Underdiagnosis bias of artificial intelligence algorithms applied to chest radiographs in under-served patient populations.
Ontology highlight
ABSTRACT:
SUBMITTER: Seyyed-Kalantari L
PROVIDER: S-EPMC8674135 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:PurposeTo assess experience with and perceptions of clinical application of artificial intelligence (AI) to chest radiographs among doctors in a single hospital.Materials and methodsA hospital-wide online survey of the use of commercially available AI-based lesion detection software for chest radiographs was conducted with all clinicians and radiologists at our hospital in this prospective study. In our hospital, version 2 of the abovementioned software was utilized from March 2020 to February 2021 and could detect three types of lesions. Version 3 was utilized for chest radiographs by detecting nine types of lesions from March 2021. The participants of this survey answered questions on their own experience using AI-based software in daily practice. The questionnaires were composed of single choice, multiple choices, and scale bar questions. Answers were analyzed according to the clinicians and radiologists using paired t-test and the Wilcoxon rank-sum test.ResultsOne hundred twenty-three doctors answered the survey, and 74% completed all questions. The proportion of individuals who utilized AI was higher among radiologists than clinicians (82.5% vs. 45.9%, p = 0.008). AI was perceived as being the most useful in the emergency room, and pneumothorax was considered the most valuable finding. Approximately 21% of clinicians and 16% of radiologists changed their own reading results after referring to AI, and trust levels for AI were 64.9% and 66.5%, respectively. Participants thought AI helped reduce reading times and reading requests. They answered that AI helped increase diagnostic accuracy and were more positive about AI after actual usage.ConclusionActual adaptation of AI for daily chest radiographs received overall positive feedback from clinicians and radiologists in this hospital-wide survey. Participating doctors preferred to use AI and regarded it more favorably after actual working with the AI-based software in daily clinical practice.
| S-EPMC9980810 | biostudies-literature
Project description:AimsWe aimed to develop models to detect aortic stenosis (AS) from chest radiographs-one of the most basic imaging tests-with artificial intelligence.Methods and resultsWe used 10 433 retrospectively collected digital chest radiographs from 5638 patients to train, validate, and test three deep learning models. Chest radiographs were collected from patients who had also undergone echocardiography at a single institution between July 2016 and May 2019. These were labelled from the corresponding echocardiography assessments as AS-positive or AS-negative. The radiographs were separated on a patient basis into training [8327 images from 4512 patients, mean age 65 ± (standard deviation) 15 years], validation (1041 images from 563 patients, mean age 65 ± 14 years), and test (1065 images from 563 patients, mean age 65 ± 14 years) datasets. The soft voting-based ensemble of the three developed models had the best overall performance for predicting AS with an area under the receiver operating characteristic curve, sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of 0.83 (95% confidence interval 0.77-0.88), 0.78 (0.67-0.86), 0.71 (0.68-0.73), 0.71 (0.68-0.74), 0.18 (0.14-0.23), and 0.97 (0.96-0.98), respectively, in the validation dataset and 0.83 (0.78-0.88), 0.83 (0.74-0.90), 0.69 (0.66-0.72), 0.71 (0.68-0.73), 0.23 (0.19-0.28), and 0.97 (0.96-0.98), respectively, in the test dataset.ConclusionDeep learning models using chest radiographs have the potential to differentiate between radiographs of patients with and without AS.Lay summaryWe created artificial intelligence (AI) models using deep learning to identify aortic stenosis (AS) from chest radiographs. Three AI models were developed and evaluated with 10 433 retrospectively collected radiographs and labelled from echocardiography reports. The ensemble AI model could detect AS in a test dataset with an area under the receiver operating characteristic curve of 0.83 (95% confidence interval 0.78-0.88). Since chest radiography is a cost-effective and widely available imaging test, our model can provide an additive resource for the detection of AS.
