ObjectivesChest radiographs (CXRs) are commonly performed in emergency units (EUs), but the interpretation requires radiology experience. We developed an artificial intelligence (AI) system (precommercial) that aims to mimic board-certified radiologists' (BCRs') performance and can therefore support non–radiology residents (NRRs) in clinical settings lacking 24/7 radiology coverage. We validated by quantifying the clinical value of our AI system for radiology residents (RRs) and EU-experienced NRRs in a clinically representative EU setting.Materials and MethodsA total of 563 EU CXRs were retrospectively assessed by 3 BCRs, 3 RRs, and 3 EU-experienced NRRs. Suspected pathologies (pleural effusion, pneumothorax, consolidations suspicious for pneumonia, lung lesions) were reported on a 5-step confidence scale (sum of 20,268 reported pathology suspicions [563 images × 9 readers × 4 pathologies]) separately by every involved reader. Board-certified radiologists' confidence scores were converted into 4 binary reference standards (RFSs) of different sensitivities. The RRs' and NRRs' performances were statistically compared with our AI system (trained on nonpublic data from different clinical sites) based on receiver operating characteristics (ROCs) and operating point metrics approximated to the maximum sum of sensitivity and specificity (Youden statistics).ResultsThe NRRs lose diagnostic accuracy to RRs with increasingly sensitive BCRs' RFSs for all considered pathologies. Based on our external validation data set, the AI system/NRRs' consensus mimicked the most sensitive BCRs' RFSs with areas under ROC of 0.940/0.837 (pneumothorax), 0.953/0.823 (pleural effusion), and 0.883/0.747 (lung lesions), which were comparable to experienced RRs and significantly overcomes EU-experienced NRRs' diagnostic performance. For consolidation detection, the AI system performed on the NRRs' consensus level (and overcomes each individual NRR) with an area under ROC of 0.847 referenced to the BCRs' most sensitive RFS.ConclusionsOur AI system matched RRs' performance, meanwhile significantly outperformed NRRs' diagnostic accuracy for most of considered CXR pathologies (pneumothorax, pleural effusion, and lung lesions) and therefore might serve as clinical decision support for NRRs.
Purpose Autologous chondrocyte implantation is an established method for the treatment of joint cartilage damage. However, to date it has not been established that autologous chondrocyte implantation is an appropriate procedure for cartilage defects therapy in athletic persons. The aim of this study is to analyze if third-generation autologous chondrocyte implantation is an appropriate treatment for athletic persons with full cartilage defect of the knee joints. Methods A total of 84 patients were treated with third-generation autologous chondrocyte implantation (NOVOCART ® 3D). The mean follow-up time was 8 years (5-14). Sports activity was measured via UCLA Activity Score and Tegner Activity Scale before the onset of knee pain and postoperatively in an annual clinical evaluation. 41 athletic persons and 43 non-athletic persons (UCLA-Cutoff: 7; Tegner Activity Scale-Cutoff: 4) were analyzed. Patient reported outcomes were captured using IKDC subjective, KOOS, Lysholm score and VAS score on movement. Results Patient reported outcomes (IKDC, VAS at rest, VAS on movement) showed significant improvement (p < 0.001) postoperatively. Athletic persons demonstrated significantly better results than non-athletic persons in the analyzed outcome scores (IKDC: p < 0.01, KOOS: p < 0.01, Lysholm score: p < 0.01). 96.4% of the patients were able to return to sport and over 50% returned or surpassed their preinjury sports level. The remaining patients were downgraded by a median of two points on the UCLA-and 2.5 on the Tegner Activity Scale. A shift from high-impact sports to active events and moderate or mild activities was found. Furthermore, it was shown that preoperative UCLA score and Tegner Activity Scale correlated significantly with the patient reported outcome postoperatively. Conclusion Autologous chondrocyte implantation is a suitable treatment option for athletic persons with full-thickness cartilage defects in the knee. The return to sports activity is possible, but includes a shift from high-impact sports to less strenuous activities.
