Blood pressure(BP)is an important indicator of an individuaPs health status and is closely related to daily behaviors.Thus,a continuous daily measurement of BP is critical for hypertension control.To assist continuous...Blood pressure(BP)is an important indicator of an individuaPs health status and is closely related to daily behaviors.Thus,a continuous daily measurement of BP is critical for hypertension control.To assist continuous measurement,BP prediction based on non-physiological data(ubiquitous mobile phone data)was studied in the research.An algorithm was proposed that predicts BP based on patients'daily routine,which includes activities such as sleep,work,and commuting.The aim of the research is to provide insight into the application of mobile data in telemonitoring and the continuous unobtrusive daily measurement of BP.A half-year data set from October 2017 of 320 individuals,including telecom data and BP measurement data,was analyzed.Two hierarchical Bayesian topic models were used to extract individuals,location-driven daily routine patterns(topics)and calculate probabilities among these topics from their day-level mobile trajectories.Based on the topic probability distribution and patients'contextual data,their BP were predicted using different models.The prediction model comparison shows that the long short-term memory(LSTM)method exceeds others when the data has a high dependency.Otherwise,the Random Forest regression model outperforms the LSTM method.Also,the experimental results validate the effectiveness of the topics in BP prediction.展开更多
目的构建并验证危重症型流行性感冒(以下简称“流感”)患者早期预测模型。方法选择2017年1月1日—2020年6月30日就诊于四川大学华西医院急诊科、四川大学华西医院上锦医院急诊科和攀枝花市中心医院急诊科的流感患者。根据K折交叉验证法...目的构建并验证危重症型流行性感冒(以下简称“流感”)患者早期预测模型。方法选择2017年1月1日—2020年6月30日就诊于四川大学华西医院急诊科、四川大学华西医院上锦医院急诊科和攀枝花市中心医院急诊科的流感患者。根据K折交叉验证法将70%的患者随机分配至模型建立组,30%的患者分配至模型验证组。并将模型建立组和模型验证组中的患者分别分为危重型组和非危重型组。基于修订版本国家早期预警评分(modified National Early Warning Score,MEWS)和简化英国胸科协会改良肺炎评分(confusion,uremia,respiratory,BP,age 65 years,CRB-65),构建危重症型流感早期预测模型,并评估该早期预测模型的准确度。结果共纳入患者612例。其中,模型建立组427例,模型验证组185例。在模型建立组中,非危重症型304例,危重症型123例。在模型验证组中,非危重型152例,危重型33例。二分类logistic回归分析结果显示,年龄、高血压、出现首发症状至急诊就诊间隔天数、意识状态、血氧饱和度、白细胞计数、淋巴细胞绝对值是危重症型流感的独立危险因素。根据这7个危险因素建立危重症型流感早期预测模型,该模型对非危重症型及危重症型患者预测的正确百分比分别为95.4%及77.2%,总体预测正确百分比为90.2%。受试者操作特征曲线分析结果显示,危重症型流感早期预测模型在预测危重症患者中的灵敏度为0.909,特异度为0.921,曲线下面积及其95%置信区间为0.931(0.860,0.999);危重症型流感早期预测模型的灵敏度、特异度及曲线下面积(0.935、0.865、0.942)高于MEWS(0.642、0.595、0.536)和CRB-65(0.628、0.862、0.703)。结论年龄、高血压、出现首发症状至急诊就诊间隔天数、意识状态、血氧饱和度、白细胞计数、淋巴细胞绝对值是预测危重症流感患者的独立危险因素。危重症型流感早期预测模型在预测危重症流感患者�展开更多
基金the National Natural Science Foundation of China(Grants No.91646205 and 71421002)the Fundamental Research Funds for the Central Universities of China(Grant No.16JCCS08)。
文摘Blood pressure(BP)is an important indicator of an individuaPs health status and is closely related to daily behaviors.Thus,a continuous daily measurement of BP is critical for hypertension control.To assist continuous measurement,BP prediction based on non-physiological data(ubiquitous mobile phone data)was studied in the research.An algorithm was proposed that predicts BP based on patients'daily routine,which includes activities such as sleep,work,and commuting.The aim of the research is to provide insight into the application of mobile data in telemonitoring and the continuous unobtrusive daily measurement of BP.A half-year data set from October 2017 of 320 individuals,including telecom data and BP measurement data,was analyzed.Two hierarchical Bayesian topic models were used to extract individuals,location-driven daily routine patterns(topics)and calculate probabilities among these topics from their day-level mobile trajectories.Based on the topic probability distribution and patients'contextual data,their BP were predicted using different models.The prediction model comparison shows that the long short-term memory(LSTM)method exceeds others when the data has a high dependency.Otherwise,the Random Forest regression model outperforms the LSTM method.Also,the experimental results validate the effectiveness of the topics in BP prediction.
