Sieve based full likelihood approach for the Cox proportional hazards model with applications to immunotherapies trials

基于筛法的 Cox 比例风险模型的完全似然法及其在免疫治疗试验中的应用

• 批准号: 10577723
• 负责人: SUSAN HALABI
• 金额: $ 22.58万
• 依托单位: DUKE UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-02-22 至 2025-01-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10577723
• 关键词: Algorithms; Area; Biological; Cancer Patient; Characteristics; Chi-Square Distribution; Clinical Research; Clinical Treatment; Clinical Trials; Cox Models; Cox Proportional Hazards Models; Data; Detection; Development; Disease; Event; Immunotherapy; Individual; Investigation; Libraries; Malignant Neoplasms; Maximum Likelihood Estimate; Methods; Molecular; Observational Study; Outcome; Patients; Pattern; Performance; Phase II/III Trial; Probability; Progression-Free Survivals; Randomized; Reporting; Research; Residual state; Sampling Studies; Survival Analysis; Test Result; Testing; Time; Treatment Efficacy; design; exceptional responders; experience; hazard; immunotherapy trials; improved; interest; novel; novel strategies; phase 2 study; phase III trial; precision medicine; primary endpoint; primary outcome; semiparametric; simulation; statistics; tool; treatment effect

In clinical studies, the time-to-event outcomes are widely used to evaluate a new treatment efficacy. When complete randomization is not possible or successful the Cox proportional hazards model can be used to adjust for the confounding effects and to increase statistical power. Phase II studies usually have relatively small number, so the survival analysis results are not very reliable or do not have enough power to detect a positive result of the experimental treatment. This project aims to provide better survival analysis results compared to existing methods for small sample studies. Sieve method has becoming a popular approach in survival analysis, we propose to use the sieve maximum likelihood estimations to improve survival analysis results for small studies and provide corresponding computing tools for public use.

在临床研究中，事件发生时间的结果被广泛用于评估新的治疗方法。 功效。当完全随机化不可能或不成功时， 可以使用危险模型来调整混杂效应并增加统计 权力。二期研究的数量通常相对较少，因此生存分析结果为 不太可靠或没有足够的能量来检测实验的阳性结果 治疗。该项目旨在提供比现有的更好的生存分析结果 方法：小样本研究。筛选法已成为一种流行的方法 生存分析，我们建议使用筛子最大似然估计来改进 为小型研究提供生存分析结果并提供相应的计算工具 公共用途。