Zaunseder Elaine, Teinert Julian, Boy Nikolas, Garbade Sven F, Haupt Saskia, Feyh Patrik, Hoffmann Georg F, Kölker Stefan, Mütze Ulrike, Heuveline Vincent
Engineering Mathematics and Computing Lab (EMCL), Interdisciplinary Center for Scientific Computing (IWR), Heidelberg University, 69120 Heidelberg, Germany.
Data Mining and Uncertainty Quantification (DMQ), Heidelberg Institute for Theoretical Studies (HITS), 69118 Heidelberg, Germany.
Int J Neonatal Screen. 2024 Dec 21;10(4):83. doi: 10.3390/ijns10040083.
Glutaric aciduria type 1 (GA1) is a rare inherited metabolic disease increasingly included in newborn screening (NBS) programs worldwide. Because of the broad biochemical spectrum of individuals with GA1 and the lack of reliable second-tier strategies, NBS for GA1 is still confronted with a high rate of false positives. In this study, we aim to increase the specificity of NBS for GA1 and, hence, to reduce the rate of false positives through machine learning methods. Therefore, we studied NBS profiles from 1,025,953 newborns screened between 2014 and 2023 at the Heidelberg NBS Laboratory, Germany. We identified a significant sex difference, resulting in twice as many false-positives male than female newborns. Moreover, the proposed digital-tier strategy based on logistic regression analysis, ridge regression, and support vector machine reduced the false-positive rate by over 90% compared to regular NBS while identifying all confirmed individuals with GA1 correctly. An in-depth analysis of the profiles revealed that in particular false-positive results with high associated follow-up costs could be reduced significantly. In conclusion, understanding the origin of false-positive NBS and implementing a digital-tier strategy to enhance the specificity of GA1 testing may significantly reduce the burden on newborns and their families from false-positive NBS results.
1型戊二酸血症（GA1）是一种罕见的遗传性代谢疾病，全球越来越多的新生儿筛查（NBS）项目将其纳入其中。由于GA1患者的生化谱广泛，且缺乏可靠的二级筛查策略，GA1的新生儿筛查仍面临着较高的假阳性率。在本研究中，我们旨在提高GA1新生儿筛查的特异性，从而通过机器学习方法降低假阳性率。因此，我们研究了2014年至2023年期间在德国海德堡新生儿筛查实验室接受筛查的1,025,953名新生儿的筛查数据。我们发现了显著的性别差异，男性新生儿的假阳性数量是女性新生儿的两倍。此外，基于逻辑回归分析、岭回归和支持向量机提出的数字分层策略与常规新生儿筛查相比，将假阳性率降低了90%以上，同时正确识别了所有确诊的GA1患者。对筛查数据的深入分析表明，特别是那些后续成本较高的假阳性结果可以显著减少。总之，了解新生儿筛查假阳性的根源并实施数字分层策略以提高GA1检测的特异性，可能会显著减轻新生儿及其家庭因假阳性筛查结果而承受的负担。
