File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Deep Learning Model to Classify and Monitor Idiopathic Scoliosis in Adolescents Using a Single Smartphone Photograph

TitleDeep Learning Model to Classify and Monitor Idiopathic Scoliosis in Adolescents Using a Single Smartphone Photograph
Authors
Issue Date23-Aug-2023
PublisherAmerican Medical Association
Citation
Jama Network Open, 2023, v. 6, n. 8, p. e2330617 How to Cite?
Abstract

Importance  Adolescent idiopathic scoliosis (AIS) is the most common pediatric spinal disorder. Routine physical examinations by trained personnel are critical to diagnose severity and monitor curve progression in AIS. In the presence of concerning malformation, radiographs are necessary for diagnosis or follow-up, guiding further management, such as bracing correction for moderate malformation and spine surgery for severe malformation. If left unattended, progressive deterioration occurs in two-thirds of patients, leading to significant health concerns for growing children.

Objective  To assess the ability of an open platform application (app) using a validated deep learning model to classify AIS severity and curve type, as well as identify progression.

Design, Setting, and Participants  This diagnostic study was performed with data from radiographs and smartphone photographs of the backs of adolescent patients at spine clinics. The ScolioNets deep learning model was developed and validated in a prospective training cohort, then incorporated and tested in the AlignProCARE open platform app in 2022. Ground truths (GTs) included severity, curve type, and progression as manually annotated by 2 experienced spine specialists based on the radiographic examinations of the participants’ spines. The GTs and app results were blindly compared with another 2 spine surgeons’ assessments of unclothed back appearance. Data were analyzed from October 2022 to February 2023.

Exposure  Acquisitions of unclothed back photographs using a mobile app.

Main Outcomes and Measures  Outcomes of interest were classification of AIS severity and progression. Quantitative statistical analyses were performed to assess the performance of the deep learning model in classifying the deformity as well as in distinguishing progression during 6-month follow-up.

Results  The training data set consisted of 1780 patients (1295 [72.8%] female; mean [SD] age, 14.3 [3.3] years), and the prospective testing data sets consisted of 378 patients (279 [73.8%] female; mean [SD] age, 14.3 [3.8] years) and 376 follow-ups (294 [78.2%] female; mean [SD] age, 15.6 [2.9] years). The model recommended follow-up with an area under receiver operating characteristic curve (AUC) of 0.839 (95% CI, 0.789-0.882) and considering surgery with an AUC of 0.902 (95% CI, 0.859-0.936), while showing good ability to distinguish among thoracic (AUC, 0.777 [95% CI, 0.745-0.808]), thoracolumbar or lumbar (AUC, 0.760 [95% CI, 0.727-0.791]), or mixed (AUC, 0.860 [95% CI, 0.834-0.887]) curve types. For follow-ups, the model distinguished participants with or without curve progression with an AUC of 0.757 (95% CI, 0.630-0.858). Compared with both surgeons, the model could recognize severities and curve types with a higher sensitivity (eg, sensitivity for recommending follow-up: model, 84.88% [95% CI, 75.54%-91.70%]; senior surgeon, 44.19%; junior surgeon, 62.79%) and negative predictive values (NPVs; eg, NPV for recommending follow-up: model, 89.22% [95% CI, 84.25%-93.70%]; senior surgeon, 71.76%; junior surgeon, 79.35%). For distinguishing curve progression, the sensitivity and NPV were comparable with the senior surgeons (sensitivity, 63.33% [95% CI, 43.86%-80.87%] vs 77.42%; NPV, 68.57% [95% CI, 56.78%-78.37%] vs 72.00%). The junior surgeon reported an inability to identify curve types and progression by observing the unclothed back alone.

Conclusions  This diagnostic study of adolescent patients screened for AIS found that the deep learning app had the potential for out-of-hospital accessible and radiation-free management of children with scoliosis, with comparable performance as spine surgeons experienced in AIS management.


