RESUMEN

BACKGROUND AND OBJECTIVES: Ambiguity in diagnosing acute heart failure (AHF) leads to inappropriate treatment and potential side effects of rescue medications. To address this issue, this study aimed to use multimodality deep learning models combining chest X-ray (CXR) and electronic health record (EHR) data to screen patients with abnormal N-terminal pro-B-type natriuretic peptide (NT-proBNP) levels in emergency departments. METHODS: Using the open-source dataset MIMIC-IV and MIMICCXR, the study population consisted of 1,432 patients and 1,833 pairs of CXRs and EHRs. We processed the CXRs, extracted relevant features through lung-heart masks, and combined these with the vital signs at triage to predict corresponding NT-proBNP levels. RESULTS: The proposed method achieved a 0.89 area under the receiver operating characteristic curve by fusing predictions from single-modality models of heart size ratio, radiomic features, CXR, and the region of interest in the CXR. The model can accurately predict dyspneic patients with abnormal NT-proBNP concentrations, allowing physicians to reduce the risks associated with inappropriate treatment. CONCLUSION: The study provided new image features related to AHF and offered insights into future research directions. Overall, these models have great potential to improve patient outcomes and reduce risks in emergency departments.

Asunto(s)

RESUMEN

INTRODUCTION: Deep neural networks (DNNs) have made significant contributions to diagnosing pneumonia from chest X-ray imaging. However, certain aspects of diagnosis and planning can be further enhanced through the implementation of a quantum deep neural network (QDNN). Therefore, we introduced a technique that integrates neural networks with quantum algorithms named the ZFNet-quantum neural network for detecting pneumonia using 5863 X-ray scans with binary cases. METHODS: The hybrid model efficiently pre-processes complex and high-dimensional data by extracting significant features from the ZFNet model. These significant features are given to the quantum circuit algorithm and further embedded into a quantum device. The parameterized quantum circuit algorithm using qubits, superposition theorem, and entanglement phenomena generates 4 features from 4098 features extracted from images via a deep transfer learning model. Moreover, to validate the outcome measures of the proposed technique, we used various PennyLane quantum devices to detect pneumonia and normal control images. By using the Adam optimizer, which exploits an adaptive learning rate that is fixed to 10-6 and six layers of a quantum circuit composed of quantum gates, the proposed model achieves an accuracy of 96.5%, corresponding to 25 epochs. RESULTS: The integrated ZFNet-quantum learning network outperforms the deep transfer learning network in terms of testing accuracy, as the accuracy gained by the convolutional neural network (CNN) is 94%. Therefore, we use a hybrid classical-quantum model to detect pneumonia in which a variational quantum algorithm enhances the outcomes of a ZFNet transfer learning method. CONCLUSION: This approach is an efficient and automated method for detecting pneumonia and could significantly enhance outcome measures related to the speed and accuracy of the network in the clinical and healthcare sectors.

RESUMEN

Histiocytic sarcoma is an extremely rare disease that's hard to diagnose and treat, often leading to a poor prognosis. Here, we present a case report detailing a rare occurrence of HS in a 37-year-old pregnant woman who first presented with left shoulder pain, palpitations, and a productive cough at 20 weeks of gestation. Her diagnostic evaluations were performed, including different imaging modalities such as chest X-rays, CT scans, and MRI. Imaging revealed a large mediastinal mass with extensive involvement of the adrenal glands, lungs, and lymph nodes. The definitive diagnosis of HS is based on pathological and morphological features, and the immunohistochemistry report plays a key role. In our case, the diagnosis of HS was confirmed through pathological evaluation and immunohistochemistry, with a positive CD68 result obtained from a supraclavicular lymph node biopsy. A hospital committee comprising medical specialists like hematologists-oncologists, pathologists, pulmonologists, and obstetricians was brought together to assess the case collectively. The patient received chemotherapy, which alleviated her symptoms and maintained her condition. Based on the committee's recommendations, despite a healthy fetus and normal obstetric sonograms, the decision was made to terminate the pregnancy with the consent of the patient and her family. Despite initial improvement postchemotherapy, the patient's condition worsened, necessitating intubation. Tragically, two months after the initial admission, the patient passed away due to severe complications. In this case report, we provide a literature review and review of the patient's imaging reports. Since the patient is pregnant and HS is uncommon, it's important to highlight that this case is unique and worth sharing.

