Dataset Information

Artificial intelligence improves the accuracy of residents in the diagnosis of hip fractures: a multicenter study.

ABSTRACT:

Background

Less experienced clinicians sometimes make misdiagnosis of hip fractures. We developed computer-aided diagnosis (CAD) system for hip fractures on plain X-rays using a deep learning model trained on a large dataset. In this study, we examined whether the accuracy of the diagnosis of hip fracture of the residents could be improved by using this system.

Methods

A deep convolutional neural network approach was used for machine learning. Pytorch 1.3 and Fast.ai 1.0 were applied as frameworks, and an EfficientNet-B4 model (a pre-trained ImageNet model) was used. We handled the 5295 X-rays from the patients with femoral neck fracture or femoral trochanteric fracture from 2009 to 2019. We excluded cases in which the bilateral hips were not included within an image range, and cases of femoral shaft fracture and periprosthetic fracture. Finally, we included 5242 AP pelvic X-rays from 4851 cases. We divided these 5242 images into two images per image, and prepared 5242 images including fracture site and 5242 images without fracture site. Thus, a total of 10,484 images were used for machine learning. The accuracy, sensitivity, specificity, F-value, and area under the curve (AUC) were assessed. Gradient-weighted class activation mapping (Grad-CAM) was used to conceptualize the basis for the diagnosis of the fracture by the deep learning algorithm. Secondly, we conducted a controlled experiment with clinicians. Thirty-one residents;young doctors within 2 years of graduation from medical school who rotate through various specialties, were tested using 300 hip fracture images that were randomly extracted from the dataset. We evaluated the diagnostic accuracy with and without the use of the CAD system for each of the 300 images.

Results

The accuracy, sensitivity, specificity, F-value, and AUC were 96.1, 95.2, 96.9%, 0.961, and 0.99, respectively, with the correct diagnostic basis generated by Grad-CAM. In the controlled experiment, the diagnostic accuracy of the residents significantly improved when they used the CAD system.

Conclusions

We developed a newly CAD system with a deep learning algorithm from a relatively large dataset from multiple institutions. Our system achieved high diagnostic performance. Our system improved the diagnostic accuracy of residents for hip fractures.

Level of evidence

Level III, Foundational evidence, before-after study.

Clinical relevance

high.

SUBMITTER: Sato Y

PROVIDER: S-EPMC8091525 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Background Although artificial intelligence (AI) shows promise across many aspects of radiology, the use of AI to create differential diagnoses for rare and common diseases at brain MRI has not been demonstrated. Purpose To evaluate an AI system for generation of differential diagnoses at brain MRI compared with radiologists. Materials and Methods This retrospective study tested performance of an AI system for probabilistic diagnosis in patients with 19 common and rare diagnoses at brain MRI acquired between January 2008 and January 2018. The AI system combines data-driven and domain-expertise methodologies, including deep learning and Bayesian networks. First, lesions were detected by using deep learning. Then, 18 quantitative imaging features were extracted by using atlas-based coregistration and segmentation. Third, these image features were combined with five clinical features by using Bayesian inference to develop probability-ranked differential diagnoses. Quantitative feature extraction algorithms and conditional probabilities were fine-tuned on a training set of 86 patients (mean age, 49 years ± 16 [standard deviation]; 53 women). Accuracy was compared with radiology residents, general radiologists, neuroradiology fellows, and academic neuroradiologists by using accuracy of top one, top two, and top three differential diagnoses in 92 independent test set patients (mean age, 47 years ± 18; 52 women). Results For accuracy of top three differential diagnoses, the AI system (91% correct) performed similarly to academic neuroradiologists (86% correct; P = .20), and better than radiology residents (56%; P < .001), general radiologists (57%; P < .001), and neuroradiology fellows (77%; P = .003). The performance of the AI system was not affected by disease prevalence (93% accuracy for common vs 85% for rare diseases; P = .26). Radiologists were more accurate at diagnosing common versus rare diagnoses (78% vs 47% across all radiologists; P < .001). Conclusion An artificial intelligence system for brain MRI approached overall top one, top two, and top three differential diagnoses accuracy of neuroradiologists and exceeded that of less-specialized radiologists. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Zaharchuk in this issue.

