Development of a tongue image-based machine learning tool for the diagnosis of gastric cancer: a prospective multicentre clinical cohort study.

Background: Tongue images (the colour, size and shape of the tongue and the colour, thickness and moisture content of the tongue coating), reflecting the health state of the whole body according to the theory of traditional Chinese medicine (TCM), have been widely used in China for thousands of years. Herein, we investigated the value of tongue images and the tongue coating microbiome in the diagnosis of gastric cancer (GC). Methods: From May 2020 to January 2021, we simultaneously collected tongue images and tongue coating samples from 328 patients with GC (all newly diagnosed with GC) and 304 non-gastric cancer (NGC) participants in China, and 16 S rDNA was used to characterize the microbiome of the tongue coating samples. Then, artificial intelligence (AI) deep learning models were established to evaluate the value of tongue images and the tongue coating microbiome in the diagnosis of GC. Considering that tongue imaging is more convenient and economical as a diagnostic tool, we further conducted a prospective multicentre clinical study from May 2020 to March 2022 in China and recruited 937 patients with GC and 1911 participants with NGC from 10 centres across China to further evaluate the role of tongue images in the diagnosis of GC. Moreover, we verified this approach in another independent external validation cohort that included 294 patients with GC and 521 participants with NGC from 7 centres. This study is registered at ClinicalTrials.gov, NCT01090362. Findings: For the first time, we found that both tongue images and the tongue coating microbiome can be used as tools for the diagnosis of GC, and the area under the curve (AUC) value of the tongue image-based diagnostic model was 0.89. The AUC values of the tongue coating microbiome-based model reached 0.94 using genus data and 0.95 using species data. The results of the prospective multicentre clinical study showed that the AUC values of the three tongue image-based models for GCs reached 0.88-0.92 in the internal verification and 0.83-0.88 in the independent external verification, which were significantly superior to the combination of eight blood biomarkers. Interpretation: Our results suggest that tongue images can be used as a stable method for GC diagnosis and are significantly superior to conventional blood biomarkers. The three kinds of tongue image-based AI deep learning diagnostic models that we developed can be used to adequately distinguish patients with GC from participants with NGC, even early GC and precancerous lesions, such as atrophic gastritis (AG). Funding: The National Key R&D Program of China (2021YFA0910100), Program of Zhejiang Provincial TCM Sci-tech Plan (2018ZY006), Medical Science and Technology Project of Zhejiang Province (2022KY114, WKJ-ZJ-2104), Zhejiang Provincial Research Center for Upper Gastrointestinal Tract Cancer (JBZX-202006), Natural Science Foundation of Zhejiang Province (HDMY22H160008), Science and Technology Projects of Zhejiang Province (2019C03049), National Natural Science Foundation of China (82074245, 81973634, 82204828), and Chinese Postdoctoral Science Foundation (2022M713203).

[Effect and mechanism of Bidens pilosa decoction on non-alcoholic fatty liver induced by high fat and high glucose in mice].

This study aimed to investigate the effect and possible mechanism of Bidens pilosa decoction on non-alcoholic fatty liver disease(NAFLD) induced by high fat and high glucose in mice. Bald/c mice were randomly divided into normal group, model group, metformin(200 mg·kg~(-1)) treatment group, Bidens pilosa decoction(10 g·kg~(-1)) treatment group, metformin and B. pilosa decoction(100 mg·kg~(-1)+5 g·kg~(-1)) treatment group. Except for the normal group, mice in the other four groups were fed with high-fat and high-glucose diet for 8 weeks to establish the non-alcoholic fatty liver model. After 4 weeks of treatment, blood was collected from the eyeballs, the mice were sacrificed, and relevant indicators were detected. The results showed that compared with the model group, blood lipid and blood glucose levels of each treatment group were significantly lower(P<0.05); HE staining results showed that liver pathological damage in each treatment group was significantly improved; oil red O staining results showed fat distribution in each treatment group significantly reduced(P<0.01); immunohistochemical staining showed that glucose regulated the protein expression of protein 78(GRP78) in liver tissues of each treatment group was also significantly reduced(P<0.01); Western blot results showed that endoplasmic reticulum stress signal pathway-related factors GRP78, phosphorylated-protein kinase R-like ER kinase(p-PERK), eukaryotic translation-initiation factor 2α(eIF2α), activating transcription factor 4(ATF4), C/EBP homologous protein(Chop), inositol requiring 1α(IRE1α), and cleaved-cysteinyl aspartate specific proteinase 12(cleaved-caspase-12) were significantly reduced(P<0.01). The results of the combined drug treatment group were better than those of the single drug treatment group. These results showed that B. pilosa decoction had the effect in improving non-alcoholic fatty liver, and its mechanism may be related to the down-regulation of the expression of endoplasmic reticulum stress(ERS)-related factors, and the reduction of the apoptosis of hepatocytes caused by ERS and the down-regulation of blood lipid and blood glucose levels.

[Study on preventive and therapeutic effects of Erzhi Pills on mice with Parkinson's disease induced by MPTP].

The aim of this study was to investigate the preventive and therapeutic effects of Erzhi Pills on 1-methyl-4-phenyl-1,2,3,6-tetrahydropyridine( MPTP)-induced Parkinson's disease( PD) in mice,and explore its possible mechanism of action. Mice were intraperitoneally injected with MPTP( 30 mg·kg-1,0. 01 m L·g-1) once daily to induce PD for 8 days. In the treatment group,Erzhi Pills were given by intragastric administration( 2. 5 g·kg-1,once daily for 30 days). The normal group received an equal volume of normalsaline. In terms of behavior,the limb movement coordination ability of the mice was detected by climbing,hanging and swimming experiments. The spatial learning and memory ability of the mice was detected by Morris water maze test. The content of MDA,as well as the activity of GSH-PX and SOD were determined in mice serum. Western blot was used to detect the protein expression levels of TH,MAOB and apoptosis-related factors CHOP and caspase-12 in brain tissues. Immunohistochemistry was used to detect the expression of TH in section of brain tissues in mice. The results showed that in behavioral aspects,as compared with the model group,the scores of limb movement ability as well as scores of spatial learning and memory ability were significantly improved in the treatment groups( P<0. 05). In terms of serological indicators,as compared with the model group,the activities of SOD and GSH-PX were significantly increased in the serum of treatment groups,and the content of MDA was significantly decreased( P<0. 05). The results of Western blot showed that as compared with the model group,the protein levels of TH in the brain tissues of the mice in treatment group were significantly up-regulated,while the protein levels of MAOB and apoptosis-related factors CHOP and caspase-12 were significantly down-regulated( P<0. 05). The results of immunohistochemistry showed that the number of TH positive cells in the brain tissues of the mice in the treatment group was significantly increased as compared with the model group( P<0. 05). In summary,Erzhi Pills have a certain preventive and therapeutic effect on MPTP-induced PD mice,which can significantly improve the limb motor coordination ability and spatial learning and memory ability of PD mice. Its mechanism may be related to down-regulating the expression of apoptosis-related factors CHOP and caspase-12,reducing the dopaminergic neuron damage and inhibiting dopaminergic neuronal apoptosis.