Transfer learning for non-image data in clinical research: A scoping review.
<h4>Background</h4>Transfer learning is a form of machine learning where a pre-trained model trained on a specific task is reused as a starting point and tailored to another task in a different dataset. While transfer learning has garnered considerable attention in medical image analysis...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2022-02-01
|
| Series: | PLOS Digital Health |
| Online Access: | https://journals.plos.org/digitalhealth/article/file?id=10.1371/journal.pdig.0000014&type=printable |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832539979555799040 |
|---|---|
| author | Andreas Ebbehoj Mette Østergaard Thunbo Ole Emil Andersen Michala Vilstrup Glindtvad Adam Hulman |
| author_facet | Andreas Ebbehoj Mette Østergaard Thunbo Ole Emil Andersen Michala Vilstrup Glindtvad Adam Hulman |
| author_sort | Andreas Ebbehoj |
| collection | DOAJ |
| description | <h4>Background</h4>Transfer learning is a form of machine learning where a pre-trained model trained on a specific task is reused as a starting point and tailored to another task in a different dataset. While transfer learning has garnered considerable attention in medical image analysis, its use for clinical non-image data is not well studied. Therefore, the objective of this scoping review was to explore the use of transfer learning for non-image data in the clinical literature.<h4>Methods and findings</h4>We systematically searched medical databases (PubMed, EMBASE, CINAHL) for peer-reviewed clinical studies that used transfer learning on human non-image data. We included 83 studies in the review. More than half of the studies (63%) were published within 12 months of the search. Transfer learning was most often applied to time series data (61%), followed by tabular data (18%), audio (12%) and text (8%). Thirty-three (40%) studies applied an image-based model to non-image data after transforming data into images (e.g. spectrograms). Twenty-nine (35%) studies did not have any authors with a health-related affiliation. Many studies used publicly available datasets (66%) and models (49%), but fewer shared their code (27%).<h4>Conclusions</h4>In this scoping review, we have described current trends in the use of transfer learning for non-image data in the clinical literature. We found that the use of transfer learning has grown rapidly within the last few years. We have identified studies and demonstrated the potential of transfer learning in clinical research in a wide range of medical specialties. More interdisciplinary collaborations and the wider adaption of reproducible research principles are needed to increase the impact of transfer learning in clinical research. |
| format | Article |
| id | doaj-art-8d3e4540c4e8484e820a71f82bcf002a |
| institution | Kabale University |
| issn | 2767-3170 |
| language | English |
| publishDate | 2022-02-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLOS Digital Health |
| spelling | doaj-art-8d3e4540c4e8484e820a71f82bcf002a2025-02-05T05:33:39ZengPublic Library of Science (PLoS)PLOS Digital Health2767-31702022-02-0112e000001410.1371/journal.pdig.0000014Transfer learning for non-image data in clinical research: A scoping review.Andreas EbbehojMette Østergaard ThunboOle Emil AndersenMichala Vilstrup GlindtvadAdam Hulman<h4>Background</h4>Transfer learning is a form of machine learning where a pre-trained model trained on a specific task is reused as a starting point and tailored to another task in a different dataset. While transfer learning has garnered considerable attention in medical image analysis, its use for clinical non-image data is not well studied. Therefore, the objective of this scoping review was to explore the use of transfer learning for non-image data in the clinical literature.<h4>Methods and findings</h4>We systematically searched medical databases (PubMed, EMBASE, CINAHL) for peer-reviewed clinical studies that used transfer learning on human non-image data. We included 83 studies in the review. More than half of the studies (63%) were published within 12 months of the search. Transfer learning was most often applied to time series data (61%), followed by tabular data (18%), audio (12%) and text (8%). Thirty-three (40%) studies applied an image-based model to non-image data after transforming data into images (e.g. spectrograms). Twenty-nine (35%) studies did not have any authors with a health-related affiliation. Many studies used publicly available datasets (66%) and models (49%), but fewer shared their code (27%).<h4>Conclusions</h4>In this scoping review, we have described current trends in the use of transfer learning for non-image data in the clinical literature. We found that the use of transfer learning has grown rapidly within the last few years. We have identified studies and demonstrated the potential of transfer learning in clinical research in a wide range of medical specialties. More interdisciplinary collaborations and the wider adaption of reproducible research principles are needed to increase the impact of transfer learning in clinical research.https://journals.plos.org/digitalhealth/article/file?id=10.1371/journal.pdig.0000014&type=printable |
| spellingShingle | Andreas Ebbehoj Mette Østergaard Thunbo Ole Emil Andersen Michala Vilstrup Glindtvad Adam Hulman Transfer learning for non-image data in clinical research: A scoping review. PLOS Digital Health |
| title | Transfer learning for non-image data in clinical research: A scoping review. |
| title_full | Transfer learning for non-image data in clinical research: A scoping review. |
| title_fullStr | Transfer learning for non-image data in clinical research: A scoping review. |
| title_full_unstemmed | Transfer learning for non-image data in clinical research: A scoping review. |
| title_short | Transfer learning for non-image data in clinical research: A scoping review. |
| title_sort | transfer learning for non image data in clinical research a scoping review |
| url | https://journals.plos.org/digitalhealth/article/file?id=10.1371/journal.pdig.0000014&type=printable |
| work_keys_str_mv | AT andreasebbehoj transferlearningfornonimagedatainclinicalresearchascopingreview AT metteøstergaardthunbo transferlearningfornonimagedatainclinicalresearchascopingreview AT oleemilandersen transferlearningfornonimagedatainclinicalresearchascopingreview AT michalavilstrupglindtvad transferlearningfornonimagedatainclinicalresearchascopingreview AT adamhulman transferlearningfornonimagedatainclinicalresearchascopingreview |