目的 分析机械通气患者亚谵妄综合征发生的危险因素， 构建风险预测模型，以预测亚谵妄的发生。 方法 采用便利抽样法，选取2021年7月-2022年6月贵州省某三级甲等医院ICU收治的机械通气患者434例，使用ICU患者意识模糊评估表将其分为亚谵妄综合征组（n=136）和非亚谵妄综合征组（n=298），通过单因素分析和多因素Logistic回归分析探索亚谵妄综合征发生的独立危险因素，建立风险预测模型并构建列线图，并对该模型进行内、外部验证。 结果 多因素Logistic回归分析显示，年龄（OR=1.029）、急性生理与慢性健康状况评分（OR=1.267）、身体约束（OR=1.029）、重症监护疼痛评分（OR=2.487）、理查兹要坎贝尔睡眠量表评分（OR=1.150）、Richmond躁动要镇静评分（OR=1.500）是亚谵妄综合征发生的独 立危险因素。 根据上述6项危险因素构建的ICU机械通气患者亚谵妄综合征风险预测模型 ROC曲线下面积为0.956，灵敏度为86.2%，特异度为94.1%。 结论 该研究构建的风险预测模型能有效预测机械通气患者亚谵妄综合征的发生，为临床医护人员科学预测亚谵妄综合征的发生提供参考。

Objective To analyze the risk factors for the occurrence of subsyndromal delirium in mechanically ventilated patients and construct a nomogram risk prediction model to predict the occurrence of subsyndromal delirium. Methods Convenience sampling was used to select 434 mechanically ventilated patients admitted to the ICU of a tertiary hospital in Guizhou Province from July 2021 to June 2022，who were categorized into the subdelirium syndrome group （n=136） and the non-subdelirium syndrome group （n=298） using the ICU Patient Ambi- guity of Consciousness Assessment Scale. We explored the independent risk factors for the occurrence of subde- lirium syndrome through univariate and multifactorial logistic regression analyses，established a risk prediction model，developed a nomogram，and validated the model both internally and externally. Results Multifactorial logistic regression analysis revealed that age（OR=1.029），acute physiological and chronic health status score（OR=1.267）， whether restrained（OR=1.029），intensive care pain score（OR=2.487），Richards-Campbell sleep scale score（OR=1.150）， Richmond agitation-sedation score（OR=1.500） were independent risk factors for the development of subdelirium. The consistency index of the nomogram model for the occurrence of subdelirium in mechanically ventilated patients in the ICU was 0.956，with a sensitivity of 86.2% and a specificity of 94.1%. Conclusion The risk prediction model construc- ted in this study can effectively predict the occurrence of subdelirium syndrome in mechanically ventilated patients， which provides a reference for clinical medical personnel to scientifically predict the occurrence of subdelirium.