To warrant clinical adoption AI models require a multi-faceted implementation evaluation
Abstract Despite artificial intelligence (AI) technology progresses at unprecedented rate, our ability to translate these advancements into clinical value and adoption at the bedside remains comparatively limited. This paper reviews the current use of implementation outcomes in randomized controlled...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-03-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-024-01064-1 |
| _version_ | 1797266545501536256 |
|---|---|
| author | Davy van de Sande Eline Fung Fen Chung Jacobien Oosterhoff Jasper van Bommel Diederik Gommers Michel E. van Genderen |
| author_facet | Davy van de Sande Eline Fung Fen Chung Jacobien Oosterhoff Jasper van Bommel Diederik Gommers Michel E. van Genderen |
| author_sort | Davy van de Sande |
| collection | DOAJ |
| description | Abstract Despite artificial intelligence (AI) technology progresses at unprecedented rate, our ability to translate these advancements into clinical value and adoption at the bedside remains comparatively limited. This paper reviews the current use of implementation outcomes in randomized controlled trials evaluating AI-based clinical decision support and found limited adoption. To advance trust and clinical adoption of AI, there is a need to bridge the gap between traditional quantitative metrics and implementation outcomes to better grasp the reasons behind the success or failure of AI systems and improve their translation into clinical value. |
| first_indexed | 2024-04-25T01:02:24Z |
| format | Article |
| id | doaj.art-14a7295dad6049ea8311a198e331f511 |
| institution | Directory Open Access Journal |
| issn | 2398-6352 |
| language | English |
| last_indexed | 2024-04-25T01:02:24Z |
| publishDate | 2024-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj.art-14a7295dad6049ea8311a198e331f5112024-03-10T12:22:46ZengNature Portfolionpj Digital Medicine2398-63522024-03-01711510.1038/s41746-024-01064-1To warrant clinical adoption AI models require a multi-faceted implementation evaluationDavy van de Sande0Eline Fung Fen Chung1Jacobien Oosterhoff2Jasper van Bommel3Diederik Gommers4Michel E. van Genderen5Erasmus MC University Medical Center, Department of Adult Intensive CareErasmus MC University Medical Center, Department of Adult Intensive CareDelft University of Technology, Faculty of Technology, Policy and ManagementErasmus MC University Medical Center, Department of Adult Intensive CareErasmus MC University Medical Center, Department of Adult Intensive CareErasmus MC University Medical Center, Department of Adult Intensive CareAbstract Despite artificial intelligence (AI) technology progresses at unprecedented rate, our ability to translate these advancements into clinical value and adoption at the bedside remains comparatively limited. This paper reviews the current use of implementation outcomes in randomized controlled trials evaluating AI-based clinical decision support and found limited adoption. To advance trust and clinical adoption of AI, there is a need to bridge the gap between traditional quantitative metrics and implementation outcomes to better grasp the reasons behind the success or failure of AI systems and improve their translation into clinical value.https://doi.org/10.1038/s41746-024-01064-1 |
| spellingShingle | Davy van de Sande Eline Fung Fen Chung Jacobien Oosterhoff Jasper van Bommel Diederik Gommers Michel E. van Genderen To warrant clinical adoption AI models require a multi-faceted implementation evaluation npj Digital Medicine |
| title | To warrant clinical adoption AI models require a multi-faceted implementation evaluation |
| title_full | To warrant clinical adoption AI models require a multi-faceted implementation evaluation |
| title_fullStr | To warrant clinical adoption AI models require a multi-faceted implementation evaluation |
| title_full_unstemmed | To warrant clinical adoption AI models require a multi-faceted implementation evaluation |
| title_short | To warrant clinical adoption AI models require a multi-faceted implementation evaluation |
| title_sort | to warrant clinical adoption ai models require a multi faceted implementation evaluation |
| url | https://doi.org/10.1038/s41746-024-01064-1 |
| work_keys_str_mv | AT davyvandesande towarrantclinicaladoptionaimodelsrequireamultifacetedimplementationevaluation AT elinefungfenchung towarrantclinicaladoptionaimodelsrequireamultifacetedimplementationevaluation AT jacobienoosterhoff towarrantclinicaladoptionaimodelsrequireamultifacetedimplementationevaluation AT jaspervanbommel towarrantclinicaladoptionaimodelsrequireamultifacetedimplementationevaluation AT diederikgommers towarrantclinicaladoptionaimodelsrequireamultifacetedimplementationevaluation AT michelevangenderen towarrantclinicaladoptionaimodelsrequireamultifacetedimplementationevaluation |