Feasibility of an AI-Based Measure of the Hand Motions of Expert and Novice Surgeons

Munenori Uemura, Morimasa Tomikawa, Tiejun Miao, Ryota Souzaki, Satoshi Ieiri, Tomohiko Akahoshi, Alan K. Lefor, Makoto Hashizume

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

This study investigated whether parameters derived from hand motions of expert and novice surgeons accurately and objectively reflect laparoscopic surgical skill levels using an artificial intelligence system consisting of a three-layer chaos neural network. Sixty-seven surgeons (23 experts and 44 novices) performed a laparoscopic skill assessment task while their hand motions were recorded using a magnetic tracking sensor. Eight parameters evaluated as measures of skill in a previous study were used as inputs to the neural network. Optimization of the neural network was achieved after seven trials with a training dataset of 38 surgeons, with a correct judgment ratio of 0.99. The neural network that prospectively worked with the remaining 29 surgeons had a correct judgment rate of 79% for distinguishing between expert and novice surgeons. In conclusion, our artificial intelligence system distinguished between expert and novice surgeons among surgeons with unknown skill levels.

Original languageEnglish
Article number9873273
JournalComputational and Mathematical Methods in Medicine
Volume2018
DOIs
Publication statusPublished - Jan 1 2018

Fingerprint

Hand
Neural Networks
Neural networks
Motion
Artificial intelligence
Artificial Intelligence
Chaos theory
Chaos
Unknown
Sensor
Skills
Surgeons
Optimization
Sensors
Judgment

All Science Journal Classification (ASJC) codes

  • Modelling and Simulation
  • Biochemistry, Genetics and Molecular Biology(all)
  • Immunology and Microbiology(all)
  • Applied Mathematics

Cite this

Feasibility of an AI-Based Measure of the Hand Motions of Expert and Novice Surgeons. / Uemura, Munenori; Tomikawa, Morimasa; Miao, Tiejun; Souzaki, Ryota; Ieiri, Satoshi; Akahoshi, Tomohiko; Lefor, Alan K.; Hashizume, Makoto.

In: Computational and Mathematical Methods in Medicine, Vol. 2018, 9873273, 01.01.2018.

Research output: Contribution to journalArticle

Uemura, Munenori ; Tomikawa, Morimasa ; Miao, Tiejun ; Souzaki, Ryota ; Ieiri, Satoshi ; Akahoshi, Tomohiko ; Lefor, Alan K. ; Hashizume, Makoto. / Feasibility of an AI-Based Measure of the Hand Motions of Expert and Novice Surgeons. In: Computational and Mathematical Methods in Medicine. 2018 ; Vol. 2018.
@article{4f38381096b74372bdd2315dd1c792e4,
title = "Feasibility of an AI-Based Measure of the Hand Motions of Expert and Novice Surgeons",
abstract = "This study investigated whether parameters derived from hand motions of expert and novice surgeons accurately and objectively reflect laparoscopic surgical skill levels using an artificial intelligence system consisting of a three-layer chaos neural network. Sixty-seven surgeons (23 experts and 44 novices) performed a laparoscopic skill assessment task while their hand motions were recorded using a magnetic tracking sensor. Eight parameters evaluated as measures of skill in a previous study were used as inputs to the neural network. Optimization of the neural network was achieved after seven trials with a training dataset of 38 surgeons, with a correct judgment ratio of 0.99. The neural network that prospectively worked with the remaining 29 surgeons had a correct judgment rate of 79{\%} for distinguishing between expert and novice surgeons. In conclusion, our artificial intelligence system distinguished between expert and novice surgeons among surgeons with unknown skill levels.",
author = "Munenori Uemura and Morimasa Tomikawa and Tiejun Miao and Ryota Souzaki and Satoshi Ieiri and Tomohiko Akahoshi and Lefor, {Alan K.} and Makoto Hashizume",
year = "2018",
month = "1",
day = "1",
doi = "10.1155/2018/9873273",
language = "English",
volume = "2018",
journal = "Computational and Mathematical Methods in Medicine",
issn = "1748-670X",
publisher = "Hindawi Publishing Corporation",

}

TY - JOUR

T1 - Feasibility of an AI-Based Measure of the Hand Motions of Expert and Novice Surgeons

AU - Uemura, Munenori

AU - Tomikawa, Morimasa

AU - Miao, Tiejun

AU - Souzaki, Ryota

AU - Ieiri, Satoshi

AU - Akahoshi, Tomohiko

AU - Lefor, Alan K.

AU - Hashizume, Makoto

PY - 2018/1/1

Y1 - 2018/1/1

N2 - This study investigated whether parameters derived from hand motions of expert and novice surgeons accurately and objectively reflect laparoscopic surgical skill levels using an artificial intelligence system consisting of a three-layer chaos neural network. Sixty-seven surgeons (23 experts and 44 novices) performed a laparoscopic skill assessment task while their hand motions were recorded using a magnetic tracking sensor. Eight parameters evaluated as measures of skill in a previous study were used as inputs to the neural network. Optimization of the neural network was achieved after seven trials with a training dataset of 38 surgeons, with a correct judgment ratio of 0.99. The neural network that prospectively worked with the remaining 29 surgeons had a correct judgment rate of 79% for distinguishing between expert and novice surgeons. In conclusion, our artificial intelligence system distinguished between expert and novice surgeons among surgeons with unknown skill levels.

AB - This study investigated whether parameters derived from hand motions of expert and novice surgeons accurately and objectively reflect laparoscopic surgical skill levels using an artificial intelligence system consisting of a three-layer chaos neural network. Sixty-seven surgeons (23 experts and 44 novices) performed a laparoscopic skill assessment task while their hand motions were recorded using a magnetic tracking sensor. Eight parameters evaluated as measures of skill in a previous study were used as inputs to the neural network. Optimization of the neural network was achieved after seven trials with a training dataset of 38 surgeons, with a correct judgment ratio of 0.99. The neural network that prospectively worked with the remaining 29 surgeons had a correct judgment rate of 79% for distinguishing between expert and novice surgeons. In conclusion, our artificial intelligence system distinguished between expert and novice surgeons among surgeons with unknown skill levels.

UR - http://www.scopus.com/inward/record.url?scp=85046283756&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046283756&partnerID=8YFLogxK

U2 - 10.1155/2018/9873273

DO - 10.1155/2018/9873273

M3 - Article

C2 - 29686724

AN - SCOPUS:85046283756

VL - 2018

JO - Computational and Mathematical Methods in Medicine

JF - Computational and Mathematical Methods in Medicine

SN - 1748-670X

M1 - 9873273

ER -