Mechanocardiography in the Detection of Acute ST Elevation Myocardial Infarction: The MECHANO-STEMI Study

Koivisto, Tero; Lahdenoja, Olli; Hurnanen, Tero; Vasankari, Tuija; Jaakkola, Samuli; Kiviniemi, Tuomas; Airaksinen, Juhani

doi:10.3390/s22124384

Cited by 10 publications

(5 citation statements)

References 34 publications

(44 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Earlier studies have shown that MCG can detect a wide range of abnormalities in cardiac function caused by myocardial infarction and heart failure (Inan et al 2018, Hossein et al 2019, Mehrang et al 2020, Blomster et al 2021, Morra et al 2021b. In the literature, a supervised machine learning approach was used, and and it is shown that -in line with the present findingsthe strength features in systolic windows were lower in patients with ST elevation myocardial infarction than in control subjects having normal left ventricular function (Koivisto et al 2022b). The clinical precision of these methods for the diagnosis of myocardial infarction or heart failure is, however, limited; inter-individual variation in all signal features is large, resulting in significant overlap between the patient groups and healthy controls, causing a high risk of misclassification for an individual subject.…”

Section: Discussionsupporting

confidence: 83%

Mechanocardiography detects improvement of systolic function caused by resynchronization pacing

Tokmak,

Koivisto,

Lahdenoja

et al. 2023

Physiol. Meas.

Self Cite

View full text Add to dashboard Cite

Objective. Cardiac resynchronization therapy (CRT) is commonly used to manage heart failure with dyssynchronous ventricular contraction. CRT pacing resynchronizes the ventricular contraction, while AAI (single-chamber atrial) pacing does not affect the dyssynchronous function. This study compared waveform characteristics during CRT and AAI pacing at similar pacing rates using seismocardiogram (SCG) and gyrocardiogram (GCG), collectively known as mechanocardiogram (MCG). Approach. We included 10 patients with heart failure with reduced ejection fraction and previously implanted CRT pacemakers. ECG and MCG recordings were taken during AAI and CRT pacing at a heart rate of 80 bpm. Waveform characteristics, including energy, vertical range (amplitude) during systole and early diastole, electromechanical systole (QS2) and left ventricular ejection time (LVET), were derived by considering 6 MCG axes and 3 MCG vectors across frequency ranges of >1 Hz, 20–90 Hz, 6–90 Hz and 1–20 Hz. Main results. Significant differences were observed between CRT and AAI pacing. CRT pacing consistently exhibited higher energy and vertical range during systole compared to AAI pacing (p < 0.05). However, QS2, LVET and waveform characteristics around aortic valve closure did not differ between the pacing modes. Optimal differences were observed in SCG-Y, GCG-X, and GCG-Y axes within the frequency range of 6–90 Hz. Significance. The results demonstrate significant differences in MCG waveforms, reflecting improved mechanical cardiac function during CRT. This information has potential implications for predicting the clinical response to CRT. Further research is needed to explore the differences in signal characteristics between responders and non-responders to CRT.

show abstract

Section: Discussionsupporting

confidence: 83%

Mechanocardiography detects improvement of systolic function caused by resynchronization pacing

Tokmak,

Koivisto,

Lahdenoja

et al. 2023

Physiol. Meas.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this context, various sensors such as ECG, accelerometer, and other sensors were used. For example, in [ 53 , 73 , 104 , 117 , 125 ], the ECG sensors ADAS1001, Shimmer 3, BMD101, ADXL355, and ADS1291 were used in combination with other materials to build a wearable device that collects records used to detect or predict cardiovascular disease. In contrast, the authors in [ 114 ] used the DS18B20 temperature sensor and ADXL1335 accelerometer to develop the desired wearable system.…”

Section: Resultsmentioning

confidence: 99%

Smart Wearables for the Detection of Cardiovascular Diseases: A Systematic Literature Review

