1.Clinical decision support system based on explainable artificial intelligence?brain of Mengchao liver disease
Guoxu FANG ; Pengfei GUO ; Jianhui FAN ; Zongren DING ; Qinghua ZHANG ; Guangya WEI ; Haitao LI ; Jingfeng LIU
Chinese Journal of Digestive Surgery 2023;22(1):70-80
In recent years, the artificial intelligence machine learning and deep learning technology have made leap progress. Using clinical decision support system for auxiliary diagnosis and treatment is the inevitable developing trend of wisdom medical. Clinicians tend to ignore the interpretability of models while pursuing its high accuracy, which leads to the lack of trust of users and hamper the application of clinical decision support system. From the perspective of explainable artificial intelligence, the authors make some preliminary exploration on the construction of clinical decision support system in the field of liver disease. While pursuing high accuracy of the model, the data governance techniques, intrinsic interpretability models, post-hoc visualization of complex models, design of human-computer interactions, providing knowledge map based on clinical guidelines and data sources are used to endow the system with interpretability.
2.Application of finite element analysis in lumbar biomechanics
Guangya FAN ; Wenshuo SU ; Musen ZHONG ; Liqiang DONG
Chinese Journal of Tissue Engineering Research 2024;28(30):4896-4901
BACKGROUND:Finite element analysis is a commonly used mathematical modeling method to analyze the biomechanics of the lumbar spine.By constructing finite element models of the complex tissues such as muscles,blood vessels,and nerves in the lumbar region,mechanical analysis is performed to elucidate the pathogenesis of lumbar spine disorders and the mechanical mechanisms of treatment approaches. OBJECTIVE:To review the progress of finite element analysis in understanding the pathogenesis and treatment modalities of lumbar spine disorders,and to propose a new clinical workflow for the implementation of finite element analysis,aiming to provide a reference for future studies and promote the widespread utilization of finite element analysis in clinical diagnosis and treatment. METHODS:The PubMed database was searched using English keywords"finite element analysis,lumbar vertebra",while the WanFang and China National Knowledge Infrastructure(CNKI)databases were searched using Chinese keywords"finite element analysis,lumbar vertebra".A total of 73 articles were included for review. RESULTS AND CONCLUSION:(1)Lumbar spine degeneration in non-slipped patients typically originates from the posterior annulus fibrosus,while in patients with lumbar spine spondylolisthesis,degeneration starts from the lumbar facet joints due to abnormal mechanical mechanisms.(2)Restoring vertebral body height can prevent adjacent-level degeneration,and finite element analysis-measured vertebral compression strength can serve as an effective predictor of fracture risk,replacing bone density measurements.(3)In lumbar spine fusion surgery,selecting fusion devices of appropriate height and placing them transversely can prevent device subsidence.Increased intervertebral strain,circumferential stress,and intervertebral pressure in adjacent segments after fusion surgery may contribute to the occurrence of degenerative changes in neighboring segments.(4)Finite element analysis results suggest that preoperative planning for transforaminal endoscopic surgery should include considerations for osteotomy size to avoid excessive destruction of the articular process,and intraoperatively,preferential selection of a technique that traverses the superior articular process for foraminal dilatation.(5)In percutaneous kyphoplasty,bilateral pedicle screw augmentation should be performed,distributing bone cement on both sides of the pedicle.More advanced non-aluminum glass polyalkenoate cement materials should be selected.(6)Traction therapy should be personalized based on individual patient characteristics,including customized traction angles and forces,to achieve optimal therapeutic effects.(7)Manual therapy can induce relative displacement between the herniated intervertebral disc and the nerve root,thereby reducing compression.(8)The workflow involving CT/MR-AI Plus FEA-AI Plus Surgical robots can enable more precise diagnosis and treatment.
3.Mechanism of Buyang Huanwu decoction in the treatment of spinal cord injury based on network pharmacology
Musen ZHONG ; Zhongcheng AN ; Guangya FAN ; Jiqian BAO ; Wenshuo SU ; Liqiang DONG
China Modern Doctor 2024;62(1):63-69
Objective To verify the mechanism of Buyang Huanwu decoction in the treatment of spinal cord injury based on network pharmacology and molecular docking.Methods The active ingredients and targets of Buyang Huanwu decoction were screened out by TCMSP,SymMap,PubChem and Swiss Target Prediction databases.Spinal cord injury targets were retrieved from OMIM,GeneCards,TTD,and DrugBank databases.Through venny software,the intersection target of Buyang Huanwu decoction and spinal cord injury was obtained.The active ingredient-target network for the treatment of spinal cord injury was constructed with Cytoscape software.Gene ontology and Kyoto Encyclopedia of Genes and Genomes enrichment analysis of common targets were carried out by DAVID,and the binding ability of drugs and targets was analyzed by molecular docking technology.Results A total of 106 active ingredients and 225 targets of Buyang Huanwu decoction,1315 targets of spinal cord injury and 112 targets of drug-disease intersection were obtained.The active ingredients of Buyang Huanwu decoction were quercetin,kaempferol,ellagic acid,luteolin and hederagenin in the treatment of spinal cord injury.Conclusion Buyang Huanwu decoction can achieve the purpose of treating spinal cord injury through various signal pathways.
4.Platinum complexes of curcumin delivered by dual-responsive polymeric nanoparticles improve chemotherapeutic efficacy based on the enhanced anti-metastasis activity and reduce side effects.
Yan CHEN ; Chen CHEN ; Xiaojuan ZHANG ; Chuanchuan HE ; Pengxuan ZHAO ; Minsi LI ; Ting FAN ; Ruicong YAN ; Yao LU ; Robert J LEE ; Muhammad Waseem KHAN ; Muhammad SARFRAZ ; Xiang MA ; Tan YANG ; Guangya XIANG
Acta Pharmaceutica Sinica B 2020;10(6):1106-1121
Platinum-based chemotherapy is used for non-small cell lung cancer (NSCLC). However, it has side effects and minimum efficacy against lung cancer metastasis. In this study, platinum-curcumin complexes were loaded into pH and redox dual-responsive nanoparticles (denoted as Pt-CUR@PSPPN) to facilitate intracellular release and synergistic anti-cancer effects. Pt-CUR@PSPPN was prepared by a nano-precipitation method and had a diameter of ∼100 nm. The nanoparticles showed increased anti-cancer effects both and . In addition, Pt-CUR@PSPPN blocked PI3K/AKT signal transduction pathway and inhibited MMP2 and VEGFR2, resulting in enhanced anti-metastatic activity. Furthermore, reduced side effects were also observed. In conclusion, Pt-CUR@PSPPN provided a novel and attractive therapeutic strategy for NSCLC.
5.A smart O2-generating nanocarrier optimizes drug transportation comprehensively for chemotherapy improving
Xiaojuan ZHANG ; Chuanchuan HE ; Yun SUN ; Xiaoguang LIU ; Yan CHEN ; Chen CHEN ; Ruicong YAN ; Ting FAN ; Tan YANG ; Yao LU ; Jun LUO ; Xiang MA ; Guangya XIANG
Acta Pharmaceutica Sinica B 2021;11(11):3608-3621
Drug transportation is impeded by various barriers in the hypoxic solid tumor, resulting in compromised anticancer efficacy. Herein, a solid lipid monostearin (MS)-coated CaO2/MnO2 nanocarrier was designed to optimize doxorubicin (DOX) transportation comprehensively for chemotherapy enhancement. The MS shell of nanoparticles could be destroyed selectively by highly-expressed lipase within cancer cells, exposing water-sensitive cores to release DOX and produce O2. After the cancer cell death, the core-exposed nanoparticles could be further liberated and continue to react with water in the tumor extracellular matrix (ECM) and thoroughly release O2 and DOX, which exhibited cytotoxicity to neighboring cells. Small DOX molecules could readily diffuse through ECM, in which the collagen deposition was decreased by O2-mediated hypoxia-inducible factor-1 inhibition, leading to synergistically improved drug penetration. Concurrently, DOX-efflux-associated P-glycoprotein was also inhibited by O2, prolonging drug retention in cancer cells. Overall, the DOX transporting processes from nanoparticles to deep tumor cells including drug release, penetration, and retention were optimized comprehensively, which significantly boosted antitumor benefits.