1
|
Ferdowsi M, Kwan BH, Tan MP, Saedon NI, Subramaniam S, Abu Hashim NFI, Mohd Nasir SS, Zainal Abidin I, Chee KH, Goh CH. Classification of vasovagal syncope from physiological signals on tilt table testing. Biomed Eng Online 2024; 23:37. [PMID: 38555421 PMCID: PMC10981362 DOI: 10.1186/s12938-024-01229-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/24/2023] [Accepted: 03/06/2024] [Indexed: 04/02/2024] Open
Abstract
BACKGROUND The diagnostic test for vasovagal syncope (VVS), the most common cause of syncope is head-up tilt test (HUTT) assessment. During the test, subjects experienced clinical symptoms such as nausea, sweating, pallor, the feeling of palpitations, being on the verge of passing out, and fainting. The study's goal is to develop an algorithm to classify VVS patients based on physiological signals blood pressure (BP) and electrocardiography (ECG) obtained from the HUTT. METHODS After 10 min of supine rest, the subject was tilted at a 70-degree angle on a tilt table for approximately a total of 35 min. 400 µg of glyceryl trinitrate (GTN) was administered sublingually after the first 20 min and monitoring continued for another 15 min. Mean imputation and K-nearest neighbors (KNN) imputation approaches to handle missing values. Next, feature selection techniques were implemented, including genetic algorithm, recursive feature elimination, and feature importance, to determine the crucial features. The Mann-Whitney U test was then performed to determine the statistical difference between two groups. Patients with VVS are categorized via machine learning models including Support Vector Machine (SVM), Gaussian Naïve Bayes (GNB), Multinomial Naïve Bayes (MNB), KNN, Logistic Regression (LR), and Random Forest (RF). The developed model is interpreted using an explainable artificial intelligence (XAI) model known as partial dependence plot. RESULTS A total of 137 subjects aged between 9 and 93 years were recruited for this study, 54 experienced clinical symptoms were considered positive tests, while the remaining 83 tested negative. Optimal results were obtained by combining the KNN imputation technique and three tilting features with SVM with 90.5% accuracy, 87.0% sensitivity, 92.7% specificity, 88.6% precision, 87.8% F1 score, and 95.4% ROC (receiver operating characteristics) AUC (area under curve). CONCLUSIONS The proposed algorithm effectively classifies VVS patients with over 90% accuracy. However, the study was confined to a small sample size. More clinical datasets are required to ensure that our approach is generalizable.
Collapse
Affiliation(s)
- Mahbuba Ferdowsi
- Department of Mechatronics and Biomedical Engineering, Lee Kong Chian Faculty of Engineering and Science, Universiti Tunku Abdul Rahman, 43000, Kajang, Malaysia
- Centre for Healthcare Science and Technology, Universiti Tunku Abdul Rahman, 43000, Kajang, Malaysia
| | - Ban-Hoe Kwan
- Department of Mechatronics and Biomedical Engineering, Lee Kong Chian Faculty of Engineering and Science, Universiti Tunku Abdul Rahman, 43000, Kajang, Malaysia
- Centre for Healthcare Science and Technology, Universiti Tunku Abdul Rahman, 43000, Kajang, Malaysia
| | - Maw Pin Tan
- Ageing and Age-Associated Disorders Research Group, Department of Medicine, Faculty of Medicine, Universiti Malaya, 50603, Kuala Lumpur, Malaysia
| | - Nor' Izzati Saedon
- Ageing and Age-Associated Disorders Research Group, Department of Medicine, Faculty of Medicine, Universiti Malaya, 50603, Kuala Lumpur, Malaysia
| | - Sukanya Subramaniam
- Cardiorespiratory Laboratories, Universiti Malaya Medical Center, 50603, Petaling Jaya, Malaysia
| | | | - Siti Sakinah Mohd Nasir
- Cardiorespiratory Laboratories, Universiti Malaya Medical Center, 50603, Petaling Jaya, Malaysia
| | - Imran Zainal Abidin
- Department of Cardiology, Department of Medicine, Faculty of Medicine, Universiti Malaya, 50603, Kuala Lumpur, Malaysia
| | - Kok Han Chee
- Department of Cardiology, Department of Medicine, Faculty of Medicine, Universiti Malaya, 50603, Kuala Lumpur, Malaysia
| | - Choon-Hian Goh
- Department of Mechatronics and Biomedical Engineering, Lee Kong Chian Faculty of Engineering and Science, Universiti Tunku Abdul Rahman, 43000, Kajang, Malaysia.
