Division of Pediatric Nutrition and Metabolism, Department of Pediatrics, Faculty of Medicine, Health Sciences University, Kayseri, Turkiye.
Department of Electrical & Electronics Engineering, Faculty of Engineering, Erciyes University, Kayseri, Turkiye.
Turk J Med Sci. 2024 Jul 12;54(4):710-717. doi: 10.55730/1300-0144.5840. eCollection 2024.
BACKGROUND/AIM: Tandem mass spectrometry is helpful in diagnosing amino acid metabolism disorders, organic acidemias, and fatty acid oxidation disorders and can provide rapid and accurate diagnosis for inborn errors of metabolism. The aim of this study was to predict inborn errors of metabolism in children with the help of artificial neural networks using tandem mass spectrometry data.
Forty-seven and 13 parameters of tandem mass spectrometry datasets obtained from 2938 different patients were respectively taken into account to train and test the artificial neural networks. Different artificial neural network models were established to obtain better prediction performances. The obtained results were compared with each other for fair comparisons.
The best results were obtained by using the rectified linear unit activation function. One, two, and three hidden layers were considered for artificial neural network models established with both 47 and 13 parameters. The sensitivity of model B2 for definitive inherited metabolic disorders was found to be 80%. The accuracy rates of model A3 and model B2 are 99.3% and 99.2%, respectively. The area under the curve value of model A3 was 0.87, while that of model B2 was 0.90.
The results showed that the proposed artificial neural networks are capable of predicting inborn errors of metabolism very accurately. Therefore, developing new technologies to identify and predict inborn errors of metabolism will be very useful.
背景/目的：串联质谱分析有助于诊断氨基酸代谢紊乱、有机酸血症和脂肪酸氧化紊乱，并能为代谢性先天缺陷提供快速准确的诊断。本研究旨在利用串联质谱数据，借助人工神经网络预测儿童代谢性先天缺陷。
分别考虑了 2938 例不同患者的串联质谱数据集的 47 个和 13 个参数，用于训练和测试人工神经网络。建立了不同的人工神经网络模型，以获得更好的预测性能。为了公平比较，将获得的结果相互比较。
使用修正线性单元激活函数获得了最佳结果。考虑了具有 47 个和 13 个参数的人工神经网络模型的一个、两个和三个隐藏层。模型 B2 对明确遗传性代谢紊乱的灵敏度为 80%。模型 A3 和模型 B2 的准确率分别为 99.3%和 99.2%。模型 A3 的曲线下面积值为 0.87，而模型 B2 的曲线下面积值为 0.90。
结果表明，所提出的人工神经网络能够非常准确地预测代谢性先天缺陷。因此，开发识别和预测代谢性先天缺陷的新技术将非常有用。
