EUVIMEDEUVIMED entdecken
Crossref

Sentiment analysis in medication adherence: using ruled-based and artificial intelligence-driven algorithms to understand patient medication experiences

Wallace Entringer Bottacin, Alexandre Luquetta, Luiz Gomes-Jr, Thais Teles de Souza, Walleri Christini Torelli Reis, Ana Carolina Melchiors

International Journal of Clinical Pharmacy · 2025-08 · 47 (4) · 970-980

DOI: 10.1007/s11096-024-01803-0 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Clinical Pharmacy, online erschienen am 04.10.2024. Verfasst von Wallace Entringer Bottacin und 5 weiteren Autor:innen. Beteiligte Einrichtung: Postgraduate Program in Pharmaceutical Services and Policies, Federal University of Paraná, Avenida Prefeito Lothário Meissner, 632 - Jardim Botânico…. Hauptthemen laut MEDLINE: Artificial Intelligence, Medication Adherence, Emotions, Algorithms. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 70 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Studies are exploring ways to improve medication adherence, with sentiment analysis (SA) being an underutilized innovation in pharmacy. This technique uses artificial intelligence (AI) and natural language processing to assess text for underlying feelings and emotions. AIM: This study aimed to evaluate the use of two SA models, Valence Aware Dictionary for Sentiment Reasoning (VADER) and Emotion English DistilRoBERTa-base (DistilRoBERTa), for the identification of patients' sentiments and emotions towards their pharmacotherapy. METHOD: A dataset containing 320,095 anonymized patients' reports of experiences with their medication was used. VADER assessed sentiment polarity on a scale from - 1 (negative) to + 1 (positive). DistilRoBERTa classified emotions into seven categories: anger, disgust, fear, joy, neutral, sadness, and surprise. Performance metrics for the models were obtained using the sklearn.metrics module of scikit-learn in Python. RESULTS: VADER demonstrated an overall accuracy of 0.70. For negative sentiments, it achieved a precision of 0.68, recall of 0.80, and an F1-score of 0.73, while for positive sentiments, it had a precision of 0.73, recall of 0.59, and an F1-score of 0.65. The AUC for the ROC curve was 0.90. DistilRoBERTa analysis showed that higher ratings for medication effectiveness, ease of use, and satisfaction corresponded with more positive emotional responses. These results were consistent with VADER's sentiment analysis, confirming the reliability of both models. CONCLUSION: VADER and DistilRoBERTa effectively analyzed patients' sentiments towards pharmacotherapy, providing valuable information. These findings encourage studies of SA in clinical pharmacy practice, paving the way for more personalized and effective patient care strategies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceMedication AdherenceEmotionsAlgorithmsHumansNatural Language ProcessingFemaleMale

Stichwörter der Autor:innen

Artificial intelligenceClinical pharmacyEmotionsMedication adherencePatient preferenceSentiment analysis

Autor:innen und Institutionen

  • Postgraduate Program in Pharmaceutical Services and Policies, Federal University of Paraná, Avenida Prefeito Lothário Meissner, 632 - Jardim Botânico, Curitiba, CEP 80210-170, PR, Brazil. wallace.bottacin@gmail.com.
  • Postgraduate Program in Applied Computing, Federal Technological University of Paraná, Curitiba, PR, Brazil.
  • Department of Pharmaceutical Sciences, Federal University of Paraíba, João Pessoa, PB, Brazil.
  • Postgraduate Program in Public Health, Federal University of Paraíba, João Pessoa, PB, Brazil.
  • Postgraduate Program in Pharmaceutical Services and Policies, Federal University of Paraná, Avenida Prefeito Lothário Meissner, 632 - Jardim Botânico, Curitiba, CEP 80210-170, PR, Brazil.

Zitieren

APA

Bottacin, W. E., Luquetta, A., Gomes-Jr, L., de Souza, T. T., Reis, W. C. T., & Melchiors, A. C. (2025). Sentiment analysis in medication adherence: using ruled-based and artificial intelligence-driven algorithms to understand patient medication experiences. International Journal of Clinical Pharmacy, 47(4), 970-980. https://doi.org/10.1007/s11096-024-01803-0

Vancouver

Bottacin WE, Luquetta A, Gomes-Jr L, de Souza TT, Reis WCT, Melchiors AC. Sentiment analysis in medication adherence: using ruled-based and artificial intelligence-driven algorithms to understand patient medication experiences. International Journal of Clinical Pharmacy. 2025;47(4):970-980. doi:10.1007/s11096-024-01803-0

BibTeX
@article{Bottacin2025,
  author = {Bottacin, Wallace Entringer and Luquetta, Alexandre and Gomes-Jr, Luiz and de Souza, Thais Teles and Reis, Walleri Christini Torelli and Melchiors, Ana Carolina},
  title = {Sentiment analysis in medication adherence: using ruled-based and artificial intelligence-driven algorithms to understand patient medication experiences},
  journal = {International Journal of Clinical Pharmacy},
  year = {2025},
  volume = {47},
  number = {4},
  pages = {970--980},
  doi = {10.1007/s11096-024-01803-0}
}
Kostenlos starten →