A Multi-Task Group Bi-LSTM Networks Application on Electrocardiogram Classification

Identification of drug use degree by integrating multi-modal features with dual-input deep learning method

Most of studies on drug use degree are based on subjective judgments without objective quantitative assessment, in this paper, a dual-input bimodal fusion algorithm is proposed to study drug use degree by using electroencephalogram (EEG) and near-infrared spectroscopy (NIRS). Firstly, this paper uses the optimized dual-input multi-modal TiCBnet for extracting the deep encoding features of the bimodal signal, then fuses and screens the features using different methods, and finally fused deep encoding features are classified. The classification accuracy of bimodal is found to be higher than that of single modal, and the classification accuracy is up to 89.9%.

MELEP: A Novel Predictive Measure of Transferability in Multi-label ECG Diagnosis

In practical electrocardiography (ECG) interpretation, the scarcity of well-annotated data is a common challenge. Transfer learning techniques are valuable in such situations, yet the assessment of transferability has received limited attention. To tackle this issue, we introduce MELEP, which stands for Muti-label Expected Log of Empirical Predictions, a measure designed to estimate the effectiveness of knowledge transfer from a pre-trained model to a downstream multi-label ECG diagnosis task. MELEP is generic, working with new target data with different label sets, and computationally efficient, requiring only a single forward pass through the pre-trained model. To the best of our knowledge, MELEP is the first transferability metric specifically designed for multi-label ECG classification problems. Our experiments show that MELEP can predict the performance of pre-trained convolutional and recurrent deep neural networks, on small and imbalanced ECG data. Specifically, we observed strong correlation coefficients (with absolute values exceeding 0.6 in most cases) between MELEP and the actual average F1 scores of the fine-tuned models. Our work highlights the potential of MELEP to expedite the selection of suitable pre-trained models for ECG diagnosis tasks, saving time and effort that would otherwise be spent on fine-tuning these models.

Meta Learning With Graph Attention Networks for Low-Data Drug Discovery

Finding candidate molecules with favorable pharmacological activity, low toxicity, and proper pharmacokinetic properties is an important task in drug discovery. Deep neural networks have made impressive progress in accelerating and improving drug discovery. However, these techniques rely on a large amount of label data to form accurate predictions of molecular properties. At each stage of the drug discovery pipeline, usually, only a few biological data of candidate molecules and derivatives are available, indicating that the application of deep neural networks for low-data drug discovery is still a formidable challenge. Here, we propose a meta learning architecture with graph attention network, Meta-GAT, to predict molecular properties in low-data drug discovery. The GAT captures the local effects of atomic groups at the atom level through the triple attentional mechanism and implicitly captures the interactions between different atomic groups at the molecular level. GAT is used to perceive molecular chemical environment and connectivity, thereby effectively reducing sample complexity. Meta-GAT further develops a meta learning strategy based on bilevel optimization, which transfers meta knowledge from other attribute prediction tasks to low-data target tasks. In summary, our work demonstrates how meta learning can reduce the amount of data required to make meaningful predictions of molecules in low-data scenarios. Meta learning is likely to become the new learning paradigm in low-data drug discovery. The source code is publicly available at: https://github.com/lol88/Meta-GAT.

Diagnosing the benign paroxysmal positional vertigo via 1D and deep-learning composite model

BACKGROUND

Benign Paroxysmal Positional Vertigo (BPPV) is the leading cause of vertigo, and its characteristic nystagmus induced by positional maneuvers makes it a good model for Artificial Intelligence (AI) diagnosis. However, during the testing procedure, up to 10 min of indivisible long-range temporal correlation data are produced, making the AI-informed real-time diagnosing unlikely in clinical practice.

METHODS

A combined 1D and Deep-Learning (DL) composite model was proposed. Two separate cohorts were recruited, with one for model generation and the other for evaluation of model's real-world generalizability. Eight features, including two head traces and three eye traces and their corresponding slow phase velocity (SPV) value, were served as the inputs. Three candidate models were tested, and a sensitivity study was conducted to determine the saliently important features.

RESULTS

The study included 2671 patients in the training cohort and 703 in the test cohort. A hybrid DL model achieved a micro-area under the receiver operating curve (AUROC) of 0.982 (95% CI 0.965, 0.994) and macro-AUROC of 0.965 (95% CI 0.898, 0.999) for overall classification. The highest accuracy was observed for right posterior BPPV, with an AUROC of 0.991 (95% CI 0.972, 1.000), followed by left posterior BPPV, with an AUROC of 0.979 (95% CI 0.940, 0.998), the lowest AUROC was 0.928 (95% CI 0.878, 0.966) for lateral BPPV. The SPV was consistently identified as the most predictive feature in the models. If the model process is carried out 100 times for a 10-min data, one single running takes 0.79 ± 0.06 s.

CONCLUSION

This study designed DL models which can accurately detect and categorize the subtype of BPPV, enabling a quick and straightforward diagnosis of BPPV in clinical setting. The critical feature identified in the model helps expand our understanding of this disorder.

