comprehensive search across three electronic databases and two clinical registry platforms from inception to December 2024. Randomized controlled trials (RCTs) evaluating acupuncture for NV in cancer patients were included. Risk ratios (RRs) and 95% confidence intervals (CIs) were calculated using a random-effects model. Safety outcomes were assessed based on the Common Terminology Criteria for Adverse Events (CTCAE). Results: Seventeen RCTs met the inclusion criteria, with twelve studies included in the meta-analysis. Acupuncture did not demonstrate significant effects on acute nausea (RR: 0.98; 95% CI: 0.84–1.15; p = 0.80) or acute vomiting (RR: 0.93; 95% CI: 0.65–1.32; p = 0.67). However, it significantly reduced delayed vomiting (RR: 0.76; 95% CI: 0.61–0.95; p = 0.02). Subgroup analysis demonstrated significant effects when acupuncture was administered for at least five days (RR: 0.56; 95% CI: 0.39–0.81; p = 0.002). The most frequently used acupoints were PC6, ST36, CV12, LI4, LR3, and ST25. No serious adverse events related to acupuncture treatments were reported, with only minor AEs such as localized bleeding and mild bruising observed. Conclusions: Acupuncture represents a safe and effective complementary therapy for managing delayed vomiting in cancer patients receiving emetogenic treatments. Clinicians can anticipate optimal benefits from at least five days of treatment, particularly using acupoints PC6, ST36, CV12, LI4, LR3, and ST25. Further high-quality studies are needed to establish standardized treatment regimens and explore its comprehensive effects on NV. Full article

Feline coronavirus (FCoV) is a major pathogen causing feline infectious peritonitis (FIP), a lethal disease in cats, necessitating accurate diagnostic methods. This study developed and compared novel primers targeting the FCoV membrane (M) gene for enhanced detection. Specific primers were designed for the M gene and their performance evaluated using reverse transcription-PCR (RT-PCR), nested RT-PCR, and reverse transcription-quantitative PCR (RT-qPCR) on 80 clinical effusion samples from cats suspected of FIP. Specificity of assays was tested against other feline viruses, with sensitivity being assessed via serial dilutions of FCoV RNA. RT-qPCR had the highest sensitivity, detecting 9.14 × 10¹ copies/µL, identifying 93.75% of positive samples, followed by nested RT-PCR (87.50%, 9.14 × 10⁴ copies/µL) and RT-PCR (61.25%, 9.14 × 10⁶ copies/µL). All assays had 100% specificity, with no cross-reactivity to other viruses. The nested RT-PCR and RT-qPCR outperformed RT-PCR significantly, with comparable diagnostic accuracy. The novel primers targeting the FCoV M gene, coupled with RT-qPCR, delivered unparalleled sensitivity and robust reliability for detecting FCoV in clinical settings. Nested RT-PCR was equally precise and amplified diagnostic confidence with its high performance. These cutting-edge assays should revolutionize FCoV detection, offering trusted tools that seamlessly integrate into veterinary practice, empowering clinicians to manage feline infectious peritonitis with unprecedented accuracy and speed. Full article

