自然语言处理诊断行为障碍与重症监护病房意识模糊评估法：患病率、患者特征、重叠及与治疗和结局的关系。
Natural language processing diagnosed behavioral disturbance vs confusion assessment method for the intensive care unit: prevalence, patient characteristics, overlap, and association with treatment and outcome.
机构信息
Data Analytics Research and Evaluation (DARE) Centre, Austin Health and The University of Melbourne, Heidelberg, VIC, Australia.
Department of Critical Care, School of Medicine, The University of Melbourne, Parkville, Melbourne, VIC, Australia.
出版信息
Intensive Care Med. 2022 May;48(5):559-569. doi: 10.1007/s00134-022-06650-z. Epub 2022 Mar 23.
PURPOSE
To compare the prevalence, characteristics, drug treatment for delirium, and outcomes of patients with Natural Language Processing (NLP) diagnosed behavioral disturbance (NLP-Dx-BD) vs Confusion Assessment Method for intensive care unit (CAM-ICU) positivity.
METHODS
In three combined medical-surgical ICUs, we obtained data on demographics, treatment with antipsychotic medications, and outcomes. We applied NLP to caregiver progress notes to diagnose behavioral disturbance and analyzed simultaneous CAM-ICU.
RESULTS
We assessed 2313 patients with a median lowest Richmond Agitation-Sedation Scale (RASS) score of - 2 (- 4.0 to - 1.0) and median highest RASS score of 1 (0 to 1). Overall, 1246 (53.9%) patients were NLP-Dx-BD positive (NLP-Dx-BD) and 578 (25%) were CAM-ICU positive (CAM-ICU). Among NLP-Dx-BD patients, 539 (43.3%) were also CAM-ICU. In contrast, among CAM-ICU patients, 539 (93.3%) were also NLP-Dx-BD. The use of antipsychotic medications was highest in patients in the CAM-ICU and NLP-Dx-BD group (24.3%) followed by the CAM-ICU and NLP-Dx-BD group (10.5%). In NLP-Dx-BD patients, antipsychotic medication use was lower at 5.1% for CAM-ICU and NLP-Dx-BD patients and 2.3% for CAM-ICU and NLP-Dx-BD patients (overall P < 0.001). Regardless of CAM-ICU status, after adjustment and on time-dependent Cox modelling, NLP-Dx-BD was associated with greater antipsychotic medication use. Finally, regardless of CAM-ICU status, NLP-Dx-BD patients had longer duration of ICU and hospital stay and greater hospital mortality (all P < 0.001).
CONCLUSION
More patients were NLP-Dx-BD positive than CAM-ICU positive. NLP-Dx-BD and CAM-ICU assessment describe partly overlapping populations. However, NLP-Dx-BD identifies more patients likely to receive antipsychotic medications. In the absence of NLP-Dx-BD, treatment with antipsychotic medications is rare.
目的
比较经自然语言处理（NLP）诊断为行为障碍（NLP-Dx-BD）与使用意识模糊评估法-重症监护病房（CAM-ICU）阳性的患者的发生率、特征、谵妄药物治疗和结局。
方法
在三个综合外科重症监护病房中，我们获得了人口统计学数据、抗精神病药物治疗和结局的数据。我们将 NLP 应用于护理人员的进展记录以诊断行为障碍，并同时分析了 CAM-ICU。
结果
我们评估了 2313 名患者，其最低 Richmond 意识激惹评分（RASS）中位数为-2（-4.0 至-1.0），最高 RASS 中位数为 1（0 至 1）。总体而言，1246 名（53.9%）患者 NLP-Dx-BD 阳性（NLP-Dx-BD），578 名（25%）CAM-ICU 阳性（CAM-ICU）。在 NLP-Dx-BD 患者中，539 名（43.3%）患者同时也是 CAM-ICU 阳性。相比之下，在 CAM-ICU 患者中，539 名（93.3%）患者同时也是 NLP-Dx-BD 阳性。CAM-ICU 和 NLP-Dx-BD 组的抗精神病药物使用率最高（24.3%），其次是 CAM-ICU 和 NLP-Dx-BD 组（10.5%）。在 NLP-Dx-BD 患者中，CAM-ICU 和 NLP-Dx-BD 患者的抗精神病药物使用率较低，为 5.1%，CAM-ICU 和 NLP-Dx-BD 患者的抗精神病药物使用率为 2.3%（总体 P < 0.001）。无论 CAM-ICU 状态如何，经调整和时间依赖性 Cox 模型分析，NLP-Dx-BD 与更高的抗精神病药物使用相关。最后，无论 CAM-ICU 状态如何，NLP-Dx-BD 患者的 ICU 和住院时间更长，住院死亡率更高（均 P < 0.001）。
结论
NLP-Dx-BD 阳性患者多于 CAM-ICU 阳性患者。NLP-Dx-BD 和 CAM-ICU 评估描述了部分重叠的人群。然而，NLP-Dx-BD 可识别出更多可能接受抗精神病药物治疗的患者。在没有 NLP-Dx-BD 的情况下，抗精神病药物治疗很少见。
Zotero 插件