Section of Women's Mental Health, Health Service and Population Research Department, Institute of Psychiatry, Psychology and Neuroscience, Kings College London, London, United Kingdom.
South London and Maudsley NHS Foundation Trust, Bethlem Royal Hospital, Kent, London, United Kingdom.
PLoS One. 2021 Aug 4;16(8):e0253809. doi: 10.1371/journal.pone.0253809. eCollection 2021.
Self-harm occurring within pregnancy and the postnatal year ("perinatal self-harm") is a clinically important yet under-researched topic. Current research likely under-estimates prevalence due to methodological limitations. Electronic healthcare records (EHRs) provide a source of clinically rich data on perinatal self-harm.
(1) To create a Natural Language Processing (NLP) tool that can, with acceptable precision and recall, identify mentions of acts of perinatal self-harm within EHRs. (2) To use this tool to identify service-users who have self-harmed perinatally, based on their EHRs.
We used the Clinical Record Interactive Search system to extract de-identified EHRs of secondary mental healthcare service-users at South London and Maudsley NHS Foundation Trust. We developed a tool that applied several layers of linguistic processing based on the spaCy NLP library for Python. We evaluated mention-level performance in the following domains: span, status, temporality and polarity. Evaluation was done against a manually coded reference standard. Mention-level performance was reported as precision, recall, F-score and Cohen's kappa for each domain. Performance was also assessed at 'service-user' level and explored whether a heuristic rule improved this. We report per-class statistics for service-user performance, as well as likelihood ratios and post-test probabilities.
Mention-level performance: micro-averaged F-score, precision and recall for span, polarity and temporality >0.8. Kappa for status 0.68, temporality 0.62, polarity 0.91. Service-user level performance with heuristic: F-score, precision, recall of minority class 0.69, macro-averaged F-score 0.81, positive LR 9.4 (4.8-19), post-test probability 69.0% (53-82%). Considering the task difficulty, the tool performs well, although temporality was the attribute with the lowest level of annotator agreement.
It is feasible to develop an NLP tool that identifies, with acceptable validity, mentions of perinatal self-harm within EHRs, although with limitations regarding temporality. Using a heuristic rule, it can also function at a service-user-level.
妊娠和产后年内发生的自伤行为（“围产期自伤”）是一个具有重要临床意义但研究不足的课题。由于方法学的限制，当前的研究可能低估了其发生率。电子医疗记录（EHR）提供了围产期自伤的丰富临床数据来源。
（1）创建一种自然语言处理（NLP）工具，该工具可以在可接受的精度和召回率的情况下，识别 EHR 中围产期自伤行为的提及。（2）基于 EHR，使用该工具来识别围产期自伤的服务使用者。
我们使用 Clinical Record Interactive Search 系统提取了伦敦南部和莫兹利国民保健信托基金会二级精神保健服务使用者的去识别 EHR。我们开发了一种工具，该工具应用了基于 Python 的 spaCy NLP 库的多层语言处理。我们在以下领域评估了提及级别的性能：范围、状态、时间性和极性。评估是针对手动编码的参考标准进行的。在每个领域，提及级别性能均以精度、召回率、F 分数和 Cohen 的 Kappa 进行报告。还评估了“服务使用者”级别上的性能，并探讨了启发式规则是否可以改善这一点。我们报告了服务使用者性能的每类统计信息，以及似然比和后测概率。
提及级别性能：范围、极性和时间性的微平均 F 分数、精度和召回率>0.8。状态的 Kappa 值为 0.68，时间性为 0.62，极性为 0.91。使用启发式规则的服务使用者级别性能：少数类别的 F 分数、精度和召回率为 0.69，宏平均 F 分数为 0.81，阳性似然比为 9.4（4.8-19），后测概率为 69.0%（53-82%）。考虑到任务的难度，该工具的性能良好，尽管时间性是注释者之间一致性最低的属性。
可以开发一种 NLP 工具，该工具可以以可接受的有效性识别 EHR 中围产期自伤的提及，尽管在时间性方面存在局限性。使用启发式规则，它也可以在服务使用者级别上运行。
