Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: JMIR Medical Informatics

Date Submitted: Aug 6, 2024
Date Accepted: Mar 24, 2025

The final, peer-reviewed published version of this preprint can be found here:

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

Jo HS, Lee H, Kim YJ, Hwang YS, Park Y

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

JMIR Med Inform 2025;13:e65127

DOI: 10.2196/65127

PMID: 40446313

PMCID: 12143735

Experience of Cardiovascular and Cerebrovascular Disease Surgery Patients: A Sentiment Analysis using the KoBERT Model

  • Heui Sug Jo; 
  • Hocheol Lee; 
  • Ye Jun Kim; 
  • Yu Seong Hwang; 
  • Yukyung Park

ABSTRACT

Background:

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. In Korea, high rates of these diseases necessitate focused transitional care during patient discharge periods.

Objective:

This study analyzed the emotional experiences of patients discharged after cardiovascular and cerebrovascular surgeries using data from Naver, a major South Korean web portal.

Methods:

Posts were collected using specific keywords and processed with the KoBERT model based on Transformer, which classified sentiments into positive, neutral, and negative categories. The model's performance was validated using precision, recall, F1 score, and support metrics. Sentiment analysis was conducted within the Transitional Care Model (TCM) framework, divided into five domains: health status, care resources, care demand, interaction, and mental state.

Results:

The KoBERT model showed high performance with precision, recall, and F1 scores over 0.8. Cerebrovascular surgery patients exhibited higher negative emotions, particularly in health status, compared to cardiovascular surgery patients who had higher negative sentiments in care demands. Keywords within the TCM framework highlighted that cerebrovascular patients emphasized rehabilitation and caregiver support, while cardiovascular patients focused on cost-related concerns.

Conclusions:

The study suggests the need for tailored transitional care for cardiovascular and cerebrovascular diseases. Cerebrovascular patients require robust rehabilitation and caregiver support, while cardiovascular patients need better cost management. These insights can guide policy recommendations to improve patient-centered transitional care, ensuring continuous and effective postoperative management.


 Citation

Please cite as:

Jo HS, Lee H, Kim YJ, Hwang YS, Park Y

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

JMIR Med Inform 2025;13:e65127

DOI: 10.2196/65127

PMID: 40446313

PMCID: 12143735

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.