Exploring artificial intelligence for differentiating early syphilis from other skin lesions: a pilot study
Abstract Background Early diagnosis of syphilis is vital for its effective control. This study aimed to develop an Artificial Intelligence (AI) diagnostic model based on radiomics technology to distinguish early syphilis from other clinical skin lesions. Methods The study collected 260 images of ski...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-01-01
|
| Series: | BMC Infectious Diseases |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12879-024-10438-5 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841544954632994816 |
|---|---|
| author | Jiajun Sun Yingping Li Zhen Yu Janet M. Towns Nyi N. Soe Phyu M. Latt Lin Zhang Zongyuan Ge Christopher K. Fairley Jason J. Ong Lei Zhang |
| author_facet | Jiajun Sun Yingping Li Zhen Yu Janet M. Towns Nyi N. Soe Phyu M. Latt Lin Zhang Zongyuan Ge Christopher K. Fairley Jason J. Ong Lei Zhang |
| author_sort | Jiajun Sun |
| collection | DOAJ |
| description | Abstract Background Early diagnosis of syphilis is vital for its effective control. This study aimed to develop an Artificial Intelligence (AI) diagnostic model based on radiomics technology to distinguish early syphilis from other clinical skin lesions. Methods The study collected 260 images of skin lesions caused by various skin infections, including 115 syphilis and 145 other infection types. 80% of the dataset was used for model development with 5-fold cross-validation, and the remaining 20% was used as a hold-out test set. The exact lesion region was manually segmented as Region of Interest (ROI) in each image with the help of two experts. 102 radiomics features were extracted from each ROI and fed into 11 different classifiers after deleting the redundant features using the Pearson correlation coefficient. Different image filters like Wavelet were investigated to improve the model performance. The area under the ROC curve (AUC) was used for evaluation, and Shapley Additive exPlanations (SHAP) for model interpretation. Results Among the 11 classifiers, the Gradient Boosted Decision Trees (GBDT) with the wavelet filter applied on the images demonstrated the best performance, offering the stratified 5-fold cross-validation AUC of 0.832 ± 0.042 and accuracy of 0.735 ± 0.043. On the hold-out test dataset, the model shows an AUC and accuracy of 0.792 and 0.750, respectively. The SHAP analysis shows that the shape 2D sphericity was the most predictive radiomics feature for distinguishing early syphilis from other skin infections. Conclusion The proposed AI diagnostic model, built based on radiomics features and machine learning classifiers, achieved an accuracy of 75.0%, and demonstrated potential in distinguishing early syphilis from other skin lesions. |
| format | Article |
| id | doaj-art-1ca1119b818942b08dffcd17dcbe6618 |
| institution | Kabale University |
| issn | 1471-2334 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Infectious Diseases |
| spelling | doaj-art-1ca1119b818942b08dffcd17dcbe66182025-01-12T12:09:31ZengBMCBMC Infectious Diseases1471-23342025-01-0125111010.1186/s12879-024-10438-5Exploring artificial intelligence for differentiating early syphilis from other skin lesions: a pilot studyJiajun Sun0Yingping Li1Zhen Yu2Janet M. Towns3Nyi N. Soe4Phyu M. Latt5Lin Zhang6Zongyuan Ge7Christopher K. Fairley8Jason J. Ong9Lei Zhang10Melbourne Sexual Health Centre, Alfred HealthSchool of Artificial Intelligence, Xidian UniversityAIM for Health Lab, Monash UniversityMelbourne Sexual Health Centre, Alfred HealthMelbourne Sexual Health Centre, Alfred HealthMelbourne Sexual Health Centre, Alfred HealthSuzhou Industrial Park Monash Research Institute of Science and TechnologyAIM for Health Lab, Monash UniversityMelbourne Sexual Health Centre, Alfred HealthMelbourne Sexual Health Centre, Alfred HealthMelbourne Sexual Health Centre, Alfred HealthAbstract Background Early diagnosis of syphilis is vital for its effective control. This study aimed to develop an Artificial Intelligence (AI) diagnostic model based on radiomics technology to distinguish early syphilis from other clinical skin lesions. Methods The study collected 260 images of skin lesions caused by various skin infections, including 115 syphilis and 145 other infection types. 