A narrative conceptual review of four commonly encountered AI model types: random forests, support vector machines, convolutional neural networks and large language models is presented, exploring their clinical applications, interpretability, limitations and relevance to perioperative and surgical settings.
Abstract
Artificial intelligence (AI) is increasingly influencing perioperative care by enhancing decision support, resource management, documentation, image analysis and patient safety. This article presents a narrative conceptual review of four commonly encountered AI model types: random forests, support vector machines, convolutional neural networks and large language models. It explores their clinical applications, interpretability, limitations and relevance to perioperative and surgical settings. Particular emphasis is placed on model explainability, evaluation metrics such as accuracy, F1 score and area under the receiver operating characteristic curve, hallucination risk and the challenges associated with opaque ‘black box’ systems, including non-interpretable algorithmic frameworks. The discussion is contextualised within the UK’s regulatory and governance frameworks, including the National Health Service Digital clinical safety standards, Medicine and Healthcare products Regulatory Agency requirements, National Institute for Health and Care Excellence evaluation tiers and data protection under UK General Data Protection Regulation. By improving clinician understanding of how AI systems function, fail and should be governed, this article aims to support informed, safe and ethical adoption of AI technologies in perioperative environments.
This article proposes seven questions that clinicians can run through to evaluate any clinical AI tool in the time it takes to read an abstract, alongside a traffic-light schema for matching oversight to risk and a short list of demands clinicians should make of vendors and institutions.
Alaa Abdelqader, M. Alkhateeb, Abdullah Al-Marrawi et al.· Avicenna Journal of Medicine· 0 citations
It is concluded that explainable artificial intelligence improves trust, reliability, and accountability in healthcare systems and is a prerequisite for successful integration of intelligent technologies into clinical practice.
Riya Jacob K· International Journal of Tec...· 0 citations
Clinical artificial intelligence is increasingly embedded in real-world care, yet existing safety mechanisms are poorly suited to reconstructing and learning from individual AI-related errors and near-misses. Aggregate model monitoring can identify performance changes, and traditional patient safety reporting can capture adverse events, but neither is designed to explain how risk emerges across the interaction among AI systems, clinicians, workflows, and institutional controls. We propose AI Morbidity and Mortality (AI M&M), a structured, blameless framework for case-based review of clinical AI failures. The framework combines standardized case intake, evidence preservation and investigator-level reconstruction, tool-in-loop attribution, and corrective-action tracking. Each event is classified across four linked dimensions: Trigger - Mechanism - Clinical Pathway - Corrective Action, separating the condition that exposed a vulnerability from the process that produced risk, its consequence for care, and the remediation assigned. We demonstrate the framework using five illustrative outpatient medication and clinical decision-support cases; two clinician reviewers independently applied all four classification axes and reached agreement across all 20 axis-level classifications. AI M&M is intended to complement, rather than replace, model monitoring, patient safety reporting, and regulatory oversight by converting individual AI-in-workflow failures into actionable institutional learning. Prospective evaluation across institutions, AI systems, and clinical settings is needed.
Paulius Mui, Dean F. Sittig, Steven Labkoff et al.· 0 citations
Artificial intelligence (AI) has become an integral component of clinical decision support systems, improving diagnostic accuracy, risk prediction, treatment planning, and healthcare resource management. But, the "black box" nature of many successful machine learning models has brought up concerns around trust and accountability, fairness and regulatory acceptance in the clinical setting. To address these challenges, Explanatory Artificial Intelligence (XAI) has become a promising method that aims to provide the explainability of the results predicted by the models without compromising the performance of the analysis. The aim of this narrative review is to provide an overview of the evolving image of XAI as a tool to create trustworthy clinical decision support systems and how it can be performed based on the concepts of transparency, interpretability and moral decision-making. It provides a summary of the current literature on essential explainability techniques, how they can be applied to different health care-related problems, and how they help increase trust and transparency in health care decision making. It also addresses human-AI collaboration, model validation, bias mitigation, privacy protection and governance frameworks to enable responsible use of AI. The new emerging developments, such as federated learning, multimodal explainable models, causal reasoning, and generative AI, are also discussed to emphasize future opportunities for clinically reliable and scalable intelligent healthcare systems. The review concludes that explainability is no longer a choice of technical attribute but rather a fundamental component to the use of AI in everyday clinical practice. For safe, equitable and trusted clinical decision support to benefit everyone in the health care sector, transparency, accountability and ethical governance will play a pivotal role.
