Evaluation of visual patient predictive for enhancing level 3 situation awareness - protocol for a multicentre randomised computer-based simulation and diagnostic accuracy study

Sep 29, 2026

Uploaded by Mimi

Visual Patient Predictive (VPP) extends the Visual Patient Avatar (VPA) by using deep learning to forecast upcoming vital-sign deviations and render them as dashed visual elements, aiming to project future patient states and strengthen level 3 situation awareness. This multicentre simulation protocol evaluates whether predictive algorithms and integrated visualisations improve clinicians’ ability to anticipate critical changes versus conventional number- and waveform-based monitoring. Outcomes include decision-making, confidence, workload, usability, and effects on interventions through diagnostic accuracy metrics and qualitative analysis.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages9

Reading Time23 min

AccessFree to download

Abstract

Introduction

Methods and analysis

Strengths and limitations of this study

Ethics and dissemination

Open access Protocol Evaluation of visual patient predictive for enhancing level 3 situation awareness: protocol for a multicentre randomised computer-based simulation and diagnostic accuracy study (true positive rate, precision, average lead time) Cynthia Alexandra Hunn,1 Hannes Bruns,1 Sebastian Sahli,2 Luca Wachtendorf,2 Johannes Schäfer,3 Stefan Schwerin,4 Achilles Delis,5 Markus Kalisch,6 Gaspar Dugac,6 Arend Rahrisch,1 Max Ebensperger,4 Arian Karimitar,2 Gregor Massoth,5 Christopher Neuhaus,3 Alina Dubatovka,7 Christoph B Nöthiger,1 G. Gasciauskaite,1 Tadzio Raoul Roche,1 David W Tscholl 1 To cite: Hunn CA, Bruns H, Sahli S, et al. Evaluation of visual patient predictive for enhancing level 3 situation awareness: protocol for amulticentre randomised computer-based simulation and diagnostic accuracy study (true positive rate, precision, average lead time) . BMJ Open 2025;15:e109171 . doi:10 . 1136/ bmjopen-2025-109171 ► Prepublication history and additional supplemental material for this paper are available online. To view these files, please visit the journal online ([https://doi.org/10.1136/](https://doi.org/10.1136/)[ ](https://doi.org/10.1136/)[bmjopen-2025-109171](bmjopen-2025-109171)) . Received 10 August 2025 Accepted 13 December 2025 © Author(s) (or their employer(s)) 2025. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ Group. For numbered affiliations see end of article. Correspondence to Dr David W Tscholl; david.tscholl@usz.ch ABSTRACT Introduction Visual Patient Predictive (VPP) is an AI-based extension of the Visual Patient Avatar (VPA) that integrates deep learning models to predict upcoming vital sign deviations and display them as dashed visual elements. By explicitly showing anticipated changes, the system aims to support level 3 situation awareness—the projection of future patient states. This multicentre simulation study will evaluate whether predictive algorithms and visualisations integrated into the VPA (resulting in VPP) improve clinicians’ ability to anticipate critical vital sign changes compared with conventional number-based and waveform-based monitoring and examine its effects on decision-making, confidence, workload and user acceptance. Methods and analysis This investigator-initiated, randomised, within-subjects crossover, computer-based simulation trial will be conducted at five academic centresin Switzerland, Germany and the United States. Medical professionals from anaesthesiology departments will complete scenario-based prediction tasks using both VPP (as the index test) and conventional monitoring (as the reference standard) in randomised order, with the same participant evaluating both modalities and the identical underlying clinical scenario used in each condition, following video-based training and a learnability test. The primary outcome is recall (true positive rate) of vital sign deviation predictions. Secondary outcomes include average lead time, precision, prediction confidence, number and correctness of proposed interventions, perceived workload (NASA-TLX) and qualitative usability feedback. Quantitative data will be analysed using a logistic generalised linear mixed model with random intercepts for centre and participant, and a random slope for the intervention effect. Qualitative interviews will undergo thematic analysis. STRENGTHS AND LIMITATIONS OF THIS STUDY ⇒ Multicentre, randomised, computer-based simulation trial to evaluate a complete AI-supported predictive visualisation system for patient monitoring. ⇒ Within-subjects design controls for inter-individual variability and allows direct comparison between VPP and conventional monitoring. ⇒ Standardised video-based training and a preceding learnability test ensure consistent baseline knowledge across participants. ⇒ Combination of quantitative and qualitative methods provides a comprehensive evaluation of usability, decision-

FAQs

What is Visual Patient Predictive (VPP) and what problem does it address?

VPP is an AI extension of the Visual Patient Avatar that predicts upcoming vital sign deviations and displays them visually as dashed elements. It is designed to support level 3 situation awareness by projecting future patient states.

How will the study compare VPP with conventional monitoring?

The multicentre, randomised within-subjects crossover simulation will test clinicians using VPP as the index test and conventional monitoring as the reference standard. The same participant will evaluate both modalities using the same underlying scenarios in randomised order.

What outcomes will be measured in this protocol?

Primary outcome is recall (true positive rate) for vital sign deviation predictions. Secondary outcomes include average lead time, precision, prediction confidence, proposed interventions and their correctness, perceived workload (NASA-TLX), and qualitative usability feedback.

Sep 29, 2026

Uploaded by Mimi