Enhancing TSH-based congenital hypothyroidism screening using machine learning and resampling algorithms

Alexander De Furia, Paula Branco, Matthew Henderson · 2025

Read Enhancing TSH-based congenital hypothyroidism screening using machine learning and resampling algorithms by Alexander De Furia, Paula Branco, Matthew Henderson (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12751215.txt.

Description

Alexander De Furia and co-authors try to sharpen newborn screening for a thyroid condition that can cause severe learning harm if missed. The current blood test flags too many healthy babies, sending families into needless follow-up. Using records from over 600,000 babies screened in Ontario, the team trained hundreds of model and data-balancing mixes.

One mix caught every true case while raising the share of flagged babies who were truly ill to about 17 percent, a 60 percent gain over the current method. The main blood marker still did most of the work. A few extra record fields added the small edge that cut false alarms.

Catalog record

CREATORAlexander De Furia, Paula Branco, Matthew Henderson
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE72 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC12751215

Browse the full library · About the Tower of Babel