The Use of Artificial Intelligence for Personalized Treatment in Psychiatry.

Introduction Brain arteriovenous malformations (bAVMs) are complex vascular anomalies with unpredictable clinical behavior. Conventional predictors of rupture and treatment outcomes such as Spetzler‐Martin grading offer limited prognostic precision. In recent years, artificial intelligence (AI) has emerged as a transformative tool in neurosurgery, offering the potential to improve outcome prediction by integrating imaging, clinical, and molecular data. This scoping review explores the application landscape, methodological rigor, and translational readiness of AI models in forecasting bAVM rupture, treatment response, and obliteration outcomes. Methods Following the PRISMA‐ScR framework, we conducted a systematic search across PubMed, Embase, IEEE Xplore, and Scopus from inception through May 2025. Inclusion criteria encompassed original studies applying machine learning (ML), deep learning (DL), or radiomics‐based models to predict bAVM‐related outcomes. We categorized studies by outcome target (e.g., rupture, post‐treatment hemorrhage, obliteration), AI methodology, input modalities (e.g., DSA, MRI, clinical variables), and validation approach. Data extraction and critical appraisal were conducted in duplicate. We visualized key trends and mapped performance metrics across model types using Python (matplotlib/seaborn). Results A total of 23 studies met inclusion criteria, published between 2018 and 2025. Predictive targets included nidus obliteration (n=11), rupture risk (n=6), post‐treatment hemorrhage (n=3), and neurological outcome (n=3). AI modalities ranged from classical ML algorithms (logistic regression, random forest) to neural networks and radiomics‐enhanced DL pipelines. Input features commonly integrated imaging (DSA 74%, MRI 39%) with clinical data (age, AVM size, prior rupture). Models incorporating radiomics achieved the highest discriminatory power, with area under the ROC curve (AUC) values up to 0.87 for obliteration prediction and 0.81 for rupture forecasting. However, methodological limitations were pervasive. Only 5 studies employed external validation; 14 relied solely on internal k‐fold cross‐validation. Model interpretability tools (e.g., SHAP, LIME) were used in just 3 studies. While 8 studies used large datasets (>500 patients), 12 were retrospective single‐center studies with high risk of overfitting. No AI tool has yet been clinically deployed or validated prospectively. Conclusion AI has demonstrated strong potential in predicting key bAVM outcomes, especially when leveraging high‐dimensional radiomic features and hybrid imaging‐clinical models. Nevertheless, translation into clinical practice is constrained by limited external validation, lack of interpretability, and heterogeneous methodology. Future work must prioritize multicenter data harmonization, prospective trials, and the development of explainable AI tools to facilitate clinical trust and integration. AI, when responsibly developed and validated, may redefine precision risk stratification and treatment planning in bAVM care. image

Real-time use of artificial intelligence at colonoscopy predicts relapse in ulcerative colitis: predicting with “intelligence”

47 Background: Colorectal cancer (CRC) remains a leading cause of cancer-related mortality worldwide. Early detection and accurate diagnosis are essential for improving survival rates and optimizing therapeutic strategies. Recently, artificial intelligence (AI) technologies, such as machine learning algorithms, convolutional neural networks (CNNs), and computer-assisted diagnostic (CAD) systems, have significantly enhanced traditional diagnostic tools like colonoscopy and histopathology. This systematic review evaluates the current role of AI in CRC management, focusing on diagnostic improvements, predictive modeling, and outcome prediction. Methods: A comprehensive literature review was conducted using PubMed, Google Scholar, and MEDLINE using MeSH term to identify studies utilizing AI in CRC diagnosis and management, with a focus on diagnostic imaging, histopathological analysis, and predictive modeling. Studies were evaluated for the accuracy of AI-driven diagnostic systems and the predictive performance of AI models in clinical outcomes. Results: Out of 147 studies identified, 37 met the eligibility criteria for this review. AI tools such as CNNs, CAD systems, and EndoBRAIN showed high accuracy in CRC detection and polyp classification. Kudo et al. (2020) reported 98% CRC detection accuracy using EndoBRAIN. Blanes-Vidal et al. (2019) achieved 96.4% accuracy in polyp detection via DCNN. Additionally, Wang et al. (2019, 2020) demonstrated improved Adenoma Detection Rates (ADR) of 34.1% and 29.1%, respectively, using AI over traditional methods. For outcome prediction, AI models, including CNNs, predicted patient prognosis with reasonable accuracy, as highlighted by Skrede et al. (2020) with 76% accuracy in prognosis prediction. Conclusions: The systematic review and analysis of AI-assisted diagnostic modalities in colorectal cancer and polyp detection reveal promising results, with most models demonstrating high sensitivity, specificity, and accuracy. CNN-based models and CAD systems, in particular, show strong potential for improving detection rates and clinical outcomes in CRC screening. The studies included in this review demonstrate that AI can enhance diagnostic precision, particularly in identifying polyps and predicting clinical outcomes, with high validation rates. However, more external validation and long-term clinical studies are needed to fully establish the robustness of these AI tools in routine clinical practice.