RESUMEN

Heart failure (HF) is associated with high rates of morbidity and mortality. The value of deep learning survival prediction models using chest radiographs in patients with heart failure is currently unclear. The aim of our study is to develop and validate a deep learning survival prediction model using chest X-ray (DLSPCXR) in patients with HF. The study retrospectively enrolled a cohort of 353 patients with HF who underwent chest X-ray (CXR) at our institution between March 2012 and March 2017. The dataset was randomly divided into training (n = 247) and validation (n = 106) datasets. Univariate and multivariate Cox analysis were conducted on the training dataset to develop clinical and imaging survival prediction models. The DLSPCXR was trained and the selected clinical parameters were incorporated into DLSPCXR to establish a new model called DLSPinteg. Discrimination performance was evaluated using the time-dependent area under the receiver operating characteristic curves (TD AUC) at 1, 3, and 5-years survival. Delong's test was employed for the comparison of differences between two AUCs of different models. The risk-discrimination capability of the optimal model was evaluated by the Kaplan-Meier curve. In multivariable Cox analysis, older age, higher N-terminal pro-B-type natriuretic peptide (NT-ProBNP), systolic pulmonary artery pressure (sPAP) > 50 mmHg, New York Heart Association (NYHA) functional class III-IV and cardiothoracic ratio (CTR) ≥ 0.62 in CXR were independent predictors of poor prognosis in patients with HF. Based on the receiver operating characteristic (ROC) curve analysis, DLSPCXR had better performance at predicting 5-year survival than the imaging Cox model in the validation cohort (AUC: 0.757 vs. 0.561, P = 0.01). DLSPinteg as the optimal model outperforms the clinical Cox model (AUC: 0.826 vs. 0.633, P = 0.03), imaging Cox model (AUC: 0.826 vs. 0.555, P < 0.001), and DLSPCXR (AUC: 0.826 vs. 0.767, P = 0.06). Deep learning models using chest radiographs can predict survival in patients with heart failure with acceptable accuracy.

RESUMEN

Introduction Lung diseases are the most frequently encountered form of diseases primarily affecting infants under one year of age. Although the chest X-ray is the first modality of choice, ultrasonography (USG) has emerged as an alternative. Lung ultrasound (LUS) finds its application in the evaluation of several pediatric lung diseases. Objective To assess the use of LUS in acute lower respiratory infections and assess the correlation between etiological diagnosis and radiological diagnosis. Methods This was a hospital-based prospective observational study conducted with children presenting with upper respiratory infections. Around 97 children were included in the study. Clinical diagnosis was made by the pediatrician. LUS was performed by a trained radiologist, using the two-dimensional (2D) ultrasound mode and motion mode (M mode) to assess the LUS in the respective areas of the chest, thereby assessing bilateral lung fields for these patients. Results The majority of our study participants were under one year old (87%), and more than half were male (55%). Bronchiolitis and lower respiratory tract infections (LRIs) were the most commonly seen clinical diagnoses. The distribution of USG findings was statistically significant across the clinical diagnosis (p-value < 0.05). Conclusion Our study found that LUS can serve as an important tool for diagnosing several acute respiratory diseases. It also showed that LUS can replace X-rays in cases of children diagnosed with acute respiratory diseases.

RESUMEN

Introduction: This study is a retrospective evaluation of the performance of deep learning models that were developed for the detection of COVID-19 from chest x-rays, undertaken with the goal of assessing the suitability of such systems as clinical decision support tools. Methods: Models were trained on the National COVID-19 Chest Imaging Database (NCCID), a UK-wide multi-centre dataset from 26 different NHS hospitals and evaluated on independent multi-national clinical datasets. The evaluation considers clinical and technical contributors to model error and potential model bias. Model predictions are examined for spurious feature correlations using techniques for explainable prediction. Results: Models performed adequately on NHS populations, with performance comparable to radiologists, but generalised poorly to international populations. Models performed better in males than females, and performance varied across age groups. Alarmingly, models routinely failed when applied to complex clinical cases with confounding pathologies and when applied to radiologist defined "mild" cases. Discussion: This comprehensive benchmarking study examines the pitfalls in current practices that have led to impractical model development. Key findings highlight the need for clinician involvement at all stages of model development, from data curation and label definition, to model evaluation, to ensure that all clinical factors and disease features are appropriately considered during model design. This is imperative to ensure automated approaches developed for disease detection are fit-for-purpose in a clinical setting.

RESUMEN

Chest X-rays (CXRs) play a pivotal role in cost-effective clinical assessment of various heart and lung related conditions. The urgency of COVID-19 diagnosis prompted their use in identifying conditions like lung opacity, pneumonia, and acute respiratory distress syndrome in pediatric patients. We propose an AI-driven solution for binary COVID-19 versus non-COVID-19 classification in pediatric CXRs. We present a Federated Self-Supervised Learning (FSSL) framework to enhance Vision Transformer (ViT) performance for COVID-19 detection in pediatric CXRs. ViT's prowess in vision-related binary classification tasks, combined with self-supervised pre-training on adult CXR data, forms the basis of the FSSL approach. We implement our strategy on the Rhino Health Federated Computing Platform (FCP), which ensures privacy and scalability for distributed data. The chest X-ray analysis using the federated SSL (CAFES) model, utilizes the FSSL-pre-trained ViT weights and demonstrated gains in accurately detecting COVID-19 when compared with a fully supervised model. Our FSSL-pre-trained ViT showed an area under the precision-recall curve (AUPR) of 0.952, which is 0.231 points higher than the fully supervised model for COVID-19 diagnosis using pediatric data. Our contributions include leveraging vision transformers for effective COVID-19 diagnosis from pediatric CXRs, employing distributed federated learning-based self-supervised pre-training on adult data, and improving pediatric COVID-19 diagnosis performance. This privacy-conscious approach aligns with HIPAA guidelines, paving the way for broader medical imaging applications.

RESUMEN

In this paper, we hypothesize that it is possible to localize image regions of preclinical tumors in a Chest X-ray (CXR) image by a weakly-supervised training of a survival prediction model using a dataset containing CXR images of healthy patients and their time-to-death label. These visual explanations can empower clinicians in early lung cancer detection and increase patient awareness of their susceptibility to the disease. To test this hypothesis, we train a censor-aware multi-class survival prediction deep learning classifier that is robust to imbalanced training, where classes represent quantized number of days for time-to-death prediction. Such multi-class model allows us to use post-hoc interpretability methods, such as Grad-CAM, to localize image regions of preclinical tumors. For the experiments, we propose a new benchmark based on the National Lung Cancer Screening Trial (NLST) dataset to test weakly-supervised preclinical tumor localization and survival prediction models, and results suggest that our proposed method shows state-of-the-art C-index survival prediction and weakly-supervised preclinical tumor localization results. To our knowledge, this constitutes a pioneer approach in the field that is able to produce visual explanations of preclinical events associated with survival prediction results.

Asunto(s)

RESUMEN

Background: The government of Korea implemented a strategy of prevention and early diagnosis in high-risk groups to reduce the tuberculosis (TB) burden. This study aims to investigate the TB epidemiology and gap in understanding of TB prevalence among homeless individuals by analyzing active TB chest X-ray (CXR) screening results in Korea. Methods: The Korean National Tuberculosis Association conducted active TB screening with CXR for homeless groups from January 1 to December 31, 2021. Sputum acid fast bacilli smear and culture were performed for the subjects suggestive of TB on CXR. We performed a cross-sectional analysis of the data in comparison with the national health screening results from the general population. Results: Among 17,713 homeless persons, 40 (0.23%), 3,077 (17.37%), and 79 (0.45%) were categorized as suggested TB, inactive TB, and observation required, respectively. Prevalence of suggested TB in the homeless was significantly higher (3-5 fold) than in the national general health screening based on age category (p < 0.005). Twenty-nine cases were confirmed as TB, yielding a prevalence of 164 cases per 100,000 individuals; 19 of these 29 cases showed inactive TB on CXR. Body mass index (p = 0.0478) and CXR result (p < 0.001) significantly correlated with confirmed TB based on multivariable analysis. Conclusion: Nutrition status and CXR results, especially that of inactive TB, should be considered in active TB screening of the homeless population, where TB prevalence is higher than the general population.

