Machine learning for otitis media diagnosis
Inventors
Corredor, Charlie • Moehring, Mark A • Cameron, Caitlin • Gates, George A.
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12137871-B2
Publication Date
2024-11-12
Expiration Date
Abstract
Disclosed herein are systems and methods for classifying a tympanic membrane by using a classifier. The classifier is a machine learning algorithm. A method for classifying a tympanic membrane includes steps of: receiving, from an interrogation system, one or more datasets relating to the tympanic membrane; determining a set of parameters from the one or more datasets, wherein at least one parameter of the set of parameters is related to a dynamic property or a static position of the tympanic membrane; and outputting a classification of the tympanic membrane based on a classifier model derived from the set of parameters. The classification comprises one or more of a state, a condition, or a mobility metric of the tympanic membrane.
Core Innovation
The invention relates to a method for classifying a tympanic membrane by receiving one or more datasets relating to the tympanic membrane from an interrogation system. A set of parameters is determined from the datasets, where at least one parameter comprises an indication of a dynamic property of the tympanic membrane. The dynamic property relates to a damped motion of the tympanic membrane in response to pneumatic excitation.
Based on the determined set of parameters, the invention outputs a classification using a trained classifier model derived from the set of parameters. The classification includes one or more of a state, a condition, or a mobility metric of the tympanic membrane. The classified outputs include state and condition categories such as acute otitis media, acute otitis media with effusion, middle ear effusion, chronic otitis media, and chronic suppurative otitis media, and may include bacterial infection, viral infection, no effusion, or an unknown classification.
A system embodiment is also provided for classifying the tympanic membrane. The system includes a computing system with memory and instructions to receive datasets from an interrogation system, determine a set of parameters including an indication of a dynamic property related to damped motion in response to pneumatic excitation, and output a classification based on the trained classifier model. The trained classifier model comprises a machine learning algorithm, with representative model types and learning modes including supervised, unsupervised, and semi-supervised learning.
Claims Coverage
The patent provides two independent claims—one method claim and one system claim. Both independent claims share three core inventive steps/features: receiving tympanic membrane datasets from an interrogation system, determining parameters including a dynamic damped-motion property in response to pneumatic excitation, and outputting a classification using a trained classifier model, where the classification comprises a state, condition, or mobility metric.
Interrogation dataset reception for tympanic membrane classification
Receiving, from an interrogation system, one or more datasets relating to the tympanic membrane.
Dynamic property parameter extraction from damped pneumatic motion
Determining a set of parameters from the one or more datasets, wherein at least one parameter comprises an indication of a dynamic property of the tympanic membrane, wherein the dynamic property relates to a damped motion of the tympanic membrane in response to a pneumatic excitation.
Trained classifier model outputting state, condition, or mobility metric
Outputting a classification of the tympanic membrane based on a trained classifier model derived from the set of parameters, wherein the classification comprises one or more of a state, a condition, or a mobility metric of the tympanic membrane.
Computing system execution to classify tympanic membrane
A computing system comprising a memory, the memory comprising instructions for classifying the tympanic membrane, wherein the computing system is configured to execute the instructions to at least receive from an interrogation system one or more datasets relating to the tympanic membrane, determine a set of parameters including a dynamic property related to damped motion in response to a pneumatic excitation, and output a classification based on a trained classifier model.
Machine-learning based trained classifier model
A trained classifier model derived from the set of parameters, wherein the trained classifier model comprises a machine learning algorithm.
Overall, claim coverage centers on using datasets relating to a tympanic membrane to derive parameters that indicate a dynamic property of damped motion under pneumatic excitation, and then using a trained classifier model to output a classification comprising a state, condition, or mobility metric of the tympanic membrane.
Stated Advantages
Documented Applications
Classifying a tympanic membrane into otitis media-related state/condition categories, including acute otitis media, acute otitis media with effusion, middle ear effusion, chronic otitis media, chronic suppurative otitis media, bacterial infection, viral infection, no effusion, and unknown classification.
Interested in licensing this patent?