A review of traditional Chinese medicine diagnosis using machine learning: Inspection, auscultation-olfaction, inquiry, and palpation.

Traditional Chinese medicine (TCM) is an essential part of the Chinese medical system and is recognized by the World Health Organization as an important alternative medicine. As an important part of TCM, TCM diagnosis is a method to understand a patient's illness, analyze its state, and identify syndromes. In the long-term clinical diagnosis practice of TCM, four fundamental and effective diagnostic methods of inspection, auscultation-olfaction, inquiry, and palpation (IAOIP) have been formed. However, the diagnostic information in TCM is diverse, and the diagnostic process depends on doctors' experience, which is subject to a high-level subjectivity. At present, the research on the automated diagnosis of TCM based on machine learning is booming. Machine learning, which includes deep learning, is an essential part of artificial intelligence (AI), which provides new ideas for the objective and AI-related research of TCM. This paper aims to review and summarize the current research status of machine learning in TCM diagnosis. First, we review some key factors for the application of machine learning in TCM diagnosis, including data, data preprocessing, machine learning models, and evaluation metrics. Second, we review and summarize the research and applications of machine learning methods in TCM IAOIP and the synthesis of the four diagnostic methods. Finally, we discuss the challenges and research directions of using machine learning methods for TCM diagnosis.

Transcranial Ultrasound Stimulation of Hypothalamus in Aging Mice.

The hypothalamus plays an important role in the control of aging. Transcranial ultrasound stimulation (TUS) has been reported as a noninvasive method of neuromodulation. However, the effect of TUS of the hypothalamus on aging remains unclear. Therefore, the aim of this study is to verify whether TUS of the hypothalamus could affect the behaviors of aging mice and the expression level of apoptosis factors and inflammatory cytokines. TUS was delivered to the hypothalamus of mice ( n = 44 ) for 14 days (15 min/day) at a fundamental frequency of 1 MHz, pulse repetition frequency of 1 kHz (US1) or 10 Hz (US2), duty cycle of 10%, and acoustic pressure of 0.13 MPa. The effect of TUS on aging was evaluated by the behavioral tests or Western blotting in different stages. The behavioral results showed that mice in the US2 group improved their movement and learning. In addition, there was a significant improvement in the grip strength after TUS in the second behavioral tests (Sham: 0.0351 ± 0.0020 N/g; US1: 0.0340 ± 0.0023 N/g; US2: 0.0425 ± 0.0029 N/g, p = 0.034 ). Furthermore, the level of inflammation (TNF- α : Sham: 0.69 ± 0.084; US1: 0.39 ± 0.054; US2: 0.49 ± 0.1, p = 0.021 ) and apoptosis (Bax: Sham: 0.47 ± 0.049; US1: 0.42 ± 0.054; US2: 0.18 ± 0.055, p = 0.001 ) was significantly reduced after TUS in this stage. We did not see a long-lasting effect of TUS in the third behavioral tests. In addition, we found that TUS is safe according to hematoxylin and eosin (HE) staining. In conclusion, TUS could effectively modulate the hypothalamus, which may provide a new method for controlling aging.

The Study of Pulse Condition of Traditional Chinese Medicine in Information Age.

Using the study of pulse condition in Traditional Chinese Medicine (TCM) as a case example, this paper discusses the characteristics of pulse information obtained by Chinese medicine practitioners, how to correctly understand the relationship between the human body and Chinese medicine in the information age, how to deal with pulse data, and how to study TCM pulse condition . Furthermore, we point out that the application of modern big data processing technology to the pulse of Chinese medicine offers new opportunities.

Antiosteoporotic activity and constituents of Podocarpium podocarpum.

Our study aimed to investigate the antiosteoporotic properties of the ethanol extract of Podocarpium podocarpum (DC.) Yang et Huang (PE) in ovariectomized (OVX) rats and to characterize the active constituents. As a result, PE significantly inhibited the increased urinary Ca excretion and activity of bone resorption markers including tartrate-resistant acid phosphatase (TRAP), deoxypyridinoline crosslinks and cathepsin K in OVX rats, whereas exhibited little effects on the body, uterus and vagina weight. Detailed micro-CT analysis showed that PE notably enhanced bone quality, with increased bone mineral content (BMC), bone volume fraction (BVF), connectivity density (CD), tissue mineral content (TMC), tissue mineral density (TMD) and trabecular number (Tb. N), and decreased trabecular separation (Tb. Sp), in OVX animal. Those findings implied that PE had notable antiosteoporotic effect, especially effective in preventing bone resorption, with little side-effects on reproductive tissue. Further chemical investigation led to the isolation of 17 flavonoids, most of which showed significantly stimulatory effect on osteoblastic proliferation, ALP activity and mineralized nodes formation as well as inhibitory effect on osteoclastic TRAP activity in osteoblastic and osteoclastic cells. Our results indicated that PE, with abundant flavonoids, had remarkable antiosteoporotic activity and therefore can be a promising candidate for the treatment of postmenopausal osteoporosis induced by estrogen deficiency through herbal remedy.

The characteristics and key issues in electronic medical records (EMR) of traditional Chinese medicine TCM.

This poster briefly introduces the characteristics of TCM data, significances of EMR of TCM, and several key factors in the establishment of EMR of TCM.

Morphology variability analysis of wrist pulse waveform for assessment of arteriosclerosis status.

In this paper, approximate entropy (ApEn) is applied to study the variability of pulse waveform for assessing coronary arteriosclerosis status. Having analyzed the wrist pulse waveforms taken from both normal subjects and the patients suffering from coronary arteriosclerosis (CA) disorders, we find that pulse morphology variability (PMV) is more efficient than pulse interval variability (PIV) in assessing the conditions of human coronary artery. Usually, the PMVs of the healthy are higher than those of the patients with CA diseases, and the PMVs of patients with CA diseases have more high frequency components than those of the healthy subjects. That is to say, the CA disease also has influence on vascular tone. The effect of changes in cardiac performance due to CA disease can be reflected through the PMV. The experiment demonstrates that the specificity and sensitivity of the PMV's spectral energy ratio for clinical diagnosis of cardiovascular system is 80% and 97%, respectively.