Department of Internal Medicine, Division of Hematology-Oncology, The University of Texas Southwestern Medical Center, Dallas.
Harold C. Simmons Comprehensive Cancer Center, The University of Texas Southwestern Medical Center, Dallas.
JAMA Oncol. 2021 Oct 1;7(10):1559-1566. doi: 10.1001/jamaoncol.2021.1165.
As cancer treatment has become more individualized, oncologic clinical trials have become more complex. Increasingly numerous and stringent eligibility criteria frequently include tumor molecular or genomic characteristics that may not be readily identified in medical records, rendering it difficult to best match clinical trials with clinical sites and to identify potentially eligible patients once a clinical trial has been selected and activated. Partly because of these factors, enrollment rates for cancer clinical trials remain low, creating delays and increased costs for drug development. Information technology (IT) platforms have been applied to the implementation and conduct of clinical trials to improve efficiencies in several medical fields, and these platforms have recently been introduced to oncologic studies.
This review summarizes cancer and noncancer studies that used IT platforms for assistance with clinical trial site selection, patient recruitment, and patient screening. The review does not address the use of IT in other aspects of clinical research, such as wearable physical activity monitors or telehealth visits. A large number of IT platforms (which may be patient facing, site or investigator facing, or sponsor facing) are now commercially available. These applications use artificial intelligence and/or natural language processing to identify and summarize protocol eligibility criteria, institutional patient populations, and individual electronic health records. Although there is an expanding body of literature examining the role of this technology, relatively few studies to date have been performed in oncologic settings.
This review found that an increasing number and variety of IT platforms were available to assist in the planning and conduct of clinical trials. Because oncologic clinical care and clinical trial protocols are particularly complex, nuanced, and individualized, published experience with this technology in other fields may not be fully applicable to cancer settings. The extent to which these services will overcome ongoing and increasing challenges in cancer clinical research remains unclear.
随着癌症治疗变得更加个体化，肿瘤学临床试验变得更加复杂。越来越多的、严格的入选标准通常包括肿瘤分子或基因组特征，这些特征可能不容易在病历中识别，从而难以在临床试验与临床站点之间进行最佳匹配，并在选择和激活临床试验后确定潜在的合格患者。部分由于这些因素，癌症临床试验的入组率仍然很低，导致药物开发的延迟和成本增加。信息技术 (IT) 平台已应用于临床试验的实施和管理，以提高多个医学领域的效率，这些平台最近已被引入肿瘤学研究中。
本综述总结了使用 IT 平台辅助临床试验站点选择、患者招募和患者筛选的癌症和非癌症研究。该综述不涉及 IT 在临床研究其他方面的应用，例如可穿戴的身体活动监测器或远程医疗访问。现在有大量的 IT 平台（可能面向患者、面向站点或研究人员、面向赞助商）可供商业使用。这些应用程序使用人工智能和/或自然语言处理来识别和总结方案入选标准、机构患者人群和个人电子健康记录。尽管有越来越多的文献研究了这项技术的作用，但迄今为止，在肿瘤学领域进行的研究相对较少。
本综述发现，越来越多的 IT 平台可用于协助临床试验的规划和实施。由于肿瘤学临床护理和临床试验方案特别复杂、微妙和个体化，该技术在其他领域的已发表经验可能不完全适用于癌症环境。这些服务将在多大程度上克服癌症临床研究中持续存在和不断增加的挑战仍不清楚。