Retinal vein occlusion (RVO) is the second most common cause of vision loss after diabetic retinopathy. It results from the occlusion of either the central retinal vein or one of its branches. Artificial intelligence (AI), particularly deep learning (DL), has shown great potential in ophthalmology for disease assessment. This review examined how AI has been applied to the diagnosis, segmentation, and treatment prediction of RVO across different imaging modalities.A comprehensive search of PubMed, Scopus, and Google Scholar up to June 19, 2024, identified 2,925 records, of which 23 met the inclusion criteria. Most studies (91%) were published after 2020, reflecting the rapid growth of AI in this field. DL algorithms were used in 87% of studies, mainly convolutional neural networks such as Residual Network, Densely Connected Convolutional Network, and Visual Geometry Group Network. Classification was the most frequent task (78%), followed by segmentation (26%) and prediction (17%). Color fundus photography was the most common imaging modality (57%), followed by fluorescein angiography (26%), with fewer studies using optical coherence tomography or optical coherence tomography angiography.Internal validation metrics were generally high (accuracy 0.79-0.99, sensitivity 0.67-1.00, specificity 0.80-1.00), but performance declined in external validation (accuracy 0.39-0.98, sensitivity 0.38-0.93), indicating limited generalizability. Segmentation models achieved Dice coefficients between 0.82 and 0.94. Only 30% of studies used external datasets, and one performed clinical validation. Explainable AI techniques were applied in 39% of studies, mostly Grad-CAM, though often in a qualitative manner.Overall, AI systems demonstrate strong potential for assisting in RVO diagnosis and management, but challenges remain. Limited dataset diversity, lack of multimodal fusion, and minimal clinical validation restrict real-world applicability. Future research should prioritize multicenter datasets, standardized evaluation, interpretability, and ethical governance to enable safe and effective integration of AI tools in ophthalmic care.

Study question What are the key considerations, validation frameworks, and safety guidelines required for the responsible implementation of Artificial Intelligence (AI) systems in MAR clinics? Summary answer The Croatia Consensus establishes internationally agreed-upon best practices for AI validation in MAR, ensuring patient safety, clinical excellence, regulatory compliance, and ethical implementation. What is known already AI applications are increasingly integrated into ART to optimise embryo selection, standardise clinical decision-making, and reduce variability. However, absence of internationally accepted validation frameworks, regulatory guidelines, and ethical oversight poses risks to patient safety and clinical efficacy. Current AI models often lack transparency, generalisation, and robust external validation. Bias in training datasets can lead to inequitable clinical outcomes. The need for structured AI governance in ART is pressing. The Croatia Consensus, formed by global experts (AI Fertility Society), aims to define best practices for AI validation and deployment in MAR clinics. Study design, size, duration A structured Delphi process involving 148 AI and MAR experts was conducted in 2024 to develop international guidelines for AI validation in ART. The consensus methodology included systematic literature reviews, expert panel discussions, and iterative feedback rounds. Topics covered included AI safety, validation protocols, data standardisation, regulatory compliance, and bias mitigation. The final consensus document was reviewed at the AI Fertility Society Meeting and endorsed by multidisciplinary stakeholders, including clinicians, embryologists, ethicists, and AI developers. Participants/materials, setting, methods Consensus guidelines were developed through contributions from embryologists, reproductive specialists, AI researchers, and regulatory experts. The process included a systematic review of AI applications in MAR, gap analysis of existing validation frameworks, and expert recommendations on AI validation strategies. Key aspects included standardised AI reporting (TRIPOD+AI compliance), real-world clinical validation across multiple centres, ethical risk mitigation, and transparent AI decision-making. AI system performance benchmarks were established using clinical outcome measures and patient safety indicators. Main results and the role of chance The Croatia Consensus establishes a comprehensive framework for AI validation in MAR, ensuring patient safety, regulatory compliance, and clinical efficacy. Key recommendations include multi-centre external validation of AI models to ensure generalisation across diverse patient populations, with the TRIPOD+AI framework recommended for transparent reporting. To mitigate bias, AI systems must undergo demographic audits, particularly in embryo selection, to prevent inequitable outcomes. Regulatory compliance with GDPR (EU), FDA (USA), and MHRA (UK) is required before clinical implementation. Transparency is critical; AI models must provide interpretable decisions, including confidence scores, feature importance, and performance metrics. Continuous post-implementation monitoring is essential to detect model drift and ensure patient safety over time. The consensus highlights that unvalidated AI models currently used in MAR clinics may introduce risks to patient outcomes. Implementing the Croatia Consensus framework will help standardise AI validation, mitigate risks, and ensure AI adoption in MAR is both evidence-based and clinically safe. Limitations, reasons for caution The consensus is based on expert opinions and current scientific literature; further empirical studies are required to validate AI best practices. The framework must evolve as AI capabilities and regulatory landscapes develop. Future research should focus on real-world AI deployment outcomes, patient safety, and long-term MAR success rates. Wider implications of the findings This is the first international AI validation framework in MAR. Standardising AI best practices will improve patient safety, optimise clinical outcomes, and enhance trust in AI-assisted fertility treatments. The framework provides a blueprint for MAR clinics, regulatory bodies, and AI developers, ensuring responsible AI integration into reproductive medicine. Trial registration number No

