TY - JOUR AU - Bickmore, Timothy W AU - Trinh, Ha AU - Olafsson, Stefan AU - O'Leary, Teresa K AU - Asadi, Reza AU - Rickles, Nathaniel M AU - Cruz, Ricardo PY - 2018 DA - 2018/09/04 TI -使用医疗信息会话助手时的患者和消费者安全风险:关于Siri、Alexa和谷歌助手的观察性研究JO - J Med Internet Res SP - e11510 VL - 20 IS - 9 KW -会话助手KW -会话界面KW -对话系统KW -医疗差错KW -患者安全AB -背景:会话助手,如Siri、Alexa和谷歌Assistant,无处不在,并开始被用作医疗服务的门户。然而,患者和消费者使用对话助手获取医疗信息的潜在安全问题尚不清楚。目的:确定患者或消费者使用对话助手获取医疗信息可能造成的伤害的普遍性和性质。方法:参与者被要求向Siri、Alexa或谷歌Assistant提出医疗问题,并被要求根据系统提供的信息决定采取的行动。任务和系统的分配在参与者中是随机的,参与者用自己的话询问对话助手,根据需要进行尽可能多的尝试,直到他们要么报告要采取的行动,要么放弃。参与者报告的每个医疗任务的行动使用医疗保健研究和质量伤害量表对患者伤害进行了评级。结果:54名受试者完成了研究,平均年龄42岁(SD 18)。29例(54%)为女性,31例(57%)为白种人,26例(50%)为大学学历。只有8人(15%)表示经常使用会话助手,22人(41%)从未使用过会话助手,24人(44%)尝试过“几次”。44人(82%)经常使用电脑。 Subjects were only able to complete 168 (43%) of their 394 tasks. Of these, 49 (29%) reported actions that could have resulted in some degree of patient harm, including 27 (16%) that could have resulted in death. Conclusions: Reliance on conversational assistants for actionable medical information represents a safety risk for patients and consumers. Patients should be cautioned to not use these technologies for answers to medical questions they intend to act on without further consultation from a health care provider. SN - 1438-8871 UR - //www.mybigtv.com/2018/9/e11510/ UR - https://doi.org/10.2196/11510 UR - http://www.ncbi.nlm.nih.gov/pubmed/30181110 DO - 10.2196/11510 ID - info:doi/10.2196/11510 ER -
Baidu
map