{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T06:31:28Z","timestamp":1790404288082,"version":"4.1.0"},"reference-count":52,"publisher":"Wiley","issue":"4","license":[{"start":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T00:00:00Z","timestamp":1703462400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100010754","name":"National Healthcare Group","doi-asserted-by":"publisher","award":["PHG20\/S\/X\/1\/1"],"award-info":[{"award-number":["PHG20\/S\/X\/1\/1"]}],"id":[{"id":"10.13039\/501100010754","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001349","name":"National Medical Research Council","doi-asserted-by":"publisher","award":["FLWSHP19nov\u20100015"],"award-info":[{"award-number":["FLWSHP19nov\u20100015"]}],"id":[{"id":"10.13039\/501100001349","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100030794","name":"Skin Research Institute of Singapore","doi-asserted-by":"publisher","award":["H17\/01\/a0\/0Y9"],"award-info":[{"award-number":["H17\/01\/a0\/0Y9"]}],"id":[{"id":"10.13039\/100030794","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["International Wound Journal"],"published-print":{"date-parts":[[2024,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Chronic wounds contribute to significant healthcare and economic burden worldwide. Wound assessment remains challenging given its complex and dynamic nature. The use of artificial intelligence (AI) and machine learning methods in wound analysis is promising. Explainable modelling can help its integration and acceptance in healthcare systems. We aim to develop an explainable AI model for analysing vascular wound images among an Asian population. Two thousand nine hundred and fifty\u2010seven wound images from a vascular wound image registry from a tertiary institution in Singapore were utilized. The dataset was split into training, validation and test sets. Wound images were classified into four types (neuroischaemic ulcer [NIU], surgical site infections [SSI], venous leg ulcers [VLU], pressure ulcer [PU]), measured with automatic estimation of width, length and depth and segmented into 18 wound and peri\u2010wound features. Data pre\u2010processing was performed using oversampling and augmentation techniques. Convolutional and deep learning models were utilized for model development. The model was evaluated with accuracy, F1 score and receiver operating characteristic (ROC) curves. Explainability methods were used to interpret AI decision reasoning. A web browser application was developed to demonstrate results of the wound AI model with explainability. After development, the model was tested on additional 15\u2009476 unlabelled images to evaluate effectiveness. After the development on the training and validation dataset, the model performance on unseen labelled images in the test set achieved an AUROC of 0.99 for wound classification with mean accuracy of 95.9%. For wound measurements, the model achieved AUROC of 0.97 with mean accuracy of 85.0% for depth classification, and AUROC of 0.92 with mean accuracy of 87.1% for width and length determination. For wound segmentation, an AUROC of 0.95 and mean accuracy of 87.8% was achieved. Testing on unlabelled images, the model confidence score for wound classification was 82.8% with an explainability score of 60.6%. Confidence score was 87.6% for depth classification with 68.0% explainability score, while width and length measurement obtained 93.0% accuracy score with 76.6% explainability. Confidence score for wound segmentation was 83.9%, while explainability was 72.1%. Using explainable AI models, we have developed an algorithm and application for analysis of vascular wound images from an Asian population with accuracy and explainability. With further development, it can be utilized as a clinical decision support system and integrated into existing healthcare electronic systems.<\/jats:p>","DOI":"10.1111\/iwj.14565","type":"journal-article","created":{"date-parts":[[2023,12,26]],"date-time":"2023-12-26T01:04:35Z","timestamp":1703552675000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["Development of an explainable artificial intelligence model for Asian vascular wound images"],"prefix":"10.1111","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2289-5266","authenticated-orcid":false,"given":"Zhiwen Joseph","family":"Lo","sequence":"first","affiliation":[{"name":"Department of Surgery Woodlands Health  Singapore Singapore"},{"name":"Lee Kong Chian School of Medicine Nanyang Technological University  Singapore Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3711-0946","authenticated-orcid":false,"given":"Malcolm Han Wen","family":"Mak","sequence":"additional","affiliation":[{"name":"Department of General Surgery Tan Tock Seng Hospital  Singapore Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanying","family":"Liang","sequence":"additional","affiliation":[{"name":"Department of Surgery Woodlands Health  Singapore Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yam Meng","family":"Chan","sequence":"additional","affiliation":[{"name":"Department of General Surgery Tan Tock Seng Hospital  Singapore Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng Cheng","family":"Goh","sequence":"additional","affiliation":[{"name":"Wound and Stoma Care, Nursing Speciality Tan Tock Seng Hospital  Singapore Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tina","family":"Lai","sequence":"additional","affiliation":[{"name":"Wound and Stoma Care, Nursing Speciality Tan Tock Seng Hospital  Singapore Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Audrey","family":"Tan","sequence":"additional","affiliation":[{"name":"Wound and Stoma Care, Nursing Speciality Tan Tock Seng Hospital  Singapore Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Patrick","family":"Thng","sequence":"additional","affiliation":[{"name":"AITIS \u2010 Advanced Intelligence and Technology Innovations  London United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jorge","family":"Rodriguez","sequence":"additional","affiliation":[{"name":"AITIS \u2010 Advanced Intelligence and Technology Innovations  London United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tillman","family":"Weyde","sequence":"additional","affiliation":[{"name":"AITIS \u2010 Advanced Intelligence and Technology Innovations  London United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sylvia","family":"Smit","sequence":"additional","affiliation":[{"name":"AITIS \u2010 Advanced Intelligence and Technology Innovations  London