Surgical Instrument Prediction From Surgeon Motion for Robotic Delivery

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The accuracy and efficiency of surgical instrument handling during operations depend heavily on the skill and endurance of surgical room nurses, leading to fatigue and potential errors.

Innovation Solution

A computer-assisted system using motion sensing and machine learning to predict the next surgical instrument needed based on the surgeon's motion and operation progress, with a robot arm to deliver the instrument.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a surgical room nurse manually predicts and handles surgical instruments based on tacit knowledge and experience, then the instrument handling can be performed with human judgment and adaptability, but the nurse becomes fatigued physically and mentally, and the accuracy depends on the nurse's skill level

Engineering Contradiction:
Improveinstrument prediction accuracyVSAvoidnurse fatigue
Core Design Contradiction:
ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The patent replaces the human nurse's manual instrument prediction and handling with an automated system comprising motion sensing devices, calculation modules with learned models, and robot arms. The system detects surgeon motion, predicts required instruments using machine learning models, and automatically retrieves/delivers instruments, eliminating the need for human physical and mental effort while maintaining or improving prediction accuracy through objective data analysis.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Adaptability or versatility

If instrument handling is based on nurse skill and experience, then complex surgical situations can be handled with human judgment, but the consistency and reliability vary depending on the nurse's skill level

Engineering Contradiction:
Improvehandling complex surgical situationsVSAvoidprediction consistency
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The system performs self-learning and self-improvement through machine learning models that are trained on surgical data. The learned models automatically adapt to different surgical situations and surgeon preferences without requiring human intervention for each case, ensuring consistent and reliable instrument predictions across various complex surgical scenarios while maintaining the ability to handle diverse situations through data-driven pattern recognition.

Inventive Principle:
Principle #25Self-service

3Device complexity

If manual instrument prediction is used, then the system is simple and easy to implement, but the speed and accuracy of instrument delivery depend on human reaction time and skill

Engineering Contradiction:
Improvesystem simplicityVSAvoidinstrument delivery speed
Core Design Contradiction:
Device complexityVSProductivity

Solution Approach 1:

The system performs preliminary actions by continuously detecting surgeon motion and predicting future instrument needs before the surgeon actually requests them. The robot arm is positioned and prepared in advance based on predicted requirements, enabling faster instrument delivery compared to reactive manual handling. The learned models are pre-trained on surgical data to enable rapid prediction and response.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS12408986B2Device and method of predicting use instrument, and surgery assisting robot
Publication Date: 2025.09.09 KAWASAKI JUKOGYO KK
  • US12408986B2 patent drawing
  • US12408986B2 patent drawing
  • US12408986B2 patent drawing

AI summary

A use instrument predicting device includes a motion recognizing module that recognizes a motion of a surgeon during a surgical operation based on motion detection data that is obtained by detecting the surgeon's motion, a situation recognizing module that recognizes a surgery situation based on the motion recognized result of the motion recognizing module, and a predicting module that predicts at least one kind of surgical instrument to be used next by the surgeon out of a plurality of kinds of surgical instruments given beforehand, based on the situation recognized result of the situation recognizing module.