Volatilome and Single-Lead Electrocardiogram Optimize Ischemic Heart Disease Diagnosis Using Machine Learning Models

I.M. Sechenov First Moscow State Medical University80 enrolled

Overview

This is a prospective, case-control, single-center, observational, non-randomized study. It is designed to evaluate the diagnostic accuracy of functional tests involving physical exertion monitored via a 12-lead ECG, combined with analysis of exhaled breath volatile organic compounds (VOCs) and single-lead ECG parameters.

The planned number of participants to include in the study is 80, admitted to the University Clinical Hospitals No. 1, at the I.M. Sechenov First Moscow State Medical University of the Ministry of Health of the Russian Federation (Sechenov University). The study includes the following stages: 1. Participants will be selected according to inclusion and exclusion criteria; 2. Work with medical documentation; 3. Instrumental and laboratory examinations of the participants: 3.1. Analysis of exhaled air will be carried out with the Compact PTR-MS instrument manufactured by Ionicon (Austria) (analytical device), registration certificate No. (C16)07/C05. 3.2. All the participants will undergo a single blood sampling during the day of performing the study, a blood test, 10 ml from a peripheral vein to determine the level of total cholesterol, low-density lipoprotein (LDL), very low-density lipoprotein (VLDL), high-density lipoprotein (HDL), triglycerides, C-reactive protein (CRP), lipoprotein a, apolipoprotein B, and interleukin-6 (IL-6). 3.3. Both groups will perform a bicycle ergometry test (on a SCHILLER c200 device) to evaluate the response to physical activity. 3.4. Before and immediately after the exercise test, all patients are scheduled to record a single-lead ECG and pulse wave, using a portable single-lead recorder (Cardio-Qvark) (Russia, Moscow). 4.5. Stress computed tomography myocardial perfusion imaging (CTP) with a vasodilation test using adenosine triphosphate on a CT device with 640 slices (Canon; Aquilion One Genesis) will be performed. After completion of the instrumental and laboratory analysis, a statistical analysis will be conducted using classical statistics and machine learning methods, including gradient boosting.

Study Type

OBSERVATIONAL

Enrollment

Conditions

Coronary Artery Disease

Interventions

Mass spectrometry using the PTR TOF-1000 (IONICON PTR-TOF-MS - Trace VOC Analyzer, Eduard-Bodem-Gasse 3, 6020 Innsbruck, Austria (Europe).DIAGNOSTIC_TEST

Once enrolled in the study, all participants are scheduled to undergo the following tests: Analysis of the exhaled breath volatile organic compounds using real-time analytical methods (PTR-TOF-MS-1000; real-time mass spectrometer with ionization by the proton transfer method) before and after the physical exertion test, during 1 minute. Machine learning models will be employed to analyze the patterns identified in the exhaled air volatilome data. Before and immediately after the physical exertion test, all participants are scheduled to record a single-lead ECG and pulse wave for 3 minutes, using a portable single-lead recorder (Cardio-Qvark) (Russia, Moscow). Single-lead ECG and pulse wave parameters will be analyzed using machine learning models.

Eligibility

Sex: ALLMin age: 40 YearsHealthy volunteers:

Medical Language ↔ Plain English

Inclusion Criteria: 1. Age ≥40 years; 2. Absence of acute exacerbations of psychiatric disorders or cognitive impairments that would preclude study participation; 3. Provision of written informed consent for study participation, blood sample collection, and anonymous publication of research results; 4. Pre-test probability of ischemic heart disease between 1% and 33%. Non-inclusion criteria: 1. Pregnancy and breastfeeding; 2. Diabetes mellitus; 3. Presence of acute myocardial ischemia (acute coronary syndrome or myocardial infarction within the preceding 48 hours) or a history of myocardial infarction; 4. Active infectious or non-infectious inflammatory diseases in the acute/exacerbation phase; 5. Connective tissue diseases (regardless of disease activity); 6. Respiratory disorders (e.g., bronchial asthma, chronic bronchitis, cystic fibrosis, or other conditions associated with significant respiratory dysfunction); 7. Acute pulmonary thromboembolism involving the pulmonary artery or its branches; 8. Aortic dissection; 9. Hemodynamically significant decompensated cardiac valvular defects\*\*; 10. Active malignancy; 11. Decompensated chronic heart failure (NYHA class III-IV) or acute heart failure; 12. Neurological disorders (e.g., Parkinson's disease, multiple sclerosis, acute psychosis, Guillain-Barré syndrome); 13. Cardiac arrhythmias or conduction abnormalities contraindicating stress testing; 14. Musculoskeletal disorders precluding exercise testing (e.g., bicycle ergometry); 15. Allergy to radiocontrast agents and/or adenosine triphosphate (ATP); 16. Chronic kidney disease with an estimated glomerular filtration rate (eGFR) \<30 mL/min/1.73 m² (CKD-EPI formula); 17. Severe hepatic insufficiency and/or Child-Pugh class B or C liver cirrhosis. Exclusion Criteria: 1. Poor recording quality of single-channel electrocardiogram (ECG) and/or plethysmography data; 2. Failure to complete the stress test due to reasons unrelated to cardiac conditions; 3. Voluntary withdrawal of consent to continue participation in the study; 4. Post-enrollment development of conditions or identification of pathologies listed in the exclusion criteria.

