Random forest classifier improving phenylketonuria screening performance in two Chinese populations

Yingnan Song; Zhe Yin; Chuan Zhang; Shengju Hao; Haibo Li; Shifan Wang; Xiangchun Yang; Qiong Li; Danyan Zhuang; Xinyuan Zhang; Zongfu Cao; Xu Ma

doi:10.3389/fmolb.2022.986556

Random forest classifier improving phenylketonuria screening performance in two Chinese populations

Front Mol Biosci. 2022 Oct 11:9:986556. doi: 10.3389/fmolb.2022.986556. eCollection 2022.

Authors

Yingnan Song^{1

2}, Zhe Yin¹, Chuan Zhang^{1

2

3}, Shengju Hao³, Haibo Li⁴, Shifan Wang³, Xiangchun Yang⁴, Qiong Li⁴, Danyan Zhuang⁴, Xinyuan Zhang¹, Zongfu Cao¹, Xu Ma^{1

2}

Affiliations

¹ National Human Genetic Resources Center, National Research Institute for Family Planning, Beijing, China.
² Graduate School of Peking Union Medical College, Beijing, China.
³ Gansu Province Medical Genetics Center, Gansu Provincial Clinical Research Center for Birth Defects and Rare Diseases, Gansu Provincial Maternity and Child-Care Hospital, Lanzhou, China.
⁴ The Central Laboratory of Birth Defects Prevention and Control, Ningbo Women and Children's Hospital, Ningbo, China.

Abstract

Phenylketonuria (PKU) is a genetic disorder with amino acid metabolic defect, which does great harms to the development of newborns and children. Early diagnosis and treatment can effectively prevent the disease progression. Here we developed a PKU screening model using random forest classifier (RFC) to improve PKU screening performance with excellent sensitivity, false positive rate (FPR) and positive predictive value (PPV) in all the validation dataset and two testing Chinese populations. RFC represented outstanding advantages comparing several different classification models based on machine learning and the traditional logistic regression model. RFC is promising to be applied to neonatal PKU screening.

Keywords: MRM; machine learning; newborn screening; phenylketonuria; random forest classifier.