Clinical features and outcomes of patients with cblC type methylmalonic acidemia carrying gene c.609G>A mutation

Improving the second-tier classification of methylmalonic acidemia patients using a machine learning ensemble method

INTRODUCTION

Methylmalonic acidemia (MMA) is a disorder of autosomal recessive inheritance, with an estimated prevalence of 1:50,000. First-tier clinical diagnostic tests often return many false positives [five false positive (FP): one true positive (TP)]. In this work, our goal was to refine a classification model that can minimize the number of false positives, currently an unmet need in the upstream diagnostics of MMA.

METHODS

We developed machine learning multivariable screening models for MMA with utility as a secondary-tier tool for false positives reduction. We utilized mass spectrometry-based features consisting of 11 amino acids and 31 carnitines derived from dried blood samples of neonatal patients, followed by additional ratio feature construction. Feature selection strategies (selection by filter, recursive feature elimination, and learned vector quantization) were used to determine the input set for evaluating the performance of 14 classification models to identify a candidate model set for an ensemble model development.

RESULTS

Our work identified computational models that explore metabolic analytes to reduce the number of false positives without compromising sensitivity. The best results [area under the receiver operating characteristic curve (AUROC) of 97%, sensitivity of 92%, and specificity of 95%] were obtained utilizing an ensemble of the algorithms random forest, C5.0, sparse linear discriminant analysis, and autoencoder deep neural network stacked with the algorithm stochastic gradient boosting as the supervisor. The model achieved a good performance trade-off for a screening application with 6% false-positive rate (FPR) at 95% sensitivity, 35% FPR at 99% sensitivity, and 39% FPR at 100% sensitivity.

CONCLUSIONS

The classification results and approach of this research can be utilized by clinicians globally, to improve the overall discovery of MMA in pediatric patients. The improved method, when adjusted to 100% precision, can be used to further inform the diagnostic process journey of MMA and help reduce the burden for patients and their families.

Methylmalonic acidemia: Neurodevelopment and neuroimaging

Methylmalonic acidemia (MMA) is a genetic disease of abnormal organic acid metabolism, which is one of the important factors affecting the survival rate and quality of life of newborns or infants. Early detection and diagnosis are particularly important. The diagnosis of MMA mainly depends on clinical symptoms, newborn screening, biochemical detection, gene sequencing and neuroimaging diagnosis. The accumulation of methylmalonic acid and other metabolites in the body of patients causes brain tissue damage, which can manifest as various degrees of intellectual disability and severe neurological dysfunction. Neuroimaging examination has important clinical significance in the diagnosis and prognosis of MMA. This review mainly reviews the etiology, pathogenesis, and nervous system development, especially the neuroimaging features of MMA.

Clinical characteristics and genotype analysis of five infants with cblX type of methylmalonic acidemia

OBJECTIVE

To investigate the clinical and genetic characteristics of infants with cobalamin (cbl) X type of methylmalonic acidemia (MMA).

METHODS

The clinical data of 5 infants with cblX type of MMA diagnosed in Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine and Shanghai Children's Hospital from the year 2016 to 2020 were collected. The levels of blood acylcarnitines were detected by tandem mass spectrometry, the levels of urinary organic acids were detected by gas-chromatography mass spectrometry, the pathogenic genes were detected by whole exon gene sequencing, and the effect of new pathogenic mutations on three-dimensional protein structure was predicted by bioinformatics analysis.

RESULTS

Five infants with cblX type were diagnosed, including 4 males and 1 female, and the onset age was 0-6 months. The main clinical manifestations of 4 males were intractable epilepsy, mental and motor retardation, metabolic abnormalities presented mild increase of blood homocysteine level. Among them, 3 cases were accompanied by slight increase of urinary methylmalonic acid, and 1 case was accompanied by increase of blood propionylcarnitine (C3) and C3/acetylcarnitine (C2). Gene detection found that 2 cases carried a same hemizygous mutation c.344C>T (p.A115V) of HCFC1 gene, which was the most reported mutation, and the other 2 cases carried novel pathogenic mutations, c.92G>A (p.R31Q) and c.166G>C (p.V56L). These 3 gene mutations located in the Kelch domain of HCFC1 protein. One female infant carried a benign mutation of c.3731G>T (p.R1244L). Her clinical symptoms were mild, and only the urinary methylmalonic acid was slightly increased.

CONCLUSIONS

The clinical manifestations of children with cblX type of MMA are intractable epilepsy, mental and motor retardation, and other serious neurological symptoms. Their metabolic abnormalities present the increase of blood homocysteine with methylmalonic acid (urinary methylmalonic acid or/and blood C3, C3/C2). The clinical and biochemical phenotypes are separated, so the diagnosis should be in combination with the results of gene testing.