Image-Based Neonatal Hyperbilirubinemia Screening after Hospital Discharge
Abstract
Background: Newborn infants who are risk for severe hyperbilirubinemia and cared at home should be monitored for progression of jaundice. We aimed to verify if a smart phone application (BiliScan Inc), which uses automated imaging for bilirubin (AIB), can be used to estimate total serum bilirubin (TSB) levels at home.
Methods: A convenience sample of 1038 “healthy” infants in China were prospectively enrolled to a single-center study in 2016. Correlations between AIB and TcB measurements were correlated to TB measurements. Bias and imprecision of AIB measurements were determined using Bland-Altman analysis. The diagnostic value of AIB was compared by the area-under-curve (AUC) values of receiver operator characteristic (ROC) curves.
Results: The best correlation and AUC for AIB were at the sternum, both with values of 0.76. We truncated performances to 369 TB values >5 and <15 mg/dL, and sternal AIB showed the best correlation to TB (r =0.5, P<0.0001). The AUC for this range was 0.54. However, from a subset of 200 AIB values >13.5 mg/dL (n=369 babies), the sensitivity and negative predictive value (NPV) were 100% with a specificity of 50%. Furthermore, Bland-Altman analyses showed a bias and imprecision of AIB and TcB when TB was >13.5 and <15 mg/dL.
Conclusion: The use of AIB may be a potentially useful screening device for neonatal jaundice. Its performance requires additional improvements for accurate measurements across wider ranges of TB levels.
2. Banerjee TK, Hazra A, Bi swas A, et al (2009). Neuro-logical disorders in children and adolescents. Indian J Pediatr, 76: 139–146.
3. Bhutani VK, Johnson LH, Jeffrey Maisels M, et al (2004). Kernicterus: epidemiological strategies for its prevention through system s-based approach-es. J Perinatal, 24: 650–662.
4. Brooks JC, Fisher-Owens SA, Wu YW, Strauss DJ, Newman TB (2011). Evidence suggests there was not a “resurgence” of kernicterus in the 1990s. Pediatrics, 127: 672–679.
5. Burgos AE, Flaherman VJ, Newman TB (2012). Screening and follow-up for neonatal hyperbiliru-binemia: a review. Clin Pediatr (Phila), 51(1): 7–16.
6. Committee on practice and ambulatory medicine, bright futures periodicity schedule workgroup (2017). 2017 recommendations for Preventive Pe-diatric Health Care. Pediatrics, 139: e20170254.
7. Ding GF (2010). Thinking and suggestions about neonatal jaundice treatment. Chinese J Pediatr, 48(9): 643-645.
8. Leung TS, Kapur K, Guilliam A, et al (2015). Screen-ing neonatal jaundice based on the sclera color of the eye using digital photography. Biomed Opt Ex-press, 6(11): 4529–4538.
9. Maisels MJ, Bhutani VK, Bogen D, et al (2009). Hy-perbilirubinemia in the newborn infant≥35 weeks’ gestation: an update with clarifications. Pediatrics, 124: 1193–8.
10. Mezaal MA, Nouri KA, Abdool S, Safar KA, Nadeem ASM (2009). Cerebralpalsy in adults on sequences of non-progressive pathology. Open Neurol J, 3: 24–26.
11. Ogunfowora OB, Daniel OJ (2006). Neonatal jaun-dice and its management: knowledge, attitude and practice of community health workers in Nigeria. BMC Public Health, 6:19.
12. Owa JA, Ogunlesi TA (2009). Why we are still doing so many exchange blood transfusion for neonatal jaundice in Nigeria. World J Pediatr, 5: 51–55.
13. Subspecialty Group of Neonatology, Pediatric Society, Chinese Medical Association (2009). Epidemio-logic survey for hospitalized neonates in China. Chin J Contemp Pediatr, 11: 15–18.
14. Watchko JF, Tiribelli C (2013). Bilirubin-induced neu-rologic damage mechanisms and management approaches. N Engl J Med, 369: 2021–2030.
15. Xue GC, Ren MX, Shen LN (2016). Parental infant jaundice colour card design successfully validated by comparing it with total serum bilirubin. Acta Pe-diatric, 105: e561–e566.
Files | ||
Issue | Vol 49 No 6 (2020) | |
Section | Original Article(s) | |
DOI | https://doi.org/10.18502/ijph.v49i6.3359 | |
Keywords | ||
Jaundice; Hyperbilirubinemia; Postnatal; Automatic image-based |
Rights and permissions | |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |