Patient perspectives on acceptability of, and implementation preferences for, use of electronic health records and machine learning to identify suicide risk.

Patient perspectives on acceptability of, and implementation preferences for, use of electronic health records and machine learning to identify suicide risk.
复制标题

DOI:
10.1016/j.genhosppsych.2021.02.008
复制
发表时间:
2021-05
影响因子:
7
通讯作者:
Stumbo SP
Stumbo SP
中科院分区:
医学2区
文献类型:
--
作者:
Yarborough BJH;Stumbo SP

文献摘要

参考文献

被引文献

相似文献

使用电子健康记录数据和机器学习评估患者对自动自杀风险识别的理解、潜在担忧和实施偏好。焦点小组(n = 23 名参与者)于 2020 年 4 月向 11,486 名 Kaiser Permanente Northwest 成员发送了一项基于网络的调查。调查项目使用李克特和视觉模拟量表(平均得分为 - 50 至 50)评估患者偏好。描述性统计总结了调查结果。 1357 名(12%)参与者做出了回应。大多数人 (84%) 认为机器学习衍生的自杀风险识别是电子健康记录数据的可接受用途;然而,67% 的人反对使用外部来源的数据。参与者认为应该需要同意(或选择退出)(平均值 = − 14)。大多数人 (69%) 支持由值得信赖的临床医生通过护理信息 (57%) 或电话 (47-54%) 向高危人群提供服务。认可度最高的是精神科医生/治疗师(99%)或初级保健临床医生(75-96%);不到一半 (42%) 的人支持任何临床医生的外展活动,并且参与者普遍认为只有值得信赖的临床医生才应该获得风险信息(平均值 = − 16)。患者普遍支持使用 EHR 数据(而非外部来源的风险信息)来为自动自杀风险识别模型提供信息,但更愿意同意或选择退出;值得信赖的临床医生应通过电话或护理信息向高危人群进行宣传。
Assess patient understanding of, potential concerns with, and implementation preferences related to automated suicide risk identification using electronic health record data and machine learning. Focus groups (n = 23 participants) informed a web-based survey sent to 11,486 Kaiser Permanente Northwest members in April 2020. Survey items assessed patient preferences using Likert and visual analog scales (means scored from − 50 to 50). Descriptive statistics summarized findings. 1357 (12%) participants responded. Most (84%) found machine learning-derived suicide risk identification an acceptable use of electronic health record data; however, 67% objected to use of externally sourced data. Participants felt consent (or opt-out) should be required (mean = − 14). The majority (69%) supported outreach to at-risk individuals by a trusted clinician through care messages (57%) or telephone calls (47–54%). Highest endorsements were for psychiatrists/therapists (99%) or a primary care clinician (75–96%); less than half (42%) supported outreach by any clinician and participants generally felt only trusted clinicians should have access to risk information (mean = − 16). Patients generally support use of EHR data (not externally sourced risk information) to inform automated suicide risk identification models but prefer to consent or opt-out; trusted clinicians should outreach by telephone or care message to at risk individuals.
DOI: 10.1176/appi.ps.201800242
发表时间: 2019-01-01
影响因子: 3.8
作者:
Reger, Greg M.;McClure, Mary Lou;Reger, Mark A.
通讯作者: Reger, Mark A.
DOI: 10.1176/appi.ajp.2017.17080844
发表时间: 2018-05-01
影响因子: 17.7
作者:
Simon, Gregory E.;Stewart, Christine;Carrell, David S.
通讯作者: Carrell, David S.
DOI: 10.1037/bul0000084
发表时间: 2017-02-01
影响因子: 22.4
作者:
Franklin, Joseph C.;Ribeiro, Jessica D.;Nock, Matthew K.
通讯作者: Nock, Matthew K.
DOI: 10.1001/jamanetworkopen.2020.1262
发表时间: 2020-03-25
期刊: JAMA NETWORK OPEN
影响因子: 13.8
作者:
Barak-Corren, Yuval;Castro, Victor M.;Smoller, Jordan W.
通讯作者: Smoller, Jordan W.
DOI: 10.1176/appi.ajp.2016.16010077
发表时间: 2017-02-01
影响因子: 17.7
作者:
Barak-Corren, Yuval;Castro, Victor M.;Reis, Ben Y.
通讯作者: Reis, Ben Y.