查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Methylmalonic Acidemia is the subject of a report. According to news reporting originating from Bangko k, Thailand, by NewsRx correspondents, research stated, "Methylmalonic acidemia (MMA) is a disorder of autosomal recessive inheritance, with an estimated preval ence of 1:50,000. First-tier clinical diagnostic tests often return many false p ositives [five false positive (FP): one true positive (TP)] ." Financial supporters for this research include National Key R&D Pro gram of China, Clinical Research Plan of SHDC, Chulalongkorn University, Science and Technology Commission of Shanghai. Our news editors obtained a quote from the research from Chulalongkorn Universit y, "In this work, our goal was to refine a classification model that can minimiz e the number of false positives, currently an unmet need in the upstream diagnos tics of MMA. We developed machine learning multivariable screening models for MM A with utility as a secondary-tier tool for false positives reduction. We utiliz ed mass spectrometry-based features consisting of 11 amino acids and 31 carnitin es 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 det ermine the input set for evaluating the performance of 14 classification models to identify a candidate model set for an ensemble model development. Our work id entified computational models that explore metabolic analytes to reduce the numb er 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, spars e linear discriminant analysis, and autoencoder deep neural network stacked with the algorithm stochastic gradient boosting as the supervisor. The model achieve d a good performance trade-off for a screening application with 6% false-positive rate (FPR) at 95% sensitivity, 35% FP R at 99% sensitivity, and 39% FPR at 100% sensitivity. The classification results and approach of this research can be uti lized by clinicians globally, to improve the overall discovery of MMA in pediatr ic patients."
NETL
NSTL