Multi-Sensor Feature Integration for Assessment of Endotracheal Intubation
- PDF / 1,236,554 Bytes
- 7 Pages / 595.276 x 790.866 pts Page_size
- 27 Downloads / 186 Views
ORIGINAL ARTICLE
Multi‑Sensor Feature Integration for Assessment of Endotracheal Intubation Chiho Lim1 · Hoo Sang Ko1 · Sohyung Cho1 · Ikechukwu Ohu2 · Henry E. Wang3 · Russell Griffin4 · Benjamin Kerrey5 · Jestin N. Carlson6,7 Received: 20 December 2019 / Accepted: 10 June 2020 © Taiwanese Society of Biomedical Engineering 2020
Abstract Purpose Traditionally, proficiency in endotracheal intubation (ETI) has been assessed by human supervisors in a subjective manner during training sessions; however, recent advances in sensor and computing technology have made it possible to obtain objective measures to evaluate the practitioner’s performance. This study presents an automated and objective ETI assessment system based on multi-sensor integration which aims at discriminating experienced from novice providers accurately. Methods To this end, four different types of sensors were used to collect data, including hand motion of the provider, and tongue force, incisor force and head angle of the training mannequin. Features were extracted from the datasets, and relevant ones were identified by applying feature selection algorithms to create individual and integrated feature sets. An artificial neural network-based classification model was developed for each feature set. Results The results show that a classifier based on a small number of integrated features achieves the best accuracy (96.4%), significantly higher than the best obtained by any individual feature sets (91.17% by hand motion). Conclusion This study demonstrated the feasibility of a multi-sensor based ETI assessment system that can provide practitioners with objective and timely feedback about their performance. Keywords Assessment system · Classification model · Endotracheal intubation · Multi-sensor integration · Surgical skill
1 Introduction
* Hoo Sang Ko [email protected] 1
Department of Industrial Engineering, Southern Illinois University, Edwardsville, IL 62026, USA
2
Industrial Engineering, Gannon University, Erie, PA 16541, USA
3
Department of Emergency Medicine, University of Texas Health Science Center at Houston, Houston, TX 77030, USA
4
RQI Partners, LLC., Gatesville, TX 76528, USA
5
Division of Emergency Medicine, Cincinnati Children’s Hospital, Cincinnati, OH 45229, USA
6
Department of Emergency Medicine, Saint Vincent Health System, Erie, PA 16544, USA
7
Patient Simulation Center, Gannon University, Erie, PA 16541, USA
Motion analysis is an important tool for evaluating human movement by revealing hidden patterns in motion characteristics. This powerful technique has been employed to analyze dexterity and skill in various areas such as sport training [1] and industrial work measurement [2]. Motion analysis has been also applied to surgical skill assessment. For example, laparoscopic skills were evaluated by accelerometer-based motion analysis [3], and an automated surgical skill assessment system for suturing and knot-tying tasks was developed by using video and accelerometer data [4]. In spite of its great potential
Data Loading...