Background: Hypotension following epidural labor analgesia (ELA) is its most common complication, affecting approximately 20% of patients and posing risks to both maternal and fetal health. As digital tools and predictive analytics increasingly shape perioperative and obstetric anesthesia practices, real-world implementation data are needed to guide their integration into clinical care. Current monitoring practices rely on intermittent non-invasive blood pressure (NIBP) measurements, which may delay recognition and treatment of hypotension. The Hypotension Prediction Index (HPI) algorithm uses continuous arterial waveform monitoring to predict hypotension for potentially earlier intervention. This clinical trial evaluated the feasibility, acceptability, and efficacy of continuous HPI-guided treatment in reducing time-to-treatment for ELA-associated hypotension and improving maternal hemodynamics. Methods: This was a prospective randomized controlled trial design involving healthy pregnant individuals receiving ELA. Participants were randomized into two groups: Group CM (conventional monitoring with NIBP) and Group HPI (continuous noninvasive blood pressure monitoring). In Group HPI, hypotension treatment was guided by HPI output; in Group CM, treatment was based on NIBP readings. Feasibility, appropriateness, and acceptability outcomes were assessed among subjects and their bedside nurse using the Acceptability of Intervention Measure (AIM), Intervention Appropriateness Measure (IAM), and Feasibility of Intervention Measure (FIM) instruments. The primary efficacy outcome was time-to-treatment of hypotension, defined as the duration between onset of hypotension and administration of a vasopressor or fluid therapy. This outcome was chosen to evaluate the clinical responsiveness enabled by HPI monitoring. Hypotension is defined as a mean arterial pressure (MAP) < 65 mmHg for more than 1 min in Group CM and an HPI threshold < 75 for more than 1 min in Group HPI. Secondary outcomes included total time in hypotension, vasopressor doses, and hemodynamic parameters. Results: There were 30 patients (Group HPI, n = 16; Group CM, n = 14) included in the final analysis. Subjects and clinicians alike rated the acceptability, appropriateness, and feasibility of the continuous monitoring device highly, with median scores ≥ 4 across all domains, indicating favorable perceptions of the intervention. The cumulative probability of time-to-treatment of hypotension was lower by 75 min after ELA initiation in Group HPI (65%) than Group CM (71%), although this difference was not statistically significant (log-rank p = 0.66). Mixed models indicated trends that Group HPI had higher cardiac output (β = 0.58, 95% confidence interval −0.18 to 1.34, p = 0.13) and lower systemic vascular resistance (β = −97.22, 95% confidence interval −200.84 to 6.40, p = 0.07) throughout the monitoring period. No differences were found in total vasopressor use or intravenous fluid administration. Conclusions: Continuous monitoring and precision hypotension treatment is feasible, appropriate, and acceptable to both patients and clinicians in a labor and delivery setting. These hypothesis-generating results support that HPI-guided treatment may be associated with hemodynamic trends that warrant further investigation to determine definitive efficacy in labor analgesia contexts. Full article

Background: Intracerebral hemorrhage management presents clinicians with a significant therapeutic challenge. Maintaining antiplatelet therapy potentially increases the risk of recurrent bleeding, while discontinuation heightens susceptibility to ischemic stroke, particularly during the critical first month after hemorrhage. In contemporary practice, physicians demonstrate considerable hesitancy regarding early antiplatelet reinitiation, complicated by the absence of clear evidence-based treatment guidelines. Aim: This meta-analysis assesses the safety of early antiplatelet resumption following ICH. Methods: We conducted a systematic review by searching Web of Science, Scopus, PubMed, and Cochrane Library from inception to April 2025. Articles were independently screened and data extracted by two reviewers who also assessed study quality. The inclusion criteria are enrollment of adults (≥18 years) with imaging-confirmed intracerebral hemorrhage surviving >24 h, comparing early vs. delayed or withheld antiplatelet therapy. Randomized trials underwent separate evaluation using Cochrane’s Risk of Bias. Statistical analysis was performed using R software (version 4.4.2), with categorical outcomes pooled as risk ratios (RRs) with 95% confidence intervals. Statistical significance was established at p < 0.05. The evidence is limited by the availability of few RCTs, variable antiplatelet regiments, male predominance, and other confounding factors. The review was registered in SFO. Results: Our meta-analysis included 10 studies (8 observational, 2 RCTs) with 5554 patients. Early antiplatelet therapy significantly reduced recurrent intracerebral hemorrhage by 46% (RR 0.54, 95% CI 0.37–0.78, p = 0.001). All-cause mortality showed a non-significant difference (RR 0.81, 95% CI 0.65–1.01, p = 0.06). No significant differences were found for ischemic stroke (RR 0.99, 95% CI 0.60–1.63, p = 0.96), major hemorrhagic events (RR 0.75, 95% CI 0.49–1.13, p = 0.17), or ischemic vascular outcomes (RR 0.71, 95% CI 0.49–1.02, p = 0.60). Conclusions: Our meta-analysis reveals that early antiplatelet therapy following intracerebral hemorrhage significantly reduces recurrent hemorrhagic events (46% reduction) without increasing major ischemic or hemorrhagic complications. Full article

