目的 探讨多模态深度学习融合心脏超声与心电图特征对冠心病患者心源性猝死的预测价值。方法 选取2024年1月—2025年6月收治的60例冠心病患者，所有患者均接受心脏超声、心电图检查及多模态深度学习模型预测，随访6个月记录心源性猝死事件。根据随访结果分为事件组（n=15）和非事件组（n=45），比较两组临床资料及各项指标差异。结果 多模态深度学习模型预测敏感度为86.67%，特异度为91.11%，准确率为90.00%，AUC为0.923，显著优于单独心脏超声（AUC=0.761）和单独心电图（AUC=0.788）。结论 多模态深度学习融合心脏超声与心电图特征能够有效预测冠心病患者心源性猝死风险，预测性能优于传统单一模态评估方法。

      Objective To investigate the predictive value of multimodal deep learning integrating echocardiography and electrocardiogram features for sudden cardiac death in patients with coronary heart disease．Methods A total of 60 patients with coronary heart disease admitted from January 2024 to June 2025 were enrolled．All patients underwent echocardiography，electrocardiogram examination，and multimodal deep learning model prediction，with a 6-month follow-up to record sudden cardiac death events．According to the follow-up results，patients were divided into the event group（n=15） and non-event group（n=45），and clinical data and various indicators were compared between the two groups．Results The multimodal deep learning model achieved a sensitivity of 86.67%，specificity of 91.11%，accuracy of 90.00%，and AUC of 0.923，which were significantly superior to echocardiography alone（AUC=0.761） and electrocardiogram alone（AUC=0.788）．Conclusions Multimodal deep learning integrating echocardiography and electrocardiogram features can effectively predict the risk of sudden cardiac death in patients with coronary heart disease，with predictive performance superior to traditional single-modality assessment methods．

       目的 探讨不同附着体类型对上颌种植覆盖义齿修复患者种植体周围软硬组织健康状况的影响。方法 选取2020年1月—2023年12月于南京医科大学附属口腔医院就诊并接受上颌种植覆盖义齿修复的90例患者，根据所用附着体类型分为杆卡组（n=30）、球帽组（n=30）和Locator组（n=30）。戴用后随访12个月，比较三组种植体周围探诊深度（PD）、探诊出血（BOP）、菌斑指数（PLI）、牙龈指数（GI）、边缘骨吸收（MBL）等指标，并记录机械并发症发生情况。结果 佩戴12个月后，杆卡组在PD［（3.25±0.41） mm vs （3.58±0.50） mm，校正后P＜0.016 7］、PLI（1.25±0.38 vs 1.55±0.44，校正后P＜0.016 7）、GI（1.15±0.35 vs 1.37±0.42，校正后P＜0.016 7）及MBL［（0.38±0.11） mm vs （0.63±0.14） mm，校正后P＜0.016 7］方面的表现均优于Locator组；球帽组PLI（1.42±0.41 vs 1.55±0.44，校正后P＜0.016 7）、GI（1.28±0.39 vs 1.37±0.42，校正后P＜0.016 7）低于Locator组；三组间BOP阳性率两两比较差异均无统计学意义（校正后P＞0.016 7）。三组机械并发症总发生率的总体差异具有统计学意义（P＜0.05），进一步两两比较显示，杆卡组并发症发生率最低（16.67%），Locator组最高（50.00%）（校正后P＜0.016 7）。结论 对于上颌种植覆盖义齿修复，杆卡式附着体在维持种植体周围软硬组织健康、减少边缘骨吸收及降低机械并发症方面表现出相对优势，临床适用性较高。

       Objective To investigate the effects of different attachment types on the health of peri-implant soft and hard tissues in patients rehabilitated with maxillary implant-supported overdentures．Methods A total of 90 patients who received maxillary implant-supported overdentures at the Affiliated Stomatological Hospital of Nanjing Medical University between January 2020 and December 2023 were selected and divided into three groups based on the attachment type：bar-clip group（n=30），ball attachment group（n=30），and Locator group（n=30）．After prosthesis delivery，patients were followed up for 12 months．Parameters including probing depth（PD），bleeding on probing（BOP），plaque index（PLI），gingival index（GI），and marginal bone loss（MBL）were compared among the groups，and mechanical complications were recorded．Results At 12 months after delivery，the bar-clip group demonstrated significantly better performance in PD（［3.25±0.41］mm vs ［3.58±0.50］mm，adjusted P＜0.016 7），PLI（［1.25±0.38］ vs ［1.55±0.44］，adjusted P＜0.016 7），GI（［1.15±0.35］ vs ［1.37±0.42］，adjusted P＜0.016 7），and MBL（［0.38±0.11］mm vs ［0.63±0.14］mm，adjusted P＜0.016 7）compared to the Locator group．The ball attachment group showed significantly lower PLI（［1.42±0.41］ vs ［1.55±0.44］，adjusted P＜0.016 7）and GI（［1.28±0.39］ vs ［1.37±0.42］，adjusted P＜0.016 7）values than the Locator group．No statistically significant difference was observed in BOP positive rates among the three groups in pairwise comparisons（adjusted P＞0.016 7）．The overall difference in the total incidence of mechanical complications among the three groups was statistically significant（P＜0.05），and further pairwise comparisons showed that the bar-clip group had the lowest incidence（16.67%），while the Locator group had the highest（50.00%）（adjusted P＜0.016 7）．Conclusions For maxillary implant-supported overdentures，bar-clip attachments demonstrate relative advantages in maintaining peri-implant soft and hard tissue health，reducing marginal bone loss，and minimizing mechanical complications，suggesting good clinical applicability．

       目的 利用心脏代谢指数（CMI）和轻量级梯度提升机（LightGBM）模型评估代谢综合征（MetS）患者靶器官损害风险，探究其性别特异性关联，为精准干预提供依据。方法 纳入2022年8月至2025年2月在惠州市第一人民医院住院的132例MetS患者以及健康体检者400例（即对照组，仅作为基线对比参数），以心肾损害、大血管病变为复合靶器官损害终点，选取CMI、年龄等为核心特征；构建LightGBM分类模型（70%训练集、30%测试集分层抽样），并采用100次随机拆分验证得出曲线下的面积（AUC）和95%置信区间（CI）并绘制校准曲线；以AUC评估性能，结合沙普利加性解释算法（SHAP）和偏依赖图（PDP）进行可解释性及性别分层分析。结果 基线对比显示，MetS患者CMI（6.8±2.3）高于对照组（3.2±1.1），靶器官损害（TOD）阳性率（57.6%）高于对照组（12.0%）（P均＜0.001）；LightGBM模型预测AUC达0.812，CMI为最重要预测特征（相对贡献度31.5%），且CMI与性别交互作用检验差异有统计学意义（P＜0.01）；CMI与靶器官损害呈非线性S形关联，风险拐点为5.7，高危平台期为7.5；女性风险加速阈值（CMI 5.0）早于男性（CMI 6.5）。结论 以健康人群为对照明确了MetS患者的高CMI水平与高TOD风险特征，LightGBM-SHAP框架明确了CMI的核心预测价值，性别特异性阈值为制定男女个性化早期干预策略提供量化指导，具有良好的临床应用潜力。

    Objective This study aims to use the cardiometabolic index（CMI）and the LightGBM model to assess the risk of target organ damage（TOD）in metabolic syndrome（MetS）patients，explore its gender-specific associations，and provide a basis for precise intervention．Methods MetS patients meeting diagnostic criteria and healthy individuals（the control group，used only as a baseline reference parameter）were enrolled．The composite endpoint of TOD was defined as cardiorenal damage and macro/microvascular lesions．Core features selected included CMI and age．A LightGBM classification model was constructed（70% training set，30% test set with stratified sampling），and 100 random splits were used for validation to generate the area under the curve（AUC） with 95% confidence interval（CI）and draw the calibration curve．Performance was assessed using AUC，combined with the SHAP algorithm and Partial Dependence Plot（PDP）for interpretability and gender-stratified analysis．Results Baseline comparison showed that the CMI level of MetS patients（6.8±2.3）was significantly higher than that of the control group（3.2±1.1），and the positive rate of TOD（57.6%）was significantly higher than that of the control group（12.0%）（both P＜0.001）．The LightGBM model achieved an AUC of 0.875 in prediction，with CMI as the most important predictive feature（relative contribution of 31.5%），and the interaction test between CMI and gender showed a significant difference（P＜0.01）．CMI showed a non-linear S-shaped association with TOD，with a risk inflection point at 5.7 and a high-risk plateau at 7.5．Significant gender differences were observed：the threshold for accelerated risk in females（CMI 5.0）was earlier than that in males（CMI 6.5）．Conclusions Using healthy individuals as controls clarifies the characteristics of high CMI levels and high TOD risk in MetS patients．The LightGBM-SHAP framework clarifies the core predictive value of CMI．The gender-specific thresholds provide quantitative guidance for formulating personalized early intervention strategies for males and females，demonstrating good potential for clinical application．

