Ethics in Multi-modal Artificial Intelligence and Hybrid Pathology Systems Development
3
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This paper explores the development of artificial intelligence systems for pathology research and practice among hospitals and startups. Using examples from South Korea and other countries, we compare the distinctions between settings based on ethical imperatives and competing priorities for innovation. Notably, recent trends in increasingly complex artificial intelligence models compel the revision of prior assumptions about the way the digital pathology artificial intelligence systems are used for innovation. Whereas past approaches to medical technology development using artificial intelligence focused on specific parameters and handcrafted settings, new models are increasingly unsupervised and opaque. In turn, research and practice assisted with these models require a more robust view of the role of clinical judgment in relation to classification systems. As digital pathology in South Korea continues to advance, these new solutions suggest the increasing importance of applying bioethical principles to manage and assess risks inherent in innovation.
Abstract
This paper explores the development of artificial intelligence systems for pathology research and practice among hospitals and startups. Using examples from South Korea and other countries, we compare the distinctions between settings based on ethical imperatives and competing priorities for innovation. Notably, recent trends in increasingly complex artificial intelligence models compel the revision of prior assumptions about the way the digital pathology artificial intelligence systems are used for innovation. Whereas past approaches to medical technology development using artificial intelligence focused on specific parameters and handcrafted settings, new models are increasingly unsupervised and opaque. In turn, research and practice assisted with these models require a more robust view of the role of clinical judgment in relation to classification systems. As digital pathology in South Korea continues to advance, these new solutions suggest the increasing importance of applying bioethical principles to manage and assess risks inherent in innovation.
참고문헌 (17)
- Bera, Kaustav, "Reimagining T Staging through Artificial Intelligence and Machine Learning Image Processing Approaches in Digital Pathology", JCO Clinical Cancer Informatics, (4), pp.1039~1050 (2020)[DOI]
- Bera, Kaustav, "Artificial Intelligence in Digital Pathology — New Tools for Diagnosis and Precision Oncology", Nature Reviews Clinical Oncology, 16(11), pp.703~715 (2019)[DOI]
- Bueno, G, "New Trends of Emerging Technologies in Digital Pathology", Pathobiology, 83(2-3), pp.61~69 (2016)[DOI]
- Cheng, Chee Leong, "Enabling Digital Pathology in the Diagnostic Setting:Navigating through the Implementation Journey in an Academic Medical Centre", Journal of Clinical Pathology, 69(9), pp.784~792 (2016)[DOI]
- Dyer, Owen, "Leading Us Cancer Hospital Alters Conflict of Interest Rules after Controversies", BMJ, 363, pp.k4151~ (2018)[DOI]
- Dyer, Owen, "Leading Us Cancer Researcher Failed to Disclose Industry Ties in Dozens of Articles", BMJ: British Medical Journal, 362 (2018), ProQuest Central Korea[DOI]
- Howard, Frederick M., "The Impact of Site-Specific Digital Histology Signatures on Deep Learning Model Accuracy and Bias", Nature Communications, 12(1), pp.1~13 (2021)[DOI]
- Kang, Yunsook, "Development and Operation of a Digital Platform for Sharing Pathology Image Data", BMC Medical Informatics and Decision Making, 21(1), pp.#114~ (2021)[DOI]
- Kim, Hannah, "South Korea: in the midst of a privacy reform centered on data sharing", Human Genetics, (137), pp.627~635 (2018)[DOI]
- Lee, Yeon Joo, "A Multicentre Validation Study of the Deep Learning-Based Early Warning Score for Predicting in-Hospital Cardiac Arrest in Patients Admitted to General Wards", Resuscitation, 163, pp.78~85 (2021)[DOI]
- Lin, Wenyi, "Comparison of Handcrafted Features and Convolutional Neural Networks for Liver Mr Image Adequacy Assessment", Scientific Reports, 10(1), pp.1~11 (2020)[DOI]
- Liu, Yingci, "Digital Pathology: Review of Current Opportunities and Challenges for Oral Pathologists", Journal of Oral Pathology & Medicine, 48(4), pp.263~269 (2019)[DOI]
- Mazer, Benjamin L., "Protecting the Pathology Commons in the Digital Era", Archives of Pathology & Laboratory Medicine, 144(9), pp.1037~1040 (2020)[DOI]
- Mea, Vincenzo, "Teaching Digital Pathology: The International School of Digital Pathology and Proposed Syllabus", Journal of Pathology Informatics, 8(1), pp.27~ (2017)[DOI]
- Nanni, Loris, "Deep Learning and Handcrafted Features for Virus Image Classification", Journal of Imaging, 6(12), pp.143~ (2020)
- Pallua, J. D., "The Future of Pathology Is Digital", Pathology - Research and Practice, 216(9), pp.#153040~ (2020)[DOI]
- Perincheri, Sudhir, "An Independent Assessment of an Artificial Intelligence System for Prostate Cancer Detection Shows Strong Diagnostic Accuracy", Modern Pathology, 34(8), pp.1588~1595 (2021)[DOI]