Support Vector Machine-Based Classification of Vasovagal Syncope Using Head-Up Tilt Test

Convolutional neural network-based method for the real-time detection of reflex syncope during head-up tilt test

BACKGROUND AND OBJECTIVES

Reflex syncope (RS) is the most common type of syncope caused by dysregulation of the autonomic nervous system. Diagnosing RS typically involves the head-up tilt test (HUTT), which tracks physiological signals such as blood pressure and electrocardiograms during postural changes. However, the HUTT is time-consuming and may trigger RS symptoms in patients. Therefore, a real-time monitoring system for RS risk assessment is necessary to enhance medical efficiency and patient convenience. Although several methods have been developed, most depend on manually extracted features from physiological signals, making them susceptible to feature extraction methods and signal noise.

METHODS

This study introduces a deep learning-based method for real-time RS detection. This method removes the need for manually extracted features by employing an end-to-end architecture consisting of residual and squeeze-and-excitation blocks. The likelihood of RS occurrence was quantified using the proposed method by analyzing a raw blood pressure signal.

RESULTS

Data from 1348 patients (1291 normal and 57 with RS) were used to develop and evaluate the proposed method. The area under the receiver operating characteristic curve was 0.972 for RS detection using ten-fold cross-validation. A threshold between zero and one can adjust the performance characteristics of the proposed method. At a threshold of 0.75, the method achieved sensitivity and specificity values of 94.74 and 94.27 %, respectively. Notably, the technique detected RS 165.35 s before its occurrence, on average.

CONCLUSIONS

The proposed method outperformed conventional methods in RS detection. In addition to its excellent detection performance, this method only requires blood pressure monitoring, reducing reliance on the number of input signals and enhancing its applicability compared to procedures that require multiple signals. These advantages contribute to the development of safer, more convenient, and more efficient RS detection systems.

Artificial intelligence-driven intelligent learning models for identification and prediction of cardioneurological disorders: A comprehensive study

The integration of Artificial Intelligence (AI) and Intelligent Learning Models (ILMs) in healthcare has transformed the field, offering precise diagnostics, remote monitoring, personalized treatment, and more. Cardioneurological disorders (CD), affecting the cardiovascular and neurological systems, present significant diagnostic and management challenges. Traditional testing methods often lack sensitivity and specificity, leading to delayed or inaccurate diagnoses. AI-driven ILMs trained on large datasets offer promise for accurate identification and prediction of CD by analyzing complex data patterns. However, there is a lack of comprehensive studies reviewing AI applications for the diagnosis of CD and inter related disorders. This paper comprehensively reviews existing integrated solutions involving AI and ILMs in CD, examining their clinical manifestations, epidemiology, diagnostic challenges, and therapeutic considerations. The study examines recent research on CD, reviews AI-driven models' landscape, evaluates existing models, addresses practical considerations, and outlines future research directions. Through this work, we aim to provide insights into the transformative potential of AI-driven ILMs in improving clinical practice and patient outcomes for CD.

Can Artificial Intelligence Enhance Syncope Management?: A JACC: Advances Multidisciplinary Collaborative Statement

Syncope, a form of transient loss of consciousness, remains a complex medical condition for which adverse cardiovascular outcomes, including death, are of major concern but rarely occur. Current risk stratification algorithms have not completely delineated which patients benefit from hospitalization and specific interventions. Patients are often admitted unnecessarily and at high cost. Artificial intelligence (AI) and machine learning may help define the transient loss of consciousness event, diagnose the cause, assess short- and long-term risks, predict recurrence, and determine need for hospitalization and therapeutic intervention; however, several challenges remain, including medicolegal and ethical concerns. This collaborative statement, from a multidisciplinary group of clinicians, investigators, and scientists, focuses on the potential role of AI in syncope management with a goal to inspire creation of AI-derived clinical decision support tools that may improve patient outcomes, streamline diagnostics, and reduce health-care costs.

