目的 探讨非重型肺源性急性呼吸窘迫综合征（ARDS）患者发生肺纤维化的影响因素，并构建Logistic回归模型，以筛选高危患者，指导临床制定针对性干预方案。方法 前瞻性选取2022年1月～2024年12月于本院诊治的134例非重型肺源性ARDS患者为研究对象，依据发病后30 d内是否发生肺纤维化将其分为发生组58例、未发生组76例。比较两组临床资料，并通过多因素Logistic回归分析肺纤维化发生的影响因素。构建Logistic回归模型，并分析该模型对肺纤维化发生的预测价值。结果 多因素Logistic回归分析显示病程中出现休克、脓毒症、吸烟史、肺动脉高压及血清白细胞介素-8（IL-8）、低氧诱导因子-1α（HIF-1α）、Clara细胞分泌蛋白16（CC-16）、成纤维细胞生长因子（FGF-2）水平为肺纤维化发生的独立危险因素（P＜0.05）；Logistic回归模型预测肺纤维化发生的AUC值为0.871，敏感度、特异度分别为77.59%、84.21%，Hosmer-Lemeshow检验该模型与观测值拟合度良好，且Bootstrap检验显示该模型具有良好的区分度。结论 病程中出现休克、脓毒症、吸烟史、肺动脉高压及血清IL-8、HIF-1α、CC-16、FGF-2水平为非重型肺源性ARDS患者发生肺纤维化的独立危险因素，基于上述危险因素构建Logistic回归模型，该模型预测肺纤维化发生具有良好的预测效能，临床可依据上述因素采取针对性干预方案，以降低肺纤维化发生率。

      目的   基于决策树构建老年患者吞咽障碍预警模型。方法  采用便利取样法对宁夏银川市宁夏回族自治区人民医院老年科住院的200例老年患者进行调查。结果  200例老年患者中，吞咽障碍发生率为40.5%。依据是否发生吞咽障碍将其患者分为两组，两组患者在性别、年龄、文化程度、职业、医保类型、家庭年收入、日常生活能力、衰弱、抑郁、营养、体质指数（BMI）比较（χ ² 值分别为13.321、4.064、31.944、36.695、18.230、19.681、52.509、10.253、20.456、9.070、9.483），差异均有统计学意义（均P＜0.05）。决策树模型筛选出老年患者吞咽障碍的影响因素主要有自理能力、职业、文化程度和抑郁，决策树模型受试者工作特征曲线下面积为0.862，灵敏度为79.8%，特异度为79.0%，P＜0.001。结论  基于自理能力、职业、文化程度和抑郁构建的决策树模型，能有效预测老年患者吞咽障碍风险。

       Objective  To construct a swallowing disorder warning model for elderly patients based on decision tree．Methods  Convenience  sampling was  used to  study  200  elderly  patients  admitted to the  geriatric  department  of  a tertiary comprehensive hospital in Yinchuan，Ningxia．Results  Among 200 elderly patients，the incidence of swallowing disorders was 40.5%．The two groups of patients were compared in terms of gender，age，education level，occupation，medical insurance type，annual family income，daily living ability，frailty，depression，nutrition，and BMI（χ ²  values were 13.321，4.064，31.944，36.695，18.230，19.681，52.509，10.253，20.456，9.070，9.483，respectively），and the  differences were  statistically significant（all P＜0.05）．The decision tree model identified the main influencing factors of swallowing disorders in elderly patients as self-care ability，occupation，education level，and depression．The Receiver Operating Characteristic curve of the decision tree model had an area under the curve of 0.862，sensitivity of 79.8%，and specificity of 79.0%，P＜0.001．Conclusions  A decision tree model based on self-care ability，occupation，education level，and depression can effectively predict the  risk of swallowing disorders in elderly patients．