RESUMEN

Deep learning (DL) has demonstrated its innate capacity to independently learn hierarchical features from complex and multi-dimensional data. A common understanding is that its performance scales up with the amount of training data. However, the data must also exhibit variety to enable improved learning. In medical imaging data, semantic redundancy, which is the presence of similar or repetitive information, can occur due to the presence of multiple images that have highly similar presentations for the disease of interest. Also, the common use of augmentation methods to generate variety in DL training could limit performance when indiscriminately applied to such data. We hypothesize that semantic redundancy would therefore tend to lower performance and limit generalizability to unseen data and question its impact on classifier performance even with large data. We propose an entropy-based sample scoring approach to identify and remove semantically redundant training data and demonstrate using the publicly available NIH chest X-ray dataset that the model trained on the resulting informative subset of training data significantly outperforms the model trained on the full training set, during both internal (recall: 0.7164 vs 0.6597, p<0.05) and external testing (recall: 0.3185 vs 0.2589, p<0.05). Our findings emphasize the importance of information-oriented training sample selection as opposed to the conventional practice of using all available training data.

Asunto(s)

RESUMEN

INTRODUCTION: Radiologists have extensively employed the interpretation of chest X-rays (CXR) to identify visual markers indicative of COVID-19 infection, offering an alternative approach for the screening of infected individuals. This research article presents CovMediScanX, a deep learning-based framework designed for a rapid and automated diagnosis of COVID-19 from CXR scan images. METHODS: The proposed approach encompasses gathering and preprocessing CXR image datasets, training deep learning-based custom-made Convolutional Neural Network (CNN), pre-trained and hybrid transfer learning models, identifying the highest-performing model based on key evaluation metrics, and embedding this model into a web interface called CovMediScanX, designed for radiologists to detect the COVID-19 status in new CXR images. RESULTS: The custom-made CNN model obtained a remarkable testing accuracy of 94.32% outperforming other models. CovMediScanX, employing the custom-made CNN underwent evaluation with an independent dataset also. The images in the independent dataset are sourced from a scanning machine that is entirely different from those used for the training dataset, highlighting a clear distinction of datasets in their origins. The evaluation outcome highlighted the framework's capability to accurately detect COVID-19 cases, showcasing encouraging results with a precision of 73% and a recall of 84% for positive cases. However, the model requires further enhancement, particularly in improving its detection of normal cases, as evidenced by lower precision and recall rates. CONCLUSION: The research proposes CovMediScanX framework that demonstrates promising potential in automatically identifying COVID-19 cases from CXR images. While the model's overall performance on independent data needs improvement, it is evident that addressing bias through the inclusion of diverse data sources during training could further enhance accuracy and reliability.

Asunto(s)

RESUMEN

Deep learning is revolutionizing radiology report generation (RRG) with the adoption of vision encoder-decoder (VED) frameworks, which transform radiographs into detailed medical reports. Traditional methods, however, often generate reports of limited diversity and struggle with generalization. Our research introduces reinforcement learning and text augmentation to tackle these issues, significantly improving report quality and variability. By employing RadGraph as a reward metric and innovating in text augmentation, we surpass existing benchmarks like BLEU4, ROUGE-L, F1CheXbert, and RadGraph, setting new standards for report accuracy and diversity on MIMIC-CXR and Open-i datasets. Our VED model achieves F1-scores of 66.2 for CheXbert and 37.8 for RadGraph on the MIMIC-CXR dataset, and 54.7 and 45.6, respectively, on Open-i. These outcomes represent a significant breakthrough in the RRG field. The findings and implementation of the proposed approach, aimed at enhancing diagnostic precision and radiological interpretations in clinical settings, are publicly available on GitHub to encourage further advancements in the field.

