Por favor, use este identificador para citar o enlazar este ítem:
http://conacyt.repositorioinstitucional.mx/jspui/handle/1000/7699| Machine Learning Generalizability Across Healthcare Settings: Insights from multi-site COVID-19 screening | |
| Jenny Yang Andrew Soltan David A. Clifton | |
| Acceso Abierto | |
| Atribución-NoComercial | |
| https://doi.org/10.1101/2022.02.09.22269744 | |
| https://www.medrxiv.org/content/10.1101/2022.02.09.22269744v1 | |
| As patient health information is highly regulated due to privacy concerns, the majority of machine learning (ML)-based healthcare studies are unable to test on external patient cohorts, resulting in a gap between locally reported model performance and cross-site generalizability. Different approaches have been introduced for developing models across multiple clinical sites, however no studies have compared methods for translating ready-made models for adoption in new settings. We introduce three methods to do this - (1) applying a ready-made model as-is; (2) readjusting the decision threshold on the output of a ready-made model using site-specific data; and (3) finetuning a ready-made model using site-specific data via transfer learning. Using a case study of COVID-19 diagnosis across four NHS Hospital Trusts, we show that all methods achieve clinically-effective performances (NPV >0.959), with transfer learning achieving the best results (mean AUROCs between 0.870-0.925). Our models demonstrate that site-specific customization improves predictive performance when compared to other ready-made approaches. | |
| medRxiv and bioRxiv | |
| 10-02-2022 | |
| Preimpreso | |
| https://www.medrxiv.org/ | |
| Inglés | |
| Epidemia COVID-19 | |
| Público en general | |
| VIRUS RESPIRATORIOS | |
| Versión publicada | |
| publishedVersion - Versión publicada | |
| Aparece en las colecciones: | Artículos científicos |
Cargar archivos:
| Fichero | Tamaño | Formato | |
|---|---|---|---|
| Machine learning generalizability across healthcare settings.pdf | 559.67 kB | Adobe PDF | Visualizar/Abrir |