       目的 探索Nrf2/HO-1通路是否参与远志皂苷元（远志）在脑出血体外细胞模型中对BV2小胶质细胞炎症反应的调控作用。方法 采用红细胞与BV2小鼠小胶质细胞共培养构建体外脑出血模型。分别给予远志单独处理、远志联合Nrf2抑制剂ML385处理，检测炎症因子水平。收集细胞上清制备条件培养基，用于培养SH-SY5Y人神经母细胞瘤细胞，并检测其铁死亡水平。结果 模型组BV2细胞炎症因子（IL-1β，IL-6，TNF-α）水平较对照组显著升高（P＜0.001）；高浓度远志（20 μM）可降低炎症因子水平，并上调Nrf2/HO-1通路蛋白表达，而ML385能逆转该作用。模型组条件培养基可诱导SH-SY5Y细胞铁死亡，而经远志处理的BV2细胞条件培养基则减轻该现象；ML385预处理可削弱远志对SH-SY5Y细胞的保护作用，远志组铁离子、丙二醛、转铁蛋白受体1水平低于远志联合ML385组（P＜0.05），铁转运蛋白、谷胱甘肽和谷胱甘肽过氧化物酶水平高于远志联合ML385组（P＜0.05）。结论 远志皂苷元通过激活Nrf2/HO-1通路抑制BV2小胶质细胞炎症反应，并在脑出血体外模型中发挥神经保护作用。

     Objective To investigate whether the Nrf2/HO1 signaling pathway is involved in the regulatory effect of tenuigenin（TEN）on the inflammatory response of BV2 microglial cells in an in vitro intracerebral hemorrhage（ICH）model．Methods An in vitro ICH model was established by coculturing BV2 murine microglial cells with red blood cells．Cells were treated with TEN alone or in combination with the Nrf2 inhibitor ML385，and the levels of inflammatory factors were measured．The conditioned medium collected from the cell supernatant was used to culture SHSY5Y human neuroblastoma cells，and ferroptosis levels were assessed．Results The levels of inflammatory factors（IL-1β，IL-6，TNF-α）in BV2 cells of the model group were significantly higher than those in the control group（P＜0.001）．High concentration of TEN（20 μM）could reduce the levels of inflammatory factors and up-regulate the expression of Nrf2/HO-1 pathway proteins，while ML385 could reverse this effect．The conditioned medium of the model group could induce ferroptosis in SH-SY5Y cells，while the conditioned medium of BV2 cells treated with TEN could alleviate this phenomenon．Pretreatment with ML385 could weaken the protective effect of TEN on SH-SY5Y cells．The levels of iron ions，malondialdehyde and transferrin receptor protein 1 in the TEN group were lower than those in the TEN combined with ML385 group（P＜0.05），while the levels of ferroportin glutathione and glutathione peroxidase 4 were higher than those in the TEN combined with ML385 group（P＜0.05）．Conclusions TEN inhibits the inflammatory response of BV2 microglial cells by activating the Nrf2/HO1 pathway and exerts a neuroprotective effect in the in vitro ICH model．

       肺癌作为全球恶性肿瘤中发病率和死亡率较高的一种，手术是其主要治疗手段。然而，肺切除手术常引起肺功能下降，影响患者术后功能恢复及生活质量。准确预测术后肺功能对制定个体化手术方案、降低并发症风险及改善患者预后具有重要意义。目前，研究者已开发出多种结合临床指标、影像学参数及生物标志物的预测模型，用于评估肺癌患者术后肺功能变化。然而，现有模型在准确性、特异性、标准化及临床推广方面仍存在诸多挑战。本文系统综述肺癌术后肺功能的影响因素，并对现有预测模型进行总结与评价，以期为患者术前评估、手术方案选择及术后管理提供参考，进而为改善治疗效果与患者生活质量提供理论依据。

       Lung cancer is a kind of malignant tumor with high morbidity and mortality in the world，and surgery is the main treatment．However，pneumonectomy is often accompanied by the loss of lung function，which seriously affects the recovery of lung function and the  quality of life．Accurate prediction of postoperative pulmonary function is of great significance for formulating individualized surgical plans，reducing the risk of complications and improving the prognosis of patients．At present，researchers have developed a variety of predictive models that combine clinical indicators，imaging parameters，and biomarkers to evaluate postoperative lung function changes in patients with lung cancer．However，there are still many challenges in the accuracy，specificity，standardization and clinical promotion of existing models．This paper systematically reviews the influencing factors of lung function after lung cancer surgery，and summarizes and evaluates the existing prediction models，in order to provide a reference for preoperative evaluation，surgical plan selection and postoperative management of patients，and then provide theoretical basis for improving treatment effect and quality of life of patients．

