AI-Based PaCO2 Monitoring from ETCO2 During Surgery

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods for monitoring arterial blood carbon dioxide during surgery are invasive and prone to measurement noise, making continuous monitoring difficult and potentially dangerous.

Innovation Solution

A non-invasive method using artificial intelligence to predict arterial blood carbon dioxide levels by analyzing biometric and clinical data, incorporating machine learning models like random forest and XGBoost to correlate end-tidal carbon dioxide with partial pressure of arterial carbon dioxide.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If arterial blood gas analysis (ABGA) is used to measure PaCO2, then measurement accuracy is improved, but measurement continuity and patient comfort deteriorate due to invasive procedures

Engineering Contradiction:

ImprovePaCO2 measurement accuracyVSAvoidMeasurement continuity and patient comfort

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The patent uses ETCO2 as an intermediary parameter to indirectly estimate PaCO2. Instead of directly measuring arterial blood CO2 through invasive ABGA, the system measures end-tidal CO2 from exhaled breath and uses machine learning models to predict PaCO2 values, thereby avoiding repeated arterial punctures while maintaining monitoring capability

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the mechanical/invasive ABGA measurement system with a non-invasive sensing system combined with computational algorithms. The invasive arterial blood sampling process is substituted by non-invasive ETCO2 sensing plus AI-based prediction, eliminating the need for physical blood collection while providing continuous monitoring

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If ABGA is performed frequently for continuous monitoring, then real-time PaCO2 data is improved, but measurement noise and arterial pressure fluctuations worsen due to blood collection disturbances

Engineering Contradiction:

ImproveReal-time monitoring capabilityVSAvoidMeasurement noise and arterial pressure rise

Core Design Contradiction:

ProductivityVSObject-affected harmful factors

Solution Approach 1:

The patent converts the limitation of ETCO2 (being an indirect measure) into a benefit by using machine learning to bridge the gap between ETCO2 and PaCO2. The algorithm learns the complex relationship between these parameters from training data, transforming the indirect measurement approach into an accurate prediction system that avoids the harmful effects of frequent blood sampling

Inventive Principle:

Principle #22Blessing in disguise (Convert harm into benefit)

Solution Approach 2:

The patent performs preliminary training of machine learning models using historical ABGA data and corresponding ETCO2 measurements. This preliminary action creates a predictive system that can estimate PaCO2 without requiring actual blood sampling during surgery, thereby preventing measurement noise and pressure fluctuations before they occur

Inventive Principle:

Principle #10Preliminary action

3Ease of operation

If non-invasive ETCO2 monitoring is used, then patient comfort and measurement continuity are improved, but PaCO2 measurement accuracy deteriorates due to the indirect measurement method

Engineering Contradiction:

ImproveNon-invasive continuous monitoringVSAvoidPaCO2 measurement accuracy

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The patent transforms the monitoring approach by changing from direct PaCO2 measurement to indirect ETCO2 measurement combined with computational prediction. By introducing machine learning models that learn the relationship between ETCO2 and PaCO2, the system maintains non-invasive operation while recovering measurement accuracy through algorithmic correction

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS20260020774A1Apparatus and method for non-invasively monitoring arterial blood carbon dioxide during surgery

Publication Date: 2026.01.22 CHONBUK NAT UNIV HOSPITAL

AI summary

A method for non-invasively monitoring arterial blood carbon dioxide during surgery include collecting and storing biometric signal information during surgery of patients, clinical information before the surgery, and end-tidal carbon dioxide (ETCO2) and partial pressure of arterial carbon dioxide (PaCO2), generating learning data in which the biometric signal information during the surgery, the clinical information before the surgery, and the ETCO2 are input conditions and the PaCO2 is an output condition on the basis of a data collection result and then allowing a prediction model to perform machine learning on a correlation between the ETCO2 and the PaCO2, acquiring and storing clinical information before surgery of the surgical patient, and, when the surgery of the surgical patient is started, predicting PaCO2 in real time by measuring biometric signal information and ETCO2 and then analyzing the biometric signal information and the ETCO2 before the surgery through the prediction model.