Your browser doesn't support javascript.
A Confidence Interval-Based Method for Classifier Re-Calibration.
Campagner, Andrea; Famiglini, Lorenzo; Cabitza, Federico.
  • Campagner A; University of Milano-Bicocca, Milano, Italy.
  • Famiglini L; University of Milano-Bicocca, Milano, Italy.
  • Cabitza F; University of Milano-Bicocca, Milano, Italy.
Stud Health Technol Inform ; 294: 127-128, 2022 May 25.
Article in English | MEDLINE | ID: covidwho-1865415
ABSTRACT
We propose a re-calibration method for Machine Learning models, based on computing confidence intervals for the predicted confidence scores. We show the effectiveness of the proposed method on a COVID-19 diagnosis benchmark.
Subject(s)
Keywords
Fulltext
Print
XML
PubMed Links
Search on Google

Full text: Available Collection: International databases Database: MEDLINE Main subject: COVID-19 Type of study: Diagnostic study / Prognostic study Limits: Humans Language: English Journal: Stud Health Technol Inform Journal subject: Medical Informatics / Health Services Research Year: 2022 Document Type: Article Affiliation country: SHTI220413

Similar

MEDLINE
LILACS
LIS
Fulltext
Print
XML
PubMed Links
Search on Google

Full text: Available Collection: International databases Database: MEDLINE Main subject: COVID-19 Type of study: Diagnostic study / Prognostic study Limits: Humans Language: English Journal: Stud Health Technol Inform Journal subject: Medical Informatics / Health Services Research Year: 2022 Document Type: Article Affiliation country: SHTI220413