       目的 汇总分析肝硬化患者消化道出血风险预测模型，为今后模型的建立和优化提供参考。方法   系统检索中国知网、维普、PubMed数据库在2025年4月22日前公开发表的所有肝硬化患者消化道出血风险预测模型，按纳入标准筛选文献，对最终纳入文章分析摘录并系统汇总，包括模型特征、危险因素及模型预测评估效果等信息。结果   共检索3 603篇预测模型相关研究论文，最终纳入30篇，其中中国27篇、韩国1篇、印度1篇、埃及1篇。22项研究收集了肝硬化病因，其中病毒性肝病最多（72.94%，2 922/4 006），药物性肝病及非酒精性脂肪性肝病最少（均为0.02%，1/4 006）。在研究类型上，有28篇单中心研究，2篇为多中心研究，其中有12个模型未进行验证，只有1个模型进行了外部验证，其余模型只进行了内部验证，曲线下面积（AUC）范围0.680~0.994。根据模型纳入因素特点，分为血常规指标、凝血指标、生化指标、影像学指标、复合指标、其他指标共6种，其中纳入因素最多为影像学指标，最少为凝血指标。在纳入危险因素中，第1位为门静脉直径，第2位为血小板计数，第3位为血红蛋白水平及脾脏硬度，所有因素中与脾脏相关的指标最多。结论   肝硬化患者消化道出血风险预测模型研究质量有待提升，影像学指标应用最广，脾脏相关指标重要性突出，门静脉直径、血小板计数、血红蛋白水平及脾脏硬度为最常用的危险预测因素。

       Objective  To  summarize and analyze the  prediction models for gastrointestinal  bleeding  risk in  patients with cirrhosis，providing references for the establishment and optimization of future models．Methods  A systematic search was conducted in CNKI，VIP，and PubMed for all published prediction models for gastrointestinal bleeding risk in patients with cirrhosis before April 22，2025．Articles were screened according to the inclusion criteria，and the finally included articles were analyzed and summarized，including model characteristics，risk factors，and model prediction evaluation effects．Results  A total of 3 603 related research papers on prediction models were initially retrieved，and 30 were finally included，with 27 from China，one from South Korea，one from India，and one from Egypt．Among the 22 studies that collected the etiology of cirrhosis，viral hepatitis was the most common（72.94%，2 922/4 006），while drug-induced liver disease and non-alcoholic fatty liver disease were the least common（0.02%，1/4 006）．In terms of study type，28 were single-center studies and two were multicenter studies．Among them，12 models were not validated，only one model was externally validated，and the rest were only internally validated，with an area under the curve range of 0.680-0.994．According to the characteristics of the factors included in the models，they were divided into six types of indicators：blood routine，coagulation，biochemistry，imaging，composite，and others，among which imaging indicators were the most common and coagulation indicators were the least．In the included risk factors，the first was portal vein diameter，the second was platelets count，and the third was hemoglobin level and spleen stiffness，with the most factors related to the spleen．Conclusions  The quality of studies on prediction models for gastrointestinal bleeding risk in cirrhosis patients needs to be improved．Imaging indicators are the most widely used，and spleen-related indicators are of prominent importance，with portal vein diameter，platelets count，hemoglobin level，and spleen stiffness being the most commonly used risk prediction factors．

      目的 分析儿童大环内酯类耐药重症肺炎支原体肺炎（SMPP）的危险因素,构建列线图预测模型。 方法 回顾性收集2023年1月—2024年9月在广州医科大学附属番禺中心医院儿科住院治疗的1 121例大环内酯类耐药肺炎支原体肺炎患儿入院初期的临床资料。按7∶3比例将患儿资料随机分为训练集（784例）和验证集（337例）。采用R4.4.1软件使用10重交叉验证最小绝对收缩与选择算法（LASSO）回归分析进行单因素变量筛选,采用Logistics回归分析建立预测模型, 绘制可视化列线图。使用受试者操作特征曲线（ROC）, 校准曲线、Hosmer-Lemeshow（HL）检验及临床决策曲线（DCA）分别评估模型的区分度、校准度和临床使用价值。 结果 在训练集中, LASSO回归结合Logistics回归分析结果显示,院前发热时间>5.5 d、谷丙转氨酶>14.5 U/L、乳酸脱氢酶>287.5 U/L、C反应蛋白>18.65 mg/L、肺实变、合并病毒感染是大环内酯类耐药SMPP发生的危险因素（P<0.05）, 根据上述危险因素构建列线图预测模型。训练集和验证集ROC曲线下面积分别为0.847和0.822; 校准曲线和HL检验显示模型具有良好的校准度; DCA显示预测模型在风险阈值为0.05~0.95时预测性能最优。 结论 院前发热时间、谷丙转氨酶、乳酸脱氢酶、C反应蛋白、肺实变、合并病毒感染是大环内酯类耐药SMPP发生的影响因素, 基于以上因素构建的列线图模型具有较好的预测效能, 有利于早期识别耐药重症病例, 及早采取有效干预,改善患者预后。