- Centre for Healthcare Science and Technology, Universiti Tunku Abdul Rahman, 43000, Kajang, Malaysia.
| |
Collapse
|
2
|
Orenshtein S, Sheiner E, Sergienko R, Wainstock T. Syncope in pregnancy, immediate pregnancy outcomes, and offspring long-term neurologic health. Am J Obstet Gynecol MFM 2023; 5:101190. [PMID: 37838012 DOI: 10.1016/j.ajogmf.2023.101190] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/03/2023] [Revised: 09/26/2023] [Accepted: 10/09/2023] [Indexed: 10/16/2023]
Abstract
BACKGROUND There are limited data regarding the perinatal consequences of maternal syncope during pregnancy, and even less is known about the potential long-term effect on offspring health. OBJECTIVE This study aimed to examine perinatal outcomes as well as long-term offspring neurologic morbidity associated with prenatal maternal syncope, and the possible differential effect by trimester of first syncope episode. STUDY DESIGN A retrospective cohort study was conducted, including all singleton deliveries occurring between 1991 and 2021 at a large tertiary medical center. Multivariable analyses were applied to study the associations between prenatal maternal syncope and various perinatal outcomes as well as offspring neurologic morbidity up to the age of 18 years, while adjusting for clinically relevant factors. Analyses were further conducted by trimester of first syncope episode. RESULTS The study population included 232,475 pregnancies, 774 (0.3%) were affected by maternal syncope, which most frequently first occurred during the second trimester (44.5%), followed by the first trimester (31.8%) and finally the third trimester (27.7%). Maternal syncope was independently associated with increased risk for intrauterine growth restriction (adjusted odds ratio, 1.52; 95% confidence interval, 1.01-2.29), which appeared to be mainly driven by first trimester syncope occurrence; as well as with increased risk for cesarean delivery (adjusted odds ratio, 1.33; 95% confidence interval, 1.10-1.61), and for long-term offspring neurologic morbidity (adjusted hazard ratio, 1.79; 95% confidence interval, 1.65-2.08), regardless of the trimester of syncope occurrence. CONCLUSION Prenatal maternal syncope is an independent risk factor for intrauterine growth restriction, cesarean delivery, and for long-term offspring neurologic morbidity.
Collapse
Affiliation(s)
- Shani Orenshtein
- Faculty of Health Sciences, Department of Epidemiology, Biostatistics and Community Health Sciences, Ben-Gurion University of the Negev, Beer-Sheva, Israel (Ms Orenshtein, Mr Sergienko, and Dr Wainstock).
| | - Eyal Sheiner
- Department of Obstetrics and Gynecology, Soroka University Medical Center, Ben-Gurion University of the Negev, Beer-Sheva, Israel (Prof Sheiner)
| | - Ruslan Sergienko
- Faculty of Health Sciences, Department of Epidemiology, Biostatistics and Community Health Sciences, Ben-Gurion University of the Negev, Beer-Sheva, Israel (Ms Orenshtein, Mr Sergienko, and Dr Wainstock)
| | - Tamar Wainstock
- Faculty of Health Sciences, Department of Epidemiology, Biostatistics and Community Health Sciences, Ben-Gurion University of the Negev, Beer-Sheva, Israel (Ms Orenshtein, Mr Sergienko, and Dr Wainstock)
| |
Collapse
|
3
|
Longo S, Legramante JM, Rizza S, Federici M. Vasovagal syncope: An overview of pathophysiological mechanisms. Eur J Intern Med 2023; 112:6-14. [PMID: 37030995 DOI: 10.1016/j.ejim.2023.03.025] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/13/2022] [Revised: 03/09/2023] [Accepted: 03/23/2023] [Indexed: 04/10/2023]
Abstract
Syncope is a short-term transient loss of consciousness, characterized by rapid onset and complete spontaneous recovery. According to the 2018 European Society of Cardiology guidelines, three different types of syncope have been identified. However, all forms of syncope share a common final pathophysiological event, global cerebral hypoperfusion, which results from the inability of the circulatory system to maintain blood pressure at the level required to efficiently supply blood to the brain. The vasovagal syncope (VVS) is the most common form of syncope. Although, VVS is generally harmless, its frequent occurrence can negatively affect quality of life and increase the risk of adverse events. The pathophysiological mechanisms underlying VVS remain obscure. The multifaceted nature of VVS presents a veritable challenge to understanding this condition and developing preventative strategies. Thus, the aim of this review was to discuss the factors contributing to the pathogenesis of VVS and provide guidance for future research.
Collapse
Affiliation(s)
- Susanna Longo
- Department of Systems Medicine, University of Rome Tor Vergata, Via Montpellier 1, Rome 00133 ITALY
| | - Jacopo M Legramante
- Department of Systems Medicine, University of Rome Tor Vergata, Via Montpellier 1, Rome 00133 ITALY
| | - Stefano Rizza
- Department of Systems Medicine, University of Rome Tor Vergata, Via Montpellier 1, Rome 00133 ITALY
| | - Massimo Federici
- Department of Systems Medicine, University of Rome Tor Vergata, Via Montpellier 1, Rome 00133 ITALY.
| |
Collapse
|
4
|
Wei WH, Smith M, Vera A, Meads K, Hessell J, Reid L, Scott L, Burge A, Kirwan S, Charlewood R, Sadani D, Walkden D, Chand A. Novel risk patterns of vasovagal reactions in NZ blood donations complicated by COVID-19 restrictions. Front Public Health 2023; 11:1180279. [PMID: 37304099 PMCID: PMC10248232 DOI: 10.3389/fpubh.2023.1180279] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/05/2023] [Accepted: 05/12/2023] [Indexed: 06/13/2023] Open
Abstract
Introduction Vasovagal reactions (VVRs) are common but complex donor adverse reactions (DAEs) in blood donations. VVRs have been extensively studied with a multitude of risk factors identified including young age, female gender and first-time donor status. How they may interplay remains obscure. Methods A total of 1,984,116 blood donations and 27,952 immediate VVRs (iVVRs) and 1,365 delayed VVRs (dVVRs) reported between 2011 and 2021 in NZ were used in multivariate logistic regression analyses each concerning donations with iVVRs as cases and those free of DAEs as controls. For each analysis stepwise selection was used to identify the best model and risk factors carrying significant main effects and/or interactions. Identified interactions informed further in-depth regression analyses to dissect iVVR risk patterns. Results Over 95% of VVRs were iVVRs that had lower female preponderance and deferrals than dVVRs. iVVRs had a school seasonal pattern in whole blood donations driven by first-time donors from schools/colleges, and interactions between gender and age group differentiating the first-time from repeat donations. Subsequent regression analyses identified the known and novel risk factors of year and mobile collection sites and their interactions. iVVR rates were roundly elevated in 2020 and 2021 probably because of COVID-19 restrictions like facemask wearing. Exclusion of the 2020 and 2021 data removed the interactions with year, but confirmed interactions of gender with mobile collection sites (p = 6.2e-07) in first-time donations only and with age group in repeat donations only (p < 2.2e-16), together indicating young female donors at the highest risk of iVVRs. Our results also revealed that donation policy changes contributed to the year effects; donors had a lower iVVR risk at mobile sites than well-medicalized donation centers probably because of under-reporting. Conclusion Modeling statistical interactions is valuable in identifying odds and revealing novel iVVR risk patterns and insights into blood donations.
Collapse
Affiliation(s)
- Wen-Hua Wei
- New Zealand Blood Service, Auckland, New Zealand
- Centre for Biostatistics, Division of Population Health, Health Services Research and Primary Care, The University of Manchester, Manchester, United Kingdom
| | | | - Amber Vera
- New Zealand Blood Service, Auckland, New Zealand
| | - Kelly Meads
- New Zealand Blood Service, Auckland, New Zealand
| | | | - Laura Reid
- New Zealand Blood Service, Auckland, New Zealand
| | - Lisa Scott
- New Zealand Blood Service, Auckland, New Zealand
| | - Asuka Burge
- New Zealand Blood Service, Auckland, New Zealand
| | - Susy Kirwan
- New Zealand Blood Service, Auckland, New Zealand
| | | | | | | | - Anup Chand
- New Zealand Blood Service, Auckland, New Zealand
| |
Collapse
|
5
|
Lopez-Lopez E. Genetics and Epigenetics in Complex Diseases. Int J Mol Sci 2023; 24:ijms24098186. [PMID: 37175893 PMCID: PMC10179620 DOI: 10.3390/ijms24098186] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/13/2023] [Accepted: 04/18/2023] [Indexed: 05/15/2023] Open
Abstract
Many of the most common diseases are influenced by a combination of multiple factors, which include environmental effectors, as well as genetic and epigenetic variations [...].