       目的 探讨肥胖与肺功能参数的相关性。方法 将90例接受肺功能检查的患者依据体质指数（BMI）分为肥胖组（BMI≥25 kg/m²，n=50）和正常体质量组（18.5 kg/m²＜BMI≤24.9 kg/m²，n=40），比较两组各项肺功能参数的差异，包括肺通气功能的参数如［用力肺活量（FVC）、第1秒用力呼气容积（FEV₁）、1秒率（FEV₁/FVC）、最大呼气流量（PEF）］以及反映小气道功能的参数［50%最大呼气流量（MEF₅₀），25%最大呼气流量（MEF₂₅）］；比较肥胖组不同性别间上述肺功能参数的差异及其与腰围（WC）与BMI的相关性。结果 肥胖组FVC、FEV₁、FEV₁/FVC、MEF₅₀、MEF₂₅低于正常体质量组（P＜0.01）；肥胖组中男性FVC及FEV₁低于女性（P＜0.01）。相关分析结果显示，肥胖组中WC与BMI均与肺功能多个参数呈负相关趋势，其中WC的负相关趋势更突出，且与FVC呈负相关关系（P＜0.05）。结论 肥胖影响反映肺功能的多个参数，表现为肺通气功能和小气道功能多个指标水平降低，且肥胖男性更甚；在肥胖人群中，相较于BMI，WC与FVC的关系更密切。

      Objective To investigate the correlation between obesity and pulmonary function parameters．Methods Ninety patients undergoing pulmonary function testing were categorized into an obese group（BMI≥25 kg/m²，n=50）and a normal-weight group（18.5 kg/m²＜ BMI≤24.9 kg/m²，n=40）．Differences in pulmonary function parameters were compared between groups，including ventilatory parameters（forced vital capacity［FVC］，forced expiratory volume in 1 second［FEV₁］，FEV₁/FVC ratio，peak expiratory flow［PEF］） and parameters reflecting small airway function（maximum expiratory flow at 50% of forced expiratory volume［MEF₅₀］，and 25% maximum expiratory flow［MEF₂₅］）．Differences in these pulmonary function parameters between genders within the obese group and their correlations with waist circumference（WC）and BMI were also assessed．Results FVC，FEV₁，FEV₁/FVC，MEF₅₀，and MEF₂₅ were significantly lower in the obese group compared to the normal-weight group（P＜0.01）．Among obese subjects，male FVC and FEV₁ were significantly lower than female values（P＜0.01）．Correlation analysis revealed negative correlations of WC and BMI with multiple pulmonary function parameters in the obese group，with WC exhibiting a more pronounced negative correlation and a significant negative relationship with FVC（P＜0.05）．Conclusions Obesity impacts multiple parameters reflecting lung function，manifesting as reduced levels of several indicators of pulmonary ventilation and small airway function，with male obese individuals exhibiting greater impairment．Within the obese population，WC correlates more closely with FVC than BMI．

       葛根芩连汤作为一种传统中药复方，在治疗代谢性疾病方面展现出显著的疗效。随着中草药现代研究方法的进步，逐渐揭示了葛根芩连汤在代谢性疾病中的治疗作用及其分子机制，包括葛根素、黄芩苷、小檗碱等活性成分的抗炎作用。然而，中草药研究领域的新理论和新机制被不断发现，如影响肠道菌群、产生植物外囊泡、中药汤剂成分自组装等，使得对葛根芩连汤作用机制的理解亟待更新。本文旨在综述葛根芩连汤在代谢性疾病中的作用及机制，并结合最新的研究成果，重点分析其在肠道菌群、植物外囊泡和中药自组装领域的相关发现，探讨其潜在的治疗靶点和未来研究方向，为临床应用和基础研究提供指导。