Background: Oral Squamous Cell Carcinoma (OSCC) accounts for a significant proportion of oral cancers, often diagnosed at late stages with poor survival outcomes. Artificial Intelligence (AI) has demonstrated promising capabilities in oncology, particularly in survival prediction. This systematic review and meta-analysis evaluates the role of AI in predicting survival outcomes, recurrence, and treatment responses in OSCC patients. Objective: To assess the diagnostic accuracy, sensitivity, specificity, and clinical impact of AI algorithms in predicting survival outcomes in OSCC. Methods: A systematic search of PubMed, Scopus, Web of Science, and Cochrane Library databases was conducted to identify studies published between 2000 and 2024. Studies were included if they evaluated AI models for survival prediction in OSCC patients. Pooled diagnostic metrics were calculated, and heterogeneity was assessed using the I² statistic. Subgroup analyses were performed based on data type, AI model, and patient population. Results: A total of 45 studies involving 8,200 patients were included. The pooled sensitivity and specificity of AI models in predicting 5-year survival were 87% and 82%, respectively. AI models incorporating clinical, imaging, and genetic data outperformed those using single data modalities (AUC: 0.91 vs. 0.79; p < 0.01). Machine learning models, particularly ensemble methods, demonstrated higher accuracy than traditional statistical approaches. Conclusion: AI provides high accuracy in predicting survival outcomes in OSCC patients, especially when integrating multimodal data. These findings highlight the potential of AI to support personalized treatment planning and improve patient outcomes. Future research should focus on external validation and implementation in clinical workflows.

Clinical deployment of AI for prostate cancer diagnosis

Is my cough COVID-19?

Populations worldwide are aging, with rapid growth in adults aged 65 years and older, particularly those aged 80 years and above. Aging is closely linked to multimorbidity, frailty and polypharmacy, which together create complex clinical profiles that traditional, single-disease models of care and conventional risk scores address poorly. At the same time, digital health infrastructures generate large, heterogeneous datasets (electronic health records, imaging, biosignals, wearable and ambient sensor data, and social determinants) that are well suited to artificial intelligence (AI), which is increasingly explored in geriatric care. We conducted a scoping review to map AI applications in the management of aging-related diseases and outcome prediction. MEDLINE (PubMed), Embase and Scopus were searched for peer-reviewed, English-language empirical studies using AI or machine learning in adults aged ≥60 years, or explicitly focused on older populations, to predict or classify clinically relevant outcomes. Studies limited to younger populations, purely simulated or technical work, and non–full-text reports were excluded. Two reviewers independently screened and extracted data on populations, data sources, model types, targets, performance and validation, followed by narrative synthesis. Most identified applications concerned risk prediction (mortality, hospitalisation, readmission, institutionalisation, frailty progression) using routinely collected clinical data, often enriched with geriatric assessments. Additional use cases included early detection of dementia, frailty and sarcopenia; prediction of treatment response and adverse drug events; remote monitoring and early warning systems; care pathway optimisation; and emerging large language model–based decision support. Across domains, many machine learning models outperformed traditional scores and captured more complex risk patterns, but methodological quality was variable, external validation was infrequent and very old, frail and institutionalised patients were under-represented. Concerns about interpretability, bias, equity, workflow integration and medico-legal responsibility remain prominent. Overall, AI has substantial potential to support more precise, person-centred care for older adults, but realising this promise will require multimorbidity-aware, transparent models, robust evaluation in diverse geriatric populations and governance frameworks that ensure fairness, privacy and meaningful human oversight.