      Objective To explore the risk factors and to construct a nomogram prediction model for severe macrolide-resistant Mycoplasma pneumoniae pneumonia（MPP）in children．Methods The clinical data during the initial admission period of 1 121 children with macrolide-resistant MPP who were hospitalized in the Department of Pediatrics of the Affiliated Panyu Central Hospital of Guangzhou Medical University from January 2023 to September 2024 were retrospectively collected．The children data were randomly divided into a training set（n=784）and a validation set（n=337）at a ratio of 7∶3．With R language software（version 4.4.1）, least absolute shrinkage and selection operator（LASSO）regression analysis with tenfold cross-validation was used to screen risk factors, Logistics regression analysis was used to establish prediction model, and a visualization of the risk variables was created using a nomogram．The receiver operating characteristic（ROC）curves, calibration curves, Hosmer-Lemeshow（HL）test and clinical decision curve analysis（DCA）were used to evaluate the discrimination, calibration and clinical application value of the model．Results In the training set, LASSO regression analysis combined with Logistics regression analysis showed that prehospital fever duration > 5.5 days, alanine aminotransferase level> 14.5 U/L, lactate dehydrogenase level> 287.5 U/L, C-reactive protein > 18.65 mg/L, lung consolidation, and co-infection with virus were risk factors for severe macrolide-resistant MPP（P<0.05）．A nomogram prediction model was constructed based on the above risk factors．The area under the ROC curves of the training set and the validation set were 0.847 and 0.822, respectively．The calibration curves and HL test showed that the model had good calibration． The DCA curves showed that the prediction model had the best prediction performance when the risk threshold was between 0.05-0.95．Conclusions Prehospital fever duration, alanine aminotransferase level, lactate dehydrogenase level, C-reactive protein level, lung consolidation and co-infection with virus were risk factors for prediction of severe macrolide-resistant MPP．The nomogram model based on the above factors had a good prediction efficiency, which was conducive to early identification of severe cases with macrolide-resistant, and taking early effective interventions to improve the prognosis．

       目的   通过机器学习方法构建脓毒症谵妄患者30 d死亡的预测模型，并识别关键预测因子。方法   采用基于医疗信息集成重症监护数据库（Medical Information Mart for Intensive Care IV）的回顾性队列研究方法，boruta筛选重要特征，并通过决策树，K近邻，LightGBM，随机森林，支持向量机，XGBoost构建模型进行分析，通过ROC曲线下面积进行评估，利用F1分数、召回率、精确率、特异度、灵敏度和阳性预测值比较模型表现。结果  XGBoost模型在训练集和验证集中的ROC曲线下面积分别为0.906和0.762，表明该模型具有良好的预测能力，入院年龄、红细胞分布宽度和白细胞计数是最重要的预测因子。结论   基于机器学习的脓毒症谵妄患者预后预测模型展现出良好的预测效能，为临床早期干预提供了重要参考依据。

       Objective  To construct a  30-day mortality  prediction model for  patients with  sepsis-associated  delirium using machine learning methods and identify key predictive factors．Methods  A  retrospective cohort study was conducted based on the Medical Information Mart for Intensive Care IV database．Important features were selected using the Boruta algorithm，and models including Decision Tree，K-Nearest Neighbors，LightGBM，Random Forest，Support Vector Machine，and XGBoost were constructed and analyzed．Model performance was evaluated using the area under the reciver operater characteristic（ROC）curve（AUC），along with F1 score，recall，precision，specificity，sensitivity，and positive predictive value．Results  The XGBoost model demonstrated strong predictive performance，with AUC values of 0.906 in the training set and 0.762 in the test set．Key predictors identified included admission age，red blood cell distribution width，and white blood cell count．Conclusions  The machine learning-based prediction model for sepsis-associated delirium prognosis exhibits robust predictive efficacy，providing a valuable tool for early clinical intervention．

