What is the clinical evidence from this study?

Study design: Other. Population: Healthy volunteers and Alzheimer's disease (n=158). Intervention: Scopolamine vs. Placebo or Baseline. Primary outcome: Cross-validated classification accuracy of the mAChR index (baseline vs peak scopolamine) (p=9 * 10^-29).

What does this research mean for the field?

An integrated index of 14 EEG biomarkers (mAChR index) discriminates scopolamine-induced cognitive impairment from baseline with 88-92% cross-validated accuracy, significantly outperforming any single EEG biomarker, and can also distinguish healthy elderly individuals from patients with Alzheimer's disease. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

July 12, 2017Open Access

EEG machine learning for accurate detection of cholinergic intervention and Alzheimer’s disease

Key Result

An integrated index of 14 EEG biomarkers (mAChR index) discriminated scopolamine-induced cognitive impairment from baseline with 90% cross-validated accuracy, significantly outperforming the single-best biomarker.

Structured PICO

Does integrating multiple EEG biomarkers using machine learning improve the detection of scopolamine-induced cholinergic deficits and Alzheimer's disease compared to single biomarkers?

Population

158 subjects across 4 trials: 83 healthy males aged 18-55 years (Trials 1 & 2), 35 healthy elderly aged 65-85 years (Trial 3), and 40 patients with mild to moderate Alzheimer's disease aged 50-80 years (Trial 4).

Intervention

Scopolamine (0.5 mg IV over 15 minutes for Trials 1 & 2; 0.3 mg IV over 15 minutes for Trial 3) and EEG biomarker extraction with machine learning classification (mAChR index and AD index).

Comparator

Placebo (Trials 1 & 2), baseline recordings prior to administration, and healthy elderly controls (Trial 3 vs Trial 4).

Outcome

Classification performance (accuracy, sensitivity, specificity, precision) of the integrated EEG biomarker indices to distinguish baseline from peak scopolamine, and healthy elderly from AD patients.surrogate

Integrating multiple EEG biomarkers using machine learning significantly enhances the accuracy of detecting cholinergic interventions and Alzheimer's disease pathophysiology, providing a robust surrogate endpoint for clinical trials.

Main Result

Absolute Event Rate: 90% vs 79%

p-value: p=9 * 10^-29

Limitations

Data were recorded only during eyes-closed rest, and it is unknown if indices apply equally well to eyes-open rest EEG.
Scopolamine alone may not fully capture AD pathophysiology, as nicotinic blockade might be needed to better resemble changes.
Exact ratio of male and female participants in Trials 3 and 4 is not known.

Abstract

Monitoring effects of disease or therapeutic intervention on brain function is increasingly important for clinical trials, albeit hampered by inter-individual variability and subtle effects. Here, we apply complementary biomarker algorithms to electroencephalography (EEG) recordings to capture the brain's multi-faceted signature of disease or pharmacological intervention and use machine learning to improve classification performance. Using data from healthy subjects receiving scopolamine we developed an index of the muscarinic acetylcholine receptor antagonist (mAChR) consisting of 14 EEG biomarkers. This mAChR index yielded higher classification performance than any single EEG biomarker with cross-validated accuracy, sensitivity, specificity and precision ranging from 88-92%. The mAChR index also discriminated healthy elderly from patients with Alzheimer's disease (AD); however, an index optimized for AD pathophysiology provided a better classification. We conclude that integrating multiple EEG biomarkers can enhance the accuracy of identifying disease or drug interventions, which is essential for clinical trials.

Demander à l'IA

Bookmark

View Full Paper

Demander à l'IA

Bookmark

View Full Paper

Cite This Study

Simpraga et al. (Wed,) conducted a other in Healthy volunteers and Alzheimer's disease (n=158). Scopolamine vs. Placebo or Baseline was evaluated on Cross-validated classification accuracy of the mAChR index (baseline vs peak scopolamine) (p=9 * 10^-29). An integrated index of 14 EEG biomarkers (mAChR index) discriminated scopolamine-induced cognitive impairment from baseline with 90% cross-validated accuracy, significantly outperforming the single-best biomarker.

synapsesocial.com/papers/6a1c524226cb5670aa9dab2a https://doi.org/https://doi.org/10.1038/s41598-017-06165-4

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: