Author/Authors :
Uemura, Munenori Department of Advanced Medical Initiatives - Faculty of Medical Sciences - Kyushu University - Fukuoka, Japan , Tomikawa, Morimasa Department of Advanced Medical Initiatives - Faculty of Medical Sciences - Kyushu University - Fukuoka, Japan , Miao, Tiejun TAOS Institute - Tokyo, Japan , Souzaki, Ryota Department of Advanced Medicine and Innovative Technology - Kyushu University Hospital - Fukuoka, Japan , Ieiri, Satoshi Department of Advanced Medicine and Innovative Technology - Kyushu University Hospital - Fukuoka, Japan , Akahoshi, Tomohiko Department of Advanced Medical Initiatives - Faculty of Medical Sciences - Kyushu University - Fukuoka, Japan , Lefor, Alan K Department of Advanced Medical Initiatives - Faculty of Medical Sciences - Kyushu University - Fukuoka, Japan , Hashizume, Makoto Department of Advanced Medical Initiatives - Faculty of Medical Sciences - Kyushu University - Fukuoka, Japan
Abstract :
Tis study investigated whether parameters derived from hand motions of expert and novice surgeons accurately and objectively
refect laparoscopic surgical skill levels using an artifcial intelligence system consisting of a three-layer chaos neural network. Sixtyseven 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 afer seven trials with a training dataset of 38 surgeons, with
a correct judgment ratio of 0.99. Te 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 artifcial intelligence system
distinguished between expert and novice surgeons among surgeons with unknown skill levels.