Quantitative Complexity Theory (QCT) in Integrative Analysis of Cardiovascular Hemodynamic Response to Posture Change

The explanation of physiological mechanisms involved in adaptation of the cardiovascular system to intrinsic and environmental demands is crucial for both basic science and clinical research. Computational algorithms integrating multivariable data that comprehensively depict complex mechanisms of cardiovascular reactivity are currently being intensively researched. Quantitative Complexity Theory (QCT) provides quantitative and holistic information on the state of multi-functional dynamic systems. The present paper aimed to describe the application of QCT in an integrative analysis of the cardiovascular hemodynamic response to posture change. Three subjects that underwent head-up tilt testing under beat-by-beat hemodynamic monitoring (impedance cardiography) were discussed in relation to the complexity trends calculated using QCT software. Complexity has been shown to be a sensitive marker of a cardiovascular hemodynamic response to orthostatic stress and vasodilator administration, and its increase has preceded changes in standard cardiovascular parameters. Complexity profiling has provided a detailed assessment of individual hemodynamic patterns of syncope. Different stimuli and complexity settings produce results of different clinical usability.

Diversity of Hemodynamic Reactive Profiles across Persons—Psychosocial Implications for Personalized Medicine

This study analyzed the individual differences in hemodynamic time patterns and reactivity to cognitive and emotional tasks, and explored the diversity of psycho-physiological profiles that could be used for the personalized prediction of different diseases. An analysis of heart rate (HR)—blood pressure (BP) relationship patterns across time using cross-correlations (CCs) during a logical-mathematical task and a task recalling negative emotions (rumination) was carried out in a laboratory setting on 45 participants. The results showed maximum HR–BP CCs during the mathematical task significantly more positive than the maximum HR–BP CCs during the rumination task. Furthermore, our results showed a large variety of hemodynamic reactivity profiles across the participants, even when carrying out the same tasks. The most frequent type showed positive HR–BP CCs under cognitive activity, and several positive–negative HR–BP CCs cycles under negative emotional activity. In general terms, our results supported the main hypothesis. We observed some distinct time-based “coordination strategies” in the reactivity of the autonomic nervous system under emotional vs. cognitive loading. Overall, large individual, as well as situational, specificities in hemodynamic reactivity time patterns were seen. The possible relationships between this variety of profiles and different psychosocial characteristics, and the potential for integrative predictive health within the provision of highly personalized medicine, are discussed.

Identification of Type 2 Diabetes Based on a Ten-Gene Biomarker Prediction Model Constructed Using a Support Vector Machine Algorithm

Background

Type 2 diabetes is a major health concern worldwide. The present study is aimed at discovering effective biomarkers for an efficient diagnosis of type 2 diabetes.

Methods

Differentially expressed genes (DEGs) between type 2 diabetes patients and normal controls were identified by analyses of integrated microarray data obtained from the Gene Expression Omnibus database using the Limma package. Functional analysis of genes was performed using the R software package clusterProfiler. Analyses of protein-protein interaction (PPI) performed using Cytoscape with the CytoHubba plugin were used to determine the most sensitive diagnostic gene biomarkers for type 2 diabetes in our study. The support vector machine (SVM) classification model was used to validate the gene biomarkers used for the diagnosis of type 2 diabetes.

Results

GSE164416 dataset analysis revealed 499 genes that were differentially expressed between type 2 diabetes patients and normal controls, and these DEGs were found to be enriched in the regulation of the immune effector pathway, type 1 diabetes mellitus, and fatty acid degradation. PPI analysis data showed that five MCODE clusters could be considered as clinically significant modules and that 10 genes (IL1B, ITGB2, ITGAX, COL1A1, CSF1, CXCL12, SPP1, FN1, C3, and MMP2) were identified as “real” hub genes in the PPI network using algorithms such as Degree, MNC, and Closeness. The sensitivity and specificity of the SVM model for identifying patients with type 2 diabetes were 100%, with an area under the curve of 1 in the training as well as the validation dataset.

Conclusion

Our results indicate that the SVM-based model developed by us can facilitate accurate diagnosis of type 2 diabetes.

Diagnosing Neurally Mediated Syncope Using Classification Techniques

Syncope is a medical condition resulting in the spontaneous transient loss of consciousness and postural tone with spontaneous recovery. The diagnosis of syncope is a challenging task, as similar types of symptoms are observed in seizures, vertigo, stroke, coma, etc. The advent of Healthcare 4.0, which facilitates the usage of artificial intelligence and big data, has been widely used for diagnosing various diseases based on past historical data. In this paper, classification-based machine learning is used to diagnose syncope based on data collected through a head-up tilt test carried out in a purely clinical setting. This work is concerned with the use of classification techniques for diagnosing neurally mediated syncope triggered by a number of neurocardiogenic or cardiac-related factors. Experimental results show the effectiveness of using classification-based machine learning techniques for an early diagnosis and proactive treatment of neurally mediated syncope.