1
|
Marzoog BA, Chomakhidze P, Gognieva D, Silantyev A, Suvorov A, Abdullaev M, Mozzhukhina N, Filippova DA, Kostin SV, Kolpashnikova M, Ershova N, Ushakov N, Mesitskaya D, Kopylov P. Development and validation of a machine learning model for diagnosis of ischemic heart disease using single-lead electrocardiogram parameters. World J Cardiol 2025; 17:104396. [PMID: 40308623 PMCID: PMC12038698 DOI: 10.4330/wjc.v17.i4.104396] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/19/2024] [Revised: 02/19/2025] [Accepted: 03/31/2025] [Indexed: 04/21/2025] Open
Abstract
BACKGROUND Ischemic heart disease (IHD) impacts the quality of life and has the highest mortality rate of cardiovascular diseases globally. AIM To compare variations in the parameters of the single-lead electrocardiogram (ECG) during resting conditions and physical exertion in individuals diagnosed with IHD and those without the condition using vasodilator-induced stress computed tomography (CT) myocardial perfusion imaging as the diagnostic reference standard. METHODS This single center observational study included 80 participants. The participants were aged ≥ 40 years and given an informed written consent to participate in the study. Both groups, G1 (n = 31) with and G2 (n = 49) without post stress induced myocardial perfusion defect, passed cardiologist consultation, anthropometric measurements, blood pressure and pulse rate measurement, echocardiography, cardio-ankle vascular index, bicycle ergometry, recording 3-min single-lead ECG (Cardio-Qvark) before and just after bicycle ergometry followed by performing CT myocardial perfusion. The LASSO regression with nested cross-validation was used to find the association between Cardio-Qvark parameters and the existence of the perfusion defect. Statistical processing was performed with the R programming language v4.2, Python v.3.10 [^R], and Statistica 12 program. RESULTS Bicycle ergometry yielded an area under the receiver operating characteristic curve of 50.7% [95% confidence interval (CI): 0.388-0.625], specificity of 53.1% (95%CI: 0.392-0.673), and sensitivity of 48.4% (95%CI: 0.306-0.657). In contrast, the Cardio-Qvark test performed notably better with an area under the receiver operating characteristic curve of 67% (95%CI: 0.530-0.801), specificity of 75.5% (95%CI: 0.628-0.88), and sensitivity of 51.6% (95%CI: 0.333-0.695). CONCLUSION The single-lead ECG has a relatively higher diagnostic accuracy compared with bicycle ergometry by using machine learning models, but the difference was not statistically significant. However, further investigations are required to uncover the hidden capabilities of single-lead ECG in IHD diagnosis.
Collapse
Affiliation(s)
- Basheer Abdullah Marzoog
- World-Class Research Center Digital Biodesign and Personalized Healthcare, I.M. Sechenov First Moscow State Medical University (Sechenov University), 8-2 Trubetskaya Street, 119991, Moscow, Russia.