RESUMEN

BACKGROUND AND AIMS: Early identification of cardiac structural abnormalities indicative of heart failure is crucial to improving patient outcomes. Chest X-rays (CXRs) are routinely conducted on a broad population of patients, presenting an opportunity to build scalable screening tools for structural abnormalities indicative of Stage B or worse heart failure with deep learning methods. In this study, a model was developed to identify severe left ventricular hypertrophy (SLVH) and dilated left ventricle (DLV) using CXRs. METHODS: A total of 71 589 unique CXRs from 24 689 different patients completed within 1 year of echocardiograms were identified. Labels for SLVH, DLV, and a composite label indicating the presence of either were extracted from echocardiograms. A deep learning model was developed and evaluated using area under the receiver operating characteristic curve (AUROC). Performance was additionally validated on 8003 CXRs from an external site and compared against visual assessment by 15 board-certified radiologists. RESULTS: The model yielded an AUROC of 0.79 (0.76-0.81) for SLVH, 0.80 (0.77-0.84) for DLV, and 0.80 (0.78-0.83) for the composite label, with similar performance on an external data set. The model outperformed all 15 individual radiologists for predicting the composite label and achieved a sensitivity of 71% vs. 66% against the consensus vote across all radiologists at a fixed specificity of 73%. CONCLUSIONS: Deep learning analysis of CXRs can accurately detect the presence of certain structural abnormalities and may be useful in early identification of patients with LV hypertrophy and dilation. As a resource to promote further innovation, 71 589 CXRs with adjoining echocardiographic labels have been made publicly available.

Asunto(s)

RESUMEN

Purpose: Medical imaging is one of the main methods of diagnosing COVID-19, along with real-time reverse trans-cription-polymerase chain reaction (RT-PCR) tests. The purpose of the study was to analyse the texture parameters of chest X-rays (CXR) of patients suspected of having COVID-19. Material and methods: Texture parameters of the CXRs of 70 patients with symptoms typical of COVID-19 infection were analysed using LIFEx software. The regions of interest (ROIs) included each lung separately, for which 57 para-meters were tested. The control group consisted of 30 healthy, age-matched patients with no pathological findings in CXRs. Results: According to the ROC analysis, 13 of the tested parameters differentiate the radiological image of lungs with COVID-19 features from the image of healthy lungs: GLRLM_LRHGE (AUC 0.91); DISCRETIZED_Q3 (AUC 0.90); GLZLM_HGZE (AUC 0.90); GLRLM_HGRE (AUC 0.89); DISCRETIZED_mean (AUC 0.89); DISCRETIZED_Q2 (AUC 0.61); GLRLM_SRHGE (AUC 0.87); GLZLM_LZHGE (AUC 0.87); GLZLM_SZHGE (AUC 0.84); DISCRETIZED_Q1 (AUC 0.81); NGLDM_Coarseness (AUC 0.70); DISCRETIZED_std (AUC 0.64); CONVENTIONAL_Q2 (AUC 0.61). Conclusions: Selected texture parameters of radiological CXRs make it possible to distinguish COVID-19 features from healthy ones.

RESUMEN

BACKGROUND: Peri-procedural complications associated with cardiac implantable electronic devices are not uncommon. European Society of Cardiology guidelines recommend device checks of all devices within 72 h of implant. European Heart Rhythm Association expert practical guide on Cardiac implantable electronic devices (CIEDs) recommend that a chest x-ray (CXR) should be performed within 24 h to rule out pneumothorax and document lead positions. First, the rate of peri-procedural complications associated with CIED implants at our center, as well as patient and/or procedural-related factors that are associated with higher rates of complications, is analyzed. Second, the yield of the guideline-recommended measures in the early detection of peri-procedural complications is examined. MATERIALS AND METHODS: Consecutive de novo transvenous device implants at our center in 2019 were retrospectively analyzed. Patients' demographics, types and indications for device therapy, procedural reports, device checks, and CXRs were obtained from the hospital electronic records. RESULTS: A total of 578 patients (Age 74 ± 16 years, 68% male) were included. All patients had routine post-procedure CXRs and device checks. There were 16 (2.8%) complications; 7 (1.2%) pneumothoraxes, 6 (1%) pericardial effusions, and 3 (0.5%) lead displacements. Procedure time correlated significantly with complications; in uncomplicated cases it was 99 ± 43 min versus 127 ± 50 min in procedures associated with complications (p = .02). CONCLUSIONS: Routine post CIED implantation CXRs can detect early peri-procedural complications, while repeat post mobilization device checks has low yield of detection of complications. The only statistically significant predictor of peri-procedural complications is the duration of the procedure; longer procedures were associated with higher rates of complications.