      Gegen Qinlian decoction（GQD），as a traditional Chinese herbal formula，has demonstrated significant efficacy in treating metabolic diseases．With advancements in modern research methodologies for Chinese herbal medicine，the therapeutic effects and molecular mechanisms of GQD in metabolic diseases have been progressively uncovered，including the anti-inflammatory properties of its active components such as puerarin，baicalin，and berberine．However，emerging theories and mechanisms in the field of herbal research，such as modulation of gut microbiota，production of plant-derived extracellular vesicles，and self-assembly of components in herbal decoctions，continuously refine our understanding，highlighting the need to update insights into GQD’s mechanisms of action．This review aims to summarize the roles and mechanisms of GQD in metabolic diseases，integrating the latest research progress with a focus on findings related to gut microbiota，plant-derived extracellular vesicles，and self-assembly phenomena．It further seeks to explore potential therapeutic targets and future research directions，thereby providing guidance for clinical applications and fundamental studies．

        目的 评估年龄调整内脏脂肪指数（AVAI）与骨关节炎患病率之间的关联。方法 采用加权多元Logistic回归模型和平滑曲线拟合分析AVAI和骨关节炎患病率之间的关系，通过亚组分析和交互作用检验探讨这一关系在不同亚组人群之间的效应差异。此外，通过受试者工作特征曲线（ROC）分析评估AVAI对骨关节炎的预测效能。结果 本研究基于美国国家健康与营养调查（NHANES）2011—2018年数据，共纳入5 929例参与者。较高的AVAI指数与骨关节炎患病率呈正相关（OR=1.22，95%CI：1.07~1.40）。随着AVAI指数的增加，骨关节炎患病风险呈现先上升后缓慢下降的趋势，AVAI的拐点为-4.48。在性别、年龄、教育程度和婚姻状况亚组中观察到交互作用。结论 AVAI与骨关节炎患病率之间存在非线性关系，当AVAI低于-4.48时，骨关节炎的患病风险增加。AVAI可作为一种有效、便捷的筛查工具，用于早期识别骨关节炎高风险人群。

    Objective This study aimed to evaluate the association between the age-adjusted visceral adiposity index（AVAI）and the prevalence of osteoarthritis（OA）．Methods Survey-weighted multivariable logistic regression models and smooth curve fitting were used to examine the relationship between AVAI and OA prevalence．Subgroup analyses and interaction tests were conducted to explore potential effect modifications across different population subgroups．Additionally，the predictive capability of AVAI for osteoarthritis was assessed using receiver operating characteristic（ROC）curve analysis． Results A total of 5 929 participants from the National Health and Nutrition Examination Survey（NHANES）2011–2018 were included．Higher AVAI levels were significantly associated with an increased prevalence of OA（OR=1.22；95%CI：1.07–1.40）．As AVAI increased，the risk of OA initially rose and then gradually declined，with an inflection point observed at ?4.48．Significant interactions were found across subgroups stratified by sex，age，education level，and marital status．Conclusions There exists a nonlinear relationship between AVAI and OA prevalence，with a significant increase in osteoarthritis risk observed when AVAI falls below -4.48．AVAI serves as an effective and convenient screening tool for identifying individuals at high risk of OA at an early stage．

       目的  压疮是指由于组织受压时间过长引起的严重并发症，2025年的数据显示，压疮在活动受限患者中发生率高。机体代谢紊乱可能会引起压疮，但是否与血清代谢物有因果影响，暂不明确。方法   本文运用孟德尔随机化（MR）方法评价血清代谢物与压疮间风险因素，基于MR方法评价血清代谢物和压疮的因果联系，分别纳入由欧洲人群全基因组关联研究（GWAS）。压疮：FinnGen R10，3 167例；血清代谢物：EMBL-EBI数据库16种代谢物数据作为研究样本；筛选条件：工具变量筛选条件［P＜5×10^-8，连锁不平衡聚类r ² ＜0.001，kb=10 000，F统计量＞10（公式：F=R² ×N-2/1-R² ）］；主要分析方法：使用（IVW）法，辅助采用加权中位数法（WM）、MR-Egger回归法校验；用Benjamini-Hochberg法进行多重检验校正（FDR＜0.05为有统计学意义）。结果  共鉴定出10种代谢物与压疮存在关联（P＜0.01），经FDR校正后4种：代谢物18：2/20：4n6的水平升高（P＜0.000 2）2-Oxopeptide的作用相反，降低压疮的风险（OR=0.73，95%CI：0.59~0.92，P=0.011）；琥珀酸可增加压疮的风险（OR=1.13，95%CI：1.03~1.24，P=0.018）；甘氨酸/丙氨酸比值降低压疮风险（OR=0.849，95%CI：0.76~0.93，P=0.022）。稳定性分析证明上述发现是可信的、稳健的（heterogeneity：P＞0.05，pleoitropy：P＞0.05）。结论  血清代谢物通过调控炎症反应、影响微循环障碍以及干预能量代谢途径，参与压疮的发生发展，可作为构建压疮风险的模型以及制定相关干预策略为压疮评估、治疗、预防提供因果层面的理论依据。

