Enhanced fracture detection on radiographs with AI assistance for clinicians: a systematic review and meta-analysis.

Han Qin; Yunxia Ding; Jiangyi Ju; Zhen Qu; Lihua Peng

doi:10.1080/07853890.2025.2610079

Home/Archive/PubMed

PubMed · 41467767

Enhanced fracture detection on radiographs with AI assistance for clinicians: a systematic review and meta-analysis.

Han Qin·Yunxia Ding·Jiangyi Ju·Zhen Qu·Lihua Peng

View original source ↗Export metadata ↓

Abstract

BACKGROUND: Emergency radiographic interpretation for fractures is prone to missed or misdiagnoses. Artificial intelligence (AI) is expected to become a powerful tool to assist clinicians in fracture detection. PURPOSE: A systematic review and meta-analysis was performed to assess whether AI improves clinicians' ability to detect fractures on radiographs. MATERIALS AND METHODS: A literature search was conducted in PubMed, Web of Science, and Cochrane Library for studies published between January 1, 2010, and October 10, 2025. A meta-analysis of diagnostic accuracy studies was performed using a Summary Receiver Operating Characteristic (SROC) curve. The quality of included studies was assessed using the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) tool. Subgroup analysis and meta-regression were conducted to explore potential sources of heterogeneity. RESULTS: A total of 26 studies were included . The pooled sensitivity of clinicians increased from 77% (95% CI: 72-81) to 87% (95% CI: 83-90) with AI assistance, while the pooled specificity improved from 88% (95% CI: 85-90) to 92% (95% CI: 89-94). The corresponding AUC values were 0.90 (95% CI: 0.87-0.92) before and 0.95 (95% CI: 0.93-0.97) after AI assistance. Eight studies were rated as high risk of bias. Subgroup analysis and meta-regression identified potential sources of heterogeneity, including fracture location, AI model type, high risk of bias, and reference standards. CONCLUSION: AI assistance significantly improves clinicians' diagnostic performance in detecting fractures on radiographs for extremity and trunk fractures.

Explore related subjects

Humans Fractures, Bone Artificial Intelligence Sensitivity and Specificity Radiography ROC Curve Radiographic interpretation assisted image interpretation clinical decision support deep learning machine learning models medical image analysis orthopedic imaging Journal Article Systematic Review Meta-Analysis Research Support, Non-U.S. Gov't

Keep this discovery

BibTeX RIS

Han Qin, Yunxia Ding, Jiangyi Ju, Zhen Qu, Lihua Peng. 2025-12-30. Enhanced fracture detection on radiographs with AI assistance for clinicians: a systematic review and meta-analysis.. https://doi.org/10.1080/07853890.2025.2610079

Cite the original work for its findings. Save a collection to share your selection of sources.

Discover connections

Artificial Intelligence subject Deep Learning subject Fractures, Bone subject Humans subject Journal Article subject Journal Article; Systematic Review; Meta-Analysis; Research Support, Non-U.S. Gov't resource Meta-Analysis subject Systematic reviews study

Connections use source metadata and explicit phrase matches, not verified experimental comparisons.

KEEP EXPLORING

Related citations

PubMed2026

Effect of photobiomodulation on pain relief and functional improvement in fractures: a systematic review and meta-analysis.

INTRODUCTION: Fractures, the most common type of trauma, can cause considerable distress to patients. Pain can not only affect the comfort of fracture patients but also delay their participation in rehabilitation training. Photobiomodulation (PBM) has been associated with pain reduction and the promotion of tissue healing. This systematic review and meta-analysis aimed to evaluate the efficacy of PBM in reducing pain and promoting rehabilitation in patients with fractures. METHODS: This study was registered on PROSPERO (CRD42024591373). We systematically searched PubMed, EMBASE, the Cochrane Library and Web of Science for RCTs that investigated PBM in fractures as of August 2025. The primary outcome was the pain score. The secondary outcomes included functional and healing. RESULT: Finally, 12 and 9 studies were ultimately included in the systematic review and meta-analysis, respectively. The pooled analysis showed that the one-week pain score was lower in the PBM group than in the placebo group (MD -0.74, 95% CI -1.00, -0.47, p < 0.0001, I2 = 0%). Subgroup analysis showed that the difference between the two groups was statistically significant regardless of fracture site or acupoint irradiation. Changes in pain scores were statistically significant in both groups at different wavelength combinations. The improvement in grip strength at 4 weeks was significantly greater in PBM than in placebo (MD 5.03, 95% CI 4.29, 5.78; p < 0.0001; I2 = 0%). There were no significant differences in pain and functional scores at 4-26 weeks. Bone healing did not show differences between the two groups. No side effects reported. CONCLUSION: PBM appears to relieve short-term pain in fractures and improve grip strength in patients with upper limb fractures, but does not show significant long-term benefits. Evidence for mandibular functional recovery and bone healing remains inconsistent. Future studies should determine therapeutic parameters and their impact on bone healing and long-term functional outcomes across fracture types.