Collapse
Affiliation(s)
- Elixabet Lopez-Lopez
- Department of Biochemistry and Molecular Biology, University of the Basque Country, UPV/EHU, 48940 Leioa, Spain
- Pediatric Oncology Group, BioCruces Bizkaia Health Research Institute, 48903 Barakaldo, Spain
| |
Collapse
|
6
|
Sun R, Kang Y, Zhang M, Wang H, Shi L, Li X. Development of a nomogram model to predict malignant vasovagal syncope in Chinese children. Front Pediatr 2023; 11:1158537. [PMID: 37077332 PMCID: PMC10109463 DOI: 10.3389/fped.2023.1158537] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/04/2023] [Accepted: 03/17/2023] [Indexed: 04/21/2023] Open
Abstract
Objective Vasovagal syncope (VVS) is the commonest form of syncope, and malignant VVS draws substantial attention due to its life-threatening cardiac asystolic risk. This study aimed to explore the predictive role of a wide panel of clinical indicators for malignant VVS in children, and further to develop a nomogram model. Methods This is a retrospective case-control study. VVS is diagnosed based on head-up tilt test (HUTT). STATA software (version 14.0) was used for statistical analysis, and effect sizes are expressed as odds ratio (OR) and 95% confidence interval (CI). Results Total 370 children with VVS were analyzed, and of them 16 children had malignant VVS. Sixteen malignant VVS and 64 non-malignant VVS were matched on age and sex by a 1:4 propensity scores matching method. Mean corpuscular hemoglobin (MCH) and standard deviation of average RR intervals milliseconds (SDANN) were significantly and independently associated with malignant VVS after adjusting for confounders, with OR reaching 1.437 (95% CI: 1.044 to 1.979; P = 0.026) and 1.035 (95% CI: 1.003 to 1.068; P = 0.029), respectively. Calibration and discrimination analyses revealed that the addition of MCH and SDANN can enhance model performance. Then, a nomogram to predict malignant VVS was developed using general characteristics and two above significant factors, and higher values in medical history, number of syncope, MCH and SDANN were associated with a greater risk of malignant VVS. Conclusion MCH and SDANN were two promising factors for the development of malignant VVS, and modeling of significant factors in a nomogram can provide strong reference to aid clinical decision-making.
Collapse
Affiliation(s)
- Rui Sun
- Department of Cardiology, Children's Hospital Capital Institute of Pediatrics, Beijing, China
- Department of Cardiology, Capital Institute of Pediatrics-Peking University Teaching Hospital, Beijing, China
| | - Yingying Kang
- Department of Cardiology, Children's Hospital Capital Institute of Pediatrics, Beijing, China
- Graduate School of Peking Union Medical College, Capital Institute of Pediatrics, Beijing, China
| | - Mingming Zhang
- Department of Cardiology, Children's Hospital Capital Institute of Pediatrics, Beijing, China
| | - Hongmao Wang
- Department of Cardiology, Children's Hospital Capital Institute of Pediatrics, Beijing, China
| | - Lin Shi
- Department of Cardiology, Children's Hospital Capital Institute of Pediatrics, Beijing, China
| | - Xiaohui Li
- Department of Cardiology, Children's Hospital Capital Institute of Pediatrics, Beijing, China
| |
Collapse
|
7
|
Cheshire WP. The grand challenge of autonomic disorders. Front Neurol 2022; 13:1052137. [PMID: 36388207 PMCID: PMC9663922 DOI: 10.3389/fneur.2022.1052137] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/23/2022] [Accepted: 10/18/2022] [Indexed: 11/05/2022] Open
|
8
|
Vasovagal Syncope Is Associated with Variants in Genes Involved in Neurohumoral Signaling Pathways. Genes (Basel) 2022; 13:genes13091653. [PMID: 36140820 PMCID: PMC9498630 DOI: 10.3390/genes13091653] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/31/2022] [Revised: 09/08/2022] [Accepted: 09/13/2022] [Indexed: 11/25/2022] Open
Abstract
Vasovagal syncope (VVS) is the most common cause of sudden loss of consciousness. VVS results from cerebral hypoperfusion, due to abnormal autonomic control of blood circulation, leading to arterial hypotension. It is a complex disease, and its development is largely associated with genetic susceptibility. Since abnormal neurohumoral regulation plays an important role in VVS development, we analyzed the association of VVS with polymorphic variants of ADRA1A, ADRB1, HTR1A, ADORA2A, COMT, and NOS3 genes, the products of which are involved in neurohumoral signaling, in patients with a confirmed VVS diagnosis (157 subjects) and individuals without a history of syncope (161 subjects). We were able to identify the associations between VVS and alleles/genotypes ADRA1A rs1048101, ADRB1 rs1801253, ADORA2A rs5751876, and COMT rs4680, as well as NOS3 rs2070744 in biallelic combination with COMT rs4680. Thus, we are the first to observe, within a single study, the role of the genes that encode α- and β-adrenergic receptors, catechol-O-methyltransferase, adenosine receptors and nitric oxide synthase in VVS development. These findings demonstrate that the genes involved in neurohumoral signaling pathways contribute to the formation of a genetic susceptibility to VVS.
Collapse
|