50 Assessment of Skin Graft in Pediatric Burn Patients Using Machine Learning Is Comparable to Human Expert Performance
Abstract Introduction Though widely used, current scar assessment scales are inaccurate and highly subjective, further complicating the already difficult task of determining the optimal management of burn patients. Additional disadvantages of these tools include the need for direct examination by an...
Published in: | Journal of Burn Care & Research |
---|---|
Main Authors: | , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Oxford University Press (OUP)
2020
|
Subjects: | |
Online Access: | http://dx.doi.org/10.1093/jbcr/iraa024.054 http://academic.oup.com/jbcr/article-pdf/41/Supplement_1/S33/32763202/iraa024.054.pdf |
id |
croxfordunivpr:10.1093/jbcr/iraa024.054 |
---|---|
record_format |
openpolar |
spelling |
croxfordunivpr:10.1093/jbcr/iraa024.054 2024-04-07T07:55:45+00:00 50 Assessment of Skin Graft in Pediatric Burn Patients Using Machine Learning Is Comparable to Human Expert Performance Ribeiro, Guilherme Aramizo Ridelman, Elika Klein, Justin D Angst, Beth A Shanti, Christina M Rastgaar, Mo 2020 http://dx.doi.org/10.1093/jbcr/iraa024.054 http://academic.oup.com/jbcr/article-pdf/41/Supplement_1/S33/32763202/iraa024.054.pdf en eng Oxford University Press (OUP) https://academic.oup.com/journals/pages/open_access/funder_policies/chorus/standard_publication_model Journal of Burn Care & Research volume 41, issue Supplement_1, page S33-S34 ISSN 1559-047X 1559-0488 Rehabilitation Emergency Medicine Surgery journal-article 2020 croxfordunivpr https://doi.org/10.1093/jbcr/iraa024.054 2024-03-08T03:08:37Z Abstract Introduction Though widely used, current scar assessment scales are inaccurate and highly subjective, further complicating the already difficult task of determining the optimal management of burn patients. Additional disadvantages of these tools include the need for direct examination by an experienced clinician and the inability to retrospectively review them. The lack of an accurate assessment tool inevitably impairs any research examining novel therapeutic strategies designed to improve burn scar outcomes by introducing observer bias at every step. Common examples of these tools include the Vancouver Scar Scale and Visual analog scale. New imaging and processing technologies have the potential of bringing accuracy, reproducibility, and accessibility to burn scar assessments. With these goals in mind, our team developed a novel scoring system and a classification model based on Machine Learning algorithms and analyzed 87 pictures to obtain scores on Inflammation (I), Scar (S), Uniformity (U), and Pigmentation (P). Methods All algorithms were trained using both the sub-acute and the long-term phase pictures. The classification model is based on supervised learning, which requires many examples of annotated pictures and corresponding scar scores. The model used a Linear Discriminant Analysis (LDA) algorithm and visual features of the scars and the natural skin. To train and evaluate this model, four burn care providers individually annotated 186 pictures of skin grafts and later formed a committee to annotate by consensus a subset of representative pictures. While the individual predictions were used as an accuracy baseline, the consensus annotation was the true score and used to train the model. Results The model predictions were more accurate in scores mainly based on color (I and P), rather than texture (S and U), as shown by the micro-averaged Area Under the Curve (AUC) of 0.86, 0.61, 0.51, and 0.80 for I, S, U, and P, respectively (Figure 1). The model accuracy was higher than the human baseline ... Article in Journal/Newspaper SCAR Oxford University Press Journal of Burn Care & Research 41 Supplement_1 S33 S34 |
institution |
Open Polar |
collection |
Oxford University Press |
op_collection_id |
croxfordunivpr |
language |
English |
topic |
Rehabilitation Emergency Medicine Surgery |
spellingShingle |
