EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Exploring Barriers and Facilitators of Inter-Professional Communication in Health IT-Supported Patient-Centered Care Systems

Sabrina Momota Saima, Md. Mahmud Al Hasan, Noopur D Costa, Dipika Mazumder, Refaya Mahmuda, Mariom Oyshe

American Journal of Medical Science and Innovation · 14.07.2026 · 5 (2) · 1-9

DOI: 10.54536/ajmsi.v5i2.8063 ↗

Kurz gefasst

Fachartikel in der Zeitschrift American Journal of Medical Science and Innovation, online erschienen am 14.07.2026. Verfasst von Sabrina Momota Saima und 5 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Interprofessional communication is essential for improving care coordination, patient safety, healthcare quality, and collaborative decision-making in Health IT-supported patient-centered care systems. Effective communication among healthcare professionals can reduce clinical errors and enhance patient outcomes, while communication barriers may negatively affect healthcare delivery. This study aims to explore barriers and facilitators to inter-professional communication in Health IT-supported patient-centered care systems using machine-learning and deep-learning classification models. For this research, a primary dataset was developed containing 3,000 records with 28 variables, including demographic characteristics, professional roles, Health IT utilization factors, communication practices, organizational support factors, workflow integration measures, and patient-centered care indicators. The study applied supervised machine learning and deep learning methods using a 70% training, 15% validation, and 15% testing split. Three classification models—Neural Network, BiLSTM, and CNN-BiLSTM—were used to classify Barrier Level and Facilitator Level into High, Moderate, and Low categories. Model performance was evaluated using accuracy, precision, recall, F1-score, confusion matrix, ROC curve, and precision-recall analysis. The results show that the Neural Network model achieved the highest overall performance with an average accuracy of 97.33%, focusing on Facilitator Level classification, which achieved 94.67% accuracy. CNN-BiLSTM achieved an average accuracy of 94.33%, while BiLSTM achieved 84.89% accuracy. The findings suggest that Health IT usability, interoperability, workflow integration, communication openness, role clarity, team trust, training quality, and technical support are important factors influencing interprofessional communication outcomes. The study concludes that machine learning-based classification models can effectively identify communication barriers and facilitators and support improved collaboration, communication effectiveness, and patient-centered care delivery in Health IT-supported healthcare environments.

Zitieren

APA

Saima, S. M., Hasan, M. M. A., Costa, N. D., Mazumder, D., Mahmuda, R., & Oyshe, M. (2026). Exploring Barriers and Facilitators of Inter-Professional Communication in Health IT-Supported Patient-Centered Care Systems. American Journal of Medical Science and Innovation, 5(2), 1-9. https://doi.org/10.54536/ajmsi.v5i2.8063

Vancouver

Saima SM, Hasan MMA, Costa ND, Mazumder D, Mahmuda R, Oyshe M. Exploring Barriers and Facilitators of Inter-Professional Communication in Health IT-Supported Patient-Centered Care Systems. American Journal of Medical Science and Innovation. 2026;5(2):1-9. doi:10.54536/ajmsi.v5i2.8063

BibTeX
@article{Saima2026,
  author = {Saima, Sabrina Momota and Hasan, Md. Mahmud Al and Costa, Noopur D and Mazumder, Dipika and Mahmuda, Refaya and Oyshe, Mariom},
  title = {Exploring Barriers and Facilitators of Inter-Professional Communication in Health IT-Supported Patient-Centered Care Systems},
  journal = {American Journal of Medical Science and Innovation},
  year = {2026},
  volume = {5},
  number = {2},
  pages = {1--9},
  doi = {10.54536/ajmsi.v5i2.8063}
}
Kostenlos starten →