# Experience of Cardiovascular and Cerebrovascular Disease Surgery Patients: Sentiment Analysis Using the Korean Bidirectional Encoder Representations from Transformers (KoBERT) Model

## TL;DR

This study uses the KoBERT model to analyze the emotional experiences of patients after cardiovascular and cerebrovascular surgeries in South Korea, revealing distinct emotional and practical challenges that can inform better post-discharge care.

## Contribution

The study introduces the use of the KoBERT model for sentiment analysis in postoperative patient experiences, revealing domain-specific emotional patterns in transitional care.

## Key findings

- Cerebrovascular surgery patients showed higher negative emotions related to health status compared to cardiovascular surgery patients.
- Cardiovascular surgery patients expressed more negative sentiments regarding care demands.
- The KoBERT model achieved high performance with 96% precision, 94% recall, and 94% F1-score in sentiment classification.

## Abstract

Cardiovascular and cerebrovascular diseases significantly contribute to global mortality and disability. The shift to outpatient postoperative care, accelerated by the COVID-19 pandemic, emphasizes the need for effective management of postoperative outcomes. The high rates of cardiovascular and cerebrovascular diseases in Korea necessitate focused transitional care during patient discharge periods. However, limited research exists on the postoperative experiences of discharged patients, underscoring the necessity of establishing evidence-based services to optimize transitional care.

The objective of this paper was to analyze the emotional experiences of patients who underwent cardiovascular and cerebrovascular surgeries using data from Naver, a major South Korean web portal.

Posts were collected using specific keywords and processed with the Korean Bidirectional Encoder Representations from Transformers (KoBERT) model based on Transformer, which classified sentiments into positive, neutral, and negative categories. Model performance was validated according to precision, recall, F1-score, and support. Sentiment analysis was conducted within the Transitional Care Model (TCM) framework, divided into 5 domains: health status, care resources, care demand, interaction, and mental state.

The KoBERT model demonstrated high classification performance, achieving a precision of 96%, recall of 94%, and an F1-score of 94%. Sentiment analysis revealed that compared with cardiovascular surgery patients, cerebrovascular surgery patients experienced higher negative emotions regarding health status, whereas cardiovascular surgery patients expressed more negative sentiments in care demands.

Different patient groups experience distinct emotional and practical challenges postdischarge. Particularly, keywords within the TCM framework highlight that cerebrovascular surgery patients require robust rehabilitation and caregiver support, whereas cardiovascular surgery patients need better cost management. These findings underscore the importance of personalized transitional care strategies tailored for cardiovascular and cerebrovascular diseases. The insights derived from this study can guide health care policymakers in designing more targeted and patient-centered interventions to improve postdischarge care and patient-centered transitional care, ensuring continuous and effective postoperative management.