目的 基于SEER数据库分析三阴性乳腺癌（TNBC）的预后,并建立Cox回归临床预测模型且进行内部验证。方法 使用SEER*Stat软件（8.4.2版）筛选2010—2015年诊断为TNBC的病例,进行单因素和Cox多因素回归以及向后逐步回归分析,明确与生存相关的独立危险因素,构建预测TNBC患者3年和5年癌症特异生存（CSS）率的Nomogram图,并用受试者工作特征曲线,Harrell’s一致性指数,临床预测模型校准曲线以及决策曲线对该模型进行评估及内部验证,以评估该模型的临床预测效能。结果 共筛选出符合纳入标准的TNBC患者5 564例,按照7∶3的比例随机拆分为训练集（n=3 894）和验证集（n=1 670）。通过单因素,多因素分析显示TNM分期、放射治疗、化学治疗以及手术和其他治疗的先后顺序是与TNBC患者CSS显著相关的独立危险因素（P<0.05）。利用上述预后相关因素建立Nomogram图模型。训练集的C-index为0.731（95%CI：0.712~0.749）,验证集的C-index为0.719（95%CI：0.688~0.749）,训练集和验证集3年和5年生存ROC曲线的曲线下面积均>0.7,区分度较好,且校准曲线拟合良好。结论 TNM分期、放射治疗、化学治疗以及手术和其他治疗的先后顺序是TNBC的独立预后因素,基于此建立的Nomogram图临床预测模型区分度、准确度以及临床适用性较好,能较好地预测TNBC患者的生存预后。

Objective To analyze the prognosis of triple negative breast cancer（TNBC）based on the SEER database,and to establish a Cox regression clinical prediction model with internal validation．Methods Cases diagnosed with TNBC from 2010 to 2015 were screened using SEER*Stat software（version 8.4.2）,and univariate and Cox multifactorial regression as well as backward stepwise regression analyses were performed to identify the independent risk factors associated with survival,and to construct a clinical prediction model for predicting the three- and five-year cancer specific survival（CSV）of TNBC patients．Survival（CSS）rates of TNBC patients at 3 and 5 years,and the model was evaluated and internally validated using the ROC curve,Harrell’s consistency index（C-index）,clinical prediction model calibration curve,and decision-making curve（DCA curve）to assess the predictive efficacy of the model for clinical prediction．Results A total of 5 564 TNBC patients meeting the inclusion criteria were screened and randomly split into a training set（n=3 894）and a validation set（n=1 670）according to a 7∶3 ratio．By univariate,multivariate analysis showed that T-stage,N-stage,M-stage,radiotherapy,chemotherapy,and the sequence of surgery and other treatments were independent risk factors significantly associated with CSS in TNBC patients．The above prognostic-related factors were utilized to build a Nomogram plot model．The C-index was 0.731（95%CI：0.712-0.749）for the training set and 0.719（95%CI：0.688-0.749）for the validation set,and the areas under the curves of the 3- and 5-year survival ROC curves of both the training and validation sets were >0.7,which was a good differentiation,and the calibration curves were well-fitted．Conclusions T-stage,N-stage,M-stage,radiotherapy,chemotherapy,and the sequence of surgery and other treatments are independent prognostic factors for TNBC,and the Nomogram clinical prediction model based on this has good differentiation,accuracy,and clinical utility,and can better predict the survival prognosis of TNBC patients．

目的 构建并验证主动脉夹层B型（TBAD）患者急性期预后的列线图预测模型,帮助临床医生在急性期内更准确地评估TBAD患者的死亡风险,并制定更合适的治疗策略。方法 回顾性分析从重症监护医学信息数据库v2.2 中提取的399例 TBAD患者的人口学资料和临床资料,结局为TBAD患者急性期（≤14 d）内死亡。先采用最小绝对收缩选择算法回归筛选特征变量,再采用多因素分析确定独立预后因素,并据此构建预测模型。通过受试者工作特征曲线、校准曲线、决策曲线分析（DCA）评价列线图预测模型的性能和临床适用性。结果 APS Ⅲ评分、二氧化碳总量、红细胞分布宽度为TBAD患者14 d内死亡的独立预测因素。列线图预测模型在内部验证中的受试者工作特征曲线下面积为0.776（95% CI：0.691 ~ 0.860）,Hosmer-Lemeshow 检验P=0.604,校准曲线和标准曲线高度重合,表明该模型具有良好的区分度和校准度。同时,DCA曲线显示,预测模型在大部分的阈值概率范围内提供了显著的净收益。结论 本研究基于APS Ⅲ评分、二氧化碳总量、红细胞分布宽度构建的列线图预测模型可以较准确地预测TBAD患者14 d内的死亡风险,有助于临床医生制定更合适的个体化治疗策略。