Interest in explainable machine learning has grown, particularly in healthcare, where transparency and trust are essential. We developed a semi-automated evaluation framework within a clinical decision support system (CDSS-EQCM) that integrates LIME and SHAP explanations with multi-criteria decision-making (TOPSIS and Borda count) to rank model interpretability. After two-phase preprocessing of 2934 COVID-19 patient records spanning four epidemic waves, we applied five classifiers (Random Forest, Decision Tree, Logistic Regression, k-NN, SVM). Five infectious disease physicians used a Streamlit interface to generate patient-specific explanations and rate models on accuracy, separability, stability, response time, understandability, and user experience. Random Forest combined with SHAP consistently achieved the highest rankings in Borda count. Clinicians reported reduced evaluation time, enhanced explanation clarity, and increased confidence in model outputs. These results demonstrate that CDSS-EQCM can effectively streamline interpretability assessment and support clinician decision-making in medical diagnostics. Future work will focus on deeper electronic medical record integration and interactive parameter tuning to further enhance real-time diagnostic support. Full article

Background: The effective use of electronic health records (EHRs) is an essential clinical skill, but medical schools have traditionally provided limited systematic teaching on the topic. Inefficient use of EHRs results in delays in diagnosis, fragmented care, and clinician burnout. This study investigates the impact on medical students’ confidence, efficiency, and proficiency in extracting clinically pertinent information from patient records following an organised EHR teaching programme. Methods: This observational cohort involved 60 final-year medical students from three London medical schools. Participants received a structured three-phase intervention involving an introductory workshop, case-based hands-on practice, and guided reflection on EHR navigation habits. Pre- and post-intervention testing involved mixed-method surveys, simulated case tasks, and faculty-assessed data retrieval exercises to measure changes in students’ confidence, efficiency, and ability to synthesise patient information. Quantitative data were analysed using paired t-tests, while qualitative reflections were theme-analysed to identify shifts in clinical reasoning. Results: All 60 students successfully finished the intervention and assessments. Pre-intervention, only 28% students reported feeling confident in using EHRs effectively, with a confidence rating of 3.0. Post-intervention, 87% reported confidence with a rating of 4.5 (p < 0.01). Efficiency in the recovery of critical patient information improved from 3.2 to 4.6 (p < 0.01). Students also demonstrated enhanced awareness regarding system-related issues, such as information overload and fragmented documentation, and provided recommendations on enhancing data synthesis for clinical decision making. Conclusions: This study emphasises the value of structured EHR instruction in enhancing the confidence and proficiency of medical students in using electronic records. The integration of structured EHR education to medical curricula can better prepare future physicians in managing information overload, improve diagnostic accuracy, and enhance the quality of patient care. Future research should explore the long-term impact of structured EHR training on clinical performance, diagnostic accuracy, and patient outcomes during real-world clinical placements and postgraduate training. Full article