| | - Peter Chomakhidze
- World-Class Research Center Digital Biodesign and Personalized Healthcare, I.M. Sechenov First Moscow State Medical University (Sechenov University), 8-2 Trubetskaya Street, 119991, Moscow, Russia
| | - Daria Gognieva
- World-Class Research Center Digital Biodesign and Personalized Healthcare, I.M. Sechenov First Moscow State Medical University (Sechenov University), 8-2 Trubetskaya Street, 119991, Moscow, Russia
| | - Artemiy Silantyev
- World-Class Research Center Digital Biodesign and Personalized Healthcare, I.M. Sechenov First Moscow State Medical University (Sechenov University), 8-2 Trubetskaya Street, 119991, Moscow, Russia
| | - Alexander Suvorov
- World-Class Research Center Digital Biodesign and Personalized Healthcare, I.M. Sechenov First Moscow State Medical University (Sechenov University), 8-2 Trubetskaya Street, 119991, Moscow, Russia
| | - Magomed Abdullaev
- World-Class Research Center Digital Biodesign and Personalized Healthcare, I.M. Sechenov First Moscow State Medical University (Sechenov University), 8-2 Trubetskaya Street, 119991, Moscow, Russia
| | - Natalia Mozzhukhina
- University Clinical Hospital Number 1, Cardiology Department, I.M. Sechenov First Moscow State Medical University (Sechenov University), 8-2 Trubetskaya Street, 119991, Moscow, Russia
| | | | | | - Maria Kolpashnikova
- Undergraduate Medical School student, Sechenov University, Moscow 119991, Moskva, Russia
| | - Natalya Ershova
- Undergraduate Medical School student, Sechenov University, Moscow 119991, Moskva, Russia
| | - Nikolay Ushakov
- Undergraduate Medical School student, Sechenov University, Moscow 119991, Moskva, Russia
| | - Dinara Mesitskaya
- University Clinical Hospital Number 1, Cardiology Department, I.M. Sechenov First Moscow State Medical University (Sechenov University), 8-2 Trubetskaya Street, 119991, Moscow, Russia
| | - Philipp Kopylov
- World-Class Research Center Digital Biodesign and Personalized Healthcare, I.M. Sechenov First Moscow State Medical University (Sechenov University), 8-2 Trubetskaya Street, 119991, Moscow, Russia
| |
Collapse
|
2
|
Stuart S, de Kok M, O’Searcoid B, Morrisroe H, Serban IB, Jagers F, Dulos R, Houben S, van de Peppel L, van den Brand J. Critical Design Considerations for Longer-Term Wear and Comfort of On-Body Medical Devices. Bioengineering (Basel) 2024; 11:1058. [PMID: 39593718 PMCID: PMC11591458 DOI: 10.3390/bioengineering11111058] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/19/2024] [Revised: 10/03/2024] [Accepted: 10/09/2024] [Indexed: 11/28/2024] Open
Abstract
The commercialization of a growing number of wearable devices has been enabled within recent years due to the availability of miniaturized sensor modalities, the development of new materials, and the scalability of flexible electronics. With the increase in resource shortages within healthcare, there is a demand to translate wearable devices from the commercial consumer stand-point to the medical field. Clinical-grade signal quality, wearability, and comfort all need to be tailored to a wearable design. Wear and comfort for user compliance and durability for longer-term use are commonly overlooked. In this study, the relationship of on-body location and material layer composition is investigated. Five non-woven medical tapes noted for longer wear time are tested over a 7-day timeframe. The impact of material properties, such as elasticity, isotropy, and hysteresis, as well as the moisture vapor transmission rate (MVTR) and adhesive thickness, are evaluated in relation to skin properties on the lower torso of 30, high-activity-level volunteers. User perception was quantified via Likert-scale questionnaires and images were obtained for the material-skin interaction. The results indicate that critical characteristics, such as MVTR and elasticity, noted for positive skin interaction in commercial products, may not translate to improved user perception and durability over time. Future work will assess new design options to manipulate material properties for improved wear and comfort.
