Seeing the Unseen: How AI Transforms Medical Imaging and Diagnosis - A Critical Analysis of Algorithmic Medicine
Year: 2026
Type: preprint
Abstract: This article examines the transformative role of artificial intelligence in medical imaging, analyzing both the unprecedented diagnostic capabilities and critical systemic failures of algorithmic medicine. Through case studies including Google DeepMind's breast cancer detection system, FDA-approved autonomous diagnostic tools, and COVID-19 triage algorithms, we demonstrate how convolutional neural networks achieve accuracy rates matching or exceeding expert radiologists. However, this analysis also reveals significant algorithmic bias, deployment failures, and ethical challenges including systematic misdiagnosis of underrepresented patient populations. Drawing on peer-reviewed research from Nature Medicine, Science, and The Lancet Digital Health, alongside philosophical frameworks from Aristotle, Plato, and Socrates, this work interrogates fundamental questions: Can prediction without comprehension constitute true diagnosis? What accountability exists when algorithmic errors harm patients? How do we prevent the automation of existing healthcare inequalities? The article concludes that while AI imaging tools show potential to prevent 2.5 million deaths annually (WHO, 2025), responsible implementation requires addressing data bias, transparency deficits, and the risk of clinical deskilling. This is the first article in a "Season 2" series providing critical, evidence-based analysis of AI in biomedical engineering. Keywords: Artificial Intelligence, Medical Imaging, Convolutional Neural Networks, Algorithmic Bias, Healthcare Ethics, Radiology, Machine Learning, Diagnostic Accuracy
Author: Adlbi, Qussai
Institutions: Pázmány Péter Catholic University, Al Andalus University
Language: English
Subfield: Health Informatics
Field: Medicine
Domain: Health Sciences
Open Access status: green
OpenAlex ID: W7119905830