      Objective  Pressure ulcer（PU）is a serious complication caused by prolonged tissue compression．Data of 2025 shows that PUs have a high incidence among patients requiring long-term bed rest．Metabolic disorders may contribute to PU development，but whether serum metabolites causally affect PU risk remains unclear．Methods  this study employed the Mendelian randomization（MR）method to evaluate whether serum metabolites are risk factors for PU．To assess the causal relationship between serum metabolites and PU，data from Genome-Wide Association Studies（GWAS）of European populations were included：PU data from FinnGen R10（3 167 cases）and data on 16 serum metabolites from the EMBL-EBI database．Instrumental variable screening criteria were as follows：P＜5×10^-8，linkage disequilibrium clustering（r ² ＜0.001，kb=10，000），and F-statistic ＞10（Formula：F=［R² ×N-2］/［1-R² ］）．The inverse variance weighting（IVW）method was used as the primary analytical approach，supplemented by the weighted median（WM）method and MR-Egger regression for verification．The Benjamini-Hochberg method was applied for multiple test correction（FDR＜0.05 was considered statistically significant）．Results  A total of 10 metabolites were identified to be associated with PU（P＜0.01），and 4 remained significant after FDR correction：elevated levels of metabolite 18：2/20：4n6（P＜0.0002）；2-Oxopeptide exerted an opposite effect，reducing PU risk（OR=0.73，95%CI：0.59-0.92，P=0.011）；succinic acid increased PU risk（OR=1.13，95%CI：1.03-1.24，P=0.018）；and the glycine/alanine  ratio  reduced PU risk（OR=0.849，95%CI：0.76-0.93，P=0.022）．Stability analysis（PH-TauNE［novel pleiotropy test］） confirmed that the above findings were credible and robust（heterogeneity：P＞0.05，pleiotropy：P＞0.05）．Conclusions  Serum metabolites are involved in the occurrence and development of PU by regulating inflammatory responses，affecting microcirculatory disorders，and interfering with energy metabolism pathways．They can provide causal theoretical basis for constructing PU risk prediction models，formulating relevant intervention strategies，and guiding PU treatment，prevention，and assessment．

      目的  探讨通过优化病案首页质控体系提高误入DRG低权重组病例转出率的效果。方法  采用PDCA循环法，通过实施分层级编码培训、基于AI赋能的专项质控模式及智能化反馈机制构建等系统性地改进措施优化质控体系。通过对比分析质控系统优化前后（2022年1—7月和2023年1—7月）DRG低权重组病例的病案首页质控过程、“经质控低权重病例入组率”和“误入低权重组病例转出率”等指标，评估质控体系优化的实施效果。结果  质控体系优化后，低权重组病例转出率由3.27%提升至4.15%（P=0.018），经质控低权重病例入组率由16.98%降至14.96%（P＜0.001）。结论  AI赋能的专项质控、分层级编码培训与智能化反馈机制三项措施并举可以系统优化质控体系，进而提升DRG低权重组病例转出率。

       Objective  To investigate the effect of optimizing the medical  record front  page  quality control  system on improving the transfer-out rate of cases mistakenly assigned to low-weight DRG groups．Methods  The Plan-Do-Check-Act（PDCA）cycle methodology was employed．Systemic improvements were implemented to  optimize the medical  record front page quality control system，including hierarchical coding training，innovation of a  specialized quality control model based on AI empowerment，and establishment of an intelligent feedback mechanism．The implementation effectiveness was evaluated by comparative analysis of the following indicators before（January-July 2022）and after（January-July 2023）optimization：the medical record quality control process for low-weight DRG cases，the  rate of low-weight cases assigned to groups after quality control，and the transfer-out rate of cases mistakenly entering low-weight groups．Results  After optimizing the medical record front page quality control system，the transfer-out rate of cases from low-weight groups increased from 3.27% to 4.15%（P=0.018），while the rate of low-weight cases assigned to groups after quality control decreased from 16.98% to 14.96%（P＜0.001）．Conclusions  Implementing a three-pronged approach—AI-powered specialized quality control，hierarchical coding training，and an intelligent feedback mechanism—can systematically optimize the medical record front page quality control system，thereby improving the transfer-out rate of cases mistakenly assigned to low-weight DRG groups．