In Journal of paediatrics and child health
AIM : Neonatal jaundice is an important and prevalent condition that can cause kernicterus and mortality. This study validated a smartphone-based screening application (Biliscan) in detecting neonatal jaundice.
METHODS : A cross-sectional prospective study was conducted at the neonatal unit in a tertiary teaching hospital between August 2020 and October 2021. All babies born at the gestation of 35 weeks and above with clinical jaundice or are recommended for screening of jaundice within 21 days of post-natal age were recruited. Using Biliscan, images of the babies' skin over the sternum were taken against a standard colour card. The application uses feature extraction and machine learning regression to estimate the bilirubin level. Independent Biliscan bilirubin estimates (BsB) were made and compared with total serum bilirubin (TSB) and transcutaneous bilirubin (TcB) levels. Bland Altman plots were used to establish the agreement between BsB and TSB, as well as TcB, using the clinically acceptable limits of agreement of ±35 μmol/L, which were defined a priori. Pearson correlation coefficient was assessed to establish the strength of the relationship between BsB versus TSB and TcB. Diagnostic accuracy was assessed through receiver operating characteristic curve analysis.
RESULTS : Sixty-one paired TSB-BsB and 85 paired TcB-BsB measurements were obtained. Bland Altman plot for the entire group showed that 54% (33/61) of the pairs of TSB and BsB readings and 66% (56/85) of the pairs of TcB and BsB readings were within the maximum clinically acceptable difference of 35 μmol/L. Pearson r for BsB versus TSB and TcB was 0.54 (P < 0.001) and 0.66 (P < 0.001) respectively. Compared with TSB, the recommended gold standard measure for jaundice, Biliscan has a sensitivity of 76.92% and specificity of 70.83% for jaundice requiring phototherapy. The positive and negative predictive values in term infants were 93.3% and 36.9%, respectively.
CONCLUSION : Our results suggest that there is moderate correlation and mediocre agreement between BsB and TSB, as well as TcB. Improvement to the application algorithm and further studies that include a larger population, and a wider range of bilirubin values are necessary before the tool may be considered for use in screening of jaundice in newborns.
Ngeow Alvin Jia Hao, Tan Mary Grace, Dong Xiaoao, Tagamolila Vina, Ereno Imelda, Tay Yih Yann, Xin Xiaohui, Poon Woei Bing, Yeo Cheo Lian
2022-Nov-28
artificial intelligence , neonatal jaundice , neonatology
