Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK
Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK.
BMJ Open. 2020 Apr 22;10(4):e036186. doi: 10.1136/bmjopen-2019-036186.
Clinician narrative style in electronic health records (EHR) has rarely been investigated. Clinicians sometimes record brief quotations from patients, possibly more frequently when higher risk is perceived. We investigated whether the frequency of quoted phrases in an EHR was higher in time periods closer to a suicide attempt.
A case-crossover study was conducted in a large mental health records database. A natural language processing tool was developed using regular expression matching to identify text occurring within quotation marks in the EHR.
Electronic records from a large mental healthcare provider serving a geographic catchment of 1.3 million residents in South London were linked with hospitalisation data.
1503 individuals were identified as having a hospitalised suicide attempt from 1 April 2006 to 31 March 2017 with at least one document in both the case period (1-30 days prior to admission) and the control period (61-90 days prior to admission).
The number of quoted phrases in the control as compared with the case period.
Both attended (OR 1.05, 95% CI 1.02 to 1.08) and non-attended (OR 1.15, 95% CI 1.04 to 1.26) clinical appointments were independently higher in the case compared with control period, while there was no difference in mental healthcare hospitalisation (OR 0.99, 95% CI 0.98 to 1.01). In addition, there was no difference in the levels of quoted text between the comparison time periods (OR 1.09, 95% CI 0.91 to 1.30).
This study successfully developed an algorithm to identify quoted speech in text fields from routine mental healthcare records. Contrary to the hypothesis, no association between this exposure and proximity to a suicide attempt was found; however, further evaluation is warranted on the way in which clinician-perceived risk might be feasibly characterised from clinical text.
电子健康记录（EHR）中的临床叙述风格很少被研究。当感知到更高的风险时，临床医生有时会记录患者的简短引语，可能更频繁。我们调查了 EHR 中引语短语的频率是否在更接近自杀尝试的时间段内更高。
在一个大型精神健康记录数据库中进行了病例交叉研究。使用正则表达式匹配开发了一种自然语言处理工具，以识别 EHR 中引号内的文本。
从一家为伦敦南部 130 万居民的地理区域提供服务的大型医疗保健提供商的电子记录与住院数据相关联。
2006 年 4 月 1 日至 2017 年 3 月 31 日期间，从住院自杀企图中确定了 1503 人，并且在病例期（入院前 1-30 天）和对照期（入院前 61-90 天）都至少有一份文档。
与对照期相比，病例期的引语数量。
在病例期与对照期相比，就诊（OR 1.05，95%CI 1.02 至 1.08）和非就诊（OR 1.15，95%CI 1.04 至 1.26）临床预约均独立增加，而心理健康护理住院（OR 0.99，95%CI 0.98 至 1.01）没有差异。此外，在比较时间段之间，引语文本的水平没有差异（OR 1.09，95%CI 0.91 至 1.30）。
这项研究成功地开发了一种算法，用于从常规精神保健记录中识别文本字段中的引语。与假设相反，没有发现这种暴露与自杀尝试的接近程度之间存在关联；但是，需要进一步评估如何从临床文本中描述临床医生感知到的风险。
