Convolutional neural networks predict the onset of paroxysmal atrial fibrillation: Theory and applications

Efficient electrocardiogram generation based on cardiac electric vector simulation model

This study introduces a novel Cardiac Electric Vector Simulation Model (CEVSM) to address the computational inefficiencies and low fidelity of traditional electrophysiological models in generating electrocardiograms (ECGs). Our approach leverages CEVSM to efficiently produce reliable ECG samples, facilitating data augmentation essential for the computer-aided diagnosis of myocardial infarction (MI). Significantly, experimental results show that our model dramatically reduces computation time compared to conventional models, with the self-adapting regression transformation matrix method (SRTM) providing clear advantages. SRTM not only achieves high fidelity in ECG simulations but also ensures exceptional consistency with the gold standard method, greatly enhancing MI localization accuracy by data augmentation. These advancements highlight the potential of our model to generate dependable ECG training samples, making it highly suitable for data augmentation and significantly advancing the development and validation of intelligent MI diagnostic systems. Furthermore, this study demonstrates the feasibility of applying life system simulations in the training of medical big models.

Localization and phenotyping of tuberculosis bacteria using a combination of deep learning and SVMs

Successful treatment of pulmonary tuberculosis (TB) depends on early diagnosis and careful monitoring of treatment response. Identification of acid-fast bacilli by fluorescence microscopy of sputum smears is a common tool for both tasks. Microscopy-based analysis of the intracellular lipid content and dimensions of individual Mycobacterium tuberculosis (Mtb) cells also describe phenotypic changes which may improve our biological understanding of antibiotic therapy for TB. However, fluorescence microscopy is a challenging, time-consuming and subjective procedure. In this work, we automate examination of fields of view (FOVs) from microscopy images to determine the lipid content and dimensions (length and width) of Mtb cells. We introduce an adapted variation of the UNet model to efficiently localising bacteria within FOVs stained by two fluorescence dyes; auramine O to identify Mtb and LipidTox Red to identify intracellular lipids. Thereafter, we propose a feature extractor in conjunction with feature descriptors to extract a representation into a support vector multi-regressor and estimate the length and width of each bacterium. Using a real-world data corpus from Tanzania, the proposed method i) outperformed previous methods for bacterial detection with a 8% improvement (Dice coefficient) and ii) estimated the cell length and width with a root mean square error of less than 0.01%. Our network can be used to examine phenotypic characteristics of Mtb cells visualised by fluorescence microscopy, improving consistency and time efficiency of this procedure compared to manual methods.

Infant death prediction using machine learning: A population-based retrospective study

BACKGROUND

Despite declines in infant death rates in recent decades in the United States, the national goal of reducing infant death has not been reached. This study aims to predict infant death using machine-learning approaches.

METHODS

A population-based retrospective study of live births in the United States between 2016 and 2021 was conducted. Thirty-three factors related to birth facility, prenatal care and pregnancy history, labor and delivery, and newborn characteristics were used to predict infant death.

RESULTS

XGBoost demonstrated superior performance compared to the other four compared machine learning models. The original imbalanced dataset yielded better results than the balanced datasets created through oversampling procedures. The cross-validation of the XGBoost-based model consistently achieved high performance during both the pre-pandemic (2016-2019) and pandemic (2020-2021) periods. Specifically, the XGBoost-based model performed exceptionally well in predicting neonatal death (AUC: 0.98). The key predictors of infant death were identified as gestational age, birth weight, 5-min APGAR score, and prenatal visits. A simplified model based on these four predictors resulted in slightly inferior yet comparable performance to the all-predictor model (AUC: 0.91 vs. 0.93). Furthermore, the four-factor risk classification system effectively identified infant deaths in 2020 and 2021 for high-risk (88.7%-89.0%), medium-risk (4.6%-5.4%), and low-risk groups (0.1), outperforming the risk screening tool based on accumulated risk factors.