| S-EPMC9707887 | biostudies-literature
Project description:PurposeTo investigate the diagnostic performance of an Artificial Intelligence (AI) system for detection of COVID-19 in chest radiographs (CXR), and compare results to those of physicians working alone, or with AI support.Materials and methodsAn AI system was fine-tuned to discriminate confirmed COVID-19 pneumonia, from other viral and bacterial pneumonia and non-pneumonia patients and used to review 302 CXR images from adult patients retrospectively sourced from nine different databases. Fifty-four physicians blind to diagnosis, were invited to interpret images under identical conditions in a test set, and randomly assigned either to receive or not receive support from the AI system. Comparisons were then made between diagnostic performance of physicians working with and without AI support. AI system performance was evaluated using the area under the receiver operating characteristic (AUROC), and sensitivity and specificity of physician performance compared to that of the AI system.ResultsDiscrimination by the AI system of COVID-19 pneumonia showed an AUROC curve of 0.96 in the validation and 0.83 in the external test set, respectively. The AI system outperformed physicians in the AUROC overall (70% increase in sensitivity and 1% increase in specificity, p < 0.0001). When working with AI support, physicians increased their diagnostic sensitivity from 47% to 61% (p < 0.001), although specificity decreased from 79% to 75% (p = 0.007).ConclusionsOur results suggest interpreting chest radiographs (CXR) supported by AI, increases physician diagnostic sensitivity for COVID-19 detection. This approach involving a human-machine partnership may help expedite triaging efforts and improve resource allocation in the current crisis.
| S-EPMC7674009 | biostudies-literature
Project description:ObjectivesDiagnostic accuracy of artificial intelligence (AI) pneumothorax (PTX) detection in chest radiographs (CXR) is limited by the noisy annotation quality of public training data and confounding thoracic tubes (TT). We hypothesize that in-image annotations of the dehiscent visceral pleura for algorithm training boosts algorithm's performance and suppresses confounders.MethodsOur single-center evaluation cohort of 3062 supine CXRs includes 760 PTX-positive cases with radiological annotations of PTX size and inserted TTs. Three step-by-step improved algorithms (differing in algorithm architecture, training data from public datasets/clinical sites, and in-image annotations included in algorithm training) were characterized by area under the receiver operating characteristics (AUROC) in detailed subgroup analyses and referenced to the well-established "CheXNet" algorithm.ResultsPerformances of established algorithms exclusively trained on publicly available data without in-image annotations are limited to AUROCs of 0.778 and strongly biased towards TTs that can completely eliminate algorithm's discriminative power in individual subgroups. Contrarily, our final "algorithm 2" which was trained on a lower number of images but additionally with in-image annotations of the dehiscent pleura achieved an overall AUROC of 0.877 for unilateral PTX detection with a significantly reduced TT-related confounding bias.ConclusionsWe demonstrated strong limitations of an established PTX-detecting AI algorithm that can be significantly reduced by designing an AI system capable of learning to both classify and localize PTX. Our results are aimed at drawing attention to the necessity of high-quality in-image localization in training data to reduce the risks of unintentionally biasing the training process of pathology-detecting AI algorithms.Key points• Established pneumothorax-detecting artificial intelligence algorithms trained on public training data are strongly limited and biased by confounding thoracic tubes. • We used high-quality in-image annotated training data to effectively boost algorithm performance and suppress the impact of confounding thoracic tubes. • Based on our results, we hypothesize that even hidden confounders might be effectively addressed by in-image annotations of pathology-related image features.
| S-EPMC8452588 | biostudies-literature
Project description:Whether the utilization of artificial intelligence (AI) during the interpretation of chest radiographs (CXRs) would affect the radiologists' workload is of particular interest. Therefore, this prospective observational study aimed to observe how AI affected the reading times of radiologists in the daily interpretation of CXRs. Radiologists who agreed to have the reading times of their CXR interpretations collected from September to December 2021 were recruited. Reading time was defined as the duration in seconds from opening CXRs to transcribing the image by the same radiologist. As commercial AI software was integrated for all CXRs, the radiologists could refer to AI results for 2 months (AI-aided period). During the other 2 months, the radiologists were automatically blinded to the AI results (AI-unaided period). A total of 11 radiologists participated, and 18,680 CXRs were included. Total reading times were significantly shortened with AI use, compared to no use (13.3 s vs. 14.8 s, p < 0.001). When there was no abnormality detected by AI, reading times were shorter with AI use (mean 10.8 s vs. 13.1 s, p < 0.001). However, if any abnormality was detected by AI, reading times did not differ according to AI use (mean 18.6 s vs. 18.4 s, p = 0.452). Reading times increased as abnormality scores increased, and a more significant increase was observed with AI use (coefficient 0.09 vs. 0.06, p < 0.001). Therefore, the reading times of CXRs among radiologists were influenced by the availability of AI. Overall reading times shortened when radiologists referred to AI; however, abnormalities detected by AI could lengthen reading times.
