失智症帶來了許多生活上的不便，除了像是記憶力減退或是生活上的各種困難，對於家人與周遭人們帶來的負擔也相當大，根據世界衛生組織WHO的估計，全球失智症人口將從2019年的五千萬人，到2050年將成長至一億五千萬。而在台灣，根據台灣失智症協會預估台灣的失智人口數平均每天增加三十六人的速度成長著。
而失智症的診斷評估主要依賴電腦斷層、磁振造影、抽取腦脊髓液及量表填寫(如MMSE量表)，耗時久、成本高且侵入式，過去前人的研究指出失智症與血液循環及供血效率有關連性，且在腦部相關的中風疾病與脈波參數有相關影響。因此本實驗室期望能利用手腕橈動脈(BPW)及手指末梢(PPG)的脈波量測得出其供血相關頻域參數，並結合機器學習對失智症做出即時、客觀且非侵入的早期偵測與針灸對於失智症的療效評估。
本研究主要架構是穿戴式裝置結合脈波參數分析，並結合機器學習分類。透過本實驗室所開發的脈波量測系統包含的設備有心電訊號放大器(ECG)、動脈血壓波形模組(BPW)及光血容積訊號儀(PPG)，分別量測心臟端、動脈端與末梢端。機器學習分類使用多層感知器(MLP)。將BPW與PPG量測到的時域脈波資料轉成頻域參數進行後續計算與機器學習分類。
脈波頻域參數在1.失智症組與對照組有顯著差異 2.不同病程(輕、中、重度)的失智症組之間有顯著差異以及 3.針灸治療前後之失智症組在參數變異度的統計上有顯著差異。在機器學習的判別上也有良好的分類能力。在去除干擾因素如高血脂或高血壓病患的情況下在統計上與對照組仍可看出差異。另外與患者在針灸治療前後的MMSE量表分數差值及透過脈波參數訓練之機器學習患病機率差值的評估可得出其相關性，此結果顯示脈波量測之頻域參數對於失智症的早期偵測與療效評估能有機會以即時且客觀的方式進行判別。此一軟硬體系統架構有助於具有失智症狀態評估功能穿戴式裝置的開發。

Dementia brings a lot of inconveniences in life. In addition to memory loss or various difficulties in life, it also places a considerable burden on family members and people around them. According to the estimates of the World Health Organization, global dementia The population will grow from 50 million in 2019 to 150 million in 2050. In Taiwan, the Taiwan Dementia Association estimates that the number of people with dementia in Taiwan is growing at an average rate of 36 people per day.
The diagnosis and evaluation of dementia mainly rely on computer tomography, magnetic resonance imaging, cerebrospinal fluid extraction and filling of scales (such as the MMSE scale), which is time-consuming, costly and invasive. Previous studies have pointed out dementia It is related to blood circulation and blood supply efficiency, and stroke diseases related to the brain have related effects on pulse wave parameters. Therefore, our laboratory hopes to use the pulse wave measurements of the radial wrist (BPW) and the tip of the finger (PPG) to obtain the blood supply-related frequency domain parameters, and combine machine learning to make an instant, objective and non-invasive diagnosis of dementia. Early detection and evaluation of the efficacy of acupuncture for dementia.
The main framework of this research is wearable devices combined with pulse wave parameter analysis, combined with machine learning classification. The pulse wave measurement system developed by our laboratory includes equipment including electrocardiogram signal amplifier (ECG), arterial blood pressure waveform module (BPW) and photovolumetric signal (PPG), which measure the heart end, arterial end and Distal end. Machine learning classification uses a multi-layer perceptron (MLP). The time-domain pulse wave data measured by BPW and PPG are converted into frequency-domain parameters for subsequent calculation and machine learning classification.