Objective To develop and verify a nomogram for predicting acute phase outcomes in patients with type B aortic dissection（TBAD）,enabling clinicians to more precisely evaluate mortality risk in TBAD patients during the acute stage and to devise better treatment plans．Methods This retrospective study analyzed demographic and clinical data of 399 TBAD patients from the Medical Information Mart for Intensive Care IV v2.2,focusing on mortality within 14 days of the acute phase in TBAD patients． Initially,the Least Absolute Shrinkage and Selection Operator regression was employed for feature variable selection,and then multivariate analysis was used to identify independent prognostic factors for constructing the predictive model．The nomogram predictive model's effectiveness and clinical applicability were assessed via the Receiver Operating Characteristic curve,calibration curve,and Decision Curve Analysis（DCA）．Results Acute Physidogy Score Ⅲ score,total carbon dioxide,and red blood cell distribution width emerged as independent predictors of 14-day mortality in TBAD patients．The internal validation of the nomogram predictive model showed an area under the curve of 0.776（95%CI：0.691-0.860）,with a Hosmer-Lemeshow test P-value of 0.604． The close alignment of the calibration and standard curves suggested the model's strong discriminative power and calibration． Furthermore,the DCA curve revealed that the predictive model offered substantial net benefits within a wide range of threshold probabilities．Conclusions This study's nomogram,developed using APS Ⅲ score,total carbon dioxide,and red blood cell distribution width,accurately predicts the 14-day mortality risk in TBAD patients,assisting clinicians in creating better personalized treatment plans．

目的 构建并验证机械通气患儿肠内营养支持发生误吸的风险预测模型。方法 回顾性分析中山市博爱医院2021年3月—2023年3月儿童重症监护病房330例行机械通气并进行肠内营养的患儿临床资料,通过二元Logistic回归,获取机械通气患儿肠内营养支持发生误吸的预测因素,绘制列线图模型,并进行模型评价及验证。结果 330例机械通气患儿中,104例患儿发生误吸、226例未发生误吸。两组患儿在意识状态、机械通气方式、管饲量、胃残留量、胃管置入深度、促胃动力药、镇静剂等方面对比差异具有统计学意义（P<0.05）。二元Logistic结果显示,胃残留量、机械通气方式、管饲量、意识状态、胃管置入深度、促胃动力药、镇静剂是机械通气患儿肠内营养支持发生误吸的影响因素（P<0.05）。建模组AUC为0.810（95%CI：0.760~0.860）,Hosmer-Lemesh结果显示,χ²=3.245,P=0.846;外部验证组AUC为0.873（95%CI：0.831~0.914）,Hosmer-Lemesh结果显示,χ²=3.567,P=0.875。建模组和训练组DCA曲线大部分落于Y=0上方。建模组与外部验证组校准曲线均与参考曲线高度贴合,预测概率与实际概率接近,校准度良好。结论 基于胃残留量、机械通气方式、管饲量、意识状态、胃管置入深度、促胃动力药、镇静剂等7项指标构建的风险预测模型具有一定的临床价值,可作为医护人员识别肠内营养机械通气误吸高危患儿的工具。

Objective To establish and verify the risk prediction model of enteral nutritional aspiration in children with mechanical ventilation．Methods The clinical data of 330 children who underwent mechanical ventilation and enteral nutrition in the PICU of Zhongshan Boai Hospital from March 2021 to March 2023 were retrospectively analyzed．The independent predictive factors of enteral nutrition support aspiration in children with mechanical ventilation were obtained by binary Logistic regression,and the nomographic model was drawn,and the model was evaluated and verified. Results Among 330 children with mechanical ventilation,104 had aspiration and 226 did not．There were statistically significant differences between the two groups in consciousness state,mechanical ventilation mode,tube feeding amount,gastric residual amount,gastric tube insertion depth,gastric motivity drugs,sedatives,etc.（P<0.05）．Binary Logistic results showed that gastric residual amount,mechanical ventilation mode,tube feeding amount,state of consciousness,depth of gastric tube insertion,gastric motonics and sedatives were the influential factors of enteral nutritional aspiration in children with mechanical ventilation（P<0.05）．The AUC of the modeling group was 0.810（95%CI：0.760-0.860）,and the Hosmer-Lemesh result showed that χ²=3.245,P=0.846．The AUC of the external verification group was 0.873（95%CI：0.831-0.914）,and the Hosmer-Lemesh result showed that χ²=3.567,P=0.875．The DCA curves of modeling group and training group mostly were above Y=0．The calibration curves of the modeling group and the external verification group are highly fit to the reference curves,and the prediction probability was close to the actual probability,and the calibration degree was good．Conclusion sThe risk prediction model based on 7 indexes,including stomach residual amount,mechanical ventilation mode,tube feeding amount,state of consciousness,depth of gastric tube insertion,gastric motivity drug and sedative,with certain clinical value,and can be used as a tool for medical staff to identify children at high risk of enteral nutritional mechanical aspiration．