Asunto(s)

RESUMEN

Clinicians without a radiology specialization face difficulties when they attempt to interpret chest X-rays (CXRs), a crucial and extensively utilized diagnostic tool that plays a fundamental role in the detection of pulmonary and cardiovascular disorders. This cross-sectional study assessed the confidence and competence of clinicians, including junior specialty trainees, higher specialty trainees, and specialist nurses, in interpreting CXRs before starting biological treatment. An online survey was used to collect data from clinicians in various healthcare settings, focusing on their experience, training, confidence levels, and CXR interpretation proficiency. The survey uncovered clinicians' insufficient confidence in interpreting the pre-biological screening CXRs despite their clinical expertise. This uncertainty raises concerns about potential misinterpretations, affecting timely treatment decisions. A Kruskal-Wallis test indicated a significant difference between training levels required with a p-value of 0.001, rejecting the null hypothesis. Subsequently, a Dunn-Bonferroni test revealed that the higher specialty trainee-specialist nurse pair differed significantly, with the specialist nurse group requiring more training. This study highlighted the need for enhanced radiology education for clinicians involved in chest radiograph interpretation for pre-biological screening. Implementing a structured training program is essential to improve skills and ensure accurate interpretation of non-formally reported chest radiographs, ultimately enhancing patient outcomes and healthcare practices.

RESUMEN

Deep learning (DL) has demonstrated its innate capacity to independently learn hierarchical features from complex and multi-dimensional data. A common understanding is that its performance scales up with the amount of training data. Another data attribute is the inherent variety. It follows, therefore, that semantic redundancy, which is the presence of similar or repetitive information, would tend to lower performance and limit generalizability to unseen data. In medical imaging data, semantic redundancy can occur due to the presence of multiple images that have highly similar presentations for the disease of interest. Further, the common use of augmentation methods to generate variety in DL training may be limiting performance when applied to semantically redundant data. We propose an entropy-based sample scoring approach to identify and remove semantically redundant training data. We demonstrate using the publicly available NIH chest X-ray dataset that the model trained on the resulting informative subset of training data significantly outperforms the model trained on the full training set, during both internal (recall: 0.7164 vs 0.6597, p<0.05) and external testing (recall: 0.3185 vs 0.2589, p<0.05). Our findings emphasize the importance of information-oriented training sample selection as opposed to the conventional practice of using all available training data.

RESUMEN

Tuberculosis (TB) remains the second leading cause of death globally from a single infectious agent, and there is a critical need to develop improved imaging biomarkers and aid rapid assessments of responses to therapy. We aimed to utilize radiomics, a rapidly developing image analysis tool, to develop a scoring system for this purpose. A chest X-ray radiomics score (RadScore) was developed by implementing a unique segmentation method, followed by feature extraction and parameter map construction. Signature parameter maps that showed a high correlation to lung pathology were consolidated into four frequency bins to obtain the RadScore. A clinical score (TBscore) and a radiological score (RLscore) were also developed based on existing scoring algorithms. The correlation between the change in the three scores, calculated from serial X-rays taken while patients received TB therapy, was evaluated using Spearman's correlation. Poor correlations were observed between the changes in the TBscore and the RLscore (0.09 (p-value = 0.36)) and the TBscore and the RadScore (0.02 (p-value = 0.86)). The changes in the RLscore and the RadScore had a much stronger correlation of 0.22, which is statistically significant (p-value = 0.02). This shows that the developed RadScore has the potential to be a quantitative monitoring tool for responses to therapy.