Background: Synthetic and pseudosynthetic images can be used to extend colonoscopy datasets, which, in turn, are used to train AI-detection models, yet their clinical acceptability depends on whether medical professionals can still recognize non-real content. Aim: To quantify the ability of practicing gastroenterologists to discriminate real, pseudosynthetic, and synthetic polyp images and to determine how training level and synthesis method impact detection. Materials and Methods: A total of 32 Romanian gastroenterologists (18 residents and 14 seniors) reviewed 24 images (8 real, 8 augmented, 4 CycleGAN, and 4 diffusion) via an online form. Classification accuracy, 95% confidence intervals (CI), class sensitivity and precision, 3 × 3 confusion matrices, and Fleiss’ κ were calculated. Resident vs. senior differences were tested with Pearson χ²; CycleGAN versus diffusion detectability was analyzed with the Wilcoxon signed-rank test (α = 0.05). Results: Overall accuracy was 61.2% (95% CI 57.7–64.6). Residents and seniors performed similarly (62.3% vs. 59.8%; χ²₁ = 0.38, p = 0.54). Sensitivity/precision were 70.7%/62.2% for real, 51.6%/58.9% for augmented, and 61.3%/62.1% for synthetic images. Collapsing to “real vs. non-real” yielded 70.7% sensitivity and 78.5% specificity for real images. CycleGAN images were always recognized as synthetic (128/128; 97.1–100% CI), whereas diffusion images were correctly classified only 22.7% of the time (16.3–30.6%; Wilcoxon p < 0.001). The training level did not impact detection performance (χ²₂ < 1.2, p > 0.5). Inter-rater agreement was fair (κ = 0.30, 95% CI 0.15–0.43). Conclusions: Clinicians detect non-real colonoscopy images only slightly above chance, irrespective of experience. The diffusion synthesis method creates images that escape human scrutiny, suggesting the need for automated authenticity safeguards before synthetic datasets are applied in clinical or AI-validation contexts. Full article

Background: The integration of artificial intelligence (AI) into healthcare research has the potential to enhance research capacity, streamline protocol development, and reduce barriers to engagement. Medway NHS Foundation Trust identified a plateau in homegrown research participation, particularly among clinicians with limited research experience. A generative AI-driven chatbot was introduced to assist researchers in protocol development by providing step-by-step guidance, prompting ethical and scientific considerations, and offering immediate feedback. Methods: The chatbot was developed using OpenAI’s GPT-3.5 architecture, customised with domain-specific training based on Trust guidelines, Health Research Authority (HRA) requirements, and Integrated Research Application System (IRAS) submission protocols. It was deployed to guide researchers through protocol planning, ensuring compliance with ethical and scientific standards. A mixed-methods evaluation was conducted using a qualitative-dominant sequential explanatory design. Seven early adopters completed a 10-item questionnaire (5-point Likert scales), followed by eight free-flowing interviews to achieve thematic saturation. Results: Since its launch, the chatbot has received an overall performance rating of 8.86/10 from the seven survey respondents. Users reported increased confidence in protocol development, reduced waiting times for expert review, and improved inclusivity in research participation across professional groups. However, limitations in usage due to free-tier platform constraints were identified as a key challenge. Conclusions: AI-driven chatbot tools show promise in supporting research engagement in busy clinical environments. Future improvements should focus on expanding access, optimising integration, and fostering collaboration among NHS institutions to enhance research efficiency and inclusivity. Full article

Background: The rapid integration of artificial intelligence (AI) technologies into healthcare systems presents new opportunities and challenges, particularly regarding legal and ethical implications. In Saudi Arabia, the lack of legal awareness could hinder safe implementation of AI tools. Methods: A sequential explanatory mixed-methods design was employed. In Phase One, a structured electronic survey was administered to 357 clinicians across public and private healthcare institutions in Saudi Arabia, assessing legal awareness, liability concerns, data privacy, and trust in AI. In Phase Two, a qualitative expert panel involving health law specialists, digital health advisors, and clinicians was conducted to interpret survey findings and identify key regulatory needs. Results: Only 7% of clinicians reported high familiarity with AI legal implications, and 89% had no formal legal training. Confidence in AI compliance with data laws was low (mean score: 1.40/3). Statistically significant associations were found between professional role and legal familiarity (χ² = 18.6, p < 0.01), and between legal training and confidence in AI compliance (t ≈ 6.1, p < 0.001). Qualitative findings highlighted six core legal barriers including lack of training, unclear liability, and gaps in regulatory alignment with national laws like the Personal Data Protection Law (PDPL). Conclusions: The study highlights a major gap in legal readiness among Saudi clinicians, which affects patient safety, liability, and trust in AI. Although clinicians are open to using AI, unclear regulations pose barriers to safe adoption. Experts call for national legal standards, mandatory training, and informed consent protocols. A clear legal framework and clinician education are crucial for the ethical and effective use of AI in healthcare. Full article