Risk of bias and applicability concerns graph.
<div><p>Background</p><p>Artificial intelligence (AI) is a promising and powerful technology with increasing use in orthopedics. The global morbidity of knee arthroplasty is expanding. This study investigated the use of AI algorithms to review radiographs of knee arthroplasty...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | , , , , , |
| Published: |
2025
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1852020713370681344 |
|---|---|
| author | Zhihong Zhang (2027) |
| author2 | Xu Hui (9392200) Huimin Tao (5315351) Zhenjiang Fu (21261786) Zaili Cai (21261789) Sheng Zhou (66217) Kehu Yang (192609) |
| author2_role | author author author author author author |
| author_facet | Zhihong Zhang (2027) Xu Hui (9392200) Huimin Tao (5315351) Zhenjiang Fu (21261786) Zaili Cai (21261789) Sheng Zhou (66217) Kehu Yang (192609) |
| author_role | author |
| dc.creator.none.fl_str_mv | Zhihong Zhang (2027) Xu Hui (9392200) Huimin Tao (5315351) Zhenjiang Fu (21261786) Zaili Cai (21261789) Sheng Zhou (66217) Kehu Yang (192609) |
| dc.date.none.fl_str_mv | 2025-05-07T17:31:49Z |
| dc.identifier.none.fl_str_mv | 10.1371/journal.pone.0321104.g003 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/figure/Risk_of_bias_and_applicability_concerns_graph_/28947558 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Medicine Biotechnology Cancer Science Policy Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified vip ), wanfang two others exhibited source software programs regarding implant measurement intraclass correlation coefficient identifying implant brands excellent reliability across detecting implant loosening cnki ), weipu classified implant brands china biology medicine 96 &# 8211 10 achieved accuracy one study showed one study achieved three separate studies determining component sizes 10 studies identified ray imaging analysis study investigated studies show component alignment 21 studies xlink "> transparent reporting systematically screened rigorous approach review radiographs recognizing implants quality assessment provide clinicians predicting pji powerful technology pji ). perfect prediction march 2024 knee arthroplasty global morbidity future research crd42024507549 ). commercial tools cochrane library artificial intelligence another reported 78 ). 5 %, 100 %. |
| dc.title.none.fl_str_mv | Risk of bias and applicability concerns graph. |
| dc.type.none.fl_str_mv | Image Figure info:eu-repo/semantics/publishedVersion image |
| description | <div><p>Background</p><p>Artificial intelligence (AI) is a promising and powerful technology with increasing use in orthopedics. The global morbidity of knee arthroplasty is expanding. This study investigated the use of AI algorithms to review radiographs of knee arthroplasty.</p><p>Methods</p><p>The Ovid-Embase, Web of Science, Cochrane Library, PubMed, China National Knowledge Infrastructure (CNKI), WeiPu (VIP), WanFang, and China Biology Medicine (CBM) databases were systematically screened from inception to March 2024 (PROSPERO study protocol registration: CRD42024507549). The quality assessment of the diagnostic accuracy studies tool assessed the risk of bias.</p><p>Results</p><p>A total of 21 studies were included in the analysis. Of these, 10 studies identified and classified implant brands, 6 measured implant size and component alignment, 3 detected implant loosening, and 2 diagnosed prosthetic joint infections (PJI). For classifying and identifying implant brands, 5 studies demonstrated near-perfect prediction with an area under the curve (AUC) ranging from 0.98 to 1.0, and 10 achieved accuracy (ACC) between 96–100%. Regarding implant measurement, one study showed an AUC of 0.62, and two others exhibited over 80% ACC in determining component sizes. Moreover, Artificial intelligence showed good to excellent reliability across all angles in three separate studies (Intraclass Correlation Coefficient > 0.78). In predicting PJI, one study achieved an AUC of 0.91 with a corresponding ACC of 90.5%, while another reported a positive predictive value ranging from 75% to 85%. For detecting implant loosening, the AUC was found to be at least as high as 0.976 with ACC ranging from 85.8% to 97.5%.</p><p>Conclusions</p><p>These studies show that AI is promising in recognizing implants in knee arthroplasty. Future research should follow a rigorous approach to AI development, with comprehensive and transparent reporting of methods and the creation of open-source software programs and commercial tools that can provide clinicians with objective clinical decisions.</p></div> |
| eu_rights_str_mv | openAccess |
| id | Manara_08f34ddc8ccd6e08231fabb4f4e7fe7d |