Humans↗

PubMed2026

Atopic dermatitis and the risk of osteoporosis and fractures: a meta-analysis of cohort studies.

BACKGROUND: This meta-analysis aims to evaluate the risk of osteoporosis and fractures in patients with atopic dermatitis (AD) by synthesizing data from cohort studies. We also provide a comprehensive analysis of fracture risks across different severities of AD and anatomical sites. METHODS: Following the PRISMA 2020 guidelines, a systematic search was conducted in PubMed, Embase, and the Cochrane Library up to May 30, 2025. Studies that investigated the relationship between AD and osteoporosis or fractures were included in the analysis. Data extraction and screening were performed independently by two reviewers. Study quality was assessed using the Newcastle-Ottawa Scale (NOS). A random-effects meta-analysis was applied, alongside sensitivity and subgroup analyses. Publication bias was evaluated using funnel plots and Egger's test. RESULTS: Ten cohort studies, involving 368 to over 2 million AD patients, were included. NOS scores ranged from 7 to 8, indicating generally high study quality. The pooled analysis revealed a 56% increased risk of osteoporosis (OR = 1.56, 95% CI: 1.14-2.13; I2 = 99.9%, p < 0.0001) and an 8% increased risk of all-cause fractures (OR = 1.08, 95% CI: 1.05-1.10; I2 = 82.1%, p < 0.0001) in AD patients. Subgroup analyses demonstrated a progressive increase in fracture risk with the severity of AD. Specific risks were significantly higher for vertebral fractures (OR = 1.14, 95% CI: 1.08-1.20; I2 = 67.3%, p = 0.009) and lower limb fractures (OR = 1.11, 95% CI: 1.08-1.13; I2 = 65.0%, p = 0.014). Sensitivity analyses confirmed the robustness of these findings, and no significant publication bias was detected (p = 0.316). CONCLUSION: AD is associated with an increased risk of osteoporosis and fractures, particularly among patients with severe AD and those experiencing vertebral or lower limb fractures. These findings highlight the importance of targeted bone health monitoring in the clinical management of AD patients.Registration: (PROSPERO: CRD420251066550).

Humans↗

PubMed2026

Artificial intelligence for dental caries detection: An umbrella review.

Artificial intelligence (AI) has been proposed as a tool to improve dental caries detection across imaging modalities; however, its clinical value remains uncertain. This umbrella review aimed to synthesize and critically appraise systematic reviews evaluating AI for caries detection and diagnosis. An umbrella review was conducted following PRIOR guidance (PROSPERO CRD420261340728). Searches were performed in MEDLINE, Embase, Scopus, Web of Science, and Google Scholar up to 15 March 2026. Methodological quality was assessed using AMSTAR 2, and overlap of primary studies was quantified using the corrected covered area (CCA). Seventeen systematic reviews were included, of which five reported diagnostic test accuracy meta-analyses using bivariate or HSROC models. Across these meta-analyses, pooled sensitivity ranged from 0.76 to 0.94 and specificity from 0.85 to 0.91. Most systems were based on deep learning models applied to bitewing radiographs and intraoral photographs. However, substantial heterogeneity was observed in imaging modalities, lesion thresholds, analytical tasks, and evaluation metrics. In addition, a high degree of overlap across reviews and recurrent methodological limitations, including reliance on retrospective datasets, limited external validation, and inconsistent reporting, substantially weaken the reliability of the evidence. Although AI models demonstrate high diagnostic performance under experimental conditions, current evidence does not support their use as stand-alone diagnostic tools. Their clinical applicability remains limited, and implementation should be restricted to decision-support contexts until robust prospective validation demonstrates meaningful impact on clinical decision-making and patient outcomes.

Dental Caries↗