频率自适应起搏器的运动——心率预测系统的研究

从基于加速度传感器的体动型频率自适应起搏器心率控制方法的研究入手,设计了一种运动--心率预测系统。系统的上位机和下位机之间通过蓝牙模块进行通讯。下位机完成人体加速度信号的采集、处理以及加速度信号向起搏心率信号的映射,同时完成加速度信号和心率信号的实时传输。上位机完成人体加速度信号和心率信号的实时显示和记录,并且通过对6个参数的分级设置实现对下位机的算法控制。应用运动--心率预测系统进行的验证实验结果表明,线性算法得到的映射起搏心率和实际心率的相关性比较好,线性比较显著(R2=0.787,P<0.001)。

基于运动量的神经网络心率预测器的设计及对比研究

目的利用神经网络建立有效的基于运动量的心率预测模型,分析运动量与心率变化之间的关系。方法通过对运动量信号进行不同分析(预处理),并采用不同的神经网络的结构及学习算法,单步或多步预测方式建立了6个预测模型,然后利用采集到的真实数据进行测试,并对各模型结构框架及预测结果进行了对比。结果建立的模型平均预测误差均保持在一个很小的范围内。结论利用神经网络建立心率预测模型可有效地反映运动量如何影响心率变化。对比结果表明,在单步预测中,利用神经网络拓扑增强技术(neuro-evolution of augmenting topologies,NEAT)建立的心率预测模型可达到最佳的预测效果,而多步预测利用Adams-Bashforth技术得到的预测结果是最好的。

心率震荡和心率变异性预测急性心肌梗死患者心脏性猝死及干预治疗

心肌梗死患者是发生猝死的高危人群，尤其在心肌梗死后近期猝死的发生率最高。为了提高心肌梗死患者的生存时间及存活率，临床研究一直在寻求心肌梗死后心脏性猝死高危患者的检测方法和指标，并根据这些有效的预测指标为患者进行危险度分层，给予及时有效的干预性治疗。心率震荡（HRT）是指发生室性早搏后窦性心律出现短暂的心率波动现象，反映窦房结的双向变时功能。已有临床试验证实了HRT临床应用的重要价值，HRT的两个评价参数，震荡初始（TO）和震荡斜率（TS）与心脏射血分数（LVEF）相似，可作为心肌梗死高危猝死患者的独立预后因素。

面向移动智能终端的人体心率监护系统设计与实现

高质量的长期健康医疗监护逐渐成为全世界人们关注的焦点;为预防突发心脏病所带来的风险,论文结合临床最常见的健康指标心率,采用基于随机森林的心率预测模型,设计了一款面向移动智能终端的可穿戴、可交互,具有实时心率采集、异常心率检测和心率异常预警等功能的小型人体心率监护系统;实验结果表明,该心率监护系统能实现用户心率的实时监测和未来时刻心率的预测,心率预测正确率可达86.67%,预测精确度可以满足用户的需求。

基于粒子群优化长短期记忆网络的运动生理数据预测算法研究与应用

为提高现有智能运动产品对运动生理数据的预测效果,本研究提出了基于粒子群(particle swarm optimization, PSO)优化长短期记忆(long short-term memory, LSTM)网络的运动生理数据预测模型。为使模型的网络拓扑结构与运动生理数据更加匹配,本研究利用传感器采集到的运动生理数据分别构建优化前后的模型,通过比较各模型的预测结果,评价其优化效果。结果显示,优化后模型预测结果的均方根误差(root mean square error, RMSE)为1.693 8,较优化前模型降低了1.757 0。本研究模型对运动生理数据的预测精准度更高。

Differences in the predictive value of red cell distribution width for the mortality of patients with heart failure due to various heart diseases

Background Increased red blood cell distribution width （RDW） is associated with adverse outcomes in patients with heart failure （HF）. The objective of this study was to compare the differences in the predictive value of RDW in patients with HF due to different causes. Methods We retrospectively investigated 1,021 HF patients from October 2009 to December 2011 at Fuwai Hospital （Beijing, China）. HF in these patients was caused by three diseases; coronary heart disease （CHD）, dilated cardiomyopathy （DCM） and valvular heart disease （VHD）. Patients were followed-up for 21 ~ 9 months. Results The RDW, mortality and survival duration were significantly different among the three groups. Kaplan-Meier analysis showed that the cumulative survival decreased significantly with increased RDW in patients with HF caused by CHD and DCM, but not in those with HF patients caused by VHD. In a multivariable model, RDW was identified as an independent predictor for the mortality of HF patients with CHD （P 〈 0.001, HR 1.315, 95% CI 1.122-1.543）. The group with higher N-terminal pro-brain natriuretic peptide （NT-proBNP） and higher RDW than median had the lowest cumulative survival in patients with HF due to CHD, but not in patients with HF due to DCM. Conclusions RDW is a prognostic indicator for patients with HF caused by CHD and DCM; thus, RDW adds important information to NT-proBNP in CHD caused HF patients.

