{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T11:20:08Z","timestamp":1768216808537,"version":"3.49.0"},"reference-count":33,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T00:00:00Z","timestamp":1768176000000},"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. Artif. Intell."],"abstract":"<jats:p>Bone fractures are among the most prominent injuries in the modern world that affect all ages and races. Traditional treatment involves radiographic imaging that relies heavily on radiologists manually analyzing images. There have been efforts to develop computer-aided diagnosis tools that employ artificial intelligence and deep learning approaches. Existing literature focuses on developing tools that only detect and classify bone fractures, rather than addressing the broader issue of bone fracture management. However, evidence of scholarly works that include treatment recommendations is still lacking. Furthermore, deep learning-based object detectors that achieve state-of-the-art results are computationally expensive and considered as black-box solutions. Developing countries, such as Sub-Saharan Africa, face a shortage of radiologists and orthopedists. For this reason, this paper proposes a methodological approach that uses a more efficient object detection model to diagnose long bone fractures and provide prescription recommendations. An enhanced anchoring process, known as adaptive anchoring, is proposed to improve the performance of the Regional Proposal Network and the object detection model. A Faster R-CNN model with ResNet-50\/101 and ResNext-50\/101 backbones was used to develop an object detection model that uses X-ray images as input. To understand and interpret the model\u2019s decision, a Gradient-based Class Activation Mapping method was used to assess the model\u2019s learnability. The results indicate that the proposed adaptive anchoring approach can improve computational efficiency, reducing training time by up to 29% compared to the traditional approach. Model accuracy during training and validation ranged between 94% and 98%. Overall, adaptive anchoring performed better when applied with the ResNet-101 backbone, yielding an Average Precision of 92.73%, an F1 score of 96.01%, a precision of 96.80%, and a recall of 95.23%. The study provides valuable insights into the use of computationally efficient deep learning models for medical recommendation systems. Future studies should develop models to diagnose fractures using input images from various modalities and to provide prescription recommendations.<\/jats:p>","DOI":"10.3389\/frai.2025.1692894","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T08:17:09Z","timestamp":1768205829000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhanced multi-class object detector for bone fracture diagnosis with prescription recommendation"],"prefix":"10.3389","volume":"8","author":[{"given":"Daudi Mashauri","family":"Migayo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shubi","family":"Kaijage","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stephen","family":"Swetala","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Devotha G.","family":"Nyambo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,1,12]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"e0244291","DOI":"10.1371\/journal.pone.0244291","article-title":"Fracture incidence in adults in relation to age and gender: a study of 27,169 fractures in the Swedish fracture register in a well-defined catchment area","volume":"15","author":"Bergh","year":"2021","journal-title":"PLoS One"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1016\/j.cjtee.2024.03.001","article-title":"A systematic analysis on global epidemiology and burden of foot fracture over three decades","volume":"28","author":"Chen","year":"2024","journal-title":"Chin. J. Traumatol."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.36937\/janset.2021.004.001","article-title":"Ensemble based neural network for the classification of MURA dataset","volume":"4","author":"Ghosh","year":"2021","journal-title":"J. Nat."},{"key":"ref4","first-page":"134","article-title":"Eine neue Methode der Fixierung der Fragmente bei complicierten Frakturen","author":"Hansmann","year":"1886","journal-title":"Verh. Dtsch. Ges. Chir."},{"key":"ref5","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"2567","DOI":"10.1016\/j.jse.2023.07.015","article-title":"Intramedullary nailing vs. open reduction\u2013internal fixation for humeral shaft fractures: a meta-analysis of randomized controlled trials","volume":"32","author":"Hurley","year":"2023","journal-title":"J. Shoulder Elb. Surg."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"2168","DOI":"10.4102\/sajr.v25i1.2168","article-title":"Radiology subspecialisation in Africa: a review of the current status","volume":"25","author":"Iyawe","year":"2021","journal-title":"S. Afr. J. Radiol."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1007\/978-981-10-5699-4_2","article-title":"Bone fracture detection using edge detection technique","volume":"584","author":"Johari","year":"2018","journal-title":"Adv. Intell. Syst. Comput"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"127","DOI":"10.3390\/jimaging6110127","article-title":"Musculoskeletal images classification for detection of fractures using transfer learning","volume":"6","author":"Kandel","year":"2020","journal-title":"J. Imaging"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"2036","DOI":"10.1016\/j.jvir.2019.08.002","article-title":"Tanzania IR initiative: training the first generation of interventional radiologists","volume":"30","author":"Laage Gaupp","year":"2019","journal-title":"J. Vasc. Interv. Radiol."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"e41177","DOI":"10.2196\/41177","article-title":"Automated monitoring of adherence to evidenced-based clinical guideline recommendations: design and implementation study","volume":"25","author":"Lichtner","year":"2023","journal-title":"J. Med. Internet Res."