{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T22:19:54Z","timestamp":1792189194306,"version":"4.4.0"},"reference-count":31,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec sec-type=\"background\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Pressure injuries (PIs) pose a negative health impact and a substantial economic burden on patients and society. Accurate staging is crucial for treating PIs. Owing to the diversity in the clinical manifestations of PIs and the lack of objective biochemical and pathological examinations, accurate staging of PIs is a major challenge. The deep learning algorithm, which uses convolutional neural networks (CNNs), has demonstrated exceptional classification performance in the intricate domain of skin diseases and wounds and has the potential to improve the staging accuracy of PIs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"objective\">\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>We explored the potential of applying AlexNet, VGGNet16, ResNet18, and DenseNet121 to PI staging, aiming to provide an effective tool to assist in staging.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"methods\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>PI images from patients\u2014including those with stage I, stage II, stage III, stage IV, unstageable, and suspected deep tissue injury (SDTI)\u2014were collected at a tertiary hospital in China. Additionally, we augmented the PI data by cropping and flipping the PI images 9 times. The collected images were then divided into training, validation, and test sets at a ratio of 8:1:1. We subsequently trained them via AlexNet, VGGNet16, ResNet18, and DenseNet121 to develop staging models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"results\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We collected 853 raw PI images with the following distributions across stages: stage I (n=148), stage II (n=121), stage III (n=216), stage IV (n=110), unstageable (n=128), and SDTI (n=130). A total of 7677 images were obtained after data augmentation. Among all the CNN models, DenseNet121 demonstrated the highest overall accuracy of 93.71%. The classification performances of AlexNet, VGGNet16, and ResNet18 exhibited overall accuracies of 87.74%, 82.42%, and 92.42%, respectively.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"conclusions\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The CNN-based models demonstrated strong classification ability for PI images, which might promote highly efficient, intelligent PI staging methods. In the future, the models can be compared with nurses with different levels of experience to further verify the clinical application effect.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/62774","type":"journal-article","created":{"date-parts":[[2025,1,11]],"date-time":"2025-01-11T07:56:02Z","timestamp":1736582162000},"page":"e62774-e62774","source":"Crossref","is-referenced-by-count":15,"title":["Convolutional Neural Network Models for Visual Classification of Pressure Ulcer Stages: Cross-Sectional Study"],"prefix":"10.2196","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5428-6003","authenticated-orcid":false,"given":"Changbin","family":"Lei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9813-3738","authenticated-orcid":false,"given":"Yan","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7946-6448","authenticated-orcid":false,"given":"Ke","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8367-6732","authenticated-orcid":false,"given":"Shanshan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7797-7477","authenticated-orcid":false,"given":"Hua","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3043-7869","authenticated-orcid":false,"given":"Cong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2025,3,25]]},"reference":[{"issue":"6","key":"R1","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1097\/WON.0000000000000281","article-title":"Revised national pressure ulcer advisory panel pressure injury staging system: revised pressure injury staging system","volume":"43","author":"Edsberg","journal-title":"J Wound Ostomy Continence Nurs"},{"key":"R2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijnurstu.2020.103546","article-title":"Global prevalence and incidence of pressure injuries in hospitalised adult patients: a systematic review and meta-analysis","volume":"105","author":"Li","journal-title":"Int J Nurs Stud"},{"issue":"3","key":"R3","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1093\/ageing\/afh086","article-title":"The cost of pressure ulcers in the UK","volume":"33","author":"Bennett","journal-title":"Age Ageing"},{"key":"R4","unstructured":"Prevention and Treatment of Pressure Ulcers\/Injuries: Clinical Practice Guideline. 3rded. European Pressure Ulcer Advisory Panel, National Pressure Injury Advisory Panel, and Pan Pacific Pressure Injury Alliance; 2019. ISBN: 978-0-6480097-8-8"},{"issue":"5","key":"R5","doi-asserted-by":"publisher","first-page":"266","DOI":"10.3928\/01484834-20160414-05","article-title":"Improving pressure ulcer staging accuracy through a nursing student experiential intervention","volume":"55","author":"Tschannen","journal-title":"J Nurs Educ"},{"issue":"4","key":"R6","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1097\/01.ASW.0000413597.20438.d2","article-title":"Financial impact of improved pressure ulcer staging in the acute hospital with use of a new tool, the NE1 Wound Assessment Tool","volume":"25","author":"Young","journal-title":"Adv Skin Wound Care"},{"key":"R7","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2019.101742","article-title":"Pressure injury image analysis with machine learning techniques: a systematic review on previous and possible future methods","volume":"102","author":"Zahia","journal-title":"Artif Intell Med"},{"issue":"4","key":"R8","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1016\/j.jmir.2019.09.005","article-title":"Machine learning and deep learning in medical imaging: intelligent imaging","volume":"50","author":"Currie","journal-title":"J Med Imaging Radiat Sci"},{"issue":"7639","key":"R9","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"Esteva","journal-title":"Nature New