Feature Selection Techniques for a Machine Learning Model to Detect Autonomic Dysreflexia

Improving the Automated Diagnosis of Breast Cancer with Mesh Reconstruction of Ultrasound Images Incorporating 3D Mesh Features and a Graph Attention Network

This study proposes a novel approach for breast tumor classification from ultrasound images into benign and malignant by converting the region of interest (ROI) of a 2D ultrasound image into a 3D representation using the point-e system, allowing for in-depth analysis of underlying characteristics. Instead of relying solely on 2D imaging features, this method extracts 3D mesh features that describe tumor patterns more precisely. Ten informative and medically relevant mesh features are extracted and assessed with two feature selection techniques. Additionally, a feature pattern analysis has been conducted to determine the feature's significance. A feature table with dimensions of 445 × 12 is generated and a graph is constructed, considering the rows as nodes and the relationships among the nodes as edges. The Spearman correlation coefficient method is employed to identify edges between the strongly connected nodes (with a correlation score greater than or equal to 0.7), resulting in a graph containing 56,054 edges and 445 nodes. A graph attention network (GAT) is proposed for the classification task and the model is optimized with an ablation study, resulting in the highest accuracy of 99.34%. The performance of the proposed model is compared with ten machine learning (ML) models and one-dimensional convolutional neural network where the test accuracy of these models ranges from 73 to 91%. Our novel 3D mesh-based approach, coupled with the GAT, yields promising performance for breast tumor classification, outperforming traditional models, and has the potential to reduce time and effort of radiologists providing a reliable diagnostic system.

A Comparative Analysis of XGBoost and Neural Network Models for Predicting Some Tomato Fruit Quality Traits from Environmental and Meteorological Data

The tomato as a raw material for processing is globally important and is pivotal in dietary and agronomic research due to its nutritional, economic, and health significance. This study explored the potential of machine learning (ML) for predicting tomato quality, utilizing data from 48 cultivars and 28 locations in Hungary over 5 seasons. It focused on °Brix, lycopene content, and colour (a/b ratio) using extreme gradient boosting (XGBoost) and artificial neural network (ANN) models. The results revealed that XGBoost consistently outperformed ANN, achieving high accuracy in predicting °Brix (R² = 0.98, RMSE = 0.07) and lycopene content (R² = 0.87, RMSE = 0.61), and excelling in colour prediction (a/b ratio) with a R² of 0.93 and RMSE of 0.03. ANN lagged behind particularly in colour prediction, showing a negative R² value of -0.35. Shapley additive explanation's (SHAP) summary plot analysis indicated that both models are effective in predicting °Brix and lycopene content in tomatoes, highlighting different aspects of the data. SHAP analysis highlighted the models' efficiency (especially in °Brix and lycopene predictions) and underscored the significant influence of cultivar choice and environmental factors like climate and soil. These findings emphasize the importance of selecting and fine-tuning the appropriate ML model for enhancing precision agriculture, underlining XGBoost's superiority in handling complex agronomic data for quality assessment.

Advancing spinal cord injury care through non-invasive autonomic dysreflexia detection with AI

This paper presents an AI-powered solution for detecting and monitoring Autonomic Dysreflexia (AD) in individuals with spinal cord injuries. Current AD detection methods are limited, lacking non-invasive monitoring systems. We propose a model that combines skin nerve activity (SKNA) signals with a deep neural network (DNN) architecture to overcome this limitation. The DNN is trained on a meticulously curated dataset obtained through controlled colorectal distension, inducing AD events in rats with spinal cord surgery above the T6 level. The proposed system achieves an impressive average classification accuracy of 93.9% ± 2.5%, ensuring accurate AD identification with high precision (95.2% ± 2.1%). It demonstrates a balanced performance with an average F1 score of 94.4% ± 1.8%, indicating a harmonious balance between precision and recall. Additionally, the system exhibits a low average false-negative rate of 4.8% ± 1.6%, minimizing the misclassification of non-AD cases. The robustness and generalizability of the system are validated on unseen data, maintaining high accuracy, F1 score, and a low false-negative rate. This AI-powered solution represents a significant advancement in non-invasive, real-time AD monitoring, with the potential to improve patient outcomes and enhance AD management in individuals with spinal cord injuries. This research contributes a promising solution to the critical healthcare challenge of AD detection and monitoring.

