Treffer: ROC curves for machine learning model performance on training data.
Title:
ROC curves for machine learning model performance on training data.
Authors:
Hiroyuki Akamine, Akiyuki Uzawa, Satoshi Kuwabara, Shigeaki Suzuki, Yosuke Onishi, Manato Yasuda, Yukiko Ozawa, Naoki Kawaguchi, Tomoya Kubota, Masanori P. Takahashi, Yasushi Suzuki, Genya Watanabe, Takashi Kimura, Takamichi Sugimoto, Makoto Samukawa, Naoya Minami, Masayuki Masuda, Shingo Konno, Yuriko Nagane, Kimiaki Utsugisawa
Publication Year:
2025
Subject Terms:
Medicine, Biotechnology, Science Policy, Infectious Diseases, using 414 registrants, potentially guiding clinicians, negative matrix factorization, matthews correlation coefficient, determining treatment objectives, autoimmune disease characterized, 92 &# 8211, 88 &# 8211, 86 &# 8211, 72 &# 8211, 91 ), precision, 88 ), sensitivity, model &# 8217, machine learning model, ensemble model achieved, study included 1, outcomes among patients, 94 &# 8211, japan mg registry, four distinct modules, 85 &# 8211, auroc ), 86 ), specificity
Document Type:
Fachzeitschrift
article in journal/newspaper
Language:
unknown
DOI:
10.1371/journal.pone.0330044.s001
Availability:
Rights:
CC BY 4.0
Accession Number:
edsbas.2DFA64F7
Database:
BASE
Weitere Informationen
ROC curves and AUC values for four machine learning models evaluated on training data using 5-fold cross-validation. (a) Logistic Regression, (b) Naive Bayes, (c) Random Forest, (d) SVM. Individual fold ROC curves (colored lines) and mean ROC curve (thick line) are shown with corresponding AUC values. (PDF)