Discrimination of vascular aging using the arterial pulse spectrum and machine-learning analysis.

Aging contributes to the progression of vascular dysfunction and is a major nonreversible risk factor for cardiovascular disease. The aim of this study was to determine the effectiveness of using arterial pulse-wave measurements, frequency-domain pulse analysis, and machine-learning analysis in distinguishing vascular aging. Radial pulse signals were measured noninvasively for 3 min in 280 subjects aged 40-80 years. The cardio-ankle vascular index (CAVI) was used to evaluate the arterial stiffness of the subjects. Forty frequency-domain pulse indices were used as features, comprising amplitude proportion (Cn), coefficient of variation of Cn, phase angle (Pn), and standard deviation of Pn (n = 1-10). Multilayer perceptron and random forest with supervised learning were used to classify the data. The detected differences were more prominent in the subjects aged 40-50 years. Several indices differed significantly between the non-vascular-aging group (aged 40-50 years; CAVI <9) and the vascular-aging group (aged 70-80 years). Fivefold cross-validation revealed an excellent ability to discriminate the two groups (the accuracy was >80%, and the AUC was >0.8). For subjects aged 50-60 and 60-70 years, the detection accuracies of the two trained algorithms were around 80%, with AUCs of >0.73 for both, which indicated acceptable discrimination. The present method of frequency-domain analysis may improve the index reliability for further machine-learning analyses of the pulse waveform. The present noninvasive and objective methodology may be meaningful for developing a wearable-device system to reduce the threat of vascular dysfunction induced by vascular aging.

Classification of patients with Alzheimer's disease using the arterial pulse spectrum and a multilayer-perceptron analysis.

Cerebrovascular atherosclerosis has been identified as a prominent pathological feature of Alzheimer's disease (AD); the link between vessel pathology and AD risk may also extend to extracranial arteries. This study aimed to determine the effectiveness of using arterial pulse-wave measurements and multilayer perceptron (MLP) analysis in distinguishing between AD and control subjects. Radial blood pressure waveform (BPW) and finger photoplethysmography signals were measured noninvasively for 3 min in 87 AD patients and 74 control subjects. The 5-layer MLP algorithm employed evaluated the following 40 harmonic pulse indices: amplitude proportion and its coefficient of variation, and phase angle and its standard deviation. The BPW indices differed significantly between the AD patients (6247 pulses) and control subjects (6626 pulses). Significant intergroup differences were found between mild, moderate, and severe AD (defined by Mini-Mental-State-Examination scores). The hold-out test results indicated an accuracy of 82.86%, a specificity of 92.31%, and a 0.83 AUC of ROC curve when using the MLP-based classification between AD and Control. The identified differences can be partly attributed to AD-induced changes in vascular elastic properties. The present findings may be meaningful in facilitating the development of a noninvasive, rapid, inexpensive, and objective method for detecting and monitoring the AD status.