Objective: To assess the knowledge and attitude of undergraduate nursing students towards the role of artificial intelligence (AI) in healthcare, aiming to understand their readiness and perception of integrating AI into clinical practice. Methods: A descriptive cross-sectional study was conducted to assess the knowledge and attitude of nursing students toward the role of Artificial Intelligence (AI) in healthcare. A total of 208 students were selected using non-probability convenience sampling technique. Informed consent was obtained from all the participants prior to the data collection. The study consisted of two parts: a 10-items knowledge questionnaire and a 10-items attitude questionnaire, designed to evaluate students' understanding of AI technologies and their perspectives on its integration into healthcare settings. The questionnaires were close-ended, focusing on basic knowledge about AI. Results: There was a significant difference in AI knowledge and attitudes between various groups. Male’s demonstrated significantly higher AI knowledge (82.1%) compared to females (69.8%) with a p-value of 0.003. Participants who attended formal AI training exhibited better knowledge, with 41.9% showing adequate knowledge, compared to 25.4% of non-attendees (p = 0.010). Prior exposure to AI workshops significantly influenced attitudes, with attendees showing a more positive attitude toward AI (67.4%) compared to non-attendees (35.8%), with a p-value of <0.001. Gender and formal AI training were found to significantly impact both knowledge and attitude towards AI in healthcare. Conclusion: The study highlights significant differences in AI knowledge and attitude among undergraduate nursing students, with males, participants with formal AI training, and those exposed to AI workshops demonstrating higher levels of knowledge and more positive attitude. These findings underscore the importance of incorporating AI education and training into nursing curricula to better prepare students for the integration of AI in clinical practice.

This study addresses a critical gap in understanding Artificial Intelligence (AI)'s role in education by empirically investigating and comparing the distinct perceptions of teachers and students regarding AI's role in a comprehensive range of social development aspects in both online and physical classroom settings. In particular, we evaluated how teachers utilize AI in their teaching methods, namely, Communicative Language Teaching (CLT), the Direct Method (DL), Task-Based Language Teaching (TBLT), Content and Language Integrated Learning (CLIL), and Community Language Learning (CLL), and students in their learning methods, namely, Communicative Learning (CL), Immersive Learning (IL), Task-Based Collaborative Learning (TBCL), Content Integrated Learning (CIL), and Community-Based Reflective Learning (CBRL), to configure their social development. We interviewed 20 teachers (10 from online and 10 from physical classes) and 40 students (20 from online and 20 from physical classes) and evaluated their perceptions regarding AI usage in teaching and learning methods towards social development. The results of our study are convincing enough to suggest that both teachers and students perceive AI usage helpful in teaching models; however, variation in their perception is observed. Notably, the divergence in the perception of teachers and students with regard to AI's role is a key observation of this study. For instance, the teachers perceived AI as a highly effective tool in fostering community building during online sessions; in contrast, the students viewed its role as being moderately effective. Likewise, the teachers perceived AI's role as a critical tool in traditional classrooms rather than in virtual ones, whereas the students associated AI with online learning-in terms of digital tools, learning opportunities, and critical discussion-by rating its impact on social confidence and verbal-nonverbal communications significantly more strongly in physical settings. On the contrary, the teachers emphasized AI's relevance to their self-confidence, emotional intelligence, and community engagement in online teaching platforms; yet, the ratings dropped to moderate in physical contexts. The students' perceptions in this regard matched those of the teachers, as they also emphasized the importance of social confidence and overall well-being in physical classrooms, where the teachers' assessment was comparatively low. These patterns provide analytical insights that are decisively valuable for designing AI-integrated pedagogical models that support social development within the educational environments.

Artificial Intelligence-related Literature in Transplantation: A Practical Guide.

Future Trends in CT for Coronary Artery Disease: From Diagnosis to Prevention.

