Development and Evaluation of a Machine Learning Approach to Interpret Optical Coherence Tomography Images of the Middle Ear to Improve Antibiotic Management

PROJECT SUMMARY IntroductionPhotoniCareIncis a medical device company developing the TOMi Scopea handheldoptical imaging device for improved diagnosis of middle ear healthThe purpose of this proposal is to establish and evaluate a machine learning approach to interpret TOMi Scope depth resolved images using a set of ear models with human middle ear effusionMEEfluidto enable improved diagnostic accuracy andultimatelyantibiotic stewardship for ear healthSignificanceEar infections affectof all childrenyet they are one of the most poorly diagnosed and managed diseases in all of medicineresulting in high antibiotic over prescription and antibiotic resistance developmentCorrectly identifying the absence or presence type of MEE through the non transparent eardrum is critical to accurate diagnosisand the limited current diagnostic tools suffer poor diagnostic accuracydue to inherent subjectivity and dependence on user experienceThereforeobjective image classification metrics to enable improved diagnostic accuracy is sorely needed to finally provide children afflicted by this disease with the correct treatment the first timeHypothesisApplying a machine learning approach to TOMi Scope image classification of a set of ear models with human MEE will facilitate detection of the presence or absence of effusionaccuracyas well as classification by the type of effusion samplesaccuracyregardless of user experienceSpecific AimsCollect robust datasets of ex vivo human MEEsufficient for machine learning image analysisDevelop a neural network model based on the MEE dataset and apply the model to a representative test clinical dataset to determine classification feasibilityCommercial OpportunityThe TOMi Scope will provide physicians with newobjective informationenabling better decision making for antibiotic prescription and surgical interventionThis has the potential to impact the standard of care forB children worldwide that experience ear infectionsrepresenting a multi billion dollar commercial opportunity PROJECT NARRATIVE Ear infectionsotitis mediaare highly prevalent in the pediatric population and represent a significant clinical challenge due to the limitations of the gold standard diagnostic toolsresulting in high antibiotic prescription but also antibiotic resistance developmentAccurate detection and classification of effusionfluidin the middle ear is a critical element for this diagnosisand for making informed medical treatment decisionsparticularly regarding antibiotic stewardshipThe long term goal of this work is to reduce antibiotic resistance and healthcare costs through improving patient outcomes by addressing the low diagnostic accuracy and user experience dependence of current subjective methodswith a novelnon invasive imaging tool capable of quantitative depth resolved measurements to not only visualize the underlying infection behind the eardrumbut alsowith automated machine learning image analysis algorithmsminimize user experience dependence and variability