Biol"},{"issue":"16","key":"R10","doi-asserted-by":"publisher","first-page":"7124","DOI":"10.3390\/app14167124","article-title":"Diagnosis of pressure ulcer stage using on-device AI","volume":"14","author":"Chang","journal-title":"Appl Sci (Basel)"},{"key":"R11","doi-asserted-by":"publisher","DOI":"10.1155\/2023\/3858997","article-title":"Simultaneous segmentation and classification of pressure injury image data using Mask-R-CNN","volume":"2023","author":"Swerdlow","journal-title":"Comput Math Methods Med"},{"issue":"8","key":"R12","doi-asserted-by":"publisher","first-page":"3047","DOI":"10.1111\/jan.15584","article-title":"Visual classification of pressure injury stages for nurses: a deep learning model applying modern convolutional neural networks","volume":"79","author":"Seo","journal-title":"J Adv Nurs"},{"key":"R13","unstructured":"National pressure injury advisory panel. URL: https:\/\/npiap.com\/ [Accessed 11-03-2025]"},{"issue":"5","key":"R14","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1037\/h0031619","article-title":"Measuring nominal scale agreement among many raters","volume":"76","author":"Fleiss","journal-title":"Psychol Bull"},{"issue":"5","key":"R15","doi-asserted-by":"publisher","first-page":"545","DOI":"10.1111\/1754-9485.13261","article-title":"A review of medical image data augmentation techniques for deep learning applications","volume":"65","author":"Chlap","journal-title":"J Med Imaging Radiat Oncol"},{"issue":"2","key":"R16","doi-asserted-by":"publisher","first-page":"63","DOI":"10.5511\/plantbiotechnology.19.0322a","article-title":"Measuring plant colors","volume":"36","author":"Kasajima","journal-title":"Plant Biotechnol (Tokyo)"},{"issue":"8","key":"R17","doi-asserted-by":"publisher","first-page":"10173","DOI":"10.1109\/TPAMI.2023.3250241","article-title":"Normalization techniques in training DNNs: methodology, analysis and application","volume":"45","author":"Huang","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"5","key":"R18","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.1007\/s10278-020-00371-9","article-title":"Classification of skin lesions into seven classes using transfer learning with AlexNet","volume":"33","author":"Hosny","journal-title":"J Digit Imaging"},{"key":"R19","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2022.1001803","article-title":"A computational classification method of breast cancer images using the VGGNet model","volume":"16","author":"Khan","journal-title":"Front Comput Neurosci"},{"key":"R20","doi-asserted-by":"publisher","DOI":"10.1016\/j.medntd.2023.100243","article-title":"Deep learning based detection of monkeypox virus using skin lesion images","volume":"18","author":"Nayak","journal-title":"Med Nov Technol Devices"},{"issue":"24","key":"R21","doi-asserted-by":"publisher","first-page":"7080","DOI":"10.3390\/s20247080","article-title":"Skin lesion classification using densely connected convolutional networks with attention residual learning","volume":"20","author":"Wu","journal-title":"Sensors (Basel)"},{"issue":"4","key":"R22","doi-asserted-by":"publisher","first-page":"735","DOI":"10.1016\/j.jtv.2022.08.004","article-title":"Determining the pressure injury and staging knowledge of nurses at a hospital in Turkey","volume":"31","author":"Sayar","journal-title":"J Tissue Viability"},{"issue":"3","key":"R23","doi-asserted-by":"publisher","DOI":"10.2196\/25704","article-title":"Using machine learning technologies in pressure injury management: systematic review","volume":"9","author":"Jiang","journal-title":"JMIR Med Inform"},{"issue":"18","key":"R24","doi-asserted-by":"publisher","first-page":"16157","DOI":"10.1007\/s00521-022-07274-6","article-title":"Deep transfer learning-based visual classification of pressure injuries stages","volume":"34","author":"Ay","journal-title":"Neural Comput Applic"},{"key":"R25","unstructured":"Fergus P Chalmers C Henderson W Roberts D Waraich A . Pressure ulcer categorization using deep learning: a clinical trial to evaluate model performance. arXiv. Preprint posted online onMar7, 2022. [doi: 10.48550\/arXiv.2203.06248]"},{"key":"R26","doi-asserted-by":"publisher","DOI":"10.3389\/fmedt.2022.905074","article-title":"An artificial intelligence-enabled smartphone app for real-time pressure injury assessment","volume":"4","author":"Lau","journal-title":"Front Med Technol"},{"key":"R27","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2020.101085","article-title":"\u201cHow many images do I need?\u201d Understanding how sample size per class affects deep learning model performance metrics for balanced designs in autonomous wildlife monitoring","volume":"57","author":"Shahinfar","journal-title":"Ecol Inform"},{"issue":"2","key":"R28","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1016\/j.prosdent.2018.03.009","article-title":"Variability of color matching with different digital photography techniques and a gray reference card","volume":"121","author":"Sampaio","journal-title":"J Prosthet Dent"},{"key":"R29","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2023.105266","article-title":"Augmented decision-making in wound care: evaluating the clinical utility of a deep-learning model for pressure injury staging","volume":"180","author":"Kim","journal-title":"Int J Med Inform"},{"key":"R30","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejro.2023.100502","article-title":"Classification of asymmetry in mammography via the DenseNet convolutional neural network","volume":"11","author":"Liao","journal-title":"Eur J Radiol Open"},{"issue":"4","key":"R31","doi-asserted-by":"publisher","first-page":"1242","DOI":"10.1109\/TNNLS.2019.2919608","article-title":"Completely automated CNN architecture design based on blocks","volume":"31","author":"Sun","journal-title":"IEEE Trans Neural Netw Learn Syst"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2025\/1\/e62774","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T22:31:29Z","timestamp":1785537089000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2025\/1\/e62774"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,25]]},"references-count":31,"URL":"https:\/\/doi.org\/10.2196\/62774","relation":{},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,25]]},"article-number":"v13i6e62774"}}