United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2023,12,25]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1111\/wrr.12683"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1111\/iwj.13540"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1111\/iwj.14082"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1111\/iwj.13481"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978\u20100\u201012\u2010818438\u20107.00002\u20102"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2020.0265"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10620\u2010021\u201007086\u2010z"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1089\/wound.2021.0091"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1002\/aorn.12102"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1111\/iwj.13952"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.12968\/jowc.2019.28.Sup10.S13"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2020.103616"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2020.103655"},{"key":"e_1_2_9_15_1","unstructured":"Ming.Imbalanced Dataset Sampler.2023Accessed June 6 2023.https:\/\/github.com\/ufoym\/imbalanced-dataset-sampler"},{"key":"e_1_2_9_16_1","unstructured":"YunS HanD OhSJ ChunS ChoeJ YooY.CutMix: regularization strategy to train strong classifiers with localizable features.2019Accessed June 5 2023.http:\/\/arxiv.org\/abs\/1905.04899"},{"key":"e_1_2_9_17_1","unstructured":"ZhangH CisseM DauphinYN Lopez\u2010PazD.Mixup: beyond empirical risk minimization.2018Accessed June 5 2023.http:\/\/arxiv.org\/abs\/1710.09412"},{"key":"e_1_2_9_18_1","unstructured":"DosovitskiyA BeyerL KolesnikovA et al.An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.2021. doi:10.48550\/arXiv.2010.11929"},{"key":"e_1_2_9_19_1","doi-asserted-by":"crossref","unstructured":"LiuZ LinY CaoY et al.Swin transformer: hierarchical vision transformer using shifted windows.2021. doi:10.48550\/arXiv.2103.14030","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_2_9_20_1","doi-asserted-by":"crossref","unstructured":"WangCY BochkovskiyA LiaoHYM.YOLOv7: trainable bag\u2010of\u2010freebies sets new state\u2010of\u2010the\u2010art for real\u2010time object detectors.2022. doi:10.48550\/arXiv.2207.02696","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_2_9_22_1","unstructured":"LinTY MaireM BelongieS et al.Microsoft COCO: common objects in context.2015. doi:10.48550\/arXiv.1405.0312"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263\u2010009\u20100275\u20104"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"e_1_2_9_25_1","unstructured":"HuangG LiuZ van derMaatenL WeinbergerKQ.Densely connected convolutional networks.2018. doi:10.48550\/arXiv.1608.06993"},{"key":"e_1_2_9_26_1","unstructured":"HowardA SandlerM ChuG et al.Searching for MobileNetV3.2019. doi:10.48550\/arXiv.1905.02244"},{"key":"e_1_2_9_27_1","unstructured":"HeK ZhangX RenS SunJ.Deep residual learning for image recognition.2015Accessed August 12 2023.http:\/\/arxiv.org\/abs\/1512.03385"},{"key":"e_1_2_9_28_1","unstructured":"ChenLC PapandreouG SchroffF AdamH.Rethinking atrous convolution for semantic image segmentation.2017. doi:10.48550\/arXiv.1706.05587"},{"key":"e_1_2_9_29_1","doi-asserted-by":"crossref","unstructured":"LinTY Doll\u00e1rP GirshickR HeK HariharanB BelongieS.Feature pyramid networks for object detection.2017. doi:10.48550\/arXiv.1612.03144","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_2_9_30_1","unstructured":"RonnebergerO FischerP BroxT.U\u2010Net: Convolutional Networks for Biomedical Image Segmentation.2015. doi:10.48550\/arXiv.1505.04597"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263\u2010019\u201001228\u20107"},{"key":"e_1_2_9_32_1","doi-asserted-by":"crossref","unstructured":"RibeiroMT SinghS GuestrinC.\u201cWhy Should I Trust You?\u201d: Explaining the predictions of any classifier.2016. doi:10.48550\/arXiv.1602.04938","DOI":"10.18653\/v1\/N16-3020"},{"key":"e_1_2_9_33_1","volume-title":"Advances in Neural Information Processing Systems, Vol. 30","author":"Lundberg SM","year":"2017"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.12968\/bjon.1999.8.20.1342"},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.1177\/1932296820942307"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.6.2.024002"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2016.2632522"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104536"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010022\u201021813\u20100"},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.esmoop.2022.100400"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.3390\/e23010018"},{"key":"e_1_2_9_42_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12911\u2010020\u201001332\u20106"},{"key":"e_1_2_9_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102470"},{"key":"e_1_2_9_44_1","doi-asserted-by":"publisher","DOI":"10.3390\/s23020634"},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics12020237"},{"key":"e_1_2_9_46_1","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10121406"},{"key":"e_1_2_9_47_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13111932"},{"key":"e_1_2_9_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/S2589\u20107500(21)00208\u20109"},{"key":"e_1_2_9_49_1","doi-asserted-by":"publisher","DOI":"10.1111\/iwj.13918"},{"key":"e_1_2_9_50_1","doi-asserted-by":"publisher","DOI":"10.1111\/iwj.13644"},{"key":"e_1_2_9_51_1","doi-asserted-by":"publisher","DOI":"10.1111\/iwj.13603"},{"key":"e_1_2_9_52_1","doi-asserted-by":"publisher","DOI":"10.1111\/iwj.13672"},{"key":"e_1_2_9_53_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvs.2023.03.265"}],"container-title":["International Wound Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/iwj.14565","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T06:30:54Z","timestamp":1754289054000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/iwj.14565"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,25]]},"references-count":52,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,4]]}},"alternative-id":["10.1111\/iwj.14565"],"URL":"https:\/\/doi.org\/10.1111\/iwj.14565","archive":["Portico"],"relation":{},"ISSN":["1742-4801","1742-481X"],"issn-type":[{"value":"1742-4801","type":"print"},{"value":"1742-481X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,25]]},"assertion":[{"value":"2023-11-04","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-12-04","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-12-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e14565"}}