A blood-based, metabolite and demographiccharacteristic markers panel for thediagnosis of Alzheimer’s disease: supplementary material

Aims: This work was designed to provide early diagnosis strategies for Alzheimer’s disease (AD) based onthe identification of blood metabolic biomarkers. Patients & methods: A total of 90 subjects aged 60 yearsor older were included in this study; 45 patients were assigned to the case group and control group,respectively. A total of 31 targetmetabolites were quantitatively analyzed by parallel reaction monitoringbetween the two groups. Results & conclusion: Three metabolites were screened out, including cystine,serine and alanine/sarcosine. Logistic regression and random forest analysis were used to establish ADdiagnosis models, and the model combining metabolic biomarkers and demographic variables had higherdetection efficiency (area under the curve = 0.869). A combination diagnostic model to provide a scientificreference for early screening and diagnosis of AD was constructed.