AI in diagnostics
Muratoski, Halid (2025)
2025
All rights reserved. This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:amk-2025112629933
https://urn.fi/URN:NBN:fi:amk-2025112629933
Tiivistelmä
This thesis investigates the role of artificial intelligence (AI) in contemporary medical diagnostics, combining theoretical analysis with insights informed by the author’s medical background. It outlines the conceptual foundations of AI, including machine learning and deep learning, and explains how these technologies enable computational systems to learn, adapt, and support clinical decision-making.
Using a semi-systematic literature review, the study examines current applications of AI in diagnostics, nursing, and broader healthcare contexts. The findings show that AI is already widely implemented in medical imaging, clinical documentation, predictive modelling, patient monitoring, and workflow optimization. Special emphasis is given to AI adoption in Finnish healthcare, where automated documentation, virtual assistants, risk prediction models, and AI-assisted social services are increasingly integrated into everyday practice.
The thesis concludes that while AI offers significant advantages—including improved diagnostic accuracy, reduced workload for healthcare professionals, and enhanced patient support—it also introduces challenges related to data security, model bias, and the risk of overreliance on automated systems. Ultimately, AI is positioned not as a replacement for healthcare professionals but as an essential supportive tool whose full potential depends on responsible, collaborative use among clinicians, developers, and patients.
Using a semi-systematic literature review, the study examines current applications of AI in diagnostics, nursing, and broader healthcare contexts. The findings show that AI is already widely implemented in medical imaging, clinical documentation, predictive modelling, patient monitoring, and workflow optimization. Special emphasis is given to AI adoption in Finnish healthcare, where automated documentation, virtual assistants, risk prediction models, and AI-assisted social services are increasingly integrated into everyday practice.
The thesis concludes that while AI offers significant advantages—including improved diagnostic accuracy, reduced workload for healthcare professionals, and enhanced patient support—it also introduces challenges related to data security, model bias, and the risk of overreliance on automated systems. Ultimately, AI is positioned not as a replacement for healthcare professionals but as an essential supportive tool whose full potential depends on responsible, collaborative use among clinicians, developers, and patients.