A CNN-RNN unified framework for intrapartum cardiotocograph classification

BACKGROUND AND OBJECTIVE

Prenatal fetal monitoring, which can monitor the growth and health of the fetus, is very vital for pregnant women before delivery. During pregnancy, it is crucial to judge whether the fetus is abnormal, which helps obstetricians carry out early intervention to avoid fetal hypoxia and even death. At present, clinical fetal monitoring widely used fetal heart rate monitoring equipment. Fetal heart rate and uterine contraction signals obtained by fetal heart monitoring equipment are important information to evaluate fetal health status.

METHODS

This paper is based on 1D-CNN (One Dimension Convolutional Neural Network) and GRU (Gate Recurrent Unit). We preprocess the obtained data and enhances them, to make the proportion of number of instances in different class in the training set is same.

RESULTS

In model performance evaluation, standard evaluation indicators are used, such as accuracy, sensitivity, specificity, and ROC (receiver operating characteristic). Finally, the accuracy of our model in the test set is 95.15%, the sensitivity is 96.20%, and the specificity is 94.09%.

CONCLUSIONS

In fetal heart rate monitoring, this paper proposes a 1D-CNN and bidirectional GRU hybrid models, and the fetal heart rate and uterine contraction signals given by monitoring are used as input feature to classify the fetal health status. The results show that our approach is effective in evaluating fetal health status and can assists obstetricians in clinical decision-making. And provide a baseline for the introduction of 1D-CNN and bidirectional GRU hybrid models into the evaluation of fetal health status.

Classification of IHC Images of NATs With ResNet-FRP-LSTM for Predicting Survival Rates of Rectal Cancer Patients

BACKGROUND

Over a decade, tissues dissected adjacent to primary tumors have been considered "normal" or healthy samples (NATs). However, NATs have recently been discovered to be distinct from both tumorous and normal tissues. The ability to predict the survival rate of cancer patients using NATs can open a new door to selecting optimal treatments for cancer and discovering biomarkers.

METHODS

This paper introduces an artificial intelligence (AI) approach that uses NATs for predicting the 5-year survival of pre-operative radiotherapy patients with rectal cancer. The new approach combines pre-trained deep learning, nonlinear dynamics, and long short-term memory to classify immunohistochemical images of RhoB protein expression on NATs.

RESULTS

Ten-fold cross-validation results show 88% accuracy of prediction obtained from the new approach, which is also higher than those provided from baseline methods.

CONCLUSION

Preliminary results not only add objective evidence to recent findings of NATs' molecular characteristics using state-of-the-art AI methods, but also contribute to the discovery of RhoB expression on NATs in rectal-cancer patients.

CLINICAL IMPACT

The ability to predict the survival rate of cancer patients is extremely important for clinical decision-making. The proposed AI tool is promising for assisting oncologists in their treatments of rectal cancer patients.

Fully Automatic Classification of Cardiotocographic Signals with 1D-CNN and Bi-directional GRU

Prenatal fetal monitoring, which can monitor the growth and health of the fetus, is vital for pregnant women before delivery. During pregnancy, it is essential to classify whether the fetus is abnormal, which helps physicians carry out early intervention to avoid fetal heart hypoxia and even death. Fetal heart rate and uterine contraction signals obtained by fetal heart monitoring equipment are essential to estimate fetal health status. In this paper, we pre-process the obtained data set and enhance them using Hermite interpolation on the abnormal classification in the samples. We use the 1D-CNN and GRU hybrid models to extract the abstract features of fetal heart rate and uterine contraction signals. Several evaluation metrics are used for evaluation, and the accuracy is 96 %, while the sensitivity is 95 %, and the specificity is 96 %. The experiments show the effectiveness of the proposed method, which can provide physicians and users with more stable, efficient, and convenient diagnosis and decision support.

Prediction and Diagnosis of Respiratory Disease by Combining Convolutional Neural Network and Bi-directional Long Short-Term Memory Methods

Objective

Based on the respiratory disease big data platform in southern Xinjiang, we established a model that predicted and diagnosed chronic obstructive pulmonary disease, bronchiectasis, pulmonary embolism and pulmonary tuberculosis, and provided assistance for primary physicians.

Methods

The method combined convolutional neural network (CNN) and long-short-term memory network (LSTM) for prediction and diagnosis of respiratory diseases. We collected the medical records of inpatients in the respiratory department, including: chief complaint, history of present illness, and chest computed tomography. Pre-processing of clinical records with “jieba” word segmentation module, and the Bidirectional Encoder Representation from Transformers (BERT) model was used to perform word vectorization on the text. The partial and total information of the fused feature set was encoded by convolutional layers, while LSTM layers decoded the encoded information.

Results

The precisions of traditional machine-learning, deep-learning methods and our proposed method were 0.6, 0.81, 0.89, and F1 scores were 0.6, 0.81, 0.88, respectively.

Conclusion

Compared with traditional machine learning and deep-learning methods that our proposed method had a significantly higher performance, and provided precise identification of respiratory disease.