| S-EPMC10148851 | biostudies-literature
Project description:Background and purpose - Recent advances in artificial intelligence (deep learning) have shown remarkable performance in classifying non-medical images, and the technology is believed to be the next technological revolution. So far it has never been applied in an orthopedic setting, and in this study we sought to determine the feasibility of using deep learning for skeletal radiographs. Methods - We extracted 256,000 wrist, hand, and ankle radiographs from Danderyd's Hospital and identified 4 classes: fracture, laterality, body part, and exam view. We then selected 5 openly available deep learning networks that were adapted for these images. The most accurate network was benchmarked against a gold standard for fractures. We furthermore compared the network's performance with 2 senior orthopedic surgeons who reviewed images at the same resolution as the network. Results - All networks exhibited an accuracy of at least 90% when identifying laterality, body part, and exam view. The final accuracy for fractures was estimated at 83% for the best performing network. The network performed similarly to senior orthopedic surgeons when presented with images at the same resolution as the network. The 2 reviewer Cohen's kappa under these conditions was 0.76. Interpretation - This study supports the use for orthopedic radiographs of artificial intelligence, which can perform at a human level. While current implementation lacks important features that surgeons require, e.g. risk of dislocation, classifications, measurements, and combining multiple exam views, these problems have technical solutions that are waiting to be implemented for orthopedics.
| S-EPMC5694800 | biostudies-other
Project description:This study evaluated the positive predictive value (PPV) of artificial intelligence (AI) in detecting pneumothorax on chest radiographs (CXRs) and its affecting factors. Patients determined to have pneumothorax on CXR by a commercial AI software from March to December 2021 were included retrospectively. The PPV was evaluated according to the true-positive (TP) and false-positive (FP) diagnosis determined by radiologists. To know the factors that might influence the results, logistic regression with generalized estimating equation was used. Among a total of 87,658 CXRs, 308 CXRs with 331 pneumothoraces from 283 patients were finally included. The overall PPV of AI about pneumothorax was 41.1% (TF:FP = 136:195). The PA view (odds ratio [OR], 29.837; 95% confidence interval [CI], 15.062-59.107), high abnormality score (OR, 1.081; 95% CI, 1.066-1.097), large amount of pneumothorax (OR, 1.005; 95% CI, 1.003-1.007), presence of ipsilateral atelectasis (OR, 3.508; 95% CI, 1.509-8.156) and a small amount of ipsilateral pleural effusion (OR, 5.277; 95% CI, 2.55-10.919) had significant effects on the increasing PPV. Therefore, PPV for pneumothorax diagnosis using AI can vary based on patients' factors, image-acquisition protocols, and the presence of concurrent lesions on CXR.
| S-EPMC11343866 | biostudies-literature
Project description:This study employed deep-learning convolutional neural networks to stage lung disease severity of Coronavirus Disease 2019 (COVID-19) infection on portable chest x-ray (CXR) with radiologist score of disease severity as ground truth. This study consisted of 131 portable CXR from 84 COVID-19 patients (51M 55.1±14.9yo; 29F 60.1±14.3yo; 4 missing information). Three expert chest radiologists scored the left and right lung separately based on the degree of opacity (0-3) and geographic extent (0-4). Deep-learning convolutional neural network (CNN) was used to predict lung disease severity scores. Data were split into 80% training and 20% testing datasets. Correlation analysis between AI-predicted versus radiologist scores were analyzed. Comparison was made with traditional and transfer learning. The average opacity score was 2.52 (range: 0-6) with a standard deviation of 0.25 (9.9%) across three readers. The average geographic extent score was 3.42 (range: 0-8) with a standard deviation of 0.57 (16.7%) across three readers. The inter-rater agreement yielded a Fleiss' Kappa of 0.45 for opacity score and 0.71 for extent score. AI-predicted scores strongly correlated with radiologist scores, with the top model yielding a correlation coefficient (R2) of 0.90 (range: 0.73-0.90 for traditional learning and 0.83-0.90 for transfer learning) and a mean absolute error of 8.5% (ranges: 17.2-21.0% and 8.5%-15.5, respectively). Transfer learning generally performed better. In conclusion, deep-learning CNN accurately stages disease severity on portable chest x-ray of COVID-19 lung infection. This approach may prove useful to stage lung disease severity, prognosticate, and predict treatment response and survival, thereby informing risk management and resource allocation.