RESUMEN

BACKGROUND: Chest X-rays (CXRs) have traditionally been used to aid the diagnosis of TB-suggestive abnormalities. Using Computer-Aided Detection (CAD) algorithms, TB risk is quantified to assist with diagnostics. However, CXRs capture all other structural abnormalities. Identification of non-TB abnormalities in individuals with CXRs that have high CAD scores but don't have bacteriologically confirmed TB is unknown. This presents a missed opportunity of extending novel CAD systems' potential to simultaneously provide information on other non-TB abnormalities alongside TB. This study aimed to characterize and estimate the prevalence of non-TB abnormalities on digital CXRs with high CAD4TB scores from a TB prevalence survey in Zambia and South Africa. METHODOLOGY: This was a cross-sectional analysis of clinical data of participants from the TREATS TB prevalence survey conducted in 21 communities in Zambia and South Africa. The study included individuals aged ≥ 15 years who had high CAD4TB scores (score ≥ 70), but had no bacteriologically confirmed TB in any of the samples submitted, were not on TB treatment, and had no history of TB. Two consultant radiologists reviewed the images for non-TB abnormalities. RESULTS: Of the 525 CXRs reviewed, 46.7% (245/525) images were reported to have non-TB abnormalities. About 11.43% (28/245) images had multiple non-TB abnormalities, while 88.67% (217/245) had a single non-TB abnormality. The readers had a fair inter-rater agreement (r = 0.40). Based on anatomical location, non-TB abnormalities in the lung parenchyma (19%) were the most prevalent, followed by Pleura (15.4%), then heart & great vessels (6.1%) abnormalities. Pleural effusion/thickening/calcification (8.8%) and cardiomegaly (5%) were the most prevalent non-TB abnormalities. Prevalence of (2.7%) for pneumonia not typical of pulmonary TB and (2.1%) mass/nodules (benign/ malignant) were also reported. CONCLUSION: A wide range of non-TB abnormalities can be identified on digital CXRs among individuals with high CAD4TB scores but don't have bacteriologically confirmed TB. Adaptation of AI systems like CAD4TB as a tool to simultaneously identify other causes of abnormal CXRs alongside TB can be interesting and useful in non-faculty-based screening programs to better link cases to appropriate care.

Asunto(s)

RESUMEN

BACKGROUND AND OBJECTIVE: The global market for AI systems used in lung tuberculosis (TB) detection has expanded significantly in recent years. Verifying their performance across diverse settings is crucial before medical organisations can invest in them and pursue safe, wide-scale deployment. The goal of this research was to synthesise the clinical evidence for the diagnostic accuracy of certified AI products designed for screening TB in chest X-rays (CXRs) compared to a microbiological reference standard. METHODS: Four databases were searched between June to September 2022. Data concerning study methodology, system characteristics, and diagnostic accuracy metrics was extracted and summarised. Study bias was evaluated using QUADAS-2 and by examining sources of funding. Forest plots for diagnostic odds ratio (DOR) and summary receiver operating characteristic (SROC) curves were constructed for the AI products individually and collectively. RESULTS: 10 out of 3642 studies satisfied the review criteria however only 8 were subject to meta-analysis following bias assessment. Three AI products were evaluated with a 95 % confidence interval producing the following pooled estimates for accuracy rankings: qXR v2 (sensitivity of 0.944 [0.887-0.973], specificity of 0.692 [0.549-0.805], DOR of 3.63 [3.17-4.09], Lunit INSIGHT CXR v3.1 (sensitivity of 0.853 [0.787-0.901], specificity of 0.646 [0.627-0.665], DOR of 2.37 [1.96-2.78]), and CAD4TB v3.07 (sensitivity of 0.917 [0.848-0.956], specificity of 0.371 [0.336-0.408], DOR of 1.91 [1.4-2.47]). Overall, the products had a sensitivity of 0.903 (0.859-0.934), specificity of 0.526 (0.409-0.641), and DOR of 2.31 (1.78-2.84). CONCLUSION: Current publicly available evidence indicates considerable variability in the diagnostic accuracy of available AI products although overall they have high sensitivity and modest specificity which is improving with time. These preliminary results are limited by the small number of studies and poor coverage for low TB burden settings. More research is needed to expand the clinical evidence base for the performance of AI products.

Asunto(s)