Jun 2026· Clinica chimica acta; international journal of clinical chemistry· Vol 592, pp.
121209
· 0 citations· 111 references
Medicine
TL;DR
A comprehensive introduction to the application of machine learning in routine clinical practice and biomedical research, including biomarker discovery is provided and the most widely used machine learning models are introduced together with their key characteristics, strengths, and limitations.
Abstract
Artificial intelligence, particularly machine learning and deep learning, is a rapidly evolving field that is increasingly permeating all areas of modern society, including public healthcare. In the present work, we provide a comprehensive introduction to the application of machine learning in routine clinical practice and biomedical research, including biomarker discovery. The most widely used machine learning models are introduced together with their key characteristics, strengths, and limitations. Furthermore, the fundamental principles governing the interpretation of model outputs and communication with regulatory authorities are discussed and illustrated using both real-world and synthetic datasets through modeling in the Python programming environment. Particular emphasis is placed on maintaining data quality and ensuring robust validation procedures in the context of dynamic, continuously updated AI systems intended for diagnostic software registered as medical devices (SaMDs). The importance of data governance, external validation, interpretability, and clinical oversight is highlighted as a prerequisite for safe and effective implementation of AI technologies in healthcare - throughout both the development and commercialization phases. Finally, current trends in medical artificial intelligence are reviewed, together with their potential benefits and associated risks for patients. The presented overview aims to facilitate a deeper understanding of the opportunities and challenges associated with the integration of AI-driven solutions into modern healthcare systems.
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
Artificial intelligence (AI) is transforming the field of clinical medicine at a fast rate. AI is being used in the field of clinical medicine in areas such as diagnostic imaging, prediction, documentation, and large language model-based clinical reasoning tools such as ChatGPT. Algorithm-based triage tools are also being used in clinical settings such as hospitals. Radiology departments are also using AI-based detection tools. However, the rate at which AI is transforming the field of clinical medicine is much higher than the rate at which the regulatory bodies are keeping pace with the developments in the field. Even though the Food and Drug Administration (FDA) has developed a pathway to regulate AI-based Software as a Medical Device (SaMD) and machine learning-based technologies, the current system that is in place to ensure the safety and efficacy of these technologies was developed to ensure the safety and efficacy of static technologies and not those that have the capability to learn. The rate at which AI is being incorporated in the field of clinical medicine is much higher than the rate at which these technologies are being regulated. The issue of clinical AI governance is not about the regulation of AI; it is about patient safety. This article outlines the need for a structured framework of five principles of safety, accountability, fairness, explainability, and adaptive oversight.
N. Butt· Pioneer Journal of Biostatis...· 0 citations
This structured narrative review examines how AI-SaMD regulation is moving beyond single-point premarket evaluation toward continuous and dynamic oversight, and synthesizes five evidence dimensions central to ongoing regulatory assurance: data evidence, algorithm evidence, software and cybersecurity evidence, clinical scenario and human factors evidence, and real-world data/real-world evidence with change management.
Yukun Dong, Ping Jiang, Xiaohua Zhou· Medical Review· 0 citations
The reviewed literature indicates that machine learning, deep learning, explainable AI, and human–AI collaboration can improve diagnostic accuracy, efficiency, and patient-centered care, but challenges related to data privacy, algorithmic bias, explainability, cybersecurity, clinical validation, regulation, and unequal access continue to restrict large-scale implementation.
Unknown authors· Journal of Cognitive Human-C...· 0 citations
Introduction: The digital transformation of healthcare is accelerating, driven by unprecedented advancements in Artificial Intelligence (AI). From large language models (LLMs) to biomolecular structure prediction, AI is redefining modern diagnostic and therapeutic standards.
Aim: This review evaluates the current state of AI applications in medicine, focusing on clinical knowledge encoding, molecular drug discovery, and administrative workflow optimization, while critically addressing the technical, ethical, and systemic challenges of their institutional implementation.
Materials and Methods: A structured analysis was conducted utilizing a hybrid approach that combines a multi-decade bibliometric trend perspective with a detailed synthesis of 21 landmark publications, clinical trials, and meta-analyses from high-impact journals.
Results: AI demonstrates expert-level performance in medical knowledge retrieval and spatiotemporal diagnostics. AlphaFold 3 has revolutionized computational therapeutics through all-atom biomolecular interaction prediction, while ambient AI scribes significantly reduce physician burnout by automating clinical documentation workflows. However, data-driven "hallucinations" in LLMs and the inherent "black box" nature of deep learning architectures remain critical barriers to autonomous deployment.
Conclusions: AI is successfully transitioning from an isolated research tool into an essential clinical "co-pilot." Achieving its full potential in Medicine 4.0 requires robust frameworks for algorithmic explainability, global dataset diversification, and a strategic synergy between machine precision and human clinical judgment.
Aleksandra Stańczyk, Kinga Haduch, Zuzanna Michalska et al.· International Journal of Inn...· 0 citations
Artificial Intelligence (AI) is transforming the pharmaceutical sector by accelerating drug discovery, improving predictive modelling, and optimising manufacturing processes. Traditional drug development is slow, costly, and associated with high failure rates due to complex biological systems and limited predictive accuracy. AI-based approaches, including machine learning and deep learning, enable rapid analysis of large biomedical datasets, facilitating efficient target identification, drug design, toxicity prediction, and clinical trial optimisation. These technologies also support advanced applications such as virtual screening, generative molecular design, and real-time process control in pharmaceutical manufacturing. Despite these advantages, the integration of AI introduces challenges related to data quality, model transparency, cybersecurity risks, and regulatory compliance. Ensuring robust validation, ethical governance, and secure digital infrastructure is essential for safe deployment in healthcare systems. In addition, AI should function as a decision-support tool that complements rather than replaces human expertise in pharmaceutical research and development. AI represents a paradigm shift in modern drug development by improving efficiency, reducing costs, and enhancing innovation potential. With appropriate safeguards and regulatory oversight, it can significantly strengthen the pharmaceutical pipeline and contribute to more effective and timely delivery of therapeutics.
Satish Singh Chandra, Manish Bhardwaj· International journal of com...· 0 citations