Multivariate CART for survival with dental applicaions

多元 CART 用于牙科应用的生存

• 批准号: 6960515
• 负责人: MARTHA E NUNN
• 金额: $ 15.8万
• 依托单位: BOSTON UNIVERSITY MEDICAL CAMPUS
• 依托单位国家: 美国
• 财政年份: 2005
• 资助国家: 美国
• 起止时间: 2005-09-01 至 2007-06-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/6960515
• 关键词: computer assisted medical decision making; dental alveolus; dental caries; dental radiography; dentistry; disease /disorder classification; human data; longitudinal human study; mathematical model; model design /development; periodontium disorder; prognosis; restorative dentistry; statistics /biometry; tooth loss

Tooth loss from periodontal disease or dental caries afflicts most adults over the course of their lives. Goals of professional dental treatment and of personal oral health self-care are to prevent tooth loss and maintain the natural dentition in a state of comfort and function. In order to develop appropriate dental treatment planning, dental health care professionals must weigh the long-term outlook for retention of each tooth against the cost and discomfort involved with each treatment option, and patients and third-party payers must make value judgments about the cost of suggested dental treatments against the probability of long-term success for those treatments Hence, it is essential to utilize dental prognosis in the development of any dental treatment plan. Goals: The primary goals of this study are to further develop multivariate CART for survival and apply this newly extended form of CART for survival to a large, well-established database in an effort to develop global dental prognostic indicators that are based on actual tooth loss. Subjects: This hypothesis will be tested on up to 1231 dentate men who were enrolled in the Dental Longitudinal Study component of the VA Normative Aging Study, an established cohort of men followed for up to 30 years with triennial oral and medical examinations. Note that these men are not VA patients, and all subjects receive dental and medical care from a variety of practitioners in the private sector. Available historical data: Data for tooth loss, clinical restorative measures, clinical periodontal indices, medical status, smoking, alcohol, behavioral, and other parameters have been collected triennally over 30 years. Change in alveolar bone loss at all interproximal sites has also been measured from at least 6 sequential sets of full-mouth films per subject spanning a minimum of 15 years, which have been digitized with a computer-assisted image transformation technique. Measures of percent remaining bone and mean rates of alveolar bone loss are also available. Significance: Development of multivariate CART for survival can be applied to other dental data, and results of this study will provide objective criteria for assignment of global dental prognostic indicators that is based on actual tooth loss.

牙周病或龋齿导致的牙齿脱落困扰着大多数成年人的一生。专业牙科治疗和个人口腔健康自我护理的目标是防止牙齿脱落，并保持自然牙列的舒适和功能状态。为了制定适当的牙科治疗计划，牙科保健专业人员必须权衡保留每颗牙齿的长期前景和每个治疗方案所涉及的成本和不适感，患者和第三方付款人必须对建议的牙科治疗的成本和这些治疗的长期成功概率做出价值判断。因此，在制定任何牙科治疗计划时，利用牙齿预后是至关重要的。目标：这项研究的主要目标是进一步发展多变量生存CART，并将这种新扩展的生存CART形式应用到一个大型的、完善的数据库中，努力开发基于实际牙齿丢失的全球牙齿预后指标。研究对象：这一假设将在多达1231名参加退伍军人标准老龄化研究的牙科纵向研究部分的齿状男性身上进行测试，该研究是一个既定的男性队列，对男性进行长达30年的跟踪调查，每三年进行一次口腔和医学检查。请注意，这些人不是退伍军人管理局患者，所有受试者都接受私营部门各种从业者的牙科和医疗护理。可获得的历史数据：30多年来每三年收集一次关于牙齿脱落、临床修复措施、临床牙周指数、医疗状况、吸烟、酒精、行为和其他参数的数据。每名受试者至少连续拍摄6组全口片，持续至少15年，并通过计算机辅助图像转换技术进行数字化，还测量了所有近端位置的牙槽骨丢失的变化。测量剩余骨百分比和平均牙槽骨丢失率也是可用的。意义：多变量生存CART的开发可应用于其他牙科数据，本研究结果将为基于实际牙齿缺失的全球牙科预后指标的分配提供客观标准。