Department of Statistics and Actuarial Science, University of Waterloo, Waterloo, Ontario, Canada.
Health Data Science Lab, School of Public Health and Health Systems, University of Waterloo, Waterloo, Ontario, Canada.
PLoS One. 2018 Jun 7;13(6):e0198687. doi: 10.1371/journal.pone.0198687. eCollection 2018.
Nursing notes have not been widely used in prediction models for clinical outcomes, despite containing rich information. Advances in natural language processing have made it possible to extract information from large scale unstructured data like nursing notes. This study extracted the sentiment-impressions and attitudes-of nurses, and examined how sentiment relates to 30-day mortality and survival.
This study applied a sentiment analysis algorithm to nursing notes extracted from MIMIC-III, a public intensive care unit (ICU) database. A multiple logistic regression model was fitted to the data to correlate measured sentiment with 30-day mortality while controlling for gender, type of ICU, and SAPS-II score. The association between measured sentiment and 30-day mortality was further examined in assessing the predictive performance of sentiment score as a feature in a classifier, and in a survival analysis for different levels of measured sentiment.
Nursing notes from 27,477 ICU patients, with an overall 30-day mortality of 11.02%, were extracted. In the presence of known predictors of 30-day mortality, mean sentiment polarity was a highly significant predictor in a multiple logistic regression model (Adjusted OR = 0.4626, p < 0.001, 95% CI: [0.4244, 0.5041]) and led to improved predictive accuracy (AUROC = 0.8189 versus 0.8092, 95% BCI of difference: [0.0070, 0.0126]). The Kaplan Meier survival curves showed that mean sentiment polarity quartiles are positively correlated with patient survival (log-rank test: p < 0.001).
This study showed that quantitative measures of unstructured clinical notes, such as sentiment of clinicians, correlate with 30-day mortality and survival, thus can also serve as a predictor of patient outcomes in the ICU. Therefore, further research is warranted to study and make use of the wealth of data that clinical notes have to offer.
尽管护理记录中包含丰富的信息，但它们在临床结局预测模型中并未得到广泛应用。自然语言处理技术的进步使得从大规模非结构化数据（如护理记录）中提取信息成为可能。本研究提取了护士的情感印象和态度，并探讨了情感与 30 天死亡率和生存率的关系。
本研究应用情感分析算法从 MIMIC-III（一个公共重症监护病房（ICU）数据库）中提取护理记录。使用多元逻辑回归模型将数据与 30 天死亡率进行拟合，同时控制性别、ICU 类型和 SAPS-II 评分。在评估情感评分作为分类器特征的预测性能以及不同测量情感水平的生存分析中，进一步研究了测量情感与 30 天死亡率之间的关联。
从 27477 名 ICU 患者的护理记录中提取数据，总体 30 天死亡率为 11.02%。在已知的 30 天死亡率预测因素存在的情况下，平均情感极性在多元逻辑回归模型中是一个非常显著的预测因素（调整后的 OR = 0.4626，p < 0.001，95%置信区间：[0.4244，0.5041]），并提高了预测准确性（AUROC = 0.8189 与 0.8092，95%置信区间差异：[0.0070，0.0126]）。Kaplan-Meier 生存曲线显示，平均情感极性四分位数与患者生存率呈正相关（对数秩检验：p < 0.001）。
本研究表明，对临床记录中量化的非结构化数据，如临床医生的情感进行测量，与 30 天死亡率和生存率相关，因此也可以作为 ICU 患者结局的预测指标。因此，有必要进一步研究和利用临床记录中提供的大量数据。
