Autonomous diagnosis of ear diseases from biomarker data
Inventors
Abramoff, Michael D. • Amelon, Ryan
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-11786148-B2
Publication Date
2023-10-17
Expiration Date
Abstract
A fully autonomous system is used to diagnose an ear infection in a patient. For example, a processor receives patient data about a patient, the patient data comprising at least one of: patient history from medical records for the patient, one or more vitals measurements of the patient, and answers from the patient about the patient's condition. The processor receives a set of biomarker features extracted from measurement data taken from an ear of the patient. The processor synthesizes the patient data and the biomarker features into input data, and applies the synthesized input data to a trained diagnostic model, the diagnostic model comprising a machine learning model configured to output a probability-based diagnosis of an ear infection from the synthesized input data. The processor outputs the determined diagnosis from the diagnostic model. A service may then determine a therapy for the patient based on the determined diagnosis.
Core Innovation
The described system diagnoses an ear infection by combining patient history and current patient data with biomarkers derived from ear images and, in some implementations, pressure-evoked acoustic responses. A machine-learning diagnostic model applies synthesized input data to produce a probability-based diagnosis. Image analysis evaluates whether an image is sufficient, provides acquisition feedback, and extracts anatomically located biomarkers with confidence values.
The described system also includes a therapy determination service that selects and outputs treatment using clinical rules or a model, and a therapeutic parameters database. The provided content does not include the background section, so the problem being solved is not explicitly described. It depicts data flow through image-analysis, acoustic-analysis, diagnostic-classifier, and therapy-service modules.
Claims Coverage
The claims identify three independent claims, covering a diagnostic method, a computer program product, and a diagnostic product stored on a non-transitory computer-readable medium. The following three inventive features summarize their principal coverage.
Probability-based ear infection diagnosis
The method synthesizes patient data and image-derived ear biomarker features into input data for a machine-learning diagnostic model, which outputs a probability-based diagnosis of an ear infection. The image features include a likelihood that an image sample contains an ear image object and the location of that object.
Computer program product for ear infection diagnosis
The computer program product contains code that uses patient data and image-derived ear biomarker features to generate synthesized input data and output a probability-based diagnosis of an ear infection from a machine-learning diagnostic model.
Stored diagnostic product with trained model parameters
The diagnostic product is stored on a non-transitory computer-readable medium and includes updated parameters for a machine-learning diagnostic model. The model is trained using examples that combine patient data with image-derived ear biomarker features and labels indicating whether a patient has an ear infection.
The independent claims cover diagnosis through a method, executable computer program code, and a stored diagnostic product. Across these forms, the claims use patient data and image-derived ear biomarkers to train or apply a machine-learning model for ear infection diagnosis.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Diagnosing an ear infection using patient data and ear-derived biomarkers, with a machine-learning model producing a probability-based diagnosis.
Selecting and outputting treatment using a therapy determination service, including selection based on a therapeutic parameters database.
Interested in licensing this patent?