Artificial intelligence (AI) is increasingly applied in clinical diagnostics, particularly in radiology, where it can assist with imaging triaging and anomaly detection. However, the integration of AI into medical education remains under researched. This study investigates the impact of an AI-focused panel discussion on medical students' perceptions, knowledge, attitudes and concerns about AI in radiology. A paired pre-post design questionnaire comprising of 13 five-point Likert scale questions was administered to 40 medical students to complete before and after an AI-focused educational panel session at the International Radiology Undergraduate Symposium in London, United Kingdom on 24th November 2024. The questionnaire assessed four domains: 'Understanding of AI,' 'Attitudes Toward AI in Radiology,' 'AI Education in Medical School,' and 'Concerns About AI in the Future.' The primary outcome was to assess the change in students' perceptions of AI's role in radiology. Differences between pre- and post-session responses were analysed using the Wilcoxon signed-rank test. The Hodges-Lehmann median difference, the effect size, r, and their corresponding 95% confidence intervals were calculated, and p-values were adjusted using the Holm-Bonferroni method. Of the 81 eligible attendees, 40 (49.4%) completed the questionnaire (39 pre-session, 40 post-session). Students demonstrated significant improvements in their understanding of AI's potential role in radiology (Z = 3.04, p = 0.002; Holm-Bonferroni = 0.029; median paired difference = 0.5, 95% CI 0.0-0.5; r = 0.49, 95% CI 0.25-0.68) and in their awareness of AI's broader clinical applications (Z = 3.65, p < 0.001; Holm-Bonferroni = 0.0035; median paired difference = 0.5, 95% CI 0.5-1.0; r = 0.60, 95% CI 0.38-0.75). Participants expressed a more positive view of AI in healthcare overall, although concerns about AI replacing radiologists and insufficient AI education persisted. Educational interventions have the potential to improve medical students' understanding and attitudes toward AI in radiology. Integrating structured AI education into undergraduate curricula may enhance AI literacy and better prepare future clinicians for an AI-enabled healthcare environment.

Rapid and accurate interpretation of neuroimaging is critical in acute stroke, but variability among human readers and the urgency of clinical workflows pose major challenges. Artificial intelligence (AI) has emerged as a promising adjunct in emergency stroke imaging, with the potential to enhance detection, scoring, and prognostication. We systematically reviewed the role of AI in this context, focusing on diagnostic performance, workflow feasibility, and implementation across key imaging modalities. A systematic search of PubMed, Scopus, Web of Science, and Cochrane CENTRAL was conducted from inception to August 20, 2025, following Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guidelines. Eligible studies were original English-language research that applied AI to emergency stroke imaging. Data were extracted on study design, population, imaging modality, AI architecture, performance metrics, workflow aspects, and interpretability, with study quality assessed using the Checklist for Artificial Intelligence in Medical Imaging (CLAIM). Nine studies met the inclusion criteria. AI models achieved high accuracy for intracranial hemorrhage (ICH) detection on non-contrast computed tomography (NCCT) scans, with area under the curve (AUC) values up to 0.98.Real-world analyses reported balanced accuracy around 0.93 with near-real-time processing. Automated Alberta Stroke Program Early CT Score (ASPECTS) grading demonstrated almost perfect agreement with expert consensus (κ up to 0.90), outperforming individual radiologists in the hyperacute phase. Ischemic lesion detection using convolutional neural networks (CNNs) applied to magnetic resonance imaging (MRI) and computed tomography angiography (CTA) achieved accuracies of 83-86%. Symmetry-based methods further improved performance, though limitations were noted in posterior circulation strokes. Prognostic models integrating imaging and clinical data yielded moderate-to-good performance (AUC 0.79-0.91), with multimodal deep learning outperforming single-modality or clinical-only models. Workflow studies reported AI processing times of 2-4 minutes, although data transfer and system integration remained key bottlenecks. Interpretability tools, such as Gradient-weighted Class Activation Mapping (Grad-CAM) and Shapley Additive Explanations (SHAP), have enhanced transparency in several studies. Overall, AI demonstrates strong diagnostic and workflow potential in emergency stroke imaging, particularly for ICH detection, automated ASPECTS, and large vessel occlusion (LVO) alerts. Multimodal and transformer-based approaches show promise for outcome prediction and lesion segmentation, but further external validation and seamless integration into clinical workflows are required. AI is best positioned as a supportive tool to augment, rather than replace, clinical expertise in acute stroke care.