A Smart Service Platform for Cost Efficient Cardiac Health Monitoring

Faust, Oliver; Lei, Ningrong; Chew, Eng K.; Ciaccio, Edward J.; Acharya, U. Rajendra

doi:10.3390/ijerph17176313

Cited by 29 publications

(15 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast, the heart beats around once a second, producing about one RR interval value per second. The fact that RR interval signals have a 250 times lower data rate when compared to ECG signals leads to significant cost savings when it comes to communication, storage, and processing [46].…”

Section: Discussionmentioning

confidence: 99%

Automated Arrhythmia Detection Based on RR Intervals

Faust

Kareem

Ali³

et al. 2021

Diagnostics

Self Cite

View full text Add to dashboard Cite

Abnormal heart rhythms, also known as arrhythmias, can be life-threatening. AFIB and AFL are examples of arrhythmia that affect a growing number of patients. This paper describes a method that can support clinicians during arrhythmia diagnosis. We propose a deep learning algorithm to discriminate AFIB, AFL, and NSR RR interval signals. The algorithm was designed with data from 4051 subjects. With 10-fold cross-validation, the algorithm achieved the following results: ACC = 99.98%, SEN = 100.00%, and SPE = 99.94%. These results are significant because they show that it is possible to automate arrhythmia detection in RR interval signals. Such a detection method makes economic sense because RR interval signals are cost-effective to measure, communicate, and process. Having such a cost-effective solution might lead to widespread long-term monitoring, which can help detecting arrhythmia earlier. Detection can lead to treatment, which improves outcomes for patients.

show abstract

Section: Discussionmentioning

confidence: 99%

Automated Arrhythmia Detection Based on RR Intervals

Faust

Kareem

Ali³

et al. 2021

Diagnostics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Previously, eAuthentication using BankID has been used to collect signed informed consent as reported by Nilsson et al [ 3 ]. Very recently, BankID has been used to access eHealth platforms, mostly in psychiatric studies, as well as in lifestyle change programs for patients with diabetes and other diseases [ 10 - 12 ]. However, this study used eAuthentication in the context of a total digital protocol to improve adherence, representative distribution of participants, and speed of the recruitment process.…”

Section: Discussionmentioning

confidence: 99%

Improving Efficiency of Clinical Studies Using a Total Digital Approach: Prospective Observational Study

Schenck‐Gustafsson¹,

Carnlöf²,

Jensen‐Urstad³

et al. 2021

JMIR Form Res

View full text Add to dashboard Cite

Background In general, most clinical studies have long recruitment periods. Signing the informed consent is particularly time-consuming when the participant must meet physically with the researchers. Therefore, introducing fully web-based techniques with the use of eAuthentication (BankID) and new digital electrocardiogram (ECG) monitoring could speed up inclusion time, increase adherence, and also reach out to more remote regions. Objective The objectives of this study were to explore whether inclusion of a large number of participants could be realized quickly by using a total digital approach both for information and signing of informed consent, along with ECG monitoring and instant feedback on a mobile device. We also explored whether this approach can increase adherence in registration of ECG recordings and answering questionnaires, and if it would result in a more geographically uniform distribution of participants covering a wide age span. Methods Women with palpitations were intensively studied over 2 months by means of a handheld ECG monitoring device (Coala Heart Monitor). The device connects to a smartphone or tablet, which allows the participants to obtain the results immediately. Recruitment, study information, and signing the informed consent form with the help of BankID were performed in a completely digital manner. Results Between March and May 2018, 2424 women indicated their interest in participating in the study. On June 19, 2018, presumptive participants were invited to log in and register. After 25 days, 1082 women were included in the study; among these, 1020 women fulfilled the inclusion criteria, 913 of whom completed all phases of the study: recording ECG using the handheld device, completion of the prestudy questionnaires, and completion of the poststudy questionnaires 2 months after the ECG recordings. The dropout rate was 9%. In total, 101,804 ECG recordings were made. The mean age was 56 (SD 11) years (range 21-88 years) and 35 participants were 75 years or older. The participants were evenly distributed between living in the countryside and in cities. Conclusions Total digital inclusion recruitment of 1082 participants was achieved in only 25 days, and resulted in a good geographical distribution, excellent adherence, and ability to reach a vast age span, including elderly women. Studies using a total digital design would be particularly appealing during a pandemic since physical contact should be avoided as much as possible. Trial Registration ISRCTN Registry ISRCTN22495299; http://www.isrctn.com/ISRCTN22495299

show abstract

“…We used service design principles to analyse and structure the AF detection problem [ 24 , 25 ]. First, we considered the needs of all stakeholders affected by the proposed service [ 26 ].…”

Section: Methodsmentioning

confidence: 99%

Hybrid Decision Support to Monitor Atrial Fibrillation for Stroke Prevention

Lei

Kareem

Moon

et al. 2021

IJERPH

Self Cite

View full text Add to dashboard Cite

In this paper, we discuss hybrid decision support to monitor atrial fibrillation for stroke prevention. Hybrid decision support takes the form of human experts and machine algorithms working cooperatively on a diagnosis. The link to stroke prevention comes from the fact that patients with Atrial Fibrillation (AF) have a fivefold increased stroke risk. Early diagnosis, which leads to adequate AF treatment, can decrease the stroke risk by 66% and thereby prevent stroke. The monitoring service is based on Heart Rate (HR) measurements. The resulting signals are communicated and stored with Internet of Things (IoT) technology. A Deep Learning (DL) algorithm automatically estimates the AF probability. Based on this technology, we can offer four distinct services to healthcare providers: (1) universal access to patient data; (2) automated AF detection and alarm; (3) physician support; and (4) feedback channels. These four services create an environment where physicians can work symbiotically with machine algorithms to establish and communicate a high quality AF diagnosis.

show abstract

A Smart Service Platform for Cost Efficient Cardiac Health Monitoring

Cited by 29 publications

References 72 publications

Automated Arrhythmia Detection Based on RR Intervals

Automated Arrhythmia Detection Based on RR Intervals

Improving Efficiency of Clinical Studies Using a Total Digital Approach: Prospective Observational Study

Hybrid Decision Support to Monitor Atrial Fibrillation for Stroke Prevention

Contact Info

Product

Resources

About