Deep learning methods for screening patients' S-ICD implantation eligibility

Dunn, Anthony J.; ElRefai, Mohamed; Roberts, Paul R.; Coniglio, Stefano; Wiles, Benedict M; Zemkoho, Alain B.

doi:10.1016/j.artmed.2021.102139

Cited by 15 publications

(19 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Raw data from the Holters were downloaded in ASCII (American Standard Code for Information Interchange) format at a frequency of 500 Hertz (Hz). A bespoke tool developed by Dunn et al efficiently and accurately tracked and analyzed the T:R ratio for the leads corresponding to the S‐ICD vectors over the 24‐h recordings period (Dunn et al, 2021).…”

Section: Methodsmentioning

confidence: 99%

“…The end result is a plot showing the variation of the T:R ratios for each lead/S-ICD vector over the recorded period (24 h in our study), where, for readability, the line graph is smoothed to where each point gives the average T:R ratio for the preceding half hour, thus making it easy to detect any period where the T:R ratio was consistently high and thus increased the risk of TWO. To better examine how the behavior of the T:R ratio differs between each lead, our tool can plot a histogram of what proportion of the 24-h screening period the T:R ratio of a particular lead spent in each range of T:R ratios (Dunn et al, 2021).…”

Section: Artifi Cial Intelli G En Ce and Neur Al Ne T Working Modelmentioning

confidence: 99%

“…We report a novel application of artificial intelligence and deep learning methods used to screen patients for S-ICD eligibility. Screening data are acquired over a much longer period than for conventional screening approaches and provide an in-depth description of the behavior of the T:R ratio over that period across the three S-ICD vectors (Dunn et al, 2021). We hypothesize that this novel screening approach could enable more reliable and descriptive screening to better assess patient eligibility for S-ICD implantation with lower risk of inappropriate shock therapy.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Role of deep learning methods in screening for subcutaneous implantable cardioverter defibrillator in heart failure

ElRefai

Abouelasaad

Wiles

et al. 2022

Noninvasive Electrocardiol

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Artifi Cial Intelli G En Ce and Neur Al Ne T Working Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Role of deep learning methods in screening for subcutaneous implantable cardioverter defibrillator in heart failure

ElRefai

Abouelasaad

Wiles

et al. 2022

Noninvasive Electrocardiol

Self Cite

View full text Add to dashboard Cite

show abstract

“…Similarly, the author of [ 43 ] proposed a convolutional neural network for the automatic segmentation of chest X-ray to diagnose cardiomegaly. Furthermore, the electrocardiogram analysis by the convolutional neural network has been employed to identify five types of arrhythmic heartbeats [ 42 ] and guide the screening process for subcutaneous implantable cardioverter-defibrillators [ 44 ]. The convolutional neural network has analysed CT to identify cerebral infarction [ 40 ] and pulmonary fibrosis [ 41 ].…”

Section: Related Workmentioning

confidence: 99%

An Entropy-Based Measure of Complexity: An Application in Lung-Damage

Ortiz-Vilchis

Ramírez-Arellano

2022

Entropy

View full text Add to dashboard Cite

The computed tomography (CT) chest is a tool for diagnostic tests and the early evaluation of lung infections, pulmonary interstitial damage, and complications caused by common pneumonia and COVID-19. Additionally, computer-aided diagnostic systems and methods based on entropy, fractality, and deep learning have been implemented to analyse lung CT images. This article aims to introduce an Entropy-based Measure of Complexity (EMC). In addition, derived from EMC, a Lung Damage Measure (LDM) is introduced to show a medical application. CT scans of 486 healthy subjects, 263 diagnosed with COVID-19, and 329 with pneumonia were analysed using the LDM. The statistical analysis shows a significant difference in LDM between healthy subjects and those suffering from COVID-19 and common pneumonia. The LDM of common pneumonia was the highest, followed by COVID-19 and healthy subjects. Furthermore, LDM increased as much as clinical classification and CO-RADS scores. Thus, LDM is a measure that could be used to determine or confirm the scored severity. On the other hand, the d-summable information model best fits the information obtained by the covering of the CT; thus, it can be the cornerstone for formulating a fractional LDM.

show abstract

“…The cut-off T:R ratio of 1:3 used for current screening practice incorporates a safety margin to accommodate for the fluctuations of the ECG signal amplitudes over time without affecting the sensing of the S-ICD. Based on a deep learning method developed by some of the authors in this study [2], we conduct a prolonged screening for S-ICD capable of accurately measuring the degree of the T:R ratio fluctuation over the monitoring/screening period. Crucially, the tool can help identify patients with high probability of TWO and inappropriate shocks that can be missed using the current screening practice.…”

Section: Introductionmentioning

confidence: 99%

Deep learning-based insights on T:R ratio behaviour during prolonged screening for S-ICD eligibility

ElRefai

Abouelasaad

Wiles

et al. 2022

J Interv Card Electrophysiol

Self Cite

View full text Add to dashboard Cite

Background A major predictor of eligibility of subcutaneous implantable cardiac defibrillators (S-ICD) is the T:R ratio. The eligibility cut-off of the T:R ratio incorporates a safety margin to accommodate for fluctuations of ECG signal amplitudes. We introduce a deep learning-based tool that accurately measures the degree of T:R ratio fluctuations and explore its role in S-ICD screening. Methods Patients were fitted with Holters for 24 h to record their S-ICD vectors. Our tool was used to assess the T:R ratio over the duration of the recordings. Multiple T:R ratio cut-off values were applied, identifying patients at high risk of T-wave oversensing (TWO) at each of the proposed values. The purpose of our study is to identify the ratio that recognises patients at high risk of TWO while not inappropriately excluding true S-ICD candidates. Results Thirty-seven patients (age 54.5 + / − 21.3 years, 64.8% male) were recruited. Fourteen patients had heart-failure, 7 hypertrophic cardiomyopathy, 7 had normal hearts, 6 had congenital heart disease, and 3 had prior inappropriate S-ICD shocks due to TWO. 54% of patients passed the screening at a T: R of 1:3. All patients passed the screening at a T: R of 1:1. The only subgroup to wholly pass the screening utilising all the proposed ratios are the participants with normal hearts. Conclusion We propose adopting prolonged screening to select patients eligible for S-ICD with low probability of TWO and inappropriate shocks. The appropriate T:R ratio likely lies between 1:3 and 1:1. Further studies are required to identify the optimal screening thresholds.

show abstract

Deep learning methods for screening patients' S-ICD implantation eligibility

Cited by 15 publications

References 33 publications

Role of deep learning methods in screening for subcutaneous implantable cardioverter defibrillator in heart failure

Role of deep learning methods in screening for subcutaneous implantable cardioverter defibrillator in heart failure

An Entropy-Based Measure of Complexity: An Application in Lung-Damage

Deep learning-based insights on T:R ratio behaviour during prolonged screening for S-ICD eligibility

Contact Info

Product

Resources

About