Moshawrab

Adda

Bouzouane

et al. 2023

Sensors

View full text Add to dashboard Cite

Background: The advancement of information and communication technologies and the growing power of artificial intelligence are successfully transforming a number of concepts that are important to our daily lives. Many sectors, including education, healthcare, industry, and others, are benefiting greatly from the use of such resources. The healthcare sector, for example, was an early adopter of smart wearables, which primarily serve as diagnostic tools. In this context, smart wearables have demonstrated their effectiveness in detecting and predicting cardiovascular diseases (CVDs), the leading cause of death worldwide. Objective: In this study, a systematic literature review of smart wearable applications for cardiovascular disease detection and prediction is presented. After conducting the required search, the documents that met the criteria were analyzed to extract key criteria such as the publication year, vital signs recorded, diseases studied, hardware used, smart models used, datasets used, and performance metrics. Methods: This study followed the PRISMA guidelines by searching IEEE, PubMed, and Scopus for publications published between 2010 and 2022. Once records were located, they were reviewed to determine which ones should be included in the analysis. Finally, the analysis was completed, and the relevant data were included in the review along with the relevant articles. Results: As a result of the comprehensive search procedures, 87 papers were deemed relevant for further review. In addition, the results are discussed to evaluate the development and use of smart wearable devices for cardiovascular disease management, and the results demonstrate the high efficiency of such wearable devices. Conclusions: The results clearly show that interest in this topic has increased. Although the results show that smart wearables are quite accurate in detecting, predicting, and even treating cardiovascular disease, further research is needed to improve their use.

show abstract

“…Motion artifacts were removed from the signals (SCG, GCG, and ECG) using an automated algorithm. The algorithm was originally developed for a more challenging usage scenario of removing motion artifacts from chest pain (myocardial infarction, STEMI) recordings [30]. It was straightforward to deploy same approach for this study.…”

Section: Motion Artifact Removalmentioning

confidence: 99%

“…Feature extraction was next performed with features that we previously developed in another study: (1) signal strength, (2) amplitudes and time-intervals (e.g., R-peak to AO and AC), and (3) stability within specific signal windows defined using the R-peaks of ECG (e.g., around different heart sounds, S1-S3) [30]. These features-i.e., their Matlab R2017a implementations-had been developed beforehand, so we did not develop new features based on the data we already had.…”

Section: Feature Extractionmentioning

confidence: 99%

Mechanocardiography-Based Measurement System Indicating Changes in Heart Failure Patients during Hospital Admission and Discharge

Koivisto

Lahdenoja

Hurnanen

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

Heart failure (HF) is a disease related to impaired performance of the heart and is a significant cause of mortality and treatment costs in the world. During its progression, HF causes worsening (decompensation) periods which generally require hospital care. In order to reduce the suffering of the patients and the treatment cost, avoiding unnecessary hospital visits is essential, as hospitalization can be prevented by medication. We have developed a data-collection device that includes a high-quality 3-axis accelerometer and 3-axis gyroscope and a single-lead ECG. This allows gathering ECG synchronized data utilizing seismo- and gyrocardiography (SCG, GCG, jointly mechanocardiography, MCG) and comparing the signals of HF patients in acute decompensation state (hospital admission) and compensated condition (hospital discharge). In the MECHANO-HF study, we gathered data from 20 patients, who each had admission and discharge measurements. In order to avoid overfitting, we used only features developed beforehand and selected features that were not outliers. As a result, we found three important signs indicating the worsening of the disease: an increase in signal RMS (root-mean-square) strength (across SCG and GCG), an increase in the strength of the third heart sound (S3), and a decrease in signal stability around the first heart sound (S1). The best individual feature (S3) alone was able to separate the recordings, giving 85.0% accuracy and 90.9% accuracy regarding all signals and signals with sinus rhythm only, respectively. These observations pave the way to implement solutions for patient self-screening of the HF using serial measurements.

show abstract

Mechanocardiography in the Detection of Acute ST Elevation Myocardial Infarction: The MECHANO-STEMI Study

Cited by 10 publications

References 34 publications

Mechanocardiography detects improvement of systolic function caused by resynchronization pacing

Mechanocardiography detects improvement of systolic function caused by resynchronization pacing

Smart Wearables for the Detection of Cardiovascular Diseases: A Systematic Literature Review

Mechanocardiography-Based Measurement System Indicating Changes in Heart Failure Patients during Hospital Admission and Discharge

Contact Info

Product

Resources

About