Login / Signup

Development and validation of a new clinical decision support tool to optimize screening for retinopathy of prematurity.

Aldina PivodicHelena JohanssonLois E H SmithAnna-Lena HårdChatarina LöfqvistBradley A YoderM Elizabeth HartnettCarolyn WuMarie-Christine BründerWolf A LagrèzeAndreas StahlAbbas Al-HawasiEva LarssonPia LundgrenLotta GränseBirgitta SunnqvistKristina TornqvistAgneta WallinGerd HolmstromKerstin Albertsson-WiklandStaffan NilssonAnn Hellström
Published in: The British journal of ophthalmology (2021)
DIGIROP-Screen, a clinical decision support tool using readily available birth and ROP screening data for infants born GA 24-30 weeks, in the European and North American populations tested can safely identify infants not needing ROP screening. DIGIROP-Screen had equal or higher sensitivity and specificity compared with other models. DIGIROP-Screen should be tested in any new cohort for validation and if not validated it can be modified using the same statistical approaches applied to a specific clinical setting.
Keyphrases
  • clinical decision support
  • electronic health record
  • high throughput
  • gestational age
  • pet ct
  • machine learning
  • preterm infants
  • pregnant women
  • deep learning
  • structural basis
  • clinical evaluation