Outcomes

Primary Outcomes

Diagnostic Accuracy (AUC, Sensitivity, Specificity, NPV, PPV) of the Stress-ECG Test in Ischemic Heart Disease

Assessing the diagnostic accuracy of the stress electrocardiography test in ischemic heart disease

Time frame: The study was completed on 10.06.2024; the outcome measure was assessed during 6 months for the stress electrocardiography test

Diagnostic Accuracy (AUC, Sensitivity, Specificity, NPV, PPV) of Exhaled Breath Analysis for Ischemic Heart Disease

Analyze the volatile organic compounds of the exhaled breath in individuals with stress-induced myocardial perfusion defect on stress computed tomography myocardial perfusion imaging (CTP) with vasodilation test (adenosine triphosphate) and compare them with individuals without stress-induced myocardial perfusion defect after a physical stress test, and compare them with rest results as independent variables. Machine learning model was used to assess the diagnostic accuracy of the exhaled breath in the diagnosis of ischemic heart disease

Time frame: The study was completed on 10.06.2024; the outcome measure was assessed during 6 months for the obtained volatilome data.

Diagnostic Accuracy (AUC, Sensitivity, Specificity, NPV, PPV) of Single-Lead ECG With Pulse Wave Analysis in Ischemic Heart Disease

Analyze the parameters of the single-lead electrocardiogram with pulse wave function in individuals with stress-induced myocardial perfusion defect on stress computed tomography myocardial perfusion imaging (CTP) with vasodilation test and compare them with individuals without stress-induced myocardial perfusion defect as an independent variable. Machine learning model was used to assess the diagnostic accuracy of the single-lead ECG with pulse wave function in the diagnosis of ischemic heart disease.

Time frame: The study was completed on 10.06.2024; the outcome measure was assessed during 6 months for the single lead ECG parameters with pulse wave function

Changes in the Concentration of Total Cholesterol, TG (mmol/L), LDL (mmol/L), LDL (mmol/L), HDL (mmol/L), and VLDL (mmol/L) in Individuals With Stress-induced Myocardial Perfusion Defect vs. Without.

Analyzing the taken blood samples for total cholesterol, TG (mmol/L), LDL (mmol/L), LDL (mmol/L), HDL (mmol/L), and VLDL (mmol/L) in individuals with stress-induced myocardial perfusion defect on stress computed tomography myocardial perfusion imaging (CTP) with vasodilation test and comparing them with individuals without stress-induced myocardial perfusion defect as independent variables.

Time frame: The study was completed on 10.06.2024; the outcome measure was assessed during 1 week for the total cholesterol, TG (mmol/L), LDL (mmol/L), LDL (mmol/L), HDL (mmol/L), and VLDL (mmol/L) data.

Changes in the Concentration of Apolipoprotein B (g/L) in Individuals With Stress-induced Myocardial Perfusion Defect vs. Without.

Analyzing the taken blood samples for Apolipoprotein B (g/L) in individuals with stress-induced myocardial perfusion defect on stress computed tomography myocardial perfusion imaging (CTP) with vasodilation test and comparing them with individuals without stress-induced myocardial perfusion defect as independent variables.

Time frame: The study was completed on 10.06.2024; the outcome measure was assessed during 1 week for the Apolipoprotein В (g/L) data.

Changes in the Concentration of Lipoprotein (а) (mg/L) and c-RP (mg/L) in Individuals With Stress-induced Myocardial Perfusion Defect vs. Without.

Analyzing the taken blood samples for lipoprotein (a) (mg/L) and C-RP (mg/L) in individuals with stress-induced myocardial perfusion defect on stress computed tomography myocardial perfusion imaging (CTP) with vasodilation test and comparing them with individuals without stress-induced myocardial perfusion defect as independent variables.

Time frame: The study was completed on 10.06.2024; the outcome measure was assessed during 1 week for the lipoprotein (а) (mg/L) and c-RP (mg/L) data.

Changes in the Concentration of IL- 6 (pg/mL) in Individuals With Stress-induced Myocardial Perfusion Defect vs. Without.

Analyzing the taken blood samples for IL-6 (pg/mL) in individuals with stress-induced myocardial perfusion defect on stress computed tomography myocardial perfusion imaging (CTP) with vasodilation test and comparing them with individuals without stress-induced myocardial perfusion defect as independent variables.

Time frame: The study was completed on 10.06.2024; the outcome measure was assessed during 1 week for the IL- 6 (pg/mL) data.