CONCLUSIONS

XGBoost-based models excel in predicting infant death, providing valuable prognostic information for perinatal care education and counselling. The simplified four-predictor classification system could serve as a practical alternative for infant death risk prediction.

MSCDA: Multi-level semantic-guided contrast improves unsupervised domain adaptation for breast MRI segmentation in small datasets

Deep learning (DL) applied to breast tissue segmentation in magnetic resonance imaging (MRI) has received increased attention in the last decade, however, the domain shift which arises from different vendors, acquisition protocols, and biological heterogeneity, remains an important but challenging obstacle on the path towards clinical implementation. In this paper, we propose a novel Multi-level Semantic-guided Contrastive Domain Adaptation (MSCDA) framework to address this issue in an unsupervised manner. Our approach incorporates self-training with contrastive learning to align feature representations between domains. In particular, we extend the contrastive loss by incorporating pixel-to-pixel, pixel-to-centroid, and centroid-to-centroid contrasts to better exploit the underlying semantic information of the image at different levels. To resolve the data imbalance problem, we utilize a category-wise cross-domain sampling strategy to sample anchors from target images and build a hybrid memory bank to store samples from source images. We have validated MSCDA with a challenging task of cross-domain breast MRI segmentation between datasets of healthy volunteers and invasive breast cancer patients. Extensive experiments show that MSCDA effectively improves the model's feature alignment capabilities between domains, outperforming state-of-the-art methods. Furthermore, the framework is shown to be label-efficient, achieving good performance with a smaller source dataset. The code is publicly available at https://github.com/ShengKuangCN/MSCDA.

Accurate detection of paroxysmal atrial fibrillation with certified-GAN and neural architecture search

This paper presents a novel machine learning framework for detecting PxAF, a pathological characteristic of electrocardiogram (ECG) that can lead to fatal conditions such as heart attack. To enhance the learning process, the framework involves a generative adversarial network (GAN) along with a neural architecture search (NAS) in the data preparation and classifier optimization phases. The GAN is innovatively invoked to overcome the class imbalance of the training data by producing the synthetic ECG for PxAF class in a certified manner. The effect of the certified GAN is statistically validated. Instead of using a general-purpose classifier, the NAS automatically designs a highly accurate convolutional neural network architecture customized for the PxAF classification task. Experimental results show that the accuracy of the proposed framework exhibits a high value of 99.0% which not only enhances state-of-the-art by up to 5.1%, but also improves the classification performance of the two widely-accepted baseline methods, ResNet-18, and Auto-Sklearn, by [Formula: see text] and [Formula: see text].

End-to-end fatigue driving EEG signal detection model based on improved temporal-graph convolution network

Fatigue driving is one of the leading causes of traffic accidents, so fatigue driving detection technology plays a crucial role in road safety. The physiological information-based fatigue detection methods have the advantage of objectivity and accuracy. Among many physiological signals, EEG signals are considered to be the most direct and promising ones. Most traditional methods are challenging to train and do not meet real-time requirements. To this end, we propose an end-to-end temporal and graph convolution-based (MATCN-GT) fatigue driving detection algorithm. The MATCN-GT model consists of a multi-scale attentional temporal convolutional neural network block (MATCN block) and a graph convolutional-Transformer block (GT block). Among them, the MATCN block extracts features directly from the original EEG signal without a priori information, and the GT block processes the features of EEG signals between different electrodes. In addition, we design a multi-scale attention module to ensure that valuable information on electrode correlations will not be lost. We add a Transformer module to the graph convolutional network, which can better capture the dependencies between long-distance electrodes. We conduct experiments on the public dataset SEED-VIG, and the accuracy of the MATCN-GT model reached 93.67%, outperforming existing algorithms. Furthermore, compared with the traditional graph convolutional neural network, the GT block has improved the accuracy rate by 3.25%. The accuracy of the MATCN block on different subjects is higher than the existing feature extraction methods.