| S-EPMC7386587 | biostudies-literature
Project description:ImportanceEarly detection of pneumothorax, most often via chest radiography, can help determine need for emergent clinical intervention. The ability to accurately detect and rapidly triage pneumothorax with an artificial intelligence (AI) model could assist with earlier identification and improve care.ObjectiveTo compare the accuracy of an AI model vs consensus thoracic radiologist interpretations in detecting any pneumothorax (incorporating both nontension and tension pneumothorax) and tension pneumothorax.Design, setting, and participantsThis diagnostic study was a retrospective standalone performance assessment using a data set of 1000 chest radiographs captured between June 1, 2015, and May 31, 2021. The radiographs were obtained from patients aged at least 18 years at 4 hospitals in the Mass General Brigham hospital network in the United States. Included radiographs were selected using 2 strategies from all chest radiography performed at the hospitals, including inpatient and outpatient. The first strategy identified consecutive radiographs with pneumothorax through a manual review of radiology reports, and the second strategy identified consecutive radiographs with tension pneumothorax using natural language processing. For both strategies, negative radiographs were selected by taking the next negative radiograph acquired from the same radiography machine as each positive radiograph. The final data set was an amalgamation of these processes. Each radiograph was interpreted independently by up to 3 radiologists to establish consensus ground-truth interpretations. Each radiograph was then interpreted by the AI model for the presence of pneumothorax and tension pneumothorax. This study was conducted between July and October 2021, with the primary analysis performed between October and November 2021.Main outcomes and measuresThe primary end points were the areas under the receiver operating characteristic curves (AUCs) for the detection of pneumothorax and tension pneumothorax. The secondary end points were the sensitivities and specificities for the detection of pneumothorax and tension pneumothorax.ResultsThe final analysis included radiographs from 985 patients (mean [SD] age, 60.8 [19.0] years; 436 [44.3%] female patients), including 307 patients with nontension pneumothorax, 128 patients with tension pneumothorax, and 550 patients without pneumothorax. The AI model detected any pneumothorax with an AUC of 0.979 (95% CI, 0.970-0.987), sensitivity of 94.3% (95% CI, 92.0%-96.3%), and specificity of 92.0% (95% CI, 89.6%-94.2%) and tension pneumothorax with an AUC of 0.987 (95% CI, 0.980-0.992), sensitivity of 94.5% (95% CI, 90.6%-97.7%), and specificity of 95.3% (95% CI, 93.9%-96.6%).Conclusions and relevanceThese findings suggest that the assessed AI model accurately detected pneumothorax and tension pneumothorax in this chest radiograph data set. The model's use in the clinical workflow could lead to earlier identification and improved care for patients with pneumothorax.
| S-EPMC9856508 | biostudies-literature
Project description:While COVID-19 diagnosis and prognosis artificial intelligence models exist, very few can be implemented for practical use given their high risk of bias. We aimed to develop a diagnosis model that addresses notable shortcomings of prior studies, integrating it into a fully automated triage pipeline that examines chest radiographs for the presence, severity, and progression of COVID-19 pneumonia. Scans were collected using the DICOM Image Analysis and Archive, a system that communicates with a hospital's image repository. The authors collected over 6,500 non-public chest X-rays comprising diverse COVID-19 severities, along with radiology reports and RT-PCR data. The authors provisioned one internally held-out and two external test sets to assess model generalizability and compare performance to traditional radiologist interpretation. The pipeline was evaluated on a prospective cohort of 80 radiographs, reporting a 95% diagnostic accuracy. The study mitigates bias in AI model development and demonstrates the value of an end-to-end COVID-19 triage platform.
| S-EPMC8760275 | biostudies-literature