ABSTRACT
Background: Neonatal screening for inherited metabolic diseases (IMDs) has been revolutionized by tandem mass spectrometry (MS/MS). This study aimed to enhance neonatal screening for IMDs using machine learning (ML) techniques. Methods: The study involved the analysis of a comprehensive dataset comprising 309,102 neonatal screening records collected in the Ningbo region, China. An advanced ML system model, encompassing nine distinct algorithms, was employed for the purpose of predicting the presence of 31 different IMDs. The model was compared with traditional cutoff schemes to assess its diagnostic efficacy. Additionally, 180 suspected positive cases underwent further evaluation. Results: The ML system exhibited a significantly reduced positive rate, from 1.17% to 0.33%, compared to cutoff schemes in the initial screening, minimizing unnecessary recalls and associated stress. In suspected positive cases, the ML system identified 142 true positives with high sensitivity (93.42%) and improved specificity (78.57%) compared to the cutoff scheme. While false negatives emerged, particularly in heterozygous carriers, our study revealed the potential of the ML system to detect asymptomatic cases. Conclusion: This research provides valuable insights into the potential of ML in pediatric medicine for IMD diagnosis through neonatal screening, emphasizing the need for accurate carrier detection and further research in this domain.
ABSTRACT
BACKGROUND: Treacher Collins Ι syndrome (TCS1, OMIM:154500) is an autosomal dominant disease with a series of clinical manifestations such as craniofacial dysplasia including eye and ear abnormalities, small jaw deformity, cleft lip, as well as repeated respiratory tract infection and conductive hearing loss. Two cases of Treacher Collins syndrome with TCOF1(OMIM:606847) gene variations were reported in the article, with clinical characteristics, gene variants and the etiology. METHODS: The clinical data of two patients with Treacher Collins syndrome caused by TCOF1 gene variation were retrospectively analyzed. The whole exome sequencing (WES) was performed to detect the pathogenic variants of TCOF1 gene in the patients, and the verification of variants were confirmed by Sanger sequencing. RESULTS: Proband 1 presented with bilateral craniofacial deformities, conductive hearing loss and recurrent respiratory tract infection. Proband 2 showed bilateral craniofacial malformations with cleft palate, which harbored similar manifestations in her family. She died soon after birth due to dyspnea and feeding difficulties. WES identified two novel pathogenic variants of TCOF1 gene in two probands, each with one variant. According to the American College of Medical Genetics and Genomics, the heterozygous variation NM_001371623.1: c.877del (p. Ala293Profs*34) of TCOF1 gene was detected in Proband 1, which was evaluated as a likely pathogenic (LP) and de novo variant. Another variant found in Proband 2 was NM_001135243.1: c.1660_1661del (p. D554Qfs*3) heterozygous variation, which was evaluated as a pathogenic variation and the variant inherited from the mother. To date, the two variants have not been reported before. CONCLUSION: Our study found two novel pathogenic variants of TCOF1 gene and clarified the etiology of Treacher Collins syndrome. We also enriched the phenotypic spectrum of Treacher Collins syndrome and TCOF1 gene variation spectrum in the Chinese population, and provided the basis for clinical diagnosis, treatment and genetic counseling.
