Method and device for evaluating difficult airway based on machine learning voice technology

Abstract

The invention relates to a difficult airway evaluation method and device based on a machine learning voice technology. The method comprises the following steps: acquiring voice data of a patient; performing feature extraction on the voice data to obtain acoustic features, voiceprint features and voice recognition features; and constructing a difficult airway evaluation classifier based on a machine learning voice technology, analyzing the extracted acoustic features, voiceprint features and voice recognition features through the trained difficult airway classifier, and scoring the severity of the difficult airway to obtain an evaluation result of the difficult airway. According to the method, early warning can be accurately carried out on difficult airways in clinical anesthesia.

Description

technical field [0001] The invention relates to the field of computer-aided technology, in particular to a difficult airway assessment method and device based on machine learning speech technology. Background technique [0002] Endotracheal intubation is an important means for anesthesiologists to manage the airway of patients under general anesthesia. It plays an important role in maintaining airway patency, ventilation and oxygen supply, respiratory support, and maintenance of oxygenation. However, despite great advances and improvements in endotracheal intubation techniques and equipment, the incidence of perioperative complications and disability due to difficult airways has not been significantly improved, especially for unanticipated difficulties airway. At present, methods for evaluating difficult airway generally include Mallampatti classification, LEMON score, Wilson score and auxiliary CT, MRI, US, etc. The process is complicated and the positive evaluation value ...

AI Technical Summary

Problems solved by technology

However, despite great advances and improvements in endotracheal intubation techniques and equipment, the incidence of perioperative complications and disability due to difficult airways has not been significantly improved, especially for unanticipated difficulties airway

At present, methods for evaluating difficult airways generally include Mallampatti classification, LEMON scoring, Wilson scoring and auxiliary CT, MRI, US, etc. The process is complicated and the positive evaluation value is not high, all of which have certain limitations

Images