Computers in biology and medicine最新文献

Background: Preoperative and noninvasive detection of isocitrate dehydrogenase (IDH) and telomerase reverse transcriptase gene promoter (TERTp) mutations in glioma is critical for prognosis and treatment planning. This study aims to develop deep learning classifiers to identify IDH and TERTp mutations using proton magnetic resonance spectroscopy (¹H-MRS) and a one-dimensional convolutional neural network (1D-CNN) architecture.

Methods: This study included ¹H-MRS data from 225 adult patients with hemispheric diffuse glioma (117 IDH mutants and 108 IDH wild-type; 99 TERTp mutants and 100 TERTp wild-type). The spectra were processed using the LCModel, and multiple deep learning models, including a baseline, a deep-shallow network, and an attention deep-shallow network (ADSN), were trained to classify mutational subgroups of gliomas. The Gradient-weighted Class Activation Mapping (Grad-CAM) technique was used to interpret the models' decision-making process.

Results: The ADSN model was the most effective for IDH mutation detection, achieving F1-scores of 93 % on the validation set and 88 % on the test set. For TERTp mutation detection, the ADSN model achieved F1-scores of 80 % in the validation set and 81 % in the test set, whereas TERTp-only gliomas were detected with F1-scores of 88 % in the validation set and 86 % in the test set using the same architecture.

Conclusion: Deep learning models accurately predicted the IDH and TERTp mutational subgroups of hemispheric diffuse gliomas by extracting relevant information from ¹H-MRS spectra without the need for manual feature extraction.

Tiny machine learning (TinyML) and edge intelligence have emerged as pivotal paradigms for enabling machine learning on resource-constrained devices situated at the extreme edge of networks. In this paper, we explore the transformative potential of TinyML in facilitating pervasive, low-power cardiovascular monitoring and real-time analytics for patients with cardiac anomalies, leveraging wearable devices as the primary interface. To begin with, we provide an overview of TinyML software and hardware enablers, accompanied by an examination of networking solutions such as Low-power Wide area network (LPWAN) that facilitate the seamless deployment of TinyML frameworks. Following this, we delve into the methodologies of knowledge distillation, quantization, and pruning, which represent the cornerstone strategies for optimizing machine learning models to operate efficiently within resource-constrained environments. Furthermore, our discussion extends to the role of efficient deep neural networks tailored specifically for cardiovascular monitoring on wearable devices with limited computational resources. Through a comprehensive review, we analyze the applications of prominent artificial neural network architectures including Convolutional Neural Networks (CNNs), Autoencoders, Deep Belief Networks (DBNs), and Transformers in the domain of Electrocardiogram (ECG) analytics, shedding light on their efficacy and potential in advancing healthcare technology.

This study highlights the importance of evaluating warfarin dosing in diabetic patients, who require careful anticoagulation management. With rising rates of diabetes and cardiovascular diseases, understanding the factors influencing warfarin therapy is vital for improving patient outcomes and reducing adverse events. Data was sourced from the IWPC dataset, examining characteristics such as age, gender, diabetes status, indication for warfarin, weight, and height. We utilized the Bidirectional Encoder Representations from Transformers (BERT) model to analyze therapeutic doses, leveraging its ability to understand contextual relationships in the data. A machine learning approach was essential for predicting appropriate warfarin dosages, employing algorithms like Random Forest, KNN, MLP, Linear Regression, and SVM classification. We allocated 20 % of the data for testing and 80 % for training. Results showed that Linear Regression performed less effectively than MLP, KNN, SVM, and Random Forest in both training and testing. Notably, Random Forest's training MAE was significantly lower, while the other models showed similar performance in predicting warfarin dosages. This study emphasizes the importance of personalized anticoagulation management for diabetic patients on warfarin. The application of the BERT model alongside machine learning algorithms, particularly Random Forest, demonstrated effectiveness in predicting appropriate dosages. These findings suggest that integrating these advanced models into clinical practice can enhance decision-making, optimize patient outcomes, and reduce adverse events.