Persistent Identifierhttp://hdl.handle.net/10722/331483
ISSN
2023 Impact Factor: 10.5
2023 SCImago Journal Rankings: 3.478
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorZhang, Teng-
dc.contributor.authorZhu, Chuang-
dc.contributor.authorZhao, Yongkang-
dc.contributor.authorZhao, Moxin-
dc.contributor.authorWang, Zhihao-
dc.contributor.authorSong, Ruoning-
dc.contributor.authorMeng, Nan-
dc.contributor.authorSial, Alisha-
dc.contributor.authorDiwan, Ashish-
dc.contributor.authorLiu, Jun-
dc.contributor.authorCheung, Jason-
dc.date.accessioned2023-09-21T06:56:13Z-
dc.date.available2023-09-21T06:56:13Z-
dc.date.issued2023-08-23-
dc.identifier.citationJama Network Open, 2023, v. 6, n. 8, p. e2330617-
dc.identifier.issn2574-3805-
dc.identifier.urihttp://hdl.handle.net/10722/331483-
dc.description.abstract<p><strong>Importance</strong>  Adolescent idiopathic scoliosis (AIS) is the most common pediatric spinal disorder. Routine physical examinations by trained personnel are critical to diagnose severity and monitor curve progression in AIS. In the presence of concerning malformation, radiographs are necessary for diagnosis or follow-up, guiding further management, such as bracing correction for moderate malformation and spine surgery for severe malformation. If left unattended, progressive deterioration occurs in two-thirds of patients, leading to significant health concerns for growing children.</p><p><strong>Objective</strong>  To assess the ability of an open platform application (app) using a validated deep learning model to classify AIS severity and curve type, as well as identify progression.</p><p><strong>Design, Setting, and Participants</strong>  This diagnostic study was performed with data from radiographs and smartphone photographs of the backs of adolescent patients at spine clinics. The ScolioNets deep learning model was developed and validated in a prospective training cohort, then incorporated and tested in the AlignProCARE open platform app in 2022. Ground truths (GTs) included severity, curve type, and progression as manually annotated by 2 experienced spine specialists based on the radiographic examinations of the participants’ spines. The GTs and app results were blindly compared with another 2 spine surgeons’ assessments of unclothed back appearance. Data were analyzed from October 2022 to February 2023.</p><p><strong>Exposure</strong>  Acquisitions of unclothed back photographs using a mobile app.</p><p><strong>Main Outcomes and Measures</strong>  Outcomes of interest were classification of AIS severity and progression. Quantitative statistical analyses were performed to assess the performance of the deep learning model in classifying the deformity as well as in distinguishing progression during 6-month follow-up.</p><p><strong>Results</strong>  The training data set consisted of 1780 patients (1295 [72.8%] female; mean [SD] age, 14.3 [3.3] years), and the prospective testing data sets consisted of 378 patients (279 [73.8%] female; mean [SD] age, 14.3 [3.8] years) and 376 follow-ups (294 [78.2%] female; mean [SD] age, 15.6 [2.9] years). The model recommended follow-up with an area under receiver operating characteristic curve (AUC) of 0.839 (95% CI, 0.789-0.882) and considering surgery with an AUC of 0.902 (95% CI, 0.859-0.936), while showing good ability to distinguish among thoracic (AUC, 0.777 [95% CI, 0.745-0.808]), thoracolumbar or lumbar (AUC, 0.760 [95% CI, 0.727-0.791]), or mixed (AUC, 0.860 [95% CI, 0.834-0.887]) curve types. For follow-ups, the model distinguished participants with or without curve progression with an AUC of 0.757 (95% CI, 0.630-0.858). Compared with both surgeons, the model could recognize severities and curve types with a higher sensitivity (eg, sensitivity for recommending follow-up: model, 84.88% [95% CI, 75.54%-91.70%]; senior surgeon, 44.19%; junior surgeon, 62.79%) and negative predictive values (NPVs; eg, NPV for recommending follow-up: model, 89.22% [95% CI, 84.25%-93.70%]; senior surgeon, 71.76%; junior surgeon, 79.35%). For distinguishing curve progression, the sensitivity and NPV were comparable with the senior surgeons (sensitivity, 63.33% [95% CI, 43.86%-80.87%] vs 77.42%; NPV, 68.57% [95% CI, 56.78%-78.37%] vs 72.00%). The junior surgeon reported an inability to identify curve types and progression by observing the unclothed back alone.</p><p><strong>Conclusions</strong>  This diagnostic study of adolescent patients screened for AIS found that the deep learning app had the potential for out-of-hospital accessible and radiation-free management of children with scoliosis, with comparable performance as spine surgeons experienced in AIS management.</p>-
dc.languageeng-
dc.publisherAmerican Medical Association-
dc.relation.ispartofJama Network Open-
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.titleDeep Learning Model to Classify and Monitor Idiopathic Scoliosis in Adolescents Using a Single Smartphone Photograph-
dc.typeArticle-
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1001/jamanetworkopen.2023.30617-
dc.identifier.scopuseid_2-s2.0-85168778200-
dc.identifier.volume6-
dc.identifier.issue8-
dc.identifier.spagee2330617-
dc.identifier.eissn2574-3805-
dc.identifier.isiWOS:001061956800003-
dc.identifier.issnl2574-3805-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats