{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T18:02:03Z","timestamp":1788976923626,"version":"build-2803163510"},"reference-count":24,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T00:00:00Z","timestamp":1768435200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Vertebral compression fractures (VCFs) commonly arise from osteoporosis, trauma, or malignancy. Accurate subtype differentiation is clinically essential but remains challenging using conventional imaging and histology.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We developed an explainable AI-driven digital pathology pipeline integrating whole-slide histopathology with clinical metadata and transcriptomic profiles to support fracture subtype classification, risk stratification, and therapy prediction. Model interpretability was assessed using Grad-CAM heatmaps and SHAP analysis, and the multi-omics risk score was validated across independent cohorts.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The deep learning classifier achieved 86\u201391% accuracy (F1 score 0.83\u20130.88) for osteoporotic, traumatic, and neoplastic fractures, despite modest per-class AUCs (0.49\u20130.54). Grad-CAM and SHAP highlighted biologically meaningful cues, including trabecular thinning, nuclear atypia, and marrow fibrosis. The multi-omics risk score stratified outcomes: high-risk fractures showed upregulated TNF\u2013NF-\u03baB signaling, reduced cytotoxic T-cell infiltration, and significantly worse 3-year survival (log-rank\n                      <jats:italic>p<\/jats:italic>\n                      &amp;lt; 0.001). Drug sensitivity modeling predicted response patterns, with low-risk patients aligned with bisphosphonates and RANKL inhibitors and high-risk cases associated with resistant phenotypes.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>This pipeline combines diagnostic performance with transparent interpretability and operates efficiently on modest computing resources, supporting telepathology deployment in resource-limited settings. By uniting classification, biological insight, and scalable implementation, the framework advances AI-enabled digital pathology toward more equitable global healthcare delivery.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2025.1726453","type":"journal-article","created":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T05:15:09Z","timestamp":1768454109000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Explainable AI for classifying vertebral fracture histology in digital spine pathology"],"prefix":"10.3389","volume":"12","author":[{"given":"Panyi","family":"Yang","sequence":"first","affiliation":[{"name":"Department of Pediatric Surgery, West China Hospital, Sichuan University","place":["Chengdu, Sichuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,1,15]]},"reference":[{"key":"ref1","first-page":"40","article-title":"Vertebral compression fractures","volume":"105","author":"McDonald","year":"2022","journal-title":"Rhode Island Med J"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"100394","DOI":"10.1016\/j.jpi.2024.100394","article-title":"Globalization of a telepathology network with artificial intelligence applications in Colombia: the GLORIA program study protocol","volume":"15","author":"Mosquera-Zamudio","year":"2024","journal-title":"J Pathol Inform"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1036","DOI":"10.1177\/02666669231200628","article-title":"Artificial intelligence in developing countries: the impact of generative artificial intelligence (AI) technologies for development","volume":"41","author":"Mannuru","year":"2025","journal-title":"Inf Dev"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"7206","DOI":"10.1007\/s00464-023-10220-9","article-title":"Increasing access to pathology services in low-and middle-income countries through innovative use of telepathology","volume":"37","author":"Kothari","year":"2023","journal-title":"Surg Endosc"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1002\/cjp2.263","article-title":"The ethical challenges of artificial intelligence-driven digital pathology","volume":"8","author":"McKay","year":"2022","journal-title":"J Pathol Clin Res"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"e53207","DOI":"10.2196\/53207","article-title":"How explainable artificial intelligence can increase or decrease clinicians\u2019 trust in AI applications in health care: systematic review","volume":"3","author":"Rosenbacke","year":"2024","journal-title":"Jmir AI"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"78","DOI":"10.3390\/make5010006","article-title":"XAIR: a systematic metareview of explainable AI (XAI) aligned to the software development process","volume":"5","author":"Clement","year":"2023","journal-title":"Mach Learn Knowl Extr"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1186\/s12880-025-01841-8","article-title":"Unveiling key pathomic features for automated diagnosis and Gleason grade estimation in prostate cancer","volume":"25","author":"Brancato","year":"2025","journal-title":"BMC Med Imaging"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1038\/s41746-020-0238-2","article-title":"Pan-cancer diagnostic consensus through searching archival histopathology images using artificial intelligence","volume":"3","author":"Kalra","year":"2020","journal-title":"NPJ Digita Med"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1101\/2025.09.04.674077","article-title":"Pathologist-interpretable breast cancer subtyping and stratification from AI-inferred nuclear features","volume-title":"bioRxiv","author":"Barman","year":"2025"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"7475","DOI":"10.3390\/ijms26157475","article-title":"Omics-mediated treatment for advanced prostate Cancer: moving towards precision oncology","volume":"26","author":"Fatima","year":"2025","journal-title":"Int J Mol Sci"},{"key":"ref12","author":"Tran","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"2102","DOI":"10.1038\/s41467-023-37179-4","article-title":"Histopathology images predict multi-omics aberrations and prognoses in colorectal cancer patients","volume":"14","author":"Tsai","year":"2023","journal-title":"Nat Commun"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"848","DOI":"10.3390\/diagnostics14080848","article-title":"Deep learning in breast cancer imaging: state of the art and recent advancements in early 2024","volume":"14","author":"Carriero","year":"2024","journal-title":"Diagnostics"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"720110","DOI":"10.3389\/fcell.2021.720110","article-title":"Histopathological images and multi-omics integration predict molecular characteristics and survival in lung adenocarcinoma","volume":"9","author":"Chen","year":"2021","journal-title":"Front Cell Dev Biol"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1038\/s41392-025-02374-w","article-title":"Pancancer outcome prediction via a unified weakly supervised deep learning model","volume":"10","author":"Yuan","year":"2025","journal-title":"Signal Transduct Target Ther"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1007\/s00432-022-04161-4","article-title":"Applications of artificial intelligence multiomics in precision oncology","volume":"149","author":"Srivastava","year":"2023","journal-title":"J Cancer Res Clin Oncol"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1007\/978-3-030-91836-1_16","article-title":"Multi-omics profiling of the tumor microenvironment","volume-title":"Computational methods for precision oncology","author":"Van Oekelen","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"e26029","DOI":"10.7759\/cureus.26029","article-title":"Osteoporotic vertebral fractures: an analysis of readability and quality of web-based information","volume":"14","author":"Hidayat","year":"2022","journal-title":"Cureus"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"e2432041","DOI":"10.1001\/jamanetworkopen.2024.32041","article-title":"Conservative treatments in the management of acute painful vertebral compression fractures: a systematic review and network meta-analysis","volume":"7","author":"Alimy","year":"2024","journal-title":"JAMA Netw Open"},{"key":"ref21","first-page":"39","article-title":"General pitfalls of model-agnostic interpretation methods for machine learning models","volume-title":"International workshop on extending explainable AI beyond deep models and classifiers","author":"Molnar","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1038\/s43856-024-00471-5","article-title":"A systematic pan-cancer study on deep learning-based prediction of multi-omic biomarkers from routine pathology images","volume":"4","author":"Arslan","year":"2024","journal-title":"Commun Med"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"876","DOI":"10.1038\/s42256-024-00868-w","article-title":"A transformer-based weakly supervised computational pathology method for clinical-grade diagnosis and molecular marker discovery of gliomas","volume":"6","author":"Jiang","year":"2024","journal-title":"Nat Mach Intell"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1038\/s41416-022-01986-1","article-title":"Role of AI and digital pathology for colorectal immuno-oncology","volume":"128","author":"Bilal","year":"2023","journal-title":"Br J Cancer"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1726453\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T06:54:35Z","timestamp":1771916075000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1726453\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,15]]},"references-count":24,"alternative-id":["10.3389\/fmed.2025.1726453"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2025.1726453","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,15]]},"article-number":"1726453"}}