Gandy Lisa M, Gumm Jordan, Blackford Amanda L, Fertig Elana J, Diaz Luis A
Department of Computer Science, Central Michigan University, Mt Pleasant, MI, USA.
Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA.
Cancer Inform. 2017 Jun 22;16:1176935117711940. doi: 10.1177/1176935117711940. eCollection 2017.
ClinicalTrials.org is a popular portal which physicians use to find clinical trials for their patients. However, the current setup of ClinicalTrials.org makes it difficult for oncologists to locate clinical trials for patients based on mutational status. We present CTMine, a system that mines ClinicalTrials.org for clinical trials per cancer mutation and displays the trials in a user-friendly Web application. The system currently lists clinical trials for 6 common genes (ALK, BRAF, ERBB2, EGFR, KIT, and KRAS). The current machine learning model used to identify relevant clinical trials focusing on the above gene mutations had an average 88% precision/recall. As part of this analysis, we compared human versus machine and found that oncologists were unable to reach a consensus on whether a clinical trial mined by CTMine was "relevant" per gene mutation, a finding that highlights an important topic which deems future exploration.
ClinicalTrials.org是一个广受欢迎的门户网站，医生们用它来为患者寻找临床试验。然而，ClinicalTrials.org目前的设置使得肿瘤学家很难根据突变状态为患者找到临床试验。我们展示了CTMine，这是一个从ClinicalTrials.org中挖掘针对每种癌症突变的临床试验并在用户友好的Web应用程序中显示这些试验的系统。该系统目前列出了6种常见基因（ALK、BRAF、ERBB2、EGFR、KIT和KRAS）的临床试验。目前用于识别聚焦于上述基因突变的相关临床试验的机器学习模型平均精确率/召回率为88%。作为该分析的一部分，我们比较了人工与机器的判断，发现肿瘤学家无法就CTMine挖掘出的一项临床试验是否针对每个基因突变“相关”达成共识，这一发现凸显了一个值得未来探索的重要课题。
