Sökning: WFRF:(Tschandl P.) > Human-computer coll...
Fältnamn | Indikatorer | Metadata |
---|---|---|
000 | 03921naa a2200541 4500 | |
001 | oai:gup.ub.gu.se/294864 | |
003 | SwePub | |
008 | 240528s2020 | |||||||||||000 ||eng| | |
024 | 7 | a https://gup.ub.gu.se/publication/2948642 URI |
024 | 7 | a https://doi.org/10.1038/s41591-020-0942-02 DOI |
040 | a (SwePub)gu | |
041 | a eng | |
042 | 9 SwePub | |
072 | 7 | a ref2 swepub-contenttype |
072 | 7 | a art2 swepub-publicationtype |
100 | 1 | a Tschandl, P.4 aut |
245 | 1 0 | a Human-computer collaboration for skin cancer recognition |
264 | c 2020-06-22 | |
264 | 1 | b Springer Science and Business Media LLC,c 2020 |
520 | a The rapid increase in telemedicine coupled with recent advances in diagnostic artificial intelligence (AI) create the imperative to consider the opportunities and risks of inserting AI-based support into new paradigms of care. Here we build on recent achievements in the accuracy of image-based AI for skin cancer diagnosis to address the effects of varied representations of AI-based support across different levels of clinical expertise and multiple clinical workflows. We find that good quality AI-based support of clinical decision-making improves diagnostic accuracy over that of either AI or physicians alone, and that the least experienced clinicians gain the most from AI-based support. We further find that AI-based multiclass probabilities outperformed content-based image retrieval (CBIR) representations of AI in the mobile technology environment, and AI-based support had utility in simulations of second opinions and of telemedicine triage. In addition to demonstrating the potential benefits associated with good quality AI in the hands of non-expert clinicians, we find that faulty AI can mislead the entire spectrum of clinicians, including experts. Lastly, we show that insights derived from AI class-activation maps can inform improvements in human diagnosis. Together, our approach and findings offer a framework for future studies across the spectrum of image-based diagnostics to improve human-computer collaboration in clinical practice. A systematic evaluation of the value of AI-based decision support in skin tumor diagnosis demonstrates the superiority of human-computer collaboration over each individual approach and supports the potential of automated approaches in diagnostic medicine. | |
650 | 7 | a NATURVETENSKAPx Biologix Biokemi och molekylärbiologi0 (SwePub)106022 hsv//swe |
650 | 7 | a NATURAL SCIENCESx Biological Sciencesx Biochemistry and Molecular Biology0 (SwePub)106022 hsv//eng |
653 | a classification | |
653 | a accuracy | |
653 | a Biochemistry & Molecular Biology | |
653 | a Cell Biology | |
653 | a Research & Experimental | |
653 | a Medicine | |
700 | 1 | a Rinner, C.4 aut |
700 | 1 | a Apalla, Z.4 aut |
700 | 1 | a Argenziano, G.4 aut |
700 | 1 | a Codella, N.4 aut |
700 | 1 | a Halpern, A.4 aut |
700 | 1 | a Janda, M.4 aut |
700 | 1 | a Lallas, A.4 aut |
700 | 1 | a Longo, C.4 aut |
700 | 1 | a Malvehy, J.4 aut |
700 | 1 | a Paoli, John,d 1975u Gothenburg University,Göteborgs universitet,Institutionen för kliniska vetenskaper, Avdelningen för dermatologi och venereologi,Institute of Clinical Sciences, Department of Dermatology and Venereology4 aut0 (Swepub:gu)xpaojo |
700 | 1 | a Puig, S.4 aut |
700 | 1 | a Rosendahl, C.4 aut |
700 | 1 | a Soyer, H. P.4 aut |
700 | 1 | a Zalaudek, I.4 aut |
700 | 1 | a Kittler, H.4 aut |
710 | 2 | a Göteborgs universitetb Institutionen för kliniska vetenskaper, Avdelningen för dermatologi och venereologi4 org |
773 | 0 | t Nature Medicined : Springer Science and Business Media LLCg 26, s. 1229-1234q 26<1229-1234x 1078-8956x 1546-170X |
856 | 4 | u https://www.nature.com/articles/s41591-020-0942-0.pdf |
856 | 4 8 | u https://gup.ub.gu.se/publication/294864 |
856 | 4 8 | u https://doi.org/10.1038/s41591-020-0942-0 |
Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.