文摘目的构建并验证危重症型流行性感冒(以下简称“流感”)患者早期预测模型。方法选择2017年1月1日—2020年6月30日就诊于四川大学华西医院急诊科、四川大学华西医院上锦医院急诊科和攀枝花市中心医院急诊科的流感患者。根据K折交叉验证法将70%的患者随机分配至模型建立组,30%的患者分配至模型验证组。并将模型建立组和模型验证组中的患者分别分为危重型组和非危重型组。基于修订版本国家早期预警评分(modified National Early Warning Score,MEWS)和简化英国胸科协会改良肺炎评分(confusion,uremia,respiratory,BP,age 65 years,CRB-65),构建危重症型流感早期预测模型,并评估该早期预测模型的准确度。结果共纳入患者612例。其中,模型建立组427例,模型验证组185例。在模型建立组中,非危重症型304例,危重症型123例。在模型验证组中,非危重型152例,危重型33例。二分类logistic回归分析结果显示,年龄、高血压、出现首发症状至急诊就诊间隔天数、意识状态、血氧饱和度、白细胞计数、淋巴细胞绝对值是危重症型流感的独立危险因素。根据这7个危险因素建立危重症型流感早期预测模型,该模型对非危重症型及危重症型患者预测的正确百分比分别为95.4%及77.2%,总体预测正确百分比为90.2%。受试者操作特征曲线分析结果显示,危重症型流感早期预测模型在预测危重症患者中的灵敏度为0.909,特异度为0.921,曲线下面积及其95%置信区间为0.931(0.860,0.999);危重症型流感早期预测模型的灵敏度、特异度及曲线下面积(0.935、0.865、0.942)高于MEWS(0.642、0.595、0.536)和CRB-65(0.628、0.862、0.703)。结论年龄、高血压、出现首发症状至急诊就诊间隔天数、意识状态、血氧饱和度、白细胞计数、淋巴细胞绝对值是预测危重症流感患者的独立危险因素。危重症型流感早期预测模型在预测危重症流感患者�
文摘目的:基于血常规和颈动脉斑块构建一种个性化nomogram风险预测模型预测颈动脉粥样硬化(carotid atherosclerosis, CAS)患者发生缺血性脑卒中(cerebral ischemic stroke, CIS)的风险。方法:选取2021年3月1日至2022年3月1日在上海市第八人民医院神经内科住院的CAS患者214例,收集患者的基本特征、血常规指标及影像学检查数据。根据是否发生缺血性脑卒中分别分为两组,随机抽取全部数据按7∶3的比例拆分为建模组和验证组。采用单因素logistic回归和lasso回归筛选CAS患者发生缺血性脑卒中的独立风险预测因子,将其导入R软件构建nomogram预测模型。ROC曲线下面积(AUC)、校准曲线和DCA决策曲线对模型进行内部验证。结果:单因素logistic回归和lasso回归分析结果显示,红细胞分布宽度、大型血小板比率、血小板计数是CAS患者发生缺血性脑卒中的独立风险预测因子(P<0.05),由于年龄对于CIS具有重要临床意义,最终也将其纳入模型。基于上述预测因子导入R软件构建nomogram预测模型并进行模型内部验证。建模组受试者工作特征曲线下面积(area under the curve, AUC)为0.644,验证组AUC为0.677,表示该nomogram模型预测能力较好。Hosmer-Lemeshow拟合优度检验(P=0.058),表明该模型具有较好的区分度。DCA曲线显示风险阈值为8%~45%时使用该模型具有临床实用价值。结论:本研究构建并验证了一个预测CAS患者发生缺血性脑卒中的nomogram风险预测模型,该模型预测能力和区分能力较好,对临床评估CAS患者发生缺血性脑卒中具有较高的临床实用价值。