Project description:BackgroundArtificial intelligence (AI) for gastric cancer diagnosis has been discussed in recent years. The role of AI in early gastric cancer is more important than in advanced gastric cancer since early gastric cancer is not easily identified in clinical practice. However, to our knowledge, past syntheses appear to have limited focus on the populations with early gastric cancer.ObjectiveThe purpose of this study is to evaluate the diagnostic accuracy of AI in the diagnosis of early gastric cancer from endoscopic images.MethodsWe conducted a systematic review from database inception to June 2020 of all studies assessing the performance of AI in the endoscopic diagnosis of early gastric cancer. Studies not concerning early gastric cancer were excluded. The outcome of interest was the diagnostic accuracy (comprising sensitivity, specificity, and accuracy) of AI systems. Study quality was assessed on the basis of the revised Quality Assessment of Diagnostic Accuracy Studies. Meta-analysis was primarily based on a bivariate mixed-effects model. A summary receiver operating curve and a hierarchical summary receiver operating curve were constructed, and the area under the curve was computed.ResultsWe analyzed 12 retrospective case control studies (n=11,685) in which AI identified early gastric cancer from endoscopic images. The pooled sensitivity and specificity of AI for early gastric cancer diagnosis were 0.86 (95% CI 0.75-0.92) and 0.90 (95% CI 0.84-0.93), respectively. The area under the curve was 0.94. Sensitivity analysis of studies using support vector machines and narrow-band imaging demonstrated more consistent results.ConclusionsFor early gastric cancer, to our knowledge, this was the first synthesis study on the use of endoscopic images in AI in diagnosis. AI may support the diagnosis of early gastric cancer. However, the collocation of imaging techniques and optimal algorithms remain unclear. Competing models of AI for the diagnosis of early gastric cancer are worthy of future investigation.Trial registrationPROSPERO CRD42020193223; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=193223.

Project description:ImportanceMost early lung cancers present as pulmonary nodules on imaging, but these can be easily missed on chest radiographs.ObjectiveTo assess if a novel artificial intelligence (AI) algorithm can help detect pulmonary nodules on radiographs at different levels of detection difficulty.Design, setting, and participantsThis diagnostic study included 100 posteroanterior chest radiograph images taken between 2000 and 2010 of adult patients from an ambulatory health care center in Germany and a lung image database in the US. Included images were selected to represent nodules with different levels of detection difficulties (from easy to difficult), and comprised both normal and nonnormal control.ExposuresAll images were processed with a novel AI algorithm, the AI Rad Companion Chest X-ray. Two thoracic radiologists established the ground truth and 9 test radiologists from Germany and the US independently reviewed all images in 2 sessions (unaided and AI-aided mode) with at least a 1-month washout period.Main outcomes and measuresEach test radiologist recorded the presence of 5 findings (pulmonary nodules, atelectasis, consolidation, pneumothorax, and pleural effusion) and their level of confidence for detecting the individual finding on a scale of 1 to 10 (1 representing lowest confidence; 10, highest confidence). The analyzed metrics for nodules included sensitivity, specificity, accuracy, and receiver operating characteristics curve area under the curve (AUC).ResultsImages from 100 patients were included, with a mean (SD) age of 55 (20) years and including 64 men and 36 women. Mean detection accuracy across the 9 radiologists improved by 6.4% (95% CI, 2.3% to 10.6%) with AI-aided interpretation compared with unaided interpretation. Partial AUCs within the effective interval range of 0 to 0.2 false positive rate improved by 5.6% (95% CI, -1.4% to 12.0%) with AI-aided interpretation. Junior radiologists saw greater improvement in sensitivity for nodule detection with AI-aided interpretation as compared with their senior counterparts (12%; 95% CI, 4% to 19% vs 9%; 95% CI, 1% to 17%) while senior radiologists experienced similar improvement in specificity (4%; 95% CI, -2% to 9%) as compared with junior radiologists (4%; 95% CI, -3% to 5%).Conclusions and relevanceIn this diagnostic study, an AI algorithm was associated with improved detection of pulmonary nodules on chest radiographs compared with unaided interpretation for different levels of detection difficulty and for readers with different experience.

Project description:BackgroundArtificial intelligence (AI) is transforming various fields, with health care, especially diagnostic specialties such as radiology, being a key but controversial battleground. However, there is limited research systematically examining the response of "human intelligence" to AI.ObjectiveThis study aims to comprehend radiologists' perceptions regarding AI, including their views on its potential to replace them, its usefulness, and their willingness to accept it. We examine the influence of various factors, encompassing demographic characteristics, working status, psychosocial aspects, personal experience, and contextual factors.MethodsBetween December 1, 2020, and April 30, 2021, a cross-sectional survey was completed by 3666 radiology residents in China. We used multivariable logistic regression models to examine factors and associations, reporting odds ratios (ORs) and 95% CIs.ResultsIn summary, radiology residents generally hold a positive attitude toward AI, with 29.90% (1096/3666) agreeing that AI may reduce the demand for radiologists, 72.80% (2669/3666) believing AI improves disease diagnosis, and 78.18% (2866/3666) feeling that radiologists should embrace AI. Several associated factors, including age, gender, education, region, eye strain, working hours, time spent on medical images, resilience, burnout, AI experience, and perceptions of residency support and stress, significantly influence AI attitudes. For instance, burnout symptoms were associated with greater concerns about AI replacement (OR 1.89; P<.001), less favorable views on AI usefulness (OR 0.77; P=.005), and reduced willingness to use AI (OR 0.71; P<.001). Moreover, after adjusting for all other factors, perceived AI replacement (OR 0.81; P<.001) and AI usefulness (OR 5.97; P<.001) were shown to significantly impact the intention to use AI.ConclusionsThis study profiles radiology residents who are accepting of AI. Our comprehensive findings provide insights for a multidimensional approach to help physicians adapt to AI. Targeted policies, such as digital health care initiatives and medical education, can be developed accordingly.

Project description:BackgroundThe introduction of multiparameter MRI and novel biomarkers has greatly improved the prediction of clinically significant prostate cancer (csPCa). However, decision-making regarding prostate biopsy and prebiopsy examinations is still difficult. We aimed to establish a quick and economic tool to improve the detection of csPCa based on routinely performed clinical examinations through an automated machine learning platform (AutoML).MethodsThis study included a multicenter retrospective cohort and two prospective cohorts with 4747 cases from 9 hospitals across China. The multimodal data, including demographics, clinical characteristics, laboratory tests, and ultrasound reports, of consecutive participants were retrieved using extract-transform-load tools. AutoML was applied to explore potential data processing patterns and the most suitable algorithm to build the Prostate Cancer Artificial Intelligence Diagnostic System (PCAIDS). The diagnostic performance was determined by the receiver operating characteristic curve (ROC) for discriminating csPCa from insignificant prostate cancer (PCa) and benign disease. The clinical utility was evaluated by decision curve analysis (DCA) and waterfall plots.ResultsThe random forest algorithm was applied in the feature selection, and the AutoML algorithm was applied for model establishment. The area under the curve (AUC) value in identifying csPCa was 0.853 in the training cohort, 0.820 in the validation cohort, 0.807 in the Changhai prospective cohort, and 0.850 in the Zhongda prospective cohort. DCA showed that the PCAIDS was superior to PSA or fPSA/tPSA for diagnosing csPCa with a higher net benefit for all threshold probabilities in all cohorts. Setting a fixed sensitivity of 95%, a total of 32.2%, 17.6%, and 26.3% of unnecessary biopsies could be avoided with less than 5% of csPCa missed in the validation cohort, Changhai and Zhongda prospective cohorts, respectively.ConclusionsThe PCAIDS was an effective tool to inform decision-making regarding the need for prostate biopsy and prebiopsy examinations such as mpMRI. Further prospective and international studies are warranted to validate the findings of this study.Trial registrationChinese Clinical Trial Registry ChiCTR2100048428. Registered on 06 July 2021.

Project description:ObjectiveThis study assesses the concordance in migraine diagnosis between an online, self-administered, Computer-based, Diagnostic Engine (CDE) and semi-structured interview (SSI) by a headache specialist, both using International Classification of Headache Disorders, 3rd edition (ICHD-3) criteria.BackgroundDelay in accurate diagnosis is a major barrier to headache care. Accurate computer-based algorithms may help reduce the need for SSI-based encounters to arrive at correct ICHD-3 diagnosis.MethodsBetween March 2018 and August 2019, adult participants were recruited from three academic headache centers and the community via advertising to our cross-sectional study. Participants completed two evaluations: phone interview conducted by headache specialists using the SSI and a web-based expert questionnaire and analytics, CDE. Participants were randomly assigned to either the SSI followed by the web-based questionnaire or the web-based questionnaire followed by the SSI. Participants completed protocols a few minutes apart. The concordance in migraine/probable migraine (M/PM) diagnosis between SSI and CDE was measured using Cohen's kappa statistics. The diagnostic accuracy of CDE was assessed using the SSI as reference standard.ResultsOf the 276 participants consented, 212 completed both SSI and CDE (study completion rate = 77%; median age = 32 years [interquartile range: 28-40], female:male ratio = 3:1). Concordance in M/PM diagnosis between SSI and CDE was: κ = 0.83 (95% confidence interval [CI]: 0.75-0.91). CDE diagnostic accuracy: sensitivity = 90.1% (118/131), 95% CI: 83.6%-94.6%; specificity = 95.8% (68/71), 95% CI: 88.1%-99.1%. Positive and negative predictive values = 97.0% (95% CI: 91.3%-99.0%) and 86.6% (95% CI: 79.3%-91.5%), respectively, using identified migraine prevalence of 60%. Assuming a general migraine population prevalence of 10%, positive and negative predictive values were 70.3% (95% CI: 43.9%-87.8%) and 98.9% (95% CI: 98.1%-99.3%), respectively.ConclusionThe SSI and CDE have excellent concordance in diagnosing M/PM. Positive CDE helps rule in M/PM, through high specificity and positive likelihood ratio. A negative CDE helps rule out M/PM through high sensitivity and low negative likelihood ratio. CDE that mimics SSI logic is a valid tool for migraine diagnosis.