Objective To evaluate the application value of artificial intelligence (AI) in the quality control of mammographic images and explore its feasibility for improving image quality. Methods A retrospective analysis was conducted on 500 mammographic images from 125 female patients. These images were acquired in December 2024 at the Department of Radiology, Obstetrics and Gynecology Hospital of Tongji University by two junior technologists with qualification certificate for junior radiologic technologists and ≤ 2 months of independent operation. The reference standard was the evaluation by a panel of senior experts comprising one associate chief radiologist and two intermediate radiologic technologists with over 10 years of experience in mammography. The evaluation was based on nine criteria within an AI quality control system. The correlation and consistency (Kappa test) of the assessment outcomes were compared among the junior technologist group, the AI quality control group, and the panel group. Additionally, the differences in the proportions of high-, medium-, and low-quality images rated by the three groups were analyzed. After one month of AI assistance, 200 images from 50 additional patients acquired by the same two junior technologists in January 2025 were collected. The area under the receiver operating characteristic curve and 95% confidence interval (95%CI) were calculated for the assessment performance of the junior technologist group before and after AI assistance. Differences were compared using the DeLong test. Changes in the disqualification rates for the nine criteria were analyzed. Results In consistency analysis, the AI quality control group showed high consistency with the panel group across multiple key criteria, with Kappa values ranging from 0.41 to 1.00. In contrast, the consistency between the junior technologist group and the panel group was generally low, with Kappa values ranging from 0.13 to 0.49. In comparison of image quality classification, no significant differences were observed in image quality classification between the AI group and the panel group (P>0.05). However, the proportion of images rated as high quality by the junior technologist group was significantly higher, while the proportions rated as medium and low quality were significantly lower, compared to those rated by the panel group (P<0.05). After AI assistance, the area under the receiver operating characteristic curve for the assessment performance of junior technologist group increased significantly from 0.56 (95%CI: 0.51-0.61) to 0.91 (95%CI: 0.87-0.94) (P<0.001). The disqualification rates for skin folds, incomplete inclusion of the pectoralis major muscle, and nipple not in profile decreased significantly. Conclusion AI demonstrates assessment capability comparable to the panel group in mammographic quality control. AI effectively enhances the quality of images acquired by junior technologists through real-time, objective feedback.

Objective To evaluate the application value of artificial intelligence (AI) in the quality control of mammographic images and explore its feasibility for improving image quality. Methods A retrospective analysis was conducted on 500 mammographic images from 125 female patients. These images were acquired in December 2024 at the Department of Radiology, Obstetrics and Gynecology Hospital of Tongji University by two junior technologists with qualification certificate for junior radiologic technologists and ≤ 2 months of independent operation. The reference standard was the evaluation by a panel of senior experts comprising one associate chief radiologist and two intermediate radiologic technologists with over 10 years of experience in mammography. The evaluation was based on nine criteria within an AI quality control system. The correlation and consistency (Kappa test) of the assessment outcomes were compared among the junior technologist group, the AI quality control group, and the panel group. Additionally, the differences in the proportions of high-, medium-, and low-quality images rated by the three groups were analyzed. After one month of AI assistance, 200 images from 50 additional patients acquired by the same two junior technologists in January 2025 were collected. The area under the receiver operating characteristic curve and 95% confidence interval (95%CI) were calculated for the assessment performance of the junior technologist group before and after AI assistance. Differences were compared using the DeLong test. Changes in the disqualification rates for the nine criteria were analyzed. Results In consistency analysis, the AI quality control group showed high consistency with the panel group across multiple key criteria, with Kappa values ranging from 0.41 to 1.00. In contrast, the consistency between the junior technologist group and the panel group was generally low, with Kappa values ranging from 0.13 to 0.49. In comparison of image quality classification, no significant differences were observed in image quality classification between the AI group and the panel group (P>0.05). However, the proportion of images rated as high quality by the junior technologist group was significantly higher, while the proportions rated as medium and low quality were significantly lower, compared to those rated by the panel group (P<0.05). After AI assistance, the area under the receiver operating characteristic curve for the assessment performance of junior technologist group increased significantly from 0.56 (95%CI: 0.51-0.61) to 0.91 (95%CI: 0.87-0.94) (P<0.001). The disqualification rates for skin folds, incomplete inclusion of the pectoralis major muscle, and nipple not in profile decreased significantly. Conclusion AI demonstrates assessment capability comparable to the panel group in mammographic quality control. AI effectively enhances the quality of images acquired by junior technologists through real-time, objective feedback.

Objective To evaluate the application value of artificial intelligence (AI) in the quality control of mammographic images and explore its feasibility for improving image quality. Methods A retrospective analysis was conducted on 500 mammographic images from 125 female patients. These images were acquired in December 2024 at the Department of Radiology, Obstetrics and Gynecology Hospital of Tongji University by two junior technologists with qualification certificate for junior radiologic technologists and ≤ 2 months of independent operation. The reference standard was the evaluation by a panel of senior experts comprising one associate chief radiologist and two intermediate radiologic technologists with over 10 years of experience in mammography. The evaluation was based on nine criteria within an AI quality control system. The correlation and consistency (Kappa test) of the assessment outcomes were compared among the junior technologist group, the AI quality control group, and the panel group. Additionally, the differences in the proportions of high-, medium-, and low-quality images rated by the three groups were analyzed. After one month of AI assistance, 200 images from 50 additional patients acquired by the same two junior technologists in January 2025 were collected. The area under the receiver operating characteristic curve and 95% confidence interval (95%CI) were calculated for the assessment performance of the junior technologist group before and after AI assistance. Differences were compared using the DeLong test. Changes in the disqualification rates for the nine criteria were analyzed. Results In consistency analysis, the AI quality control group showed high consistency with the panel group across multiple key criteria, with Kappa values ranging from 0.41 to 1.00. In contrast, the consistency between the junior technologist group and the panel group was generally low, with Kappa values ranging from 0.13 to 0.49. In comparison of image quality classification, no significant differences were observed in image quality classification between the AI group and the panel group (P>0.05). However, the proportion of images rated as high quality by the junior technologist group was significantly higher, while the proportions rated as medium and low quality were significantly lower, compared to those rated by the panel group (P<0.05). After AI assistance, the area under the receiver operating characteristic curve for the assessment performance of junior technologist group increased significantly from 0.56 (95%CI: 0.51-0.61) to 0.91 (95%CI: 0.87-0.94) (P<0.001). The disqualification rates for skin folds, incomplete inclusion of the pectoralis major muscle, and nipple not in profile decreased significantly. Conclusion AI demonstrates assessment capability comparable to the panel group in mammographic quality control. AI effectively enhances the quality of images acquired by junior technologists through real-time, objective feedback.

ObjectiveTo explore the mechanism of Hei Xiaoyaosan in improving the cognitive function in Alzheimer's disease （AD） from cell apoptosis mediated by the phosphatidylinositol 3-kinase （PI3K）/protein kinase B （Akt）/nuclear factor kappa B （NF-κB） signaling pathway. MethodsFour-month-old SD male rats were randomly assigned into a blank group， a sham group， a model group， a donepezil hydrochloride （0.45 mg·kg^-1） group， and high-， medium-， and low-dose （15.30， 7.65， and 3.82 g·kg^-1， respectively） Hei Xiaoyaosan groups， with 10 rats in each group. The sham group received bilateral hippocampal injection of 1 μL normal saline， while the other groups received bilateral hippocampal injection of 1 μL beta-amyloid 1-42 （Aβ_1-42） solution for the modeling of AD. Rats were administrated with corresponding agents once a day for 42 consecutive days. The Morris water maze test was carried out to assess the learning and memory abilities of rats. Hematoxylin-eosin staining was employed to observe pathological changes in the hippocampus of rats. Enzyme-linked immunosorbent assay was employed to measure the levels of cysteinyl aspartate-specific proteinase-3 （Caspase-3）， B-cell lymphoma-2 （Bcl-2）， and Bcl-2-associated X protein （Bax）. Western blot was employed to determine the protein levels of PI3K， Akt， and NF-κB. A cell model of AD was established by co-culturing Aβ_1-42 and PC12 cells in vitro. Cell viability and apoptosis were detected by the cell-counting kit 8 （CCK-8） assay and flow cytometry （FC）， respectively. ResultsAnimal experiments showed that compared with the blank group， the model group had a prolonged escape latency （P<0.01）， a reduced number of crossing platforms （P<0.01）， disarrangement and a reduced number of hippocampal neurons， up-regulated expression of Bax and Caspase-3， down-regulated expression of Bcl-2 （P<0.01）， decreased p-PI3K/PI3K and p-Akt/Akt levels， and an increased p-NF-κB/NF-κB level （P<0.01）. Compared with the model group， donepezil hydrochloride and high- and medium-dose Hei Xiaoyaosan shortened the escape latency and increased the number of crossing platforms （P<0.05， P<0.01）， improved the arrangement and increased the number of hippocampal neurons， down-regulated the expression levels of Bax and Caspase-3， up-reguated the expression level of Bcl-2 （P<0.05， P<0.01）， increased the p-PI3K/PI3K and p-Akt/Akt levels （P<0.05， P<0.01）， and reduced the p-NF-κB/NF-κB level （P<0.05， P<0.01）. Cell experiments showed that compared with the blank group， the model group exhibited an increased apoptosis rate （P<0.01）. Compared with the model group， the serum containing Hei Xiaoyaosan at various doses improved the cell viability （P<0.01）， and the serum containing Hei Xiaoyaosan at the high dose decreased the cell apoptosis （P<0.01）. ConclusionHei Xiaoyaosan may improve the learning and memory abilities of AD model rats by regulating cell apoptosis， while increasing the vitality and reducing the apoptosis rate of AD model cells via the PI3K/Akt/NF-κB signaling pathway.

ObjectiveTo observe the effects of Hei Xiaoyaosan on the learning and memory abilities of Alzheimer's disease model mice （APP/PS1 mice）， and to explore its mechanism through the inflammatory cascade mediated by nucleotide-binding oligomerization domain-like receptor family pyrin domain-containing 3 （NLRP3）/cysteine aspartate-specific protease （Caspase-1）/gasdermin D （GSDMD） signaling pathway. MethodsSPF-grade 4-month-old APP/PS1 mice were randomly divided into the model group， MCC950 group， and Hei Xiaoyaosan high-， medium-， and low-dose groups. C57BL/6J mice were used as the blank group. After 7 days of adaptive feeding， mice in each group were intervened. The Hei Xiaoyaosan high-， medium-， and low-dose groups were given corresponding doses by gavage （25.79， 12.90， 6.45 g·kg^-1·d^-1）， the MCC950 group was intraperitoneally injected with 10 mg·kg^-1·2 d^-1， and the blank group received the same volume of physiological saline by gavage. After 90 days of intervention， the learning and memory abilities were assessed using the Y maze and Morris water maze tests. The structural changes of hippocampal neurons were observed by hematoxylin-eosin （HE） staining. The expression of amyloid precursor protein （APP） in the hippocampal CA3 region was detected by immunohistochemistry. Enzyme-linked immunosorbent assay （ELISA） was used to measure the levels of interleukin （IL）-10， IL-18， and IL-1β in the hippocampus. Western blot was applied to detect the protein expression of NLRP3， Caspase-1， GSDMD， and GSDMD-N in the hippocampus. Immunofluorescence was used to detect the co-localization of GSDMD-N and ionized calcium-binding adapter molecule-1 （Iba-1） in the hippocampus. Results① In the Y maze test， compared with the blank group， the spontaneous alternation rate of the model group was significantly reduced （P<0.01）. Compared with the model group， the spontaneous alternation rate in the Hei Xiaoyaosan high- and low-dose groups was significantly increased （P<0.01）. ② In the Morris water maze test， during the 1-4 days of the location navigation test， the escape latency time of mice decreased with the extension of training time. On day 4， compared with the blank group， the model group showed a significantly increased escape latency （P<0.05）. Compared with the model group， the MCC950 group and the Hei Xiaoyaosan low-dose group showed significantly reduced escape latency （P<0.05）. In the spatial exploration experiment， compared with the blank group， the number of platform crossings in the model group was significantly reduced （P<0.01）. Compared with the model group， the Hei Xiaoyaosan low-dose group showed significantly increased platform crossings （P<0.05）. ③ HE staining showed that， compared with the blank group， the hippocampal CA3 cells of the model group were damaged， arranged loosely and irregularly， swollen， with unclear boundaries， and the nuclei were pyknotic and deeply stained. MCC950 and all doses of Hei Xiaoyaosan improved the hippocampal CA3 cell damage in APP/PS1 mice to varying degrees. ④ Immunohistochemical results indicated that， compared with the blank group， the expression of APP in the hippocampal CA3 region was significantly increased in the model group （P<0.01）. MCC950 and all doses of Hei Xiaoyaosan could reduce the expression of APP in the hippocampal CA3 region of APP/PS1 mice （P<0.01）. ⑤ ELISA results showed that the levels of IL-18 and IL-1β in the hippocampus of mice in the model group were significantly increased， and IL-10 levels were significantly reduced （P<0.01）. Compared with the model group， the IL-18 levels in the MCC950 group and the Hei Xiaoyaosan medium- and low-dose groups were significantly reduced （P<0.01）. IL-1β levels in the hippocampus of the MCC950 group and Hei Xiaoyaosan high-， medium-， and low-dose groups were significantly decreased （P<0.01）. The IL-10 levels in the hippocampus of the MCC950 group and the Hei Xiaoyaosan medium- and low-dose groups were increased （P<0.05， P<0.01）. ⑥ Western blot results showed that compared with the blank group， the protein levels of NLRP3， Caspase-1， GSDMD， and GSDMD-N in the hippocampus of the model group were significantly elevated （P<0.01）. Compared with the model group， the content of NLRP3 and Caspase-1 in the hippocampus of the treated groups was decreased （P<0.05， P<0.01）. The content of GSDMD in the hippocampus of the Hei Xiaoyaosan high-， medium-， and low-dose groups was reduced （P<0.05， P<0.01）， and the content of GSDMD-N in the hippocampus of the Hei Xiaoyaosan medium- and low-dose groups was decreased （P<0.05， P<0.01）. ⑦ Immunofluorescence results showed that， compared with the blank group， the co-expression of GSDMD-N and Iba-1 in the hippocampus of the model group was significantly increased （P<0.01）. Compared with the model group， the co-expression of GSDMD-N and Iba-1 in the treated groups was significantly reduced （P<0.01）. ConclusionHei Xiaoyaosan may regulate the NLRP3/Caspase-1/GSDMD signaling pathway to affect the release of inflammatory factors， alleviate neuroinflammation，improve hippocampal histopathological changes，and improve learning and memory deficits，thus providing potential therapeutic benefits for Alzheimer's disease.

Objective To investigate the mechanism by which angiopoietin-like protein 8(ANGPTL8)regulates vascular smooth muscle cell(VSMCs)apoptosis.Methods An in vitro abdominal aortic aneurysm cell model was established by stimulating human VSMCs(HUSMCs)with angiotensin Ⅱ(AngⅡ).Stable ANGPTL8 knockdown and over-expression VSMC cell strains were generated using lentiviral transfection.TUNEL staining was used to de-tect apoptosis.Western blot analysis was performed to measure the protein expression of ANGPTL8,caspase9,caspase3,Bcl-2,Bax,p53,and PUMA,while RT-qPCR was used to assess mRNA expression of ANGPTL8,Bcl-2 and Bax.Results AngⅡ significantly induced ANGPTL8 expression in HVSMCs in a time-and dose-de-pendent manner(P＜0.05).ANGPTL8 knockdown significantly reduced the expression of apoptosis-related proteins caspase9,caspase3,and Bax,while increased the expression of the anti-apoptotic protein Bcl-2(P＜0.05).Con-versely,ANGPTL8 over-expression markedly induced HVSMCs apoptosis,which was significantly suppressed by treatment with the p53 pathway inhibitor pifithrin-α(PFT-α).Conclusions ANGPTL8 may promote VSMC apop-tosis by activation of p53 signaling pathway.

ObjectiveTo explore the effect and mechanism of Hei Xiaoyaosan in regulating the tumor necrosis factor receptor superfamily member 6 （Fas）/Fas ligand （FasL）/cysteine protease-8 （Caspase-8）/cysteine protease-3 （Caspase-3） signaling pathway to intervene in neuronal apoptosis and prevent Alzheimer's disease （AD）. MethodNinety SPF-grade SD male rats of 4 months old were selected and randomly grouped as follows： 10 rats in the blank group， 10 rats in the sham group （bilateral hippocampus injected with 1 μL normal saline）， and 70 rats in the modeling group ［bilater hippocampus injected with 1 μL amyloid-beta protein 1-42 （Aβ_1-42） solution for the modeling of AD］. Fifty successfully modeled rats were selected and randomly assigned into model， donepezil hydrochloride （0.45 mg·kg^-1）， and high-， medium-， and low-dose （15.30， 7.65， 3.82 g·kg^-1） Hei Xiaoyaosan groups. Rats were administrated with corresponding agents by gavage once a day for 42 days. Terminal-deoxynucleoitidyl transferase-mediated nick end labeling （TUNEL） was employed to observe the apoptosis of neurons in the cortex and hippocampus， and immunohistochemistry （IHC） was used to detect the expression of B-cell lymphoma-2 （Bcl-2） and Bcl-2-associated X protein （Bax） in the hippocampus. Real-time fluorescence quantitative polymerase chain reaction（Real-time PCR） was employed to determine the mRNA levels of Fas， FasL， and Fas-associated protein with death domain （Fadd）. Western blot was used to determine the protein levels of Fas， FasL， Fadd， Caspase-3， cleved Caspase-3， Caspase-8， and cleved Caspase-8. ResultCompared with the blank group and sham group， the model group showed increased apoptosis rate in the cortex and hippocampus （P<0.01）， elevated Bax level （P<0.01）， lowered Bcl-2 level （P<0.01）， up-regulated mRNA levels of Fas， FasL， and Fadd in the hippocampus （P<0.01）， and up-regulated protein levels of Fas， FasL， Fadd， cleaved Caspase-3， and cleaved Caspase-8 （P<0.01）. Compared with the model group， donepezil hydrochloride and Hei Xiaoyaosan at high and medium doses decreased the apoptosis rate in the cortex and hippocampus （P<0.05， P<0.01）， lowered the Bax level （P<0.01）， elevated the Bcl-2 level （P<0.01）， and down-regulated the mRNA levels of Fas， FasL， and Fadd and the protein levels of Fas， FasL， Fadd， cleaved Caspase-3， and cleaved Caspase-8 （P<0.05， P<0.01） in the hippocampus. Low-dose Hei Xiaoyaosan decreased the apoptosis rate in the cortex and hippocampus （P<0.05， P<0.01）， lowered the Bcl-2 level （P<0.01）， and down-regulated the mRNA levels of FasL and Fadd （P<0.05） and the protein levels of Fas， FasL， Fadd， cleaved Caspase-3， and cleaved Caspase-8 （P<0.05） in the hippocampus. ConclusionHei Xiaoyaosan can protect neurons in the cortex and hippocampus of AD rats by inhibiting the apoptosis mediated by the Fas/FasL/Caspase-8/Caspase-3 signaling pathway.

ObjectiveTo explore the effect and mechanism of Hei Xiaoyaosan in modulating the synaptic plasticity in APP/PS1 mice by regulating the cyclic adenosine monophosphate （cAMP）/protein kinase A （PKA）/N-methyl-D-aspartate receptor （NMDAR） signaling pathway. MethodTwelve 4-month-old male C57BL/6J mice were selected as the blank control group， and 60 4-month-old male APP/PS1 double transgenic mice were randomized into model， KW-6002 （adenosine receptor antagonist， 3 mg·kg^-1）， and high-， medium-， and low-dose （22.10， 11.05， 5.53 g·kg^-1， respectively） Hei Xiaoyaosan groups， with 12 mice in each group. Mice were administrated with corresponding drugs for 90 days. Transmission electron microscopy was employed to observe the synaptic ultrastructure of hippocampal neurons， and Golgi staining was used to observe the dendritic spine density of neurons in hippocampal CA1 region. Western blot was employed to measure the protein levels of cAMP， PKA， N-methyl-D-aspartate receptors 1， 2A， and 2B （NR1， NR2A， and NR2B， respectively）， postsynaptic density protein 95 （PSD95）， and synapsin 1 （SYN1）. Real-time fluorescence quantitative polymerase chain reaction（Real-time PCR） was performed to determine the mRNA levels of cAMP， PKA， and NR1. Enzyme-linked immunosorbent assay was employed to determine the content of interleukin-12 （IL-12） and interleukin-4 （IL-4） in the hippocampus. ResultCompared with the blank group， the model group showed blurred boundaries between presynaptic membrane and postsynaptic membrane in hippocampal CA1 region， reduced and scattered synaptic vesicles， and decreased density of postsynaptic membrane， and irregular， disarranged， and loosened dendritic spines of neurons in hippocampal CA1 region （P<0.01）. In addition， the model group presented down-regulated protein levels of cAMP， PKA， NR1， NR2A， NR2B， PSD95， and SYN1 and mRNA levels of cAMP， PKA， and NR1， elevated IL-12 level， and lowered IL-4 level in the hippocampus （P<0.01）. Compared with the model group， the drug intervention groups showed clear and intact boundaries between presynaptic membrane and postsynaptic membrane in hippocampal CA1 region， increased synaptic vesicles with dense arrangement， increased density of postsynaptic membrane， and improved morphology， arrangement， and density of neuronal dendritic spines （P<0.05， P<0.01）. In addition， the drug interventions up-regulated the protein levels of cAMP， PKA， NR1， NR2A， NR2B， PSD95， and SYN1 （P<0.05，P<0.01） and mRNA levels of cAMP， PKA， and NR1 （P<0.01）， lowered the IL-12 level （P<0.01）， and elevated the IL-4 level （P<0.01） in the hippocampus. ConclusionHei Xiaoyaosan can improve the structure and morphology of hippocampal neurons in APP/PS1 mice by activating the cAMP/PKA/NMDAR signaling pathway and repairing synaptic plasticity.

ObjectiveTo investigate the role and mechanism of Hei Xiaoyaosan in intervening in oxidative stress in the rat model of Alzheimer's disease （AD） via modulating the rat sarcoma （RAS）/rapidly accelerating fibrosarcoma （RAF）/mitogen-activated protein kinase kinase （MEK）/extracellular signal-regulated kinase （ERK） signaling pathway. MethodOne hundred 4-month-old SPF-grade Wistar male rats were randomly grouped as follows： 10 in the blank group， 10 in the sham group （bilateral hippocampus injected with 1 μL normal saline）， and 80 in the modeling group ［bilateral hippocampus injected with 1 μL amyloid beta protein 1-42 （Aβ_1-42） solution for the modeling of AD］. Fifty rats qualified for modeling were selected and randomized into the model， donepezil hydrochloride （0.5 mg·kg^-1）， and high-， medium-， and low-dose （15.30， 7.65， 3.82 g·kg^-1， respectively） Hei Xiaoyaosan groups. The rats were administrated with corresponding drugs by gavage once a day for 42 consecutive days. At the end of gavage， Morris water maze test was performed to examine the learning and memory abilities of the rats， and Nissl staining was used to observe the pathological changes of neurons in CA3 region of the hippocampus. The immunofluorescence assay was used to observe Aβ deposition and tau phosphorylation. Western blot was employed to determine the protein levels of RAS， RAF， phosphorylated （p）-RAF， MEK， p-MEK， ERK， and p-ERK in the hippocampal tissue. Biochemical methods were used to determine the levels of reactive oxygen species （ROS）， malondialdehyde （MDA）， and superoxide dismutase （SOD） in the hippocampal tissue. ResultCompared with the sham group， the model group showed prolonged escape latency （P<0.01）， shortened swimming distance in the target quadrant （P<0.01）， reduced and uneven stained Nissl bodies， enhanced fluorescence intensity of Aβ and p-tau （P<0.01）， up-regulated protein levels of RAS， p-RAF， p-MEK， and p-ERK in the hippocampal tissue （P<0.01）， increased ROS and MDA content （P<0.01）， and decreased SOD activity （P<0.01） on day 5. Compared with the model group， donepezil hydrochloride and high-， medium-， and low-dose Hei Xiaoyaosan shortened the escape latency （P<0.01）， increased the swimming distance in the target quadrant （P<0.01）， improved the arrangement， morphology， and structures of neurons and the number and distribution of Nissl bodies， decreased the fluorescence intensity of Aβ and p-tau （P<0.01）， up-regulated the protein levels of RAS， p-RAF， p-MEK， and p-ERK （P<0.05， P<0.01）， decreased the ROS and MDA content （P<0.01）， and increased the SOD activity （P<0.01） on day 5. ConclusionHei Xiaoyaosan may ameliorate oxidative stress， reduce Aβ and p-tau levels， and inhibit hippocampal neuronal damage by regulating the RAS/RAF/MEK/ERK signaling pathway， thus improving learning and memory abilities.

Alzheimer's disease （AD） is a neurodegenerative disease that predominantly affects the elderly. It belongs to the category of dementia in traditional Chinese medicine （TCM）， with the onset and progression closely associated with the functions of the kidney， liver， and spleen. The classic TCM formula Hei Xiaoyaosan， which regulates the three Yin of liver， spleen， and kidney， shows broad prospects in treating neurodegenerative diseases. This article reviews the experimental studies reported in the past decade to summarize the mechanisms of Hei Xiaoyaosan and its active components in intervening in AD. Hei Xiaoyaosan can treat AD via multiple targets， levels， and aspects comprehensively. The clinical studies have demonstrated that Hei Xiaoyaosan alone or in combination with other therapies has a definite therapeutic effect on AD. Specifically， it can ameliorate the cognitive impairment， mitigate oxidative stress， and inhibit the overexpression of soluble apoptotic factors in AD patients. This review aims to provide a theoretical basis for the treatment of AD with Hei Xiaoyaosan and explore new research directions. Moreover， it gives new insights into the clinical application of Hei Xiaoyaosan and the development of products with both medicinal and edible values.