Dataset Information

Noninvasive assessment of dofetilide plasma concentration using a deep learning (neural network) analysis of the surface electrocardiogram: A proof of concept study.

ABSTRACT:

Background

Dofetilide is an effective antiarrhythmic medication for rhythm control in atrial fibrillation, but carries a significant risk of pro-arrhythmia and requires meticulous dosing and monitoring. The cornerstone of this monitoring, measurement of the QT/QTc interval, is an imperfect surrogate for plasma concentration, efficacy, and risk of pro-arrhythmic potential.

Objective

The aim of our study was to test the application of a deep learning approach (using a convolutional neural network) to assess morphological changes on the surface ECG (beyond the QT interval) in relation to dofetilide plasma concentrations.

Methods

We obtained publically available serial ECGs and plasma drug concentrations from 42 healthy subjects who received dofetilide or placebo in a placebo-controlled cross-over randomized controlled clinical trial. Three replicate 10-s ECGs were extracted at predefined time-points with simultaneous measurement of dofetilide plasma concentration We developed a deep learning algorithm to predict dofetilide plasma concentration in 30 subjects and then tested the model in the remaining 12 subjects. We compared the deep leaning approach to a linear model based only on QTc.

Results

Fourty two healthy subjects (21 females, 21 males) were studied with a mean age of 26.9 ± 5.5 years. A linear model of the QTc correlated reasonably well with dofetilide drug levels (r = 0.64). The best correlation to dofetilide level was achieved with the deep learning model (r = 0.85).

Conclusion

This proof of concept study suggests that artificial intelligence (deep learning/neural network) applied to the surface ECG is superior to analysis of the QT interval alone in predicting plasma dofetilide concentration.

SUBMITTER: Attia ZI

PROVIDER: S-EPMC6104915 | biostudies-literature | 2018

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Noninvasive assessment of dofetilide plasma concentration using a deep learning (neural network) analysis of the surface electrocardiogram: A proof of concept study.

Attia Zachi I ZI Sugrue Alan A Asirvatham Samuel J SJ Ackerman Michael J MJ Kapa Suraj S Friedman Paul A PA Noseworthy Peter A PA

PloS one 20180822 8

<h4>Background</h4>Dofetilide is an effective antiarrhythmic medication for rhythm control in atrial fibrillation, but carries a significant risk of pro-arrhythmia and requires meticulous dosing and monitoring. The cornerstone of this monitoring, measurement of the QT/QTc interval, is an imperfect surrogate for plasma concentration, efficacy, and risk of pro-arrhythmic potential.<h4>Objective</h4>The aim of our study was to test the application of a deep learning approach (using a convolutional ...[more]

PMID: 30133452

Similar Datasets

Project description:BackgroundAlthough total plasma lipoproteome consists of proteins that have shown promises as biomarkers that can identify Alzheimer's disease (AD), effect sizes are modest. The objective of this study is to provide initial proof-of-concept that the plasma lipoproteome more likely differ between AD cases and controls when measured in individual plasma lipoprotein fractions than when measured as total in immunodepleted plasma.MethodsWe first developed a targeted proteomics method based on selected reaction monitoring (SRM) and liquid chromatography and tandem mass spectrometry for measurement of 120 tryptic peptides from 79 proteins that are commonly present in plasma lipoproteins. Then in a proof-of concept case-control study of 5 AD cases and 5 sex- and age-matched controls, we applied the targeted proteomic method and performed relatively quantification of 120 tryptic peptides in plasma lipoprotein fractions (fractionated by sequential gradient ultracentrifugation) and in immunodepleted plasma (of albumin and IgG). Unadjusted p values from two-sample t-tests and overall fold change was used to evaluate a peptide relative difference between AD cases and controls, with lower p values (< 0.05) or greater fold differences (> 1.05 or < 0.95) suggestive of greater peptide/protein differences.ResultsWithin-day and between-days technical precisions (mean %CV [SD] of all SRM transitions) of the targeted proteomic method were 3.95% (2.65) and 9.31% (5.59), respectively. Between-days technical precisions (mean % CV [SD]) of the entire plasma lipoproteomic workflow including plasma lipoprotein fractionation was 27.90% (14.61). Ten tryptic peptides that belonged to 5 proteins in plasma lipoproteins had unadjusted p values < 0.05, compared to no peptides in immunodepleted plasma. Furthermore, 27, 32, 17, and 20 tryptic peptides in VLDL, IDL, LDL and HDL, demonstrated overall peptide fold differences > 1.05 or < 0.95, compared to only 6 tryptic peptides in immunodepleted plasma. The overall comparisons, therefore, suggested greater peptide/protein differences in plasma lipoproteome when measured in individual plasma lipoproteins than as total in immunodepleted plasma. Specifically, protein complement C3's peptide IHWESASLLR, had unadjusted p values of 0.00007, 0.00012, and 0.0006 and overall 1.25, 1.17, 1.14-fold changes in VLDL, IDL, and LDL, respectively. After positive False Discovery Rate (pFDR) adjustment, the complement C3 peptide IHWESASLLR in VLDL remained statistically different (adjusted p value < 0.05).DiscussionThe findings may warrant future studies to investigate plasma lipoproteome when measured in individual plasma lipoprotein fractions for AD diagnosis.

Project description:BackgroundAfter stroke, restoring safe, independent, and efficient walking is a top rehabilitation priority. However, in nearly 70% of stroke survivors asymmetrical walking patterns and reduced walking speed persist. This case series study aims to investigate the effectiveness of transcutaneous spinal cord stimulation (tSCS) in enhancing walking ability of persons with chronic stroke.MethodsEight participants with hemiparesis after a single, chronic stroke were enrolled. Each participant was assigned to either the Stim group (N = 4, gait training + tSCS) or Control group (N = 4, gait training alone). Each participant in the Stim group was matched to a participant in the Control group based on age, time since stroke, and self-selected gait speed. For the Stim group, tSCS was delivered during gait training via electrodes placed on the skin between the spinous processes of C5-C6, T11-T12, and L1-L2. Both groups received 24 sessions of gait training over 8 weeks with a physical therapist providing verbal cueing for improved gait symmetry. Gait speed (measured from 10 m walk test), endurance (measured from 6 min walk test), spatiotemporal gait symmetries (step length and swing time), as well as the neurophysiological outcomes (muscle synergy, resting motor thresholds via spinal motor evoked responses) were collected without tSCS at baseline, completion, and 3 month follow-up.ResultsAll four Stim participants sustained spatiotemporal symmetry improvements at the 3 month follow-up (step length: 17.7%, swing time: 10.1%) compared to the Control group (step length: 1.1%, swing time 3.6%). Additionally, 3 of 4 Stim participants showed increased number of muscle synergies and/or lowered resting motor thresholds compared to the Control group.ConclusionsThis study provides promising preliminary evidence that using tSCS as a therapeutic catalyst to gait training may increase the efficacy of gait rehabilitation in individuals with chronic stroke. Trial registration NCT03714282 (clinicaltrials.gov), registration date: 2018-10-18.

Dataset Information

Noninvasive assessment of dofetilide plasma concentration using a deep learning (neural network) analysis of the surface electrocardiogram: A proof of concept study.

Background

Objective

Methods

Results

Conclusion

Publications

Noninvasive assessment of dofetilide plasma concentration using a deep learning (neural network) analysis of the surface electrocardiogram: A proof of concept study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets