Purpose: Women who are surgically treated for vulvar cancer often have complications leading to substantial patient morbidity. Post-surgical complications could be minimized by the identification of pre-surgical risks...Purpose: Women who are surgically treated for vulvar cancer often have complications leading to substantial patient morbidity. Post-surgical complications could be minimized by the identification of pre-surgical risks for complications and by planned post-surgical interventions. Therefore, the aim of this study was to develop a clinical care algorithm for vulvar cancer to assess risk for complications and prevent and control post-surgical complications. Methods: Key elements of the algorithm were identified via a literature review, structured chart review, a survey of care team members and interviews with stakeholders including healthcare team, patients and their family. Results: An algorithm for the management of wound and psychosocial complications was developed, based on internal and external evidence and was vetted by expert reviewers. Conclusion: Describing the process and defining the roles of health care professionals contributes to purposeful, systematic prevention and treatment of post-surgical complications. The care algorithm provides structured reference points for healthcare professionals with regard to multidisciplinary post-surgical management of vulvar cancer patients.展开更多
目的利用FP-Growth和Apriori算法的深度学习(deep learning,DL)功能预测重症监护病房(ICU)患者院内死亡的关联因素。方法筛选美国重症监护医学信息数据库-Ⅲ(medical information mart for intensive care-Ⅲ,MIMIC-Ⅲ)中患者10000例,...目的利用FP-Growth和Apriori算法的深度学习(deep learning,DL)功能预测重症监护病房(ICU)患者院内死亡的关联因素。方法筛选美国重症监护医学信息数据库-Ⅲ(medical information mart for intensive care-Ⅲ,MIMIC-Ⅲ)中患者10000例,包含死亡患者1320例,收集其基线资料进行回顾性研究。使用SPSS Modeler 18.0软件编制FP-Growth和Apriori算法程序,通过DL功能计算1320例死亡患者的基线资料间有效强关联规则。对全部患者行Logistic回归分析导致死亡的独立风险因素。参考Logistic回归分析对患者死亡风险的预测结果来验证DL功能的预测结果。结果通过DL功能计算获得死亡患者的基线资料间有效强关联规则9项,其前项包括:年龄、急性生理学与慢性健康状况评估系统Ⅱ(APACHEⅡ)评分、序贯器官衰竭评分(SOFA)、院内感染、机械通气、动静脉插管、动静脉插管时间、导尿管插管。除“肝脏疾病”和“昏迷”外,DL功能同Logistic回归分析预测结果高度一致。两种方法预测结果的比较在一定程度上证实DL功能的科学性和可靠性。结论基于FP-Growth和Apriori算法的DL功能可用于预测ICU患者死亡的关联因素,具有一定应用和推广价值。展开更多
目的构建可预测心脏骤停患者住院期间死亡风险的机器学习模型,并对其进行解释。方法提取美国重症监护医学信息数据库Ⅳ(Medical Information Mart for Intensive Care databaseⅣ,MIMIC-Ⅳ)2.0中心脏骤停患者转入ICU 24 h内首次临床资...目的构建可预测心脏骤停患者住院期间死亡风险的机器学习模型,并对其进行解释。方法提取美国重症监护医学信息数据库Ⅳ(Medical Information Mart for Intensive Care databaseⅣ,MIMIC-Ⅳ)2.0中心脏骤停患者转入ICU 24 h内首次临床资料及住院期间转归,基于机器学习算法构建6种可预测心脏骤停患者院内死亡风险的模型,包括XGBoost模型、轻量级梯度提升机(light gradient boosting machine,LGBM)模型、决策树(decision tree,DT)模型、K近邻(K-nearest neighbor,KNN)模型、Logistic回归模型、随机森林(random forest,RF)模型。采用受试者操作特征(receiver operator characteristic,ROC)曲线、临床决策曲线及校准曲线对模型进行评价,并采用Shapley加性解释(Shapley additive explanation,SHAP)算法评估不同临床特征对最优模型的影响,以增加模型的可解释性。结果共1465例符合纳入与排除标准的心脏骤停患者入选本研究。其中住院期间存活773例、死亡692例。经筛选,共纳入82个临床特征用于机器学习模型构建。模型评价结果显示,相较于其余5种模型,LGBM模型预测心脏骤停患者院内死亡的曲线下面积(area under the curve,AUC)更高[0.834(95%CI:0.688~0.894)],且相对于Logistic回归模型、XGBoost模型,其对死亡风险的预测准确性更高(校准度:0.166),临床决策性能更优,整体性能最佳。SHAP算法分析显示,对LGBM模型输出结果影响最大的3个临床特征分别为格拉斯哥睁眼反应评分、碳酸氢盐水平、白细胞计数。结论基于大型公共医疗卫生数据库建立的可预测心脏骤停患者住院期间死亡风险的机器学习模型中,LGBM模型性能最优,其可辅助临床进行更高效的疾病管理和更精准的医疗干预。展开更多
文摘Purpose: Women who are surgically treated for vulvar cancer often have complications leading to substantial patient morbidity. Post-surgical complications could be minimized by the identification of pre-surgical risks for complications and by planned post-surgical interventions. Therefore, the aim of this study was to develop a clinical care algorithm for vulvar cancer to assess risk for complications and prevent and control post-surgical complications. Methods: Key elements of the algorithm were identified via a literature review, structured chart review, a survey of care team members and interviews with stakeholders including healthcare team, patients and their family. Results: An algorithm for the management of wound and psychosocial complications was developed, based on internal and external evidence and was vetted by expert reviewers. Conclusion: Describing the process and defining the roles of health care professionals contributes to purposeful, systematic prevention and treatment of post-surgical complications. The care algorithm provides structured reference points for healthcare professionals with regard to multidisciplinary post-surgical management of vulvar cancer patients.
文摘目的利用FP-Growth和Apriori算法的深度学习(deep learning,DL)功能预测重症监护病房(ICU)患者院内死亡的关联因素。方法筛选美国重症监护医学信息数据库-Ⅲ(medical information mart for intensive care-Ⅲ,MIMIC-Ⅲ)中患者10000例,包含死亡患者1320例,收集其基线资料进行回顾性研究。使用SPSS Modeler 18.0软件编制FP-Growth和Apriori算法程序,通过DL功能计算1320例死亡患者的基线资料间有效强关联规则。对全部患者行Logistic回归分析导致死亡的独立风险因素。参考Logistic回归分析对患者死亡风险的预测结果来验证DL功能的预测结果。结果通过DL功能计算获得死亡患者的基线资料间有效强关联规则9项,其前项包括:年龄、急性生理学与慢性健康状况评估系统Ⅱ(APACHEⅡ)评分、序贯器官衰竭评分(SOFA)、院内感染、机械通气、动静脉插管、动静脉插管时间、导尿管插管。除“肝脏疾病”和“昏迷”外,DL功能同Logistic回归分析预测结果高度一致。两种方法预测结果的比较在一定程度上证实DL功能的科学性和可靠性。结论基于FP-Growth和Apriori算法的DL功能可用于预测ICU患者死亡的关联因素,具有一定应用和推广价值。
文摘目的构建可预测心脏骤停患者住院期间死亡风险的机器学习模型,并对其进行解释。方法提取美国重症监护医学信息数据库Ⅳ(Medical Information Mart for Intensive Care databaseⅣ,MIMIC-Ⅳ)2.0中心脏骤停患者转入ICU 24 h内首次临床资料及住院期间转归,基于机器学习算法构建6种可预测心脏骤停患者院内死亡风险的模型,包括XGBoost模型、轻量级梯度提升机(light gradient boosting machine,LGBM)模型、决策树(decision tree,DT)模型、K近邻(K-nearest neighbor,KNN)模型、Logistic回归模型、随机森林(random forest,RF)模型。采用受试者操作特征(receiver operator characteristic,ROC)曲线、临床决策曲线及校准曲线对模型进行评价,并采用Shapley加性解释(Shapley additive explanation,SHAP)算法评估不同临床特征对最优模型的影响,以增加模型的可解释性。结果共1465例符合纳入与排除标准的心脏骤停患者入选本研究。其中住院期间存活773例、死亡692例。经筛选,共纳入82个临床特征用于机器学习模型构建。模型评价结果显示,相较于其余5种模型,LGBM模型预测心脏骤停患者院内死亡的曲线下面积(area under the curve,AUC)更高[0.834(95%CI:0.688~0.894)],且相对于Logistic回归模型、XGBoost模型,其对死亡风险的预测准确性更高(校准度:0.166),临床决策性能更优,整体性能最佳。SHAP算法分析显示,对LGBM模型输出结果影响最大的3个临床特征分别为格拉斯哥睁眼反应评分、碳酸氢盐水平、白细胞计数。结论基于大型公共医疗卫生数据库建立的可预测心脏骤停患者住院期间死亡风险的机器学习模型中,LGBM模型性能最优,其可辅助临床进行更高效的疾病管理和更精准的医疗干预。