目的 基于随机森林方法构建甲状腺功能减退（简称甲减）患病风险预测模型。方法 从MIMIC-IV数据库纳入5 735名甲减患者为病例组,4 803名非甲减患者为对照组,基于随机森林模型进行建模。同时利用逻辑回归、贝叶斯正则化神经网络、XGBoost作为比较模型。最后用准确率、F1分数、精确率、召回率、特异性以及AUC值评价四个机器学习模型性能。结果 随机森林模型准确率为0.85,F1分数为0.84,精确率为0.84,召回率为0.84,特异性为0.86,AUC值为0.91。在该模型中,促甲状腺激素、年龄、绝对淋巴细胞计数、血液中红细胞数、中性白细胞、性别、碱性磷酸酶、丙氨酸氨基转移酶、嗜酸性粒细胞绝对计数、尿素氮为甲减患者诊断重要性排前10的指标。结论 采用随机森林方法构建的甲减患病预测模型为甲减的早期诊断有潜在应用价值。

Objective To construct a risk prediction model for hypothyroidism based on the random forest model．Methods A total of 5 735 hypothyroidism patients were included from the MIMIC-IV database as the case group, and 4 803 non-hypothyroidism patients were included as the control group．Random forest models were constructed for both groups, and logistic regression, Bayesian regularized neural network, and XGBoost were used as comparative models．The performance of the four machine learning models was evaluated using accuracy, F1 score, precision, recall, specificity, and AUC value．Results The random forest model had an accuracy of 0.85, an F1 score of 0.84, a precision of 0.84, a recall of 0.84, a specificity of 0.86, and an AUC value of 0.91．In this model, thyroid-stimulating hormone, age, absolute lymphocyte count, red blood cell count in blood, neutrophil, gender, alkaline phosphatase, aspartate aminotransferase, absolute eosinophil count, and blood urea nitrogen were the top 10 indicators for diagnosing hypothyroidism patients．Conclusions The hypothyroidism disease prediction model constructed using the random forest method has potential application value for the early diagnosis of hypothyroidism．

目的 探讨老年吸入性肺炎的危险因素,建立风险预测模型,以期降低老年吸入性肺炎的发病率。方法 选取2017年8月28日—2020年 10月30日广州市第一人民医院老年病科住院治疗的老年肺炎患者205例,按照是否发生吸入性肺炎分为吸入性肺炎组和非吸入性肺炎组,对比2组患者的各项指标,分析老年吸入性肺炎的危险因素,建立风险预测模型,采用ROC曲线对模型进行预测效果检验。结果 多因素Logistic回归分析结果显示,脑梗塞、帕金森、留置胃管、长期卧床为老年吸入性肺炎的危险因素(P<0.05)。模型公式为Logit(P)=-2.952+1.221X₂+2.417X₃+2.388X₈+1.683X₁₀。该模型ROC曲线下面积为0.894。结论 本研究中的模型预测效果良好,可为医护人员预测老年患者发生吸入性肺炎的概率,及时采取相应的预见性护理及干预性治疗。

Objective To explore the risk factors of aspiration pneumonia in the elderly and establish the risk prediction model, in order to reduce the incidence of aspiration pneumonia in the elderly. Methods A total of 205 elderly patients with pneumonia who were hospitalized in the department of geriatrics, Guangzhou First People's Hospital from August 28, 2017 to October 30, 2020, were divided into aspiration pneumonia group and non-aspiration pneumonia group according to whether aspiration pneumonia occurred. The indicators of the two groups of patients were compared, the risk factors of aspiration pneumonia in the elderly were analyzed, the risk prediction model was established, and the prediction effect of the model was tested by receiver operating characteristic curve. Results Multivariate Logistic regression analysis showed that cerebral infarction, Parkinson's disease, indwelling nasogastric tube, and being bedridden were risk factors for aspiration pneumonia in elderly patients (P<0.05). The model formula was Logit (P)=-2.952+1.221X₂+2.417X₃+2.388X₈+1.683X₁₀. The area under receiver operating characteristic curve of this model was 0.894. Conclusion The prediction effect of the model in this study was good, which could predict the probability of aspiration pneumonia in elderly patients for medical staff, and to timely take the corresponding predictive care and interventional treatment.