Sentiment Analysis Based on the Nursing Notes on In-Hospital 28-Day Mortality of Sepsis Patients Utilizing the MIMIC-III Database
Qiaoyan Gao, Dandan Wang, Pingping Sun, Xiaorong Luan, Wenfeng Wang
Abstract
In medical visualization, nursing notes contain rich information about a patient’s pathological condition. However, they are not widely used in the prediction of clinical outcomes. With advances in the processing of natural language, information begins to be extracted from large-scale unstructured data like nursing notes. This study extracted sentiment information in nursing notes and explored its association with in-hospital 28-day mortality in sepsis patients. The data of patients and nursing notes were extracted from the MIMIC-III database. A COX proportional hazard model was used to analyze the relationship between sentiment scores in nursing notes and in-hospital 28-day mortality. Based on the COX model, the individual prognostic index (PI) was calculated, and then, survival was analyzed. Among eligible 1851 sepsis patients, 580 cases suffered from in-hospital 28-day mortality (dead group), while 1271 survived (survived group). Significant differences were shown between two groups in sentiment polarity, Simplified Acute Physiology Score II (SAPS-II) score, age, and intensive care unit (ICU) type (all <a:math xmlns:a="http://www.w3.org/1998/Math/MathML" id="M1"> <a:mi>P</a:mi> <a:mo><</a:mo> <a:mn>0.001</a:mn> </a:math> ). Multivariate COX analysis exhibited that sentiment polarity (HR: 0.499, 95% CI: 0.409-0.610, <c:math xmlns:c="http://www.w3.org/1998/Math/MathML" id="M2"> <c:mi>P</c:mi> <c:mo><</c:mo> <c:mn>0.001</c:mn> </c:math> ) and sentiment subjectivity (HR: 0.710, 95% CI: 0.559-0.902, <e:math xmlns:e="http://www.w3.org/1998/Math/MathML" id="M3"> <e:mi>P</e:mi> <e:mo>=</e:mo> <e:mn>0.005</e:mn> </e:math> ) were inversely associated with in-hospital 28-day mortality, while the SAPS-II score (HR: 1.034, 95% CI: 1.029-1.040, <g:math xmlns:g="http://www.w3.org/1998/Math/MathML" id="M4"> <g:mi>P</g:mi> <g:mo><</g:mo> <g:mn>0.001</g:mn> </g:math> ) was positively correlated with in-hospital 28-day mortality. The median death time of patients with <i:math xmlns:i="http://www.w3.org/1998/Math/MathML" id="M5"> <i:mtext>PI</i:mtext> <i:mo>≥</i:mo> <i:mn>0.561</i:mn> </i:math> was significantly earlier than that of patients with <k:math xmlns:k="http://www.w3.org/1998/Math/MathML" id="M6"> <k:mtext>PI</k:mtext> <k:mo><</k:mo> <k:mn>0.561</k:mn> </k:math> (13.5 vs. 49.8 days, <m:math xmlns:m="http://www.w3.org/1998/Math/MathML" id="M7"> <m:mi>P</m:mi> <m:mo><</m:mo> <m:mn>0.001</m:mn> </m:math> ). In conclusion, sentiments in nursing notes are associated with the in-hospital 28-day mortality and survival of sepsis patients.