RESUMO
OBJECTIVES: Anti-thrombotic therapy is the basis of thrombosis prevention and treatment. Bleeding is the main adverse event of anti-thrombosis. Existing laboratory indicators cannot accurately reflect the real-time coagulation function. It is necessary to develop tools to dynamically evaluate the risk and benefits of anti-thrombosis to prescribe accurate anti-thrombotic therapy. METHODS: The prediction model,daily prediction of bleeding risk in ICU patients treated with anti-thrombotic therapy, was built using deep learning algorithm recurrent neural networks, and the model results and performance were compared with clinicians. RESULTS: There was no significant statistical discrepancy in the baseline. ROC curves of the four models in the validation and test set were drawn, respectively. One-layer GRU of the validation set had a larger AUC (0.9462; 95%CI, 0.9147-0.9778). Analysis was conducted in the test set, and the ROC curve showed the superiority of two layers LSTM over one-layer GRU, while the former AUC was 0.8391(95%CI, 0.7786-0.8997). One-layer GRU in the test set possessed a better specificity (sensitivity 0.5942; specificity 0.9300). The Fleiss' k of junior clinicians, senior clinicians, and machine learning classifiers is 0.0984, 0.4562, and 0.8012, respectively. CONCLUSIONS: Recurrent neural networks were first applied for daily prediction of bleeding risk in ICU patients treated with anti-thrombotic therapy. Deep learning classifiers are more reliable and consistent than human classifiers. The machine learning classifier suggested strong reliability. The deep learning algorithm significantly outperformed human classifiers in prediction time.
Assuntos
Algoritmos , Redes Neurais de Computação , Humanos , Reprodutibilidade dos Testes , Laboratórios , Unidades de Terapia IntensivaRESUMO
Mycoplasma pneumonia may lead to hospitalizations and pose life-threatening risks in children. The automated identification of mycoplasma pneumonia from electronic medical records holds significant potential for improving the efficiency of hospital resource allocation. In this study, we proposed a novel method for identifying mycoplasma pneumonia by integrating multi-modal features derived from both free-text descriptions and structured test data in electronic medical records. Our approach begins with the extraction of free-text and structured data from clinical records through a systematic preprocessing pipeline. Subsequently, we employ a pre-trained transformer language model to extract features from the free-text, while multiple additive regression trees are used to transform features from the structured data. An attention-based fusion mechanism is then applied to integrate these multi-modal features for effective classification. We validated our method using clinic records of 7157 patients, retrospectively collected for training and testing purposes. The experimental results demonstrate that our proposed multi-modal fusion approach achieves significant improvements over other methods across four key performance metrics.
Assuntos
Registros Eletrônicos de Saúde , Pneumonia por Mycoplasma , Humanos , Pneumonia por Mycoplasma/diagnóstico , Registros Eletrônicos de Saúde/estatística & dados numéricos , Criança , Estudos Retrospectivos , Mycoplasma pneumoniae/patogenicidade , Feminino , Masculino , Pré-EscolarRESUMO
Background: Community-acquired pneumonia is one of the most common infectious diseases in children and is a leading cause of death among children under 5 years of age, resulting in high rates of antibiotic usage and hospitalization. It is of extremely practical significance to make full use of the existing electronic medical records to study pneumonia and to establish automatic diagnosis models for pneumonia. Methods: We established pneumonia diagnosis models of Bayesian network using a total of 13,448 electronic medical records. We investigated learning network structure and parameter estimation and evaluated different structure learning strategies and various modeling methods. By identifying the key predictors of model, the pneumonia status was analyzed. Results: The performance of the proposed Bayesian network was evaluated using a set of 3361 cases with a precision of 0.7861, a recall of 0.9889, and an F1-score of 0.8759. On an independent external validation set containing 4925 cases, Bayesian network achieved a precision of 0.7382, a recall of 0.9947, and an F1-score of 0.8475. Our proposed Bayesian network outperformed all other methods, including CatBoost, XGBoost, LightGBM, logistic regression, and ridge classification. Conclusion: The appropriate feature selection improved the performance of Bayesian networks. The proposed Bayesian network had good generalizability and could be directly applied to clinical research centers. And the key predictors identified by the network demonstrated good clinical interpretability, allowing for a better understanding of pneumonia status and complications. This study had important clinical value and practical significance for the research and diagnosis of pediatric pneumonia.
RESUMO
Secundum atrial septal defect (ASD) is one of the most common congenital heart diseases (CHDs). This study aims to evaluate the feasibility and accuracy of automatic detection of ASD in children based on color Doppler echocardiographic images using convolutional neural networks. In this study, we propose a fully automatic detection system for ASD, which includes three stages. The first stage is used to identify four target echocardiographic views (that is, the subcostal view focusing on the atrium septum, the apical four-chamber view, the low parasternal four-chamber view, and the parasternal short-axis view). These four echocardiographic views are most useful for the diagnosis of ASD clinically. The second stage aims to segment the target cardiac structure and detect candidates for ASD. The third stage is to infer the final detection by utilizing the segmentation and detection results of the second stage. The proposed ASD detection system was developed and validated using a training set of 4,031 cases containing 370,057 echocardiographic images and an independent test set of 229 cases containing 203,619 images, of which 105 cases with ASD and 124 cases with intact atrial septum. Experimental results showed that the proposed ASD detection system achieved accuracy, recall, precision, specificity, and F1 score of 0.8833, 0.8545, 0.8577, 0.9136, and 0.8546, respectively on the image-level averages of the four most clinically useful echocardiographic views. The proposed system can automatically and accurately identify ASD, laying a good foundation for the subsequent artificial intelligence diagnosis of CHDs.
RESUMO
Standard echocardiographic view recognition is a prerequisite for automatic diagnosis of congenital heart defects (CHDs). This study aims to evaluate the feasibility and accuracy of standard echocardiographic view recognition in the diagnosis of CHDs in children using convolutional neural networks (CNNs). A new deep learning-based neural network method was proposed to automatically and efficiently identify commonly used standard echocardiographic views. A total of 367,571 echocardiographic image slices from 3,772 subjects were used to train and validate the proposed echocardiographic view recognition model where 23 standard echocardiographic views commonly used to diagnose CHDs in children were identified. The F1 scores of a majority of views were all ≥0.90, including subcostal sagittal/coronal view of the atrium septum, apical four-chamber view, apical five-chamber view, low parasternal four-chamber view, sax-mid, sax-basal, parasternal long-axis view of the left ventricle (PSLV), suprasternal long-axis view of the entire aortic arch, M-mode echocardiographic recording of the aortic (M-AO) and the left ventricle at the level of the papillary muscle (M-LV), Doppler recording from the mitral valve (DP-MV), the tricuspid valve (DP-TV), the ascending aorta (DP-AAO), the pulmonary valve (DP-PV), and the descending aorta (DP-DAO). This study provides a solid foundation for the subsequent use of artificial intelligence (AI) to identify CHDs in children.