Fluids and Barriers of the CNS

Table 3 Predictive performance comparison of machine learning models on protein ventricular dataset

From: Applying machine learning to high-dimensional proteomics datasets for the identification of Alzheimer’s disease biomarkers

Model	Accuracy	\(F_1\)-score	AUC	MCC
Task A2
XGB	0.80 (± 0.03)	0.55 (± 0.05)	0.81 (± 0.03)	0.43 (± 0.07)
LR	0.76 (± 0.02)	0.53 (± 0.04)	0.80 (± 0.03)	0.39 (± 0.05)
RF	0.80 (± 0.01)	0.58 (± 0.03)	0.84 (± 0.03)	0.46 (± 0.04)
Soft ensemble	0.81 (± 0.02)	0.58 (± 0.03)	0.84 (± 0.02)	0.46 (± 0.045)
Hard ensemble	0.81 (± 0.02)	0.58 (± 0.05)	0.84 (± 0.02)	0.445 (± 0.06)

This table presents the performance of five machine learning models on Task A2, using protein ventricular data. Metrics include accuracy, \(F_1\)-score, AUC, and MCC, each with 95% confidence intervals

Back to article page

ISSN: 2045-8118

Contact us

Submission enquiries: journalsubmissions@springernature.com