Accuracy of Raman spectroscopy in the diagnosis of Alzheimer's disease

Abstract

ObjectiveTo systematically evaluate the accuracy of Raman spectroscopy in the diagnosis of Alzheimer's disease.MethodsDatabases including Web of Science, PubMed, The Cochrane Library, EMbase, CBM, CNKI, Wan Fang Data, and VIP were electronically searched for studies on Raman spectroscopy in diagnosis of Alzheimer's disease from inception to November 2022. Two reviewers independently screened the literature, extracted data, and assessed the risk of bias in the included studies. Then, meta-analysis was performed using Meta-Disc1.4 and Stata 16.0 software.ResultsA total of eight studies were finally included. The pooled sensitivity of Raman spectroscopy was 0.86 [95% CI (0.80–0.91)], specificity was 0.87 [95% CI (0.79–0.92)], positive likelihood ratio was 5.50 [95% CI (3.55–8.51)], negative likelihood ratio was 0.17 [95% CI (0.09–0.34)], diagnosis odds ratio and area under the curve of SROC were 42.44 [95% CI (19.80–90.97)] and 0.931, respectively. Sensitivity analysis was carried out after each study was excluded one by one, and the results showed that pooled sensitivity and specificity had no significant change, indicating that the stability of the meta-analysis results was great.ConclusionsOur findings indicated that Raman spectroscopy had high accuracy in the diagnosis of AD, though it still did not rule out the possibility of misdiagnosis and missed diagnosis. Limited by the quantity and quality of the included studies, the above conclusions need to be verified by more high-quality studies.

Alzheimer Disease Detection from Raman Spectroscopy of the Cerebrospinal Fluid via Topological Machine Learning

“…Recently, RS techniques demonstrated significant potential in identifying AD by detecting specific biomarkers in body fluids [2]. Given the increasing number of RS studies, a systematic evaluation of the accuracy of RS in the diagnosis of AD was already performed, showing that RS is an effective and accurate tool for diagnosing AD, though it cannot rule out the possibility of misdiagnosis [3]. Recently, RS of tissue samples has been coupled with Topological Machine Learning (TML) for bone cancer grading [4], showing the feasibility of a topological approach for multi-label classification.…”