| identifier_str_mv | 10.1371/journal.pone.0321104.g003 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/28947558 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Risk of bias and applicability concerns graph.Zhihong Zhang (2027)Xu Hui (9392200)Huimin Tao (5315351)Zhenjiang Fu (21261786)Zaili Cai (21261789)Sheng Zhou (66217)Kehu Yang (192609)MedicineBiotechnologyCancerScience PolicySpace ScienceBiological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedvip ), wanfangtwo others exhibitedsource software programsregarding implant measurementintraclass correlation coefficientidentifying implant brandsexcellent reliability acrossdetecting implant looseningcnki ), weipuclassified implant brandschina biology medicine96 &# 821110 achieved accuracyone study showedone study achievedthree separate studiesdetermining component sizes10 studies identifiedray imaging analysisstudy investigatedstudies showcomponent alignment21 studiesxlink ">transparent reportingsystematically screenedrigorous approachreview radiographsrecognizing implantsquality assessmentprovide clinicianspredicting pjipowerful technologypji ).perfect predictionmarch 2024knee arthroplastyglobal morbidityfuture researchcrd42024507549 ).commercial toolscochrane libraryartificial intelligenceanother reported78 ).5 %,100 %.<div><p>Background</p><p>Artificial intelligence (AI) is a promising and powerful technology with increasing use in orthopedics. The global morbidity of knee arthroplasty is expanding. This study investigated the use of AI algorithms to review radiographs of knee arthroplasty.</p><p>Methods</p><p>The Ovid-Embase, Web of Science, Cochrane Library, PubMed, China National Knowledge Infrastructure (CNKI), WeiPu (VIP), WanFang, and China Biology Medicine (CBM) databases were systematically screened from inception to March 2024 (PROSPERO study protocol registration: CRD42024507549). The quality assessment of the diagnostic accuracy studies tool assessed the risk of bias.</p><p>Results</p><p>A total of 21 studies were included in the analysis. Of these, 10 studies identified and classified implant brands, 6 measured implant size and component alignment, 3 detected implant loosening, and 2 diagnosed prosthetic joint infections (PJI). For classifying and identifying implant brands, 5 studies demonstrated near-perfect prediction with an area under the curve (AUC) ranging from 0.98 to 1.0, and 10 achieved accuracy (ACC) between 96–100%. Regarding implant measurement, one study showed an AUC of 0.62, and two others exhibited over 80% ACC in determining component sizes. Moreover, Artificial intelligence showed good to excellent reliability across all angles in three separate studies (Intraclass Correlation Coefficient > 0.78). In predicting PJI, one study achieved an AUC of 0.91 with a corresponding ACC of 90.5%, while another reported a positive predictive value ranging from 75% to 85%. For detecting implant loosening, the AUC was found to be at least as high as 0.976 with ACC ranging from 85.8% to 97.5%.</p><p>Conclusions</p><p>These studies show that AI is promising in recognizing implants in knee arthroplasty. Future research should follow a rigorous approach to AI development, with comprehensive and transparent reporting of methods and the creation of open-source software programs and commercial tools that can provide clinicians with objective clinical decisions.</p></div>2025-05-07T17:31:49ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0321104.g003https://figshare.com/articles/figure/Risk_of_bias_and_applicability_concerns_graph_/28947558CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/289475582025-05-07T17:31:49Z |
| spellingShingle | Risk of bias and applicability concerns graph. Zhihong Zhang (2027) Medicine Biotechnology Cancer Science Policy Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified vip ), wanfang two others exhibited source software programs regarding implant measurement intraclass correlation coefficient identifying implant brands excellent reliability across detecting implant loosening cnki ), weipu classified implant brands china biology medicine 96 &# 8211 10 achieved accuracy one study showed one study achieved three separate studies determining component sizes 10 studies identified ray imaging analysis study investigated studies show component alignment 21 studies xlink "> transparent reporting systematically screened rigorous approach review radiographs recognizing implants quality assessment provide clinicians predicting pji powerful technology pji ). perfect prediction march 2024 knee arthroplasty global morbidity future research crd42024507549 ). commercial tools cochrane library artificial intelligence another reported 78 ). 5 %, 100 %. |
| status_str | publishedVersion |
| title | Risk of bias and applicability concerns graph. |
| title_full | Risk of bias and applicability concerns graph. |
| title_fullStr | Risk of bias and applicability concerns graph. |
| title_full_unstemmed | Risk of bias and applicability concerns graph. |
| title_short | Risk of bias and applicability concerns graph. |
| title_sort | Risk of bias and applicability concerns graph. |
| topic | Medicine Biotechnology Cancer Science Policy Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified vip ), wanfang two others exhibited source software programs regarding implant measurement intraclass correlation coefficient identifying implant brands excellent reliability across detecting implant loosening cnki ), weipu classified implant brands china biology medicine 96 &# 8211 10 achieved accuracy one study showed one study achieved three separate studies determining component sizes 10 studies identified ray imaging analysis study investigated studies show component alignment 21 studies xlink "> transparent reporting systematically screened rigorous approach review radiographs recognizing implants quality assessment provide clinicians predicting pji powerful technology pji ). perfect prediction march 2024 knee arthroplasty global morbidity future research crd42024507549 ). commercial tools cochrane library artificial intelligence another reported 78 ). 5 %, 100 %. |