Artificial intelligence (AI) algorithms evaluating [supine] chest radiographs ([S]CXRs) have remarkably increased in number recently. Since training and validation are often performed on subsets of the same overall dataset, external validation is mandatory to reproduce results and reveal potential training errors. We applied a multicohort benchmarking to the publicly accessible (S)CXR analyzing AI algorithm CheXNet, comprising three clinically relevant study cohorts which differ in patient positioning ([S]CXRs), the applied reference standards (CT-/[S]CXR-based) and the possibility to also compare algorithm classification with different medical experts’ reading performance. The study cohorts include [1] a cohort, characterized by 563 CXRs acquired in the emergency unit that were evaluated by 9 readers (radiologists and non-radiologists) in terms of 4 common pathologies, [2] a collection of 6,248 SCXRs annotated by radiologists in terms of pneumothorax presence, its size and presence of inserted thoracic tube material which allowed for subgroup and confounding bias analysis and [3] a cohort consisting of 166 patients with SCXRs that were evaluated by radiologists for underlying causes of basal lung opacities, all of those cases having been correlated to a timely acquired computed tomography scan (SCXR and CT within < 90 min). CheXNet non-significantly exceeded the radiology resident (RR) consensus in the detection of suspicious lung nodules (cohort [1], AUC AI/RR: 0.851/0.839, p = 0.793) and the radiological readers in the detection of basal pneumonia (cohort [3], AUC AI/reader consensus: 0.825/0.782, p = 0.390) and basal pleural effusion (cohort [3], AUC AI/reader consensus: 0.762/0.710, p = 0.336) in SCXR, partly with AUC values higher than originally published (“Nodule”: 0.780, “Infiltration”: 0.735, “Effusion”: 0.864). The classifier “Infiltration” turned out to be very dependent on patient positioning (best in CXR, worst in SCXR). The pneumothorax SCXR cohort [2] revealed poor algorithm performance in CXRs without inserted thoracic material and in the detection of small pneumothoraces, which can be explained by a known systematic confounding error in the algorithm training process. The benefit of clinically relevant external validation is demonstrated by the differences in algorithm performance as compared to the original publication. Our multi-cohort benchmarking finally enables the consideration of confounders, different reference standards and patient positioning as well as the AI performance comparison with differentially qualified medical readers.
Breast cancer is one of the most common malignancies which appear during pregnancy. Since women are increasingly not giving birth until they are at a more advanced age, it can be assumed that the incidence of pregnancy-related breast cancers will continue to increase in the future. Because of pregnancy-induced changes and conservative diagnosis, these carcinomas are frequently not detected until they are at an advanced stage and thus generally require systemic adjuvant therapy. The available data on optimal chemotherapeutic management are limited. Particularly for the use of the target agent trastuzumab which could crucially contribute to improving the prognosis in the therapy of HER2-overexpressing breast cancer in non-pregnant women, there is a lack of definitive information regarding the profile of action and safety in pregnancy as well as with regard to any long-term effects on the child. Thirty-eight pregnancies on trastuzumab for the treatment of breast cancer were able to be analysed in the literature currently available. Information can be gained from this and conclusions can be drawn which can individualise and decisively improve therapeutic options in the future for the pregnant breast cancer patient.
Objective Correct identification of adhesive capsulitis of the shoulder (ACS) has an important impact on adequate therapy. The aim of our study was to investigate the influence of intravenous contrast administration and of reader’s experience on sensitivity and specificity of MRI in diagnosing ACS. Materials and methods A total of 180 patients were included in a retrospective study: 60 subjects with at least 4 of 5 clinical signs of adhesive capsulitis of the shoulder and 120 patients with other shoulder diseases who underwent contrast-enhanced MRI. In a first session, only non-enhanced images and in a second session also contrast-enhanced (CE) series were independently evaluated by three radiologists with various levels of professional experience. Readers were blinded to all clinical information and had to rate the shoulder MRIs for absence or presence of adhesive capsulitis. Data analysis included McNemar’s test, t test, and U test (p < .05). Results Using non-enhanced MRI, readers achieved a mean sensitivity of 63.9% and a mean specificity of 86.4%. By additional use of CE sequences, the mean sensitivity (85.5%) and the sensitivity for each reader increased significantly (p = .046, p < .01, p < .001, p = .045) while the improvement in mean specificity was not significant. Reader’s experience had a positive effect on sensitivity and specificity, which was in part but not consistently significant. Conclusion The addition of CE sequences can significantly increase the sensitivity of MRI in the diagnosis of ACS. Reader’s experience has shown to be another important factor for the diagnostic outcome.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.