Journal of Sun Yat-sen University (Medical Sciences)

Journal of Sun Yat-sen University (Medical Sciences) Journal of Sun Yat-sen University (Medical Sciences)

Editor-in-Chief:GAO Guoquan

ISSN:1672-3554

CN:44-1575/R

Supervisor:the Ministry of Education of China

Sponsor:Sun Yat-sen University

Publication frequency:Bimonthly

Tel.:020-87331643

Quick Entry

  • Author Center Author Center
  • Review Center Review Center
  • Office Center Office Center
  • Journal Center Journal Center
  • Latest Articles
  • Online First
  • Archive
更多
Volume 47 期 2，2026 2026年第47卷第2期

  • Review

    ZHANG Shucheng, SI Xiaoqing

    DOI：10.11714/jsysu.med.YX20260019
    摘要：Machine learning （ML） is increasingly being integrated into clinical decision-making in dermatology， penetrating multiple critical stages including lesion identification， multimodal differential diagnosis， personalized treatment recommendation， efficacy prediction， and prognosis evaluation. By synthesizing multi-source data such as medical imaging， genomics， and clinical characteristics， ML models not only assist clinicians in improving diagnostic accuracy but also optimize therapeutic selection， enabling dynamic disease management and individualized intervention， thereby demonstrating substantial clinical application potential. For instance， convolutional neural network-based image analysis systems have exhibited performance comparable to or exceeding that of dermatology experts in the recognition of cutaneous neoplasms. Regarding treatment optimization， ML can recommend personalized medication regimens， predict treatment responses and adverse event risks by analyzing multidimensional patient data， thereby providing robust support for precision medicine. In the realm of prognosis assessment and long-term management， ML models incorporating patient-reported outcomes and time-series data facilitate dynamic monitoring of disease progression and individualized prediction of recurrence risk. However， despite rapid technological advances， the practical translation of ML into dermatological clinical decision-making still confronts multiple bottlenecks， including data bias， insufficient algorithmic generalization， lack of robust clinical validation， difficulties in system integration， and incomplete ethical supervision. This review systematically outlines the current applications and research progress of ML across various stages of dermatological clinical decision-making， thoroughly analyzes the key bottlenecks encountered， and comprehensively synthesizes advances in ML-assisted clinical decision support spanning image recognition， treatment optimization， prognosis evaluation， and ethical challenges， aiming to provide valuable insights for related research and clinical practice.  
    关键词：machine learning;dermatology;clinical decision-making;artificial intelligence-assisted diagnosis;multimodal data   
    79
    |
    42
    |
    0
    <HTML>
    <L-PDF><Meta-XML>
    <引用本文> <批量引用> 153123609 false
    更新时间：2026-03-20

    QU Yanfei, LI Yanjie

    DOI：10.11714/jsysu.med.YX20250175
    摘要：Parkinson’s disease （PD） is a neurodegenerative disorder characterized by the loss of dopaminergic neurons in the substantia nigra pars compacta （SNpc） of the midbrain. Current therapeutic strategies are unable to reverse the neurodegenerative process， highlighting an urgent need for neuroprotective interventions. The phosphatidylinositol 3-kinase/protein kinase B （PI3K/Akt） signaling pathway， as a key pathway regulating cell survival， has emerged as an important target for PD intervention. In recent years， traditional Chinese medicine （TCM）， with its distinctive properties of multi-targeted action and holistic regulation， has demonstrated considerable potential in PD neuroprotection research based on the PI3K/Akt pathway. However， most studies in this field are currently limited to the preclinical stage， and there is a lack of high-quality clinical evidence that correlates patients’ clinical endpoints ［e.g.， Unified Parkinson’s Disease Rating Scale （UPDRS） scores］ with pathway-related biomarkers ［e.g.， phosphorylated Akt （p-Akt） levels］， which hinders its clinical translation. Therefore， this paper reviews the research progress of TCM in the prevention and treatment of PD by regulating the PI3K/Akt pathway， and prospects the future direction of integrated research on “clinical phenotype-pathway activity-TCM intervention”， aiming to provide references for relevant basic research and clinical translation.  
    关键词：Parkinson's disease;traditional chinese medicine;PI3K/Akt;signaling pathway;mechanisms   
    57
    |
    51
    |
    0
    <HTML>
    <L-PDF><Meta-XML>
    <引用本文> <批量引用> 153123354 false
    更新时间：2026-03-20

    WAN Chenlei, REN Binbin

    DOI：10.11714/jsysu.med.YX20250151
    摘要：Ischemic stroke （IS） is a neurological disorder with high rates of disability and mortality worldwide， characterized by complex interactions between immune-inflammatory responses and various forms of cell death during its onset and progression. In recent years， pyroptosis， a form of programmed cell death mediated by inflammasomes， has attracted increasing attention for its critical role in post-stroke neuronal injury. Among the underlying mechanisms， the NOD-like receptor family pyrin domain-containing 3 inflammasome-Gasdermin D （NLRP3-GSDMD） pathway， as the central signaling axis of pyroptosis， plays a crucial regulatory role in immune responses and neuronal dysfunction following cerebral ischemia. However， current therapeutic strategies targeting this pathway remain limited by insufficient specificity and an incomplete understanding of its mechanisms of action. Therefore， this review summarizes the immuno-inflammatory pathology of IS， the mechanisms of the NLRP3-GSDMD pathway and pyroptosis， as well as emerging immunotherapeutic strategies targeting this signaling axis， aiming to provide insights and references for future research on pyroptosis-based immunomodulatory therapies for stroke.  
    关键词：NLRP3-GSDMD pathway;pyroptosis;ischemic stroke;immune inflammation;treatment   
    72
    |
    55
    |
    0
    <HTML>
    <L-PDF><Meta-XML>
    <引用本文> <批量引用> 153123364 false
    更新时间：2026-03-20

  • Preclinic Research

    WU Yixi, PAN Rui, YANG Yang, FENG Liang, WU Weirui, FANG Zhenzhen, QI Weiwei, YANG Xia

    DOI：10.11714/jsysu.med.YX20260020
    摘要：ObjectiveTo explore the key genes influencing diacylglycerol metabolism in neuroblastoma （NB）， clarify the expression and clinical significance of diacylglycerol acyltransferase 2 （DGAT2） in NB， and provide a theoretical basis for the diagnosis and targeted therapy of NB.MethodsNB transcriptome data were obtained from GEO （GSE49710） and TCGA （TARGET-NBL） databases. Differentially expressed genes （DEGs） commonly upregulated in MYCN-amplified groups were screened， and the key gene DGAT2 was identified by intersecting the screened DEGs with the diacylglycerol metabolism-related gene set followed by prognostic analysis and comparison. The expression of DGAT2 was analyzed via the R2 database. The potential impact of DGAT2 on the immune microenvironment was explored by combining the single-cell dataset GSE137804. Immunohistochemistry （IHC） was used to detect the expression level of DGAT2 and its correlation with MYCN expression in 55 clinical NB tissues and mouse xenograft tumor tissues.ResultsA total of 907 DEGs commonly upregulated in the MYCN-amplified groups were screened， among which three DEGs were highly expressed in the diacylglycerol metabolism-related gene set （P＜0.05）. After comparison， DGAT2 was found to have the most significant impact on prognosis （HR=1.4， 95% CI：1.2，1.7； P=5.41×10-7）. Survival analysis showed that patients with high DGAT2 expression had a significantly shorter overall survival. Single-cell analysis revealed that high expression of DGAT2 led to an immunosuppressive microenvironment in NB. IHC results showed that the expression of DGAT2 in NB tissues was significantly positively correlated with MYCN expression in the tumor tissue microarrays of clinical NB patients and the tissues of mouse ectopic xenograft tumors （rs=0.369 4，P＜0.01）.ConclusionsDGAT2 is highly expressed in MYCN-amplified NB， and may independently predict poor prognosis in NB patients. It is expected to become a diagnostic marker for NB and a potential therapeutic target for MYCN-amplified NB.  
    关键词：diacylglycerol acyltransferase 2;neuroblastoma;diacylglycerol;MYCN;prognosis   
    48
    |
    49
    |
    0
    <HTML>
    <L-PDF><Meta-XML>
    <引用本文> <批量引用> 153123624 false
    更新时间：2026-03-20
查看更多
0