Immediate learning outcomes of AI-and sensor-integrated versus face-to-face CPR retraining for chest compression quality - A randomized trial

Q: What was the objective of the randomized trial?

To evaluate immediate learning outcomes of an AI-and sensor-integrated CPR retraining system (IPTS) compared with conventional face-to-face retraining in healthcare professionals.

Q: How were learning outcomes measured in the study?

Learning outcomes were measured objectively using a manikin, without providing feedback or assessment results to participants.

Q: Which CPR outcomes did IPTS improve compared with face-to-face training?

IPTS did not show superiority for chest compression depth accuracy or chest compression rate, but it produced significantly superior rescue-breath quality compared with face-to-face training.

Sep 29, 2026

Uploaded by Mafia Boss

Objective: Evaluate immediate learning outcomes of an AI-and sensor-integrated cardiopulmonary resuscitation (CPR) retraining system (IPTS) versus conventional face-to-face retraining in healthcare professionals. Methods: Randomized trial of 136 participants assigned 1:1 to a 30-minute IPTS or face-to-face session, with objective manikin-based measurement and no feedback. Primary outcomes were chest compression depth accuracy and chest compression rate; secondary outcomes included rescue-breath tidal volumes and CPR self-efficacy.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages16

Reading Time40 min

AccessFree to download

Abstract

Introduction

Immediate learning outcomes of AI-and sensor-integrated versus face-to-face CPR retraining for chest compression quality: A randomized trial DIGITAL HEALTH Volume 12: 1–16 © The Author(s) 2026 Article reuse guidelines: [sagepub.com/journals-permissions](sagepub.com/journals-permissions)[ ](sagepub.com/journals-permissions)[DOI: 10.1177/20552076251411030](DOI: 10.1177/20552076251411030)[ ](DOI: 10.1177/20552076251411030)[journals.sagepub.com/home/dhj](journals.sagepub.com/home/dhj) Jingdong Ma 1 , Wei Dai 1 , Xiaoge Yuan 1, Xingce Zhu 1 , Guo Ding2, Yang Song 1, Hong Wu 1 , Yan Zhang 1, Yuran Zhou3, Wen Chen 1 and Jinghui Nan4 Abstract Objective: To evaluate the immediate learning outcomes of an AI-and sensor-integrated cardiopulmonary resuscitation (CPR) retraining system (Intelligent Practical Training System, IPTS) with conventional face-to-face retraining in healthcare professionals. Methods: We conducted a randomized trial of 136 healthcare professionals, allocated 1:1 to a 30-minute IPTS or faceto-face groups. IPTS integrates AI and sensors to enable instructor-free learning and examiner-free assessment. Learning outcomes were measured objectively using the manikin, without providing any feedback or assessment results to participants. Primary outcomes were chest compression depth (CC) accuracy and CC rate. Secondary outcomes included tidal volumes of the two rescue breaths and CPR self-efﬁcacy. Results: No evidence supports the superiority of IPTS in CC depth accuracy (P_adj = .878) or CC rate (P_adj = .729). However, the IPTS group achieved signiﬁcantly superior rescue breath quality (ﬁrst: rank-biserial r = − .585, 95% CI [−0.737, −0.416], P_adj < .006, large; second: rank-biserial r = − .512, 95% CI [−0.687, −0.323], P_adj < .006, large), with median values falling within the American Heart Association recommended range (ﬁrst: 548.99 mL, second: 542.68 mL), whereas the face-to-face group’s values were excessively high (ﬁrst: 806.97 mL, second: 800.23 mL). Both groups showed signiﬁcant and similar improvements in CPR self-efﬁcacy, indicating comparable psychological beneﬁts. Conclusion: Under controlled conditions, IPTS did not demonstrate superiority in immediate outcomes for CC quality and CPR self-efﬁcacy compared to sensor-free face-to-face instruction, but achieved superior immediate outcomes for rescue breaths. These results demonstrate the feasibility of a novel integration of AI and sensors in medical education. Keywords Cardiopulmonary resuscitation retraining, AI- and sensor-integrated system, face-to-face retraining, digital medical education Received: 5 September 2025; accepted: 9 December 2025 Introduction The integration of artiﬁcial intelligence (AI) and sensor data enables potential solutions in complex environments.1 Multisensor systems generate large volumes of heterogeneous data,2 while transformer architectures have fundamentally reshaped cross-modal tasks in language and vision.3 The interdisciplinary AI–sensor approach has been widely applied in ﬁelds such as autonomous driving,4 the Internet of Things,5 and infrastructure monitoring,6 delivering improvements in closed-loop feedback, precise prediction, and performance assessment. In healthcare, sensors 1 School of Medicine and Health Management, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China 2Health Human Resources Exchange and Development Center of Hubei Province, Wuhan, China 3Emergency Department, Union Hospital, Tongji Medical College, Huazhong University of Science and Technolog, Wuhan, China 4Graduate Management Ofﬁce, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China Corresponding author: Jinghui Nan, Graduate Management Ofﬁce, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, No. 1277 Jiefang Avenue, Wuhan, 430022, China. Email: [4946312@qq.com](4946312@qq.com) Creative Commons No

FAQs

What was the objective of the randomized trial?

To evaluate immediate learning outcomes of an AI-and sensor-integrated CPR retraining system (IPTS) compared with conventional face-to-face retraining in healthcare professionals.

How were learning outcomes measured in the study?

Learning outcomes were measured objectively using a manikin, without providing feedback or assessment results to participants.

Which CPR outcomes did IPTS improve compared with face-to-face training?

IPTS did not show superiority for chest compression depth accuracy or chest compression rate, but it produced significantly superior rescue-breath quality compared with face-to-face training.

Sep 29, 2026

Uploaded by Mafia Boss