The pulse wave frequency domain parameters are 1. There are significant differences between the dementia group and the control group 2. There are significant differences between the dementia groups of different courses (mild, moderate, and severe) and 3. The dementia group before and after acupuncture treatment There are statistically significant differences in parameter variability. It also has good classification ability in the judgment of machine learning. In the case of removing interfering factors such as hyperlipidemia or hypertension patients, statistical differences can still be seen with the control group. In addition, it is correlated with the patient’s MMSE scale score difference before and after acupuncture treatment and the prevalence difference of machine learning through pulse wave parameter training. This result shows that the frequency domain parameters of the pulse wave measurement are more The early detection and efficacy evaluation of mental illness can have the opportunity to make judgments in an instant and objective manner. This software and hardware system architecture is helpful for the development of wearable devices with dementia state assessment functions.

1. 台灣失智症協會.(2020). 失智症人口統計. Retrieved from
http://www.tada2002.org.tw/About/IsntDementia
2. 衛生福利部.(2017). 失智症診療手冊. Retrieved from
https://www.mohw.gov.tw/dl-27189-8993c3ad-0f47-45e0-a602-6a4362faae9a.html
3. Funato, H., Yoshimura, M., Yamazaki, T., Saido, T. C., Ito, Y., Yokofujita, J., Okeda, R., & Ihara, Y. (1998). Astrocytes containing amyloid beta-protein (Abeta)-positive granules are associated with Abeta40-positive diffuse plaques in the aged human brain. The American Journal of Pathology, 152(4), 983–992.
4. Iqbal, K., Liu, F., Gong, C. X., & Grundke-Iqbal, I. (2010). Tau in Alzheimer disease and related tauopathies. Current Alzheimer Research, 7(8), 656–664.
5. Folstein, M. F., Folstein, S. E., & McHugh, P. R. (1975). Mini-mental state: A practical method for grading the cognitive state of patients for the clinician. Journal of Psychiatric Research, 12(3), 189–198.
6. 陳均曄.(2019). 非侵入式循環訊號量測系統應用於不同癌症之偵測與評估.
7. 許家良,”血壓波形的諧波分析應用於多囊性卵巢集中風之偵測及療效評估研究” 博士論文, 國立台灣科技大學, 台北, 2014
8. 劉人銘.(2018). 循環量測應用於服用高血壓藥物患者之研究.
9. Iadecola, C., & Gottesman, R. F. (2018). Cerebrovascular Alterations in Alzheimer Disease. Circulation Research, 123(4), 406–408.
10. Marta Cortes-Canteli., & Costantino Iadecola. (2020). Alzheimer’s Disease and Vascular Aging.
11. Wolters, F. J., Zonneveld, H. I., Hofman, A., van der Lugt, A., Koudstaal, P. J., Vernooij, M. W., & Ikram, M. A. (2017). Cerebral perfusion and the risk of dementia: a population-based study. Circulation, 136(8), 719-728.
12. Chen, C. T., Huang, S. M., Hsiu, H., Hsu, W. C., Lin, F. C., & Lin, H. W. (2011). Using a blood pressure harmonic variability index to monitor the cerebral blood flow condition in stroke patients. Biorheology, 48(3-4), 219-228.
13. Ratmansky, M., Levy, A., Messinger, A., Birg, A., Front, L., & Treger, I. (2016). The Effects of Acupuncture on Cerebral Blood Flow in Post-Stroke Patients: A Randomized Controlled Trial. Journal of Alternative and Complementary Medicine (New York, N.Y.), 22(1), 33–37. https://doi.org/10.1089/acm.2015.0066.
14. Dolan, H., Crain, B., Troncoso, J., Resnick, S. M., Zonderman, A. B., & Obrien, R. J. (2010). Atherosclerosis, dementia, and Alzheimer disease in the Baltimore Longitudinal Study of Aging cohort. Annals of Neurology, 68(2), 231–240. https://doi.org/10.1002/ana.22055
15. Takayama, S., Watanabe, M., Kusuyama, H., Nagase, S., Seki, T., Nakazawa, T., & Yaegashi, N. (2012). Evaluation of the effects of acupuncture on blood flow in humans with ultrasound color Doppler imaging. Evidence-based complementary and alternative medicine : eCAM, 2012, 513638. https://doi.org/10.1155/2012/513638