Rakesh Venuturumilli, Amoli Singh, Hemanshi Dhaduk et al.· European Journal of Prosthod...· 0 citations
Introduction Artificial intelligence (AI) is reshaping healthcare, enabled by advances in computing, affordable data storage, and the widespread adoption of electronic health records (EHRs). Machine learning (ML), deep learning (DL), and natural language processing (NLP) are increasingly used for disease diagnosis, risk prediction, and treatment planning. Objective This systematic review aimed to examine AI applications across clinical domains from 2020 to 2025, assess their diagnostic accuracy and clinical performance relative to standard practice, identify key implementation barriers including regulatory compliance, algorithmic fairness, and transparency challenges, and compare validation practices and methodological quality with earlier systematic reviews. Methods This systematic review followed PRISMA 2020 guidelines. We searched five databases (PubMed, IEEE Xplore, Web of Science, Springer, and Semantic Scholar) for studies published from January 2020 to September 2025. We included original clinical AI studies that reported prospective validation and/or external validation. Results Twenty studies met the inclusion criteria. Publication volume peaked in 2024 (n = 7, 35.0%). DL approaches were most common (n = 12, 60.0%), with convolutional neural networks (CNNs) frequently applied to medical imaging tasks. By clinical domain, 30.0% of studies focused on radiology (n = 6), 20.0% on oncology (n = 4), and 15.0% on cardiology (n = 3). For imaging-based diagnostic models, the descriptive median performance across individual studies was 0.91 AUC (no formal meta-analysis was conducted due to heterogeneity in study designs, populations, and outcome metrics). The most frequently reported challenges were regulatory compliance (55.0%, n = 11), limited algorithmic transparency (40.0%, n = 8), data quality limitations (35.0%, n = 7), and barriers to clinical integration (30.0%, n = 6). Conclusions AI demonstrates strong potential to improve the effectiveness, safety, and quality of healthcare. However, broader clinical adoption remains constrained by regulatory requirements, interpretability gaps, data quality issues, and workflow integration challenges, underscoring the need for stronger validation practices and more implementation-focused research.
Ghulam Hussain Noori, Shaista Bibi, Seung Won Lee· Inquiry : a journal of medic...· 0 citations
Background: The rapid integration of Artificial Intelligence (AI), specifically Clinical Decision Support Systems (CDSS), into healthcare offers substantial efficiency but introduces critical ethical and legal challenges, particularly the perpetuation of systemic bias against older adults (“Digital Ageism”). While technological advances may improve care, they can violate fundamental bioethical principles when models are trained on unrepresentative data. Aim: This article argues that traditional clinical risk-management models are structurally insufficient to address opaque algorithmic bias and presents a conceptual, multidimensional governance framework designed to prevent the codification of human ageism into AI infrastructure. Methods: Drawing on systemic failures observed during the COVID-19 pandemic, the normative model integrates legal and governance standards aligned with the EU AI Act, Explainable AI (XAI) tools, and a three-phase implementation protocol. Results: To illustrate potential application without overburdening medical staff, the article introduces a theoretical Targeted Escalation Protocol and an Autonomous High-Load Safety Mode. The latter applies deterministic hardcoded constraints to contain age-dominant outputs during acute surges while preserving attending-clinician authority. The framework is explored through an Intensive Care Unit (ICU) thought experiment. Conclusions: The framework provides a structured roadmap for policymakers, ethicists, and healthcare administrators to move from reactive defensive medicine toward proactive ethical safety, safeguarding the dignity of the aging population while aiming to mitigate institutional legal exposure.
