Evaluating eligibility criteria of oncology trials using real-world data and AI
一、背景
1. 临床试验入组规则过于严苛
around 80% of patients with advanced non-small-cell lung cancer (aNSCLC) did not meet the criteria of the analysed trials.
As a result, 86% of clinical trials failed to complete their recruitment within the targeted time
(简单、包容性更强的入组标准十分有必要)
2. 更改入组规则有安全性隐患
Some eligibility criteria are included to reduce the risks of severe toxicity adverse events, which is a critical consideration.
3. 真实世界数据+数据驱动的AI算法为评价、调整现有入组规则带来希望。
Artificial intelligence can screen patients that meet eligibility14–16, predict which patients are more likely to enrol in trials17,18 and extract features fromelectronic health records (EHRs)19–21.
Several studies have introduced approaches to quantify the difference between the study samples of a
clinical trial and the target population that can use the treatment
Recent research also used EHR data to evaluate how different eligibility criteria can affect the number of adverse events associated with COVID-19 that are observed in the selected cohort.
二、方法
1. 基于Flatiron Heath数据库选定肿瘤人群—aNSCLC
advanced non-small cell lung cancer
focused on aNSCLC, because aNSCLC is a prevalentcancer type and has the largest number of patients in the Flatiron Health database.
Flatiron Health, a nationwide EHR-derived de-identified databasecontaining 219,312 patients with cancer with an average of 2.6 yearsof follow-up. The Flatiron Health database is considered one of the industry’s leading research databases in oncology owing to the rigorous data curation and abstraction processes as well as publications in which their efforts to validate outcomes are demonstrated.
the Flatiron data areharmonized and aggregated across approximately 280 cancer clinics across the country, which enables its data to be more representative than the EHRs of a single healthcare centre.
2. 选取临床试验
从临床注册网站上抓取相关临床试验：ClinicalTrials.gov websiteof the National Library of Medicine (共3684)
筛选临床试验：
3. 基于真实数据模拟临床入组情况
4. 比较不同入组策略对生存、入组人数的影响
比较原则：原入组标准 VS 实际标准 VS 采用部分标准
比较结局：
生存情况 （采用指标为HR, 经过倾向性评分匹配控制了其他协变量后的）
入组人数的变化
5. 拓宽入组标准的安全性评价
比较实验室指标的不同水平所致毒副反应情况:胆红素、血小板、血红蛋白和碱性磷酸酶
统计学指标： two-sided P values from two-tailed Student’s t-tests to evaluate whether there is a significant difference in the baseline laboratory values between two toxicity groups .
6. 敏感性分析
亚组分析：by 地域 & 保险计划
by their geography of residence as in the US census—Northeast (n = 11,777), Midwest (n = 8,895), South (n = 23,895) and West (n = 9,061) .
by their insurance plan as an additional robustness analysis—commercial health plans (n = 22,423), Medicare (n = 10,841) and the remaining patients (n = 22,361).
增加结局指标：无进展生存情况
增补其他癌种结果：colorectal cancer (CRC), advanced melanoma and metastatic breast cancer
外部数据集验证（增补了基因相关因子作为covariates）
We used the nationwide (US-based) de-identified Flatiron Health-Foundation Medicine aNSCLC
clinicogenomic database (FH-FMI CGDB) for further validation. we added 17 additional genes to the adjustment of the covariates that have alterations in at least 1,000 patients .
三、结果
1. 不同入组策略对生存、入组人数的影响
2. 拓宽入组标准的安全性评价结果
3. 敏感性分析结果
亚组分析结果：
略，见Supplementary Tables 22–25 ：http://static—content-springer-com-s.webvpn.zju.edu.cn:8001/esm/art%3A10.1038%2Fs41586-021-03430-5/MediaObjects/41586_2021_3430_MOESM1_ESM.pdf
PFS结果
其他癌种结果
外部验证集结果
四、讨论及意义
1. RWE支持扩宽临床试验入组标准，为后续试验设计提供参考依据
Our findings suggest that it is particularly promising to standardize and potentially broaden several eligibility criteria based on cut-offs for bilirubin, platelets, haemoglobin and ALP values.
Our data-driven evaluation of eligibility criteria should be interpreted as one factor among several that can assist clinical trial specialists in their designs.
2. 后续研究可探讨除肿瘤以外领域的临床研究入组标准
Currently, longitudinal real-world data with robust outcomes are more limited for diseases other than cancer, which can have more complex end points. There will be opportunities to extend this work outside of
oncology as additional high-quality data become available.
若有收获，就点个赞吧
0 人点赞
