JMIR Publications

ABSTRACT

Background:

The COVID-19 pandemic has changed the usual work in many hospitalization units (or wards). This is a special occasion to explore the difference among COVID-19 care and usual care. Few studies use electronic nursing clinical notes (ENCN) and their unstructured text to identify alterations in patients' feelings and therapeutic procedures of interest.

Objective:

Analysis of positive/negative sentiments through inspection of the free text of the ENCN; comparison of sentiments of ENCN with/without hospitalized COVID-19 patients; temporal analysis of the sentiments of the patients during the start of the first wave of the COVID-19 pandemic; and identification of the topics in ENCN.

Methods:

This is a descriptive study with analysis of the text content of ENCN. All ENCNs between January and June 2020 at Guadarrama Hospital extracted from the CGM Selene Electronic Health Records System were included. Two groups of ENCNs were analyzed: one from hospitalized patients in post intensive care units COVID-19, and a second group from hospitalized patients with non COVID-19. A sentiment analysis was performed on the lemmatized text, using the dictionaries NRC, Affin and Bing. A polarity analysis of the sentences was performed using the Bing dictionary, the SO Dictionaries V1.11Spa dictionary as amplifiers and decrementators. Machine learning techniques were applied in order to evaluate the presence of significant differences in the ENCN in groups of COVID-19 or non COVID-19 patients. Finally, a structural analysis of thematic models was performed to study the abstract topics that occur in the ENCN, using Latent Dirichlet Allocation topic modeling.

Results:

A total of 37,564 electronic health records were analyzed. Sentiment analysis in ENCN showed that patients with subacute COVID-19 have a higher proportion of positive sentiments compared to non COVID-19. Also, there are significant differences in polarity between both groups (Z=5.532, P<.001) with a polarity in COVID-19 patients of 0.108±0.299 versus a polarity in non COVID-19 patients of 0.09±0.301. Machine learning modeling reported that despite all models presenting high values, it is the neural network that presents the best indicators, over 0.8, and with significant P values between both groups. From Structural Topic Modeling analysis, the final model containing 10 topics was selected. It is noted a high correlation between topics 2, 5 and 8 (pressure ulcer and pharmacotherapy treatment), topics 1, 4, 7 and 9 (incidences related to fever and well-being state, and baseline oxygen saturation) and topics 3, 10 (blood glucose level and pain).

Conclusions:

The ENCN may help in the development and implementation of more effective programs which allows to the COVID-19 pandemic patients a faster come back to a pre-pandemic way of life. Topic modeling could help identify specific clinical problems in patients and better target the care they receive.