大数据健康干预措施对代谢性疾病的影响分析

Analysis of big data health intervention strategies on metabolic diseases

目的探讨运用大数据采集处理模式对一般人群常见代谢性疾病的监测及干预效果。方法运用计算机技术建立信息化健康档案管理系统。选取高血压、高血脂、高血糖、高尿酸血症、脂肪肝等代谢性疾病为监测指标,将样本数据与社会同期大数据对比分析,敏感识别目标人群主要健康问题。选取脂肪肝为观测指标,对该人群进行针对性干预并分析效果。通过大数据长期追踪对个体健康指标进行个性化干预并评价效果。结果从2008年起,运用信息技术连续采集同一人群健康数据13 591人次,建立起动态健康管理系统。经分析得出,该人群的血压控制良好,高血糖与高尿酸血症基本与社会平均水平相同,高脂血症及脂肪肝为主要健康问题。通过针对性干预后,人群脂肪肝检出率有所下降,显示该措施具有积极作用。通过数据动态追踪预警1例癌前病变患者,经过个性化干预获得痊愈。结论大数据健康干预模式在人群主要健康隐患排查及针对性干预方面取得良好成效。

Objective To analysis the effects of surveillance and intervention strategies on metabolic diseases by big data information processing mode. Methods The digital health information system was established with computer technology. Metabolic diseases including hypertension, hyperlipidemia, hyperglycemia, hyperuricemia and fatty liver were chosen as monitoring indicators. The sample detection rate was compared with the general prevalence to identify the major health problems of the population. The effects of health intervention strategies were evaluated by the detection rate of fatty liver. The results of personalized intervention were observed by information technology. Results Since 2008, 13 591 units of continuous health data have been collected to establish a dynamic health management system. The annalistic results showed a well controlled blood pressure and average level of hyperglycemia and hyperuricemia. The major health concerns among the sample population were hyperlipidemia and fatty liver. Health intervention strategies resulted in a decreased detection rate of fatty liver. A case of precancerous lesion was recovered after individualized intervention. Conclusion Big data health intervention strategies have achieved satisfying results in health risk detection and intervention.