Time Series Modeling of Trends in Medication Prescribing

描述：医生对药物处方的决定有一个 对医疗保健成本和临床结果有很大影响。令人惊讶的是几乎没有 然而，我们知道一系列因素的相对影响，这些因素可能 影响医生在开药时的行为。推而广之， 解释和预测药物处方趋势的能力是 目前是有限的。这项研究将开发一种新的经济模型 多个决定因素对药物趋势的同时影响 开处方。计量经济学时间序列回归技术将用于 估计时间变化的预测变量的相对影响 在处方中观察到的国家趋势的离散时间事件 治疗高血压、抑郁症、哮喘和充血性心脏的药物 失败了。1978年至2000年具有全国代表性的季度趋势数据 这些疾病的药物处方将来自国家疾病 和治疗指数调查可通过IMS Health获得。每季度患者 1998年抑郁症的样本量约为1700，充血性心脏病的样本量约为550 失败者中，有5100人患有高血压，2000人患有哮喘。关于潜力的数据 对趋势的预测将从各种来源发展出来。 药品促销和药品批发的具体趋势信息 价格也将从IMS Health获得。其他预测因素包括 有关药物剂量、其他药物特性、临床试验结果的信息 出版、媒体报道药物和临床指南 出版。通过构建一个综合的时态模型 决定开药行为的因素，本研究将对相关人员进行评估 这些因素的影响。建立计量经济学时间序列回归模型 关于差异化产品需求的理论将被用来检验 关于这些因素作用的具体假设。一个关键假说 将是宣传的影响比科学的影响更强大 影响。此外，这项研究还将评估与 药品价格的影响，科学和推广的相互作用，以及 品牌名称过期的影响。分析的结果将是相关的 致力于设计和实施临床和卫生政策，以鼓励 药物的有效和成本效益高的使用。

DESCRIPTION: Physician decisions regarding medication prescribing have a large impact on health care costs and clinical outcomes. Surprisingly little is known, however, about the relative impact of a range of factors that may influence physician behavior in the prescribing of medications. By extension, the ability to explain and project trends in medication prescribing is currently limited. This study will develop a novel economic model of the simultaneous influence of multiple determinants on trends in medication prescribing. Econometric time-series regression techniques will be used to estimate the relative influence of temporally varying predictor variables and discrete temporal events on observed national trends in the prescribing of pharmaceuticals for hypertension, depression, asthma, and congestive heart failure. Nationally representative quarterly data on 1978 through 2000 trends in drug prescribing for these conditions will come from the National Disease and Therapeutic Index survey available through IMS Health. Quarterly patient sample sizes in 1998 are about 1,700 for depression, 550 for congestive heart failure, 5,100 for hypertension and 2,000 for asthma. Data on potential predictors of trends will be developed from a variety of sources. Drug-specific trend information on pharmaceutical promotion and wholesale drug prices also will be available from IMS Health. Other predictors will include information on drug dosing, other drug characteristics, clinical trial results publication, media reporting on medications, and clinical guideline publication. By constructing a comprehensive model of the temporal determinants of prescribing behavior, this study will assess the relative influence of these factors. Econometric time series regression models built on the theory of demand for differentiated products will be employed to test specific hypotheses regarding the role of these factors. A key hypothesis will be that promotional influences are more potent than scientific influences. In addition, the research will evaluate hypotheses related to the influence of drug prices, the interaction of science and promotion, and the impact of brand name expiration. Results from the analysis will be relevant to efforts to design and implement clinical and health policies to encourage the effective and cost-effective use of medications.