80% of the dataset was used for model development with 5-fold cross-validation, and the remaining 20% was used as a hold-out test set. The exact lesion region was manually segmented as Region of Interest (ROI) in each image with the help of two experts. 102 radiomics features were extracted from each ROI and fed into 11 different classifiers after deleting the redundant features using the Pearson correlation coefficient. Different image filters like Wavelet were investigated to improve the model performance. The area under the ROC curve (AUC) was used for evaluation, and Shapley Additive exPlanations (SHAP) for model interpretation. Results Among the 11 classifiers, the Gradient Boosted Decision Trees (GBDT) with the wavelet filter applied on the images demonstrated the best performance, offering the stratified 5-fold cross-validation AUC of 0.832 ± 0.042 and accuracy of 0.735 ± 0.043. On the hold-out test dataset, the model shows an AUC and accuracy of 0.792 and 0.750, respectively. The SHAP analysis shows that the shape 2D sphericity was the most predictive radiomics feature for distinguishing early syphilis from other skin infections. Conclusion The proposed AI diagnostic model, built based on radiomics features and machine learning classifiers, achieved an accuracy of 75.0%, and demonstrated potential in distinguishing early syphilis from other skin lesions.https://doi.org/10.1186/s12879-024-10438-5RadiomicsArtificial IntelligenceEarly SyphilisSkin LesionsSexually Transmitted InfectionMachine Learning |
| spellingShingle | Jiajun Sun Yingping Li Zhen Yu Janet M. Towns Nyi N. Soe Phyu M. Latt Lin Zhang Zongyuan Ge Christopher K. Fairley Jason J. Ong Lei Zhang Exploring artificial intelligence for differentiating early syphilis from other skin lesions: a pilot study BMC Infectious Diseases Radiomics Artificial Intelligence Early Syphilis Skin Lesions Sexually Transmitted Infection Machine Learning |
| title | Exploring artificial intelligence for differentiating early syphilis from other skin lesions: a pilot study |
| title_full | Exploring artificial intelligence for differentiating early syphilis from other skin lesions: a pilot study |
| title_fullStr | Exploring artificial intelligence for differentiating early syphilis from other skin lesions: a pilot study |
| title_full_unstemmed | Exploring artificial intelligence for differentiating early syphilis from other skin lesions: a pilot study |
| title_short | Exploring artificial intelligence for differentiating early syphilis from other skin lesions: a pilot study |
| title_sort | exploring artificial intelligence for differentiating early syphilis from other skin lesions a pilot study |
| topic | Radiomics Artificial Intelligence Early Syphilis Skin Lesions Sexually Transmitted Infection Machine Learning |
| url | https://doi.org/10.1186/s12879-024-10438-5 |
| work_keys_str_mv | AT jiajunsun exploringartificialintelligencefordifferentiatingearlysyphilisfromotherskinlesionsapilotstudy AT yingpingli exploringartificialintelligencefordifferentiatingearlysyphilisfromotherskinlesionsapilotstudy AT zhenyu exploringartificialintelligencefordifferentiatingearlysyphilisfromotherskinlesionsapilotstudy AT janetmtowns exploringartificialintelligencefordifferentiatingearlysyphilisfromotherskinlesionsapilotstudy AT nyinsoe exploringartificialintelligencefordifferentiatingearlysyphilisfromotherskinlesionsapilotstudy AT phyumlatt exploringartificialintelligencefordifferentiatingearlysyphilisfromotherskinlesionsapilotstudy AT linzhang exploringartificialintelligencefordifferentiatingearlysyphilisfromotherskinlesionsapilotstudy AT zongyuange exploringartificialintelligencefordifferentiatingearlysyphilisfromotherskinlesionsapilotstudy AT christopherkfairley exploringartificialintelligencefordifferentiatingearlysyphilisfromotherskinlesionsapilotstudy AT jasonjong exploringartificialintelligencefordifferentiatingearlysyphilisfromotherskinlesionsapilotstudy AT leizhang exploringartificialintelligencefordifferentiatingearlysyphilisfromotherskinlesionsapilotstudy |