A scoping review of robustness concepts for machine learning in healthcare
Abstract While machine learning (ML)-based solutions—often referred to as artificial intelligence (AI) solutions—have demonstrated comparable or superior performance to human experts across various healthcare applications, their vulnerability to perturbations and stability to variations due to new e...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-024-01420-1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832594384818798592 |
|---|---|
| author | Alan Balendran Céline Beji Florie Bouvier Ottavio Khalifa Theodoros Evgeniou Philippe Ravaud Raphaël Porcher |
| author_facet | Alan Balendran Céline Beji Florie Bouvier Ottavio Khalifa Theodoros Evgeniou Philippe Ravaud Raphaël Porcher |
| author_sort | Alan Balendran |
| collection | DOAJ |
| description | Abstract While machine learning (ML)-based solutions—often referred to as artificial intelligence (AI) solutions—have demonstrated comparable or superior performance to human experts across various healthcare applications, their vulnerability to perturbations and stability to variations due to new environments—essentially, their robustness—remains ambiguous and often overlooked. In this review, we aimed to identify the types of robustness addressed in the literature for ML models in healthcare. A total of 274 eligible records were retrieved from PubMed, Web of Science, IEEE Xplore, and additional sources. Eight general concepts of robustness emerged. Furthermore, an analysis of those concepts across types of data and types of predictive models revealed that the concepts were differently addressed. Our findings offer valuable insights for stakeholders seeking to understand and navigate the robustness of machine learning models during their development, validation, and deployment in healthcare settings, where interpretation of robustness may vary. |
| format | Article |
| id | doaj-art-06e0727fc2ae4fe7a2f6deada5a52d1c |
| institution | Kabale University |
| issn | 2398-6352 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj-art-06e0727fc2ae4fe7a2f6deada5a52d1c2025-01-19T12:39:44ZengNature Portfolionpj Digital Medicine2398-63522025-01-01811910.1038/s41746-024-01420-1A scoping review of robustness concepts for machine learning in healthcareAlan Balendran0Céline Beji1Florie Bouvier2Ottavio Khalifa3Theodoros Evgeniou4Philippe Ravaud5Raphaël Porcher6Université Paris Cité, Université Sorbonne Paris Nord, INSERM, INRAE, Centre for Research in Epidemiology and StatisticS (CRESS)Université Paris Cité, Université Sorbonne Paris Nord, INSERM, INRAE, Centre for Research in Epidemiology and StatisticS (CRESS)Université Paris Cité, Université Sorbonne Paris Nord, INSERM, INRAE, Centre for Research in Epidemiology and StatisticS (CRESS)Université Paris Cité, Université Sorbonne Paris Nord, INSERM, INRAE, Centre for Research in Epidemiology and StatisticS (CRESS)INSEAD Decision SciencesUniversité Paris Cité, Université Sorbonne Paris Nord, INSERM, INRAE, Centre for Research in Epidemiology and StatisticS (CRESS)Université Paris Cité, Université Sorbonne Paris Nord, INSERM, INRAE, Centre for Research in Epidemiology and StatisticS (CRESS)Abstract While machine learning (ML)-based solutions—often referred to as artificial intelligence (AI) solutions—have demonstrated comparable or superior performance to human experts across various healthcare applications, their vulnerability to perturbations and stability to variations due to new environments—essentially, their robustness—remains ambiguous and often overlooked. In this review, we aimed to identify the types of robustness addressed in the literature for ML models in healthcare. A total of 274 eligible records were retrieved from PubMed, Web of Science, IEEE Xplore, and additional sources. Eight general concepts of robustness emerged. Furthermore, an analysis of those concepts across types of data and types of predictive models revealed that the concepts were differently addressed. Our findings offer valuable insights for stakeholders seeking to understand and navigate the robustness of machine learning models during their development, validation, and deployment in healthcare settings, where interpretation of robustness may vary.https://doi.org/10.1038/s41746-024-01420-1 |
| spellingShingle | Alan Balendran Céline Beji Florie Bouvier Ottavio Khalifa Theodoros Evgeniou Philippe Ravaud Raphaël Porcher A scoping review of robustness concepts for machine learning in healthcare npj Digital Medicine |
| title | A scoping review of robustness concepts for machine learning in healthcare |
| title_full | A scoping review of robustness concepts for machine learning in healthcare |
| title_fullStr | A scoping review of robustness concepts for machine learning in healthcare |
| title_full_unstemmed | A scoping review of robustness concepts for machine learning in healthcare |
| title_short | A scoping review of robustness concepts for machine learning in healthcare |
| title_sort | scoping review of robustness concepts for machine learning in healthcare |
| url | https://doi.org/10.1038/s41746-024-01420-1 |
| work_keys_str_mv | AT alanbalendran ascopingreviewofrobustnessconceptsformachinelearninginhealthcare AT celinebeji ascopingreviewofrobustnessconceptsformachinelearninginhealthcare AT floriebouvier ascopingreviewofrobustnessconceptsformachinelearninginhealthcare AT ottaviokhalifa ascopingreviewofrobustnessconceptsformachinelearninginhealthcare AT theodorosevgeniou ascopingreviewofrobustnessconceptsformachinelearninginhealthcare AT philipperavaud ascopingreviewofrobustnessconceptsformachinelearninginhealthcare AT raphaelporcher ascopingreviewofrobustnessconceptsformachinelearninginhealthcare AT alanbalendran scopingreviewofrobustnessconceptsformachinelearninginhealthcare AT celinebeji scopingreviewofrobustnessconceptsformachinelearninginhealthcare AT floriebouvier scopingreviewofrobustnessconceptsformachinelearninginhealthcare AT ottaviokhalifa scopingreviewofrobustnessconceptsformachinelearninginhealthcare AT theodorosevgeniou scopingreviewofrobustnessconceptsformachinelearninginhealthcare AT philipperavaud scopingreviewofrobustnessconceptsformachinelearninginhealthcare AT raphaelporcher scopingreviewofrobustnessconceptsformachinelearninginhealthcare |