Artificial Intelligence in Fracture Detection: A Systematic Review and Meta-Analysis.

Background Patients with fractures are a common emergency presentation and may be misdiagnosed at radiologic imaging. An increasing number of studies apply artificial intelligence (AI) techniques to fracture detection as an adjunct to clinician diagnosis. Purpose To perform a systematic review and meta-analysis comparing the diagnostic performance in fracture detection between AI and clinicians in peer-reviewed publications and the gray literature (ie, articles published on preprint repositories). Materials and Methods A search of multiple electronic databases between January 2018 and July 2020 (updated June 2021) was performed that included any primary research studies that developed and/or validated AI for the purposes of fracture detection at any imaging modality and excluded studies that evaluated image segmentation algorithms. Meta-analysis with a hierarchical model to calculate pooled sensitivity and specificity was used. Risk of bias was assessed by using a modified Prediction Model Study Risk of Bias Assessment Tool, or PROBAST, checklist. Results Included for analysis were 42 studies, with 115 contingency tables extracted from 32 studies (55 061 images). Thirty-seven studies identified fractures on radiographs and five studies identified fractures on CT images. For internal validation test sets, the pooled sensitivity was 92% (95% CI: 88, 93) for AI and 91% (95% CI: 85, 95) for clinicians, and the pooled specificity was 91% (95% CI: 88, 93) for AI and 92% (95% CI: 89, 92) for clinicians. For external validation test sets, the pooled sensitivity was 91% (95% CI: 84, 95) for AI and 94% (95% CI: 90, 96) for clinicians, and the pooled specificity was 91% (95% CI: 81, 95) for AI and 94% (95% CI: 91, 95) for clinicians. There were no statistically significant differences between clinician and AI performance. There were 22 of 42 (52%) studies that were judged to have high risk of bias. Meta-regression identified multiple sources of heterogeneity in the data, including risk of bias and fracture type. Conclusion Artificial intelligence (AI) and clinicians had comparable reported diagnostic performance in fracture detection, suggesting that AI technology holds promise as a diagnostic adjunct in future clinical practice. Clinical trial registration no. CRD42020186641 © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Cohen and McInnes in this issue.

Redefining the stress cortisol response to surgery.

BACKGROUND: Cortisol levels rise with the physiological stress of surgery. Previous studies have used older, less-specific assays, have not differentiated by severity or only studied procedures of a defined type. The aim of this study was to examine this phenomenon in surgeries of varying severity using a widely used cortisol immunoassay. METHODS: Euadrenal patients undergoing elective surgery were enrolled prospectively. Serum samples were taken at 8 am on surgical day, induction and 1 hour, 2 hour, 4 hour and 8 hour after. Subsequent samples were taken daily at 8 am until postoperative day 5 or hospital discharge. Total cortisol was measured using an Abbott Architect immunoassay, and cortisol-binding globulin (CBG) using a radioimmunoassay. Surgical severity was classified by POSSUM operative severity score. RESULTS: Ninety-three patients underwent surgery: Major/Major+ (n = 37), Moderate (n = 33) and Minor (n = 23). Peak cortisol positively correlated to severity: Major/Major+ median 680 [range 375-1452], Moderate 581 [270-1009] and Minor 574 [272-1066] nmol/L (Kruskal-Wallis test, P = .0031). CBG fell by 23%; the magnitude of the drop positively correlated to severity. CONCLUSIONS: The range in baseline and peak cortisol response to surgery is wide, and peak cortisol levels are lower than previously appreciated. Improvements in surgery, anaesthetic techniques and cortisol assays might explain our observed lower peak cortisols. The criteria for the dynamic testing of cortisol response may need to be reduced to take account of these factors. Our data also support a lower-dose, stratified approach to dosing of steroid replacement in hypoadrenal patients, to minimize the deleterious effects of over-replacement.

Stakeholder perspectives towards diagnostic artificial intelligence: a co-produced qualitative evidence synthesis.

Background: Diagnosis is a cornerstone of medical practice. Worldwide, there is increased demand for diagnostic services, exacerbating workforce shortages. Artificial intelligence (AI) technologies may improve diagnostic efficiency, accuracy, and access. Understanding stakeholder perspectives is key to informing implementation of complex interventions. We systematically reviewed the literature on stakeholder perspectives on diagnostic AI, including all English-language peer-reviewed primary qualitative or mixed-methods research. Methods: We searched PubMed, Ovid MEDLINE/Embase, Scopus, CINAHL and Web of Science (22/2/2023 and updated 8/2/2024). The Critical Appraisal Skills Programme Checklist informed critical appraisal. We used a 'best-fit' framework approach for analysis, using the Non-adoption, Abandonment, Scale-up, Spread, Sustainability (NASSS) framework. This study was pre-registered (PROSPERO CRD42022313782). Findings: We screened 16,577 articles and included 44. 689 participants were interviewed, and 402 participated in focus groups. Four stakeholder groups were described: patients, clinicians, researchers and healthcare leaders. We found an under-representation of patients, researchers and leaders across articles. We summarise the differences and relationships between each group in a conceptual model, hinging on the establishment of trust, engagement and collaboration. We present a modification of the NASSS framework, tailored to diagnostic AI. Interpretation: We provide guidance for future research and implementation of diagnostic AI, highlighting the importance of representing all stakeholder groups. We suggest that implementation strategies consider how any proposed software fits within the extended NASSS-AI framework, and how stakeholder priorities and concerns have been addressed. Funding: RK is supported by an NIHR Doctoral Research Fellowship grant (NIHR302562), which funded patient and public involvement activities, and access to Covidence.

Rare and unusual case of familial focal dermal hypoplasia (Goltz syndrome) presenting to otolaryngology in the UK.

Goltz syndrome or focal dermal hypoplasia (FDH), is an X-linked dominant condition which predominantly involves the skin, limbs and eyes. In otolaryngology, FDH has been poorly described, but can result in increased symptoms of obstructive sleep apnoea requiring surgery. There have also been documented cases of mixed severe hearing loss secondary to congenital ossicular anomalies. More frequently, patients present to the ear-nose-throat clinic with symptoms of dysphagia, secondary to papillomatosis. A 36-year-old woman presented with pain, irritation and dysphagia with a known diagnosis of FDH. She was subsequently investigated with an oesophago-gastro-duodenoscopy, Barium Swallow and an MRI neck scan with contrast. Lymphoid hyperplasia was found on investigation and the patient underwent a panendoscopy with CO2 laser to the lesion with good clinical outcome. This case report highlights the need for multidisciplinary team involvement to ensure full consideration of management options.