Collapse
Affiliation(s)
- Shavini Stuart
- TNO, Holst Centre, High Tech Campus 31, 5656AE Eindhoven, The Netherlands
| | - Margreet de Kok
- TNO, Holst Centre, High Tech Campus 31, 5656AE Eindhoven, The Netherlands
| | - Ben O’Searcoid
- TNO, Holst Centre, High Tech Campus 31, 5656AE Eindhoven, The Netherlands
| | - Hannah Morrisroe
- TNO, Holst Centre, High Tech Campus 31, 5656AE Eindhoven, The Netherlands
| | - Irina Bianca Serban
- Industrial Design and Artificial Intelligence Systems Institute, Eindhoven University of Technology, 5612AZ Eindhoven, The Netherlands
| | - Ferry Jagers
- TNO, Healthy Living, Sylviusweg 71, 2333BE Leiden, The Netherlands
| | - Remon Dulos
- TNO, Healthy Living, Sylviusweg 71, 2333BE Leiden, The Netherlands
| | - Steven Houben
- Industrial Design and Artificial Intelligence Systems Institute, Eindhoven University of Technology, 5612AZ Eindhoven, The Netherlands
| | | | | |
Collapse
|
3
|
Starling JAK, Haahr-Raunkjaer C, Rasmussen SS, Ekenberg L, Loft FC, Meyhoff CS, Aasvang EK. Wireless continuous single-lead ST-segment monitoring to detect new-onset myocardial injury at the general ward-An exploratory subanalysis. Acta Anaesthesiol Scand 2024; 68:681-692. [PMID: 38425057 DOI: 10.1111/aas.14391] [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: 11/05/2023] [Revised: 01/11/2024] [Accepted: 02/04/2024] [Indexed: 03/02/2024]
Abstract
Patients admitted for acute medical conditions and major noncardiac surgery are at risk of myocardial injury. This is frequently asymptomatic, especially in the context of concomitant pain and analgesics, and detection thus relies on cardiac biomarkers. Continuous single-lead ST-segment monitoring from wireless electrocardiogram (ECG) may enable more timely intervention, but criteria for alerts need to be defined to reduce false alerts. This study aimed to determine optimal ST-deviation thresholds from wireless single-lead ECG for detection of myocardial injury following major abdominal cancer surgery and during acute exacerbation of chronic obstructive pulmonary disease. Patients were monitored with a wireless single-lead ECG patch for up to 4 days and had daily troponin measurements. Single-lead ST-segment deviations of <0.255 mV and/or >0.245 mV (based on previous study comparison with 0.1 mV 12-lead ECG and variation in single-lead ECG) were analyzed for relation to myocardial injury defined as hsTnT elevation of 20-64 ng/L with an absolute change of ≥5 ng/L, or a hsTnT level ≥ 65 ng/L. In total, 528 patients were included for analysis, of which 15.5% had myocardial injury. For corrected ST-thresholds lasting ≥10 and ≥ 20 min, we found specificities of 91% and 94% and sensitivities of 17% and 13% with odds ratios of 2.0 (95% CI: 1.1; 3.9) and 2.4 (95% CI: 1.1; 5.1) for myocardial injury. In conclusion, wireless single-lead ECG monitoring with corrected ST thresholds detected patients developing myocardial injury with specificities >90% and sensitivities <20%, suggesting increased focus on sensitivity improvement.
Collapse
Affiliation(s)
- Jonathan Attilla Koefoed Starling
- Department of Anesthesiology, Centre for Cancer and Organ Diseases, Copenhagen University Hospital-Rigshospitalet, Copenhagen, Denmark
| | - Camilla Haahr-Raunkjaer
- Department of Anesthesiology, Centre for Cancer and Organ Diseases, Copenhagen University Hospital-Rigshospitalet, Copenhagen, Denmark
| | - Søren S Rasmussen
- Department of Health Technology, Technical University of Denmark, Lyngby, Denmark
| | - Luna Ekenberg
- Department of Anesthesiology, Centre for Cancer and Organ Diseases, Copenhagen University Hospital-Rigshospitalet, Copenhagen, Denmark
| | - Frederik Cornelius Loft
- Department of Anaesthesia and Intensive Care, Copenhagen University Hospital-Bispebjerg and Frederiksberg Hospital, Copenhagen, Denmark
| | - Christian Sylvest Meyhoff
- Department of Health Technology, Technical University of Denmark, Lyngby, Denmark
- Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark
| | - Eske Kvanner Aasvang
- Department of Anesthesiology, Centre for Cancer and Organ Diseases, Copenhagen University Hospital-Rigshospitalet, Copenhagen, Denmark
- Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark
| |
Collapse
|