Western North Pacific Tropical Cyclone Intensity Guidance Evaluations Using an Alternative Verification Technique

In this study,six intensity forecast guidance techniques from the East China Regional Meteorological Center are verified for the 2008 and 2009 typhoon seasons through an alternative forecast verification technique.This technique is used to verify intensity forecasts if those forecasts call for a typhoon to dissipate or if the real typhoon dissipates.Using a contingency table,skill scores,chance,and probabilities are computed.It is shown that the skill of the six tropical cyclone intensity guidance techniques was highest for the 12-h forecasts,while the lowest skill of all the six models did not occur in 72-h forecasting.For both the 2008 and 2009 seasons,the average probabilities of the forecast intensity having a small error(6 m s-1) tended to decrease steadily.Some of the intensity forecasts had small skill scores,but the associated probabilities of the forecast intensity errors > 15 m s-1 were not the highest.

Ankle-brachial index as a predictor of all-cause and cardio- vascular disease mortality in 3733 Chinese patients with high cardiovascular risk

Objective To assess the association between 1-year risk of all-cause and cardiovascular disease （CVD） mortality and ankle-brachial index （ABI） in Chinese patients who were at high CVD risk. Methods Totally 3733 patients with high CV risk had bilateral ABI measurements at baseline and were followed up for 1-1.5 years. Patients were divided to four groups： 1） coronary heart disease （CHD）; 2） ischemic stroke （IS）; 3） diabetes mellitus （DM）; 4） very high risk group（VHR）, low ABI was defined as 〈0.9. Results A total of 3179 patients were analyzed. The prevalence of low ABI was 28.1%. At 1 year, all-cause mortality was 8.7%, and 27.6% was attributable to CVD; mortality due to CV events was 4.8% and 1.5%. After adjusting other risk factors the hazard ratio of low ABI was 1.623 for all-cause mortality and 2.304 for CVD mortality. Similar in patient with and without low ABI, respectively were found in four groups.Conclusion ABI is a strong and independent predictor ofrnortality. Patients with a low ABI have a substantially increased risk of all-cause mortality and CVD mortality （J Geriatr Cardio12010; 7：17-20）.

Time Series Models for Short Term Prediction of the Incidence of Japanese Encephalitis in Xianyang City, P R China

Objective To construct a model of Seasonal Autoregressive Integrated Moving Average （SARIMA） for forecasting the epidemic of Japanese encephalitis （JE） in Xianyang, Shaanxi, China, and provide valuable reference information for JE control and prevention. Methods Theoretically epidemiologic study was employed in the research process. Monthly incidence data on JE for the period from Jan 2005 to Sep 2014 were obtained from a passive surveillance system at the Center for Diseases Prevention and Control in Xianyang, Shaanxi province. An optimal SARIMA model was developed for JE incidence from 2005 to 2013 with the Box and Jenkins approach. This SARIMA model could predict JE incidence for the year 2014 and 2015. Results SARIMA （1, 1, 1） （2, 1, 1）12 was considered to be the best model with the lowest Bayesian information criterion, Akaike information criterion, Mean Absolute Error values, the highest R2, and a lower Mean Absolute Percent Error. SARIMA （1, 1, 1） （2, 1, 1）12 was stationary and accurate for predicting JE incidence in Xianyang. The predicted incidence, around 0.3/100 000 from June to August in 2014 with low errors, was higher compared with the actual incidence. Therefore, SARIMA （1, 1, 1） （2, 1, 1）12 appeared to be reliable and accurate and could be applied to incidence prediction. Conclusions The proposed prediction model could provide clues to early identification of the JE incidence that is increased abnormally （≥0.4/100 000）. According to the predicted results in 2014, the JE incidence in Xianyang will decline slightly and reach its peak from June to August.The authors wish to thank the staff from the CDCs from 13 counties of Xianyang, Shaanxi province, China, for their contribution to Japanese encephalitis cases reporting.