Rehabilitation Emergency Medicine Surgery Ribeiro, Guilherme Aramizo Ridelman, Elika Klein, Justin D Angst, Beth A Shanti, Christina M Rastgaar, Mo 50 Assessment of Skin Graft in Pediatric Burn Patients Using Machine Learning Is Comparable to Human Expert Performance |
topic_facet |
Rehabilitation Emergency Medicine Surgery |
description |
Abstract Introduction Though widely used, current scar assessment scales are inaccurate and highly subjective, further complicating the already difficult task of determining the optimal management of burn patients. Additional disadvantages of these tools include the need for direct examination by an experienced clinician and the inability to retrospectively review them. The lack of an accurate assessment tool inevitably impairs any research examining novel therapeutic strategies designed to improve burn scar outcomes by introducing observer bias at every step. Common examples of these tools include the Vancouver Scar Scale and Visual analog scale. New imaging and processing technologies have the potential of bringing accuracy, reproducibility, and accessibility to burn scar assessments. With these goals in mind, our team developed a novel scoring system and a classification model based on Machine Learning algorithms and analyzed 87 pictures to obtain scores on Inflammation (I), Scar (S), Uniformity (U), and Pigmentation (P). Methods All algorithms were trained using both the sub-acute and the long-term phase pictures. The classification model is based on supervised learning, which requires many examples of annotated pictures and corresponding scar scores. The model used a Linear Discriminant Analysis (LDA) algorithm and visual features of the scars and the natural skin. To train and evaluate this model, four burn care providers individually annotated 186 pictures of skin grafts and later formed a committee to annotate by consensus a subset of representative pictures. While the individual predictions were used as an accuracy baseline, the consensus annotation was the true score and used to train the model. Results The model predictions were more accurate in scores mainly based on color (I and P), rather than texture (S and U), as shown by the micro-averaged Area Under the Curve (AUC) of 0.86, 0.61, 0.51, and 0.80 for I, S, U, and P, respectively (Figure 1). The model accuracy was higher than the human baseline ... |
format |
Article in Journal/Newspaper |
author |
Ribeiro, Guilherme Aramizo Ridelman, Elika Klein, Justin D Angst, Beth A Shanti, Christina M Rastgaar, Mo |
author_facet |
Ribeiro, Guilherme Aramizo Ridelman, Elika Klein, Justin D Angst, Beth A Shanti, Christina M Rastgaar, Mo |
author_sort |
Ribeiro, Guilherme Aramizo |
title |
50 Assessment of Skin Graft in Pediatric Burn Patients Using Machine Learning Is Comparable to Human Expert Performance |
title_short |
50 Assessment of Skin Graft in Pediatric Burn Patients Using Machine Learning Is Comparable to Human Expert Performance |
title_full |
50 Assessment of Skin Graft in Pediatric Burn Patients Using Machine Learning Is Comparable to Human Expert Performance |
title_fullStr |
50 Assessment of Skin Graft in Pediatric Burn Patients Using Machine Learning Is Comparable to Human Expert Performance |
title_full_unstemmed |
50 Assessment of Skin Graft in Pediatric Burn Patients Using Machine Learning Is Comparable to Human Expert Performance |
title_sort |
50 assessment of skin graft in pediatric burn patients using machine learning is comparable to human expert performance |
publisher |
Oxford University Press (OUP) |
publishDate |
2020 |
url |
http://dx.doi.org/10.1093/jbcr/iraa024.054 http://academic.oup.com/jbcr/article-pdf/41/Supplement_1/S33/32763202/iraa024.054.pdf |
genre |
SCAR |
genre_facet |
SCAR |
op_source |
Journal of Burn Care & Research volume 41, issue Supplement_1, page S33-S34 ISSN 1559-047X 1559-0488 |
op_rights |
https://academic.oup.com/journals/pages/open_access/funder_policies/chorus/standard_publication_model |
op_doi |
https://doi.org/10.1093/jbcr/iraa024.054 |
container_title |
Journal of Burn Care & Research |
container_volume |
41 |
container_issue |
Supplement_1 |
container_start_page |
S33 |
op_container_end_page |
S34 |
_version_ |
1795673244967108608 |