A computer vision approach to the assessment of dried blood spot size and quality in newborn screening

• Published in: Clinica chimica acta 2023-07, Vol.547, p.117418-117418, Article 117418
• Main Authors: Flynn, Nick, Moat, Stuart J., Hogg, Sarah L.
• Format: Article
• Language: English
• Subjects: Algorithms; Artificial intelligence; Blood Specimen Collection - methods; Computer vision; Dried blood spot quality; Dried Blood Spot Testing - methods; Humans; Infant, Newborn; Laboratories; Machine learning; Neonatal Screening - methods; Newborn screening
• ISSN: 0009-8981; 1873-3492
• DOI: 10.1016/j.cca.2023.117418

•Computer vision measurement of dried blood spot diameter is accurate and precise.•Shape analysis of DBS can detect incorrectly applied blood.•Computer vision can be used for service evaluation to monitor DBS quality.•DBS size affects analyte concentrations in newborn blood spot specimens. Dried blood spot (DBS) size and quality affect newborn screening (NBS) test results. Visual assessment of DBS quality is subjective. We developed and validated a computer vision (CV) algorithm to measure DBS diameter and identify incorrectly applied blood in images from the Panthera DBS puncher. We used CV to assess historical trends in DBS quality and correlate DBS diameter to NBS analyte concentrations in 130,620 specimens. CV estimates of DBS diameter were precise (percentage coefficient of variation  14 mm. CV identified a reduction in unsuitable NBS specimens from 25.5% in 2015 to 2% in 2021. Each mm decrease in DBS diameter decreased analyte concentrations by up to 4.3%. CV can aid assessment of DBS size and quality to harmonize specimen rejection both within and between laboratories.