Electrocardiogram-based biometrics for user identification - Using your heartbeat as a digital key

External biometrics such as thumbprint and facial recognition have become standard tools for securing our digital devices and protecting our data. These systems, however, are potentially prone to copying and cybercrime access. Researchers have therefore explored internal biometrics, such as the electrical patterns within an electrocardiogram (ECG). The heart's electrical signals carry sufficient distinctiveness to allow the ECG to be used as an internal biometric for user authentication and identification. Using the ECG in this way has many potential advantages and limitations. This article reviews the history of ECG biometrics and explores some of the technical and security considerations. It also explores current and future uses of the ECG as an internal biometric.

Time and frequency domain analysis of physiological features during autonomic dysreflexia after spinal cord injury

Introduction

Autonomic dysreflexia (AD) affects about 70% of individuals with spinal cord injury (SCI) and can have severe consequences, including death if not promptly detected and managed. The current gold standard for AD detection involves continuous blood pressure monitoring, which can be inconvenient. Therefore, a non-invasive detection device would be valuable for rapid and continuous AD detection.

Methods

Implanted rodent models were used to analyze autonomic dysreflexia after spinal cord injury. Skin nerve activity (SKNA) features were extracted from ECG signals recorded non-invasively, using ECG electrodes. At the same time, blood pressure and ECG data sampled was collected using an implanted telemetry device. Heart rate variability (HRV) features were extracted from these ECG signals. SKNA and HRV parameters were analyzed in both the time and frequency domain.

Results

We found that SKNA features showed an increase approximately 18 seconds before the typical rise in systolic blood pressure, indicating the onset of AD in a rat model with upper thoracic SCI. Additionally, low-frequency components of SKNA in the frequency domain were dominant during AD, suggesting their potential inclusion in an AD detection system for improved accuracy.

Discussion

Utilizing SKNA measurements could enable early alerts to individuals with SCI, allowing timely intervention and mitigation of the adverse effects of AD, thereby enhancing their overall well-being and safety.

PseU-ST: A new stacked ensemble-learning method for identifying RNA pseudouridine sites

Background: Pseudouridine (Ψ) is one of the most abundant RNA modifications found in a variety of RNA types, and it plays a significant role in many biological processes. The key to studying the various biochemical functions and mechanisms of Ψ is to identify the Ψ sites. However, identifying Ψ sites using experimental methods is time-consuming and expensive. Therefore, it is necessary to develop computational methods that can accurately predict Ψ sites based on RNA sequence information. Methods: In this study, we proposed a new model called PseU-ST to identify Ψ sites in Homo sapiens (H. sapiens), Saccharomyces cerevisiae (S. cerevisiae), and Mus musculus (M. musculus). We selected the best six encoding schemes and four machine learning algorithms based on a comprehensive test of almost all of the RNA sequence encoding schemes available in the iLearnPlus software package, and selected the optimal features for each encoding scheme using chi-square and incremental feature selection algorithms. Then, we selected the optimal feature combination and the best base-classifier combination for each species through an extensive performance comparison and employed a stacking strategy to build the predictive model. Results: The results demonstrated that PseU-ST achieved better prediction performance compared with other existing models. The PseU-ST accuracy scores were 93.64%, 87.74%, and 89.64% on H_990, S_628, and M_944, respectively, representing increments of 13.94%, 6.05%, and 0.26%, respectively, higher than the best existing methods on the same benchmark training datasets. Conclusion: The data indicate that PseU-ST is a very competitive prediction model for identifying RNA Ψ sites in H. sapiens, M. musculus, and S. cerevisiae. In addition, we found that the Position-specific trinucleotide propensity based on single strand (PSTNPss) and Position-specific of three nucleotides (PS3) features play an important role in Ψ site identification. The source code for PseU-ST and the data are obtainable in our GitHub repository (https://github.com/jluzhangxinrubio/PseU-ST).