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"11591","DOI":"10.1073\/pnas.1806905115","article-title":"Deep neural network improves fracture detection by clinicians","volume":"115","author":"Lindsey","year":"2018","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"100452","DOI":"10.1016\/j.imu.2020.100452","article-title":"Bone fracture detection through the two-stage system of crack-sensitive convolutional neural network","volume":"22","author":"Ma","year":"2021","journal-title":"Inf. Med. Unlocked"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/diagnostics12102420","article-title":"Bone fracture detection using deep supervised learning from radiological images: a paradigm shift","volume":"12","author":"Meena","year":"2022","journal-title":"Diagnostics"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3578938","article-title":"Efficient deep learning: a survey on making deep learning models smaller, faster, and better","volume":"55","author":"Menghani","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"ref16","first-page":"496","article-title":"Ideal dataset splitting ratios in machine learning algorithms: general concerns for data scientists and data analysts","author":"Muraina","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"371","DOI":"10.29322\/IJSRP.8.9.2018.p8150","article-title":"Analysis on detecting of leg bone fracture from X-ray images","volume":"8","author":"Myint","year":"2018","journal-title":"Int. J. Scient. Res Publicat."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"99304","DOI":"10.1109\/ACCESS.2023.3314332","article-title":"An intelligent disease prediction and drug recommendation prototype by using multiple approaches of machine learning algorithms","volume":"11","author":"Nayak","year":"2023","journal-title":"IEEE Access"},{"key":"ref19","first-page":"1","article-title":"Deep convolutional neural networks with transfer learning for bone fracture recognition using small exemplar image datasets","author":"Nikhil","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"e026","DOI":"10.1097\/OI9.0000000000000026","article-title":"A multicenter observational study on the distribution of orthopaedic fracture types across 17 low- and middle-income countries","volume":"2","author":"Pouramin","year":"2019","journal-title":"OTA Int. Open Access J. Orthop. Trauma"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"189436","DOI":"10.1109\/ACCESS.2020.3029039","article-title":"Ground truth annotated femoral X-ray image dataset and object detection based method for fracture types classification","volume":"8","author":"Qi","year":"2020","journal-title":"IEEE Access"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"e316","DOI":"10.1097\/OI9.0000000000000316","article-title":"Open tibial shaft fracture fixation strategies: intramedullary nailing, external fixation, and plating","volume":"7","author":"Shen","year":"2024","journal-title":"OTA Int."},{"key":"ref23","first-page":"587","article-title":"Performance analysis and comparison of faster R- CNN, mask R-CNN and ResNet50 for the detection and counting of vehicles","author":"Tahir","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"1507","DOI":"10.3390\/app10041507","article-title":"X-ray bone fracture classification using deep learning: a baseline for designing a reliable approach","volume":"10","author":"Tanzi","year":"2020","journal-title":"Appl. Sci."},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.21428\/bf6fb269.1f033948","volume-title":"The computational limits of deep learning","author":"Thompson","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"18773","DOI":"10.1007\/s00521-022-07412-0","article-title":"Attention mechanism-based deep learning method for hairline fracture detection in hand X-rays","volume":"34","author":"Wang","year":"2022","journal-title":"Neural Comput. and Applic."},{"key":"ref27","doi-asserted-by":"publisher","first-page":"116612","DOI":"10.1109\/ACCESS.2021.3106116","article-title":"Guideline-driven medical decision support methods for family healthcare","volume":"9","author":"Wang","year":"2021","journal-title":"IEEE Access"},{"key":"ref28","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1177\/0049475517717178","article-title":"Task-shifting of orthopaedic surgery to non-physician clinicians in Malawi: effective and safe?","volume":"47","author":"Wilhelm","year":"2017","journal-title":"Trop. Dr."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"1589","DOI":"10.1038\/s41598-021-81236-1","article-title":"The feature ambiguity mitigate operator model helps improve bone fracture detection on X-ray radiograph","volume":"11","author":"Wu","year":"2021","journal-title":"Sci. Rep."},{"key":"ref31","doi-asserted-by":"publisher","first-page":"4555","DOI":"10.1016\/j.aej.2021.03.005","article-title":"Detection and localization of hand fractures based on GA_Faster R-CNN","volume":"60","author":"Xue","year":"2021","journal-title":"Alex. Eng. J."},{"key":"ref32","first-page":"282","article-title":"Bone fracture detection and classification using deep learning approach","author":"Yadav","year":"2020"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"895","DOI":"10.3390\/diagnostics12040895","article-title":"Scaphoid fracture detection by using convolutional neural network","volume":"12","author":"Yang","year":"2022","journal-title":"Diagnostics"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1692894\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T08:17:11Z","timestamp":1768205831000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1692894\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,12]]},"references-count":33,"alternative-id":["10.3389\/frai.2025.1692894"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1692894","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,12]]},"article-number":"1692894"}}