System Maintenance Notice

Please note that maintenance work is scheduled between 4 AM and 5 AM - CET. During this time, you may experience reduced performance. Thanks for your patience.

Publications

Journal Article Epublish

PubMed: 42871328 DOI: 10.3389/fdgth.2026.1864704

Real-world deployment and longitudinal evaluation of a human-in-the-loop telemedicine communication support system.

Front Digit Health 8:1864704

Authors: Roland Roller, Ajay Madhavan Ravichandran, Tillmann-Leonhard Breitenstein, Marcel Naik, Bianca Zukunft, Bilgin Osmanodja, Matthias Pfefferkorn, Tim Gielsdorf, Judith Schleder, Sinem Karaterzi, Kristina Boss, Philipp Winnekens, Mario A Cypko, Aditya Kumar, Ulrich Kunze, Lisa Raithel, Oliver Witzke, Oliver Amft, Lars Pape, Sebastian Möller, Mario Schiffer, Klemens Budde, Wiebke Duettmann

Affiliations

  • Speech and Language Technology Lab, German Research Center for Artificial Intelligence (DFKI), Berlin, Germany.
  • Department of Nephrology and Medical Intensive Care, Charité - Universitätsmedizin Berlin, Berlin, Germany.
  • Department of Infectious Diseases and Nephrology, University Hospital Essen, Essen, Germany.
  • Hahn-Schickard-Gesellschaft für angewandte Forschung e.V. Freiburg, Germany.
  • Intelligent Embedded Systems Lab, University of Freiburg, Freiburg, Germany.
  • Department of Medicine 4 - Nephrology and Hypertension, University Hospital Erlangen, Erlangen, Germany.
  • Quality & Usability Lab, Technische Universität Berlin, Berlin, Germany.
  • BIFOLD - Berlin Institute for the Foundations of Learning and Data, Berlin, Germany.
  • Institute for Artificial Intelligence in Medicine, Charité - Universitätsmedizin Berlin, Berlin, Germany.
  • Vivantes, Auguste Viktoria Krankenhaus, Berlin, Germany.
  • Berlin Institute of Health, Charité - Universitätsmedizin Berlin, Berlin, Germany.

Abstract

BACKGROUND

Telemedicine platforms are increasingly used to support the long-term monitoring of chronically ill patients. However, continuous streams of patient-reported data and messages may impose substantial workload on telemedicine teams. To address this challenge, we developed a human-in-the-loop communication support system for telemedicine monitoring of kidney transplant recipients.

METHODS

The system was integrated into the telemedicine program of the nephrology department at Charité - Universitätsmedizin Berlin. It analyzes telemedicine data in combination with locally stored electronic health record (EHR) data and generates suggested responses and reminders for clinical staff. All suggestions are reviewed by telemedicine personnel and can be accepted, modified, or discarded before being sent to patients. System usage was evaluated based on routine operation data collected since deployment.

RESULTS

The system has been in productive use since May 15, 2024. During the observation period, more than 22,000 message suggestions were generated, of which over 16,000 were sent without modification. Overall, approximately 76% of all generated suggestions resulted in patient communication. Usage increased steadily over time, indicating successful integration into routine telemedicine workflows. Standardized reminders and routine communication tasks showed particularly high utilization.

CONCLUSIONS

Our findings demonstrate the potential of automated communication support systems to assist routine telemedicine workflows while maintaining human oversight of patient communication. At the same time, practical challenges related to system integration, data timeliness, and context awareness remain important considerations for successful deployment in clinical environments.

MeSH

Suggestion, Communication, Workflow, Telemedicine, Nephrology