Computer vision-based analysis of provider data

A computer-implemented method comprising:

• as implemented by one or more computing devices configured with specific executable instructions,
• training, using a plurality of training images depicting dental radiographs as training image data, a plurality of machine learning models to localize and classify dental conditions depicted in the training image data, wherein at least a subset of the plurality of machine learning models comprise neural networks;
• obtaining, for a plurality of patients of a dental provider, patient records originating from a practice management system of the dental provider;
• providing, for each of the plurality of patients, at least one radiograph of the patient as input to one or more trained machine learning models of the plurality of machine learning models;
• receiving, for each of the plurality of patients, output of the one or more machine learning models that are provided with the input comprising the at least one radiograph of the patient, wherein the output of the one or more machine learning models identifies at least one dental condition determined by the one or more machine learning models to be depicted in the at least one radiograph of the patient;
• comparing conditions identified in radiographs by the one or more machine learning models with treatments identified in corresponding patient records from the practice management system;
• based at least in part on instances in which a condition identified by the one or more machine learning models does not match corresponding data from records in the practice management system, identifying a plurality of missed periodontal opportunities associated with the dental provider, wherein the instances are identified based at least in part on data mapping each of a plurality of dental conditions to a corresponding dental treatment;
• generating provider performance data regarding the dental provider for a time period, wherein the provider performance data comprises a numeric score or percentage representing how often, based on the instances in which the condition identified by the one or more machine learning models does not match the corresponding data from records in the practice management system, the dental provider missed periodontal opportunities among a plurality of patients that visited the dental provider over the time period;
• and
• generating a user interface that presents at least the provider performance data regarding the dental provider over the time period.

A computer-readable, non-transitory storage medium storing computer executable instructions that, when executed by one or more computer systems, configure the one or more computer systems to perform operations comprising:

• training, using a plurality of training images depicting dental radiographs as training image data, a plurality of machine learning models to localize and classify dental conditions depicted in the training image data, wherein at least a subset of the plurality of machine learning models comprise neural networks;
• obtaining, for a plurality of patients of a dental provider, patient records originating from a practice management system of the dental provider;
• providing, for each of the plurality of patients, at least one radiograph of the patient as input to one or more trained machine learning models of the plurality of machine learning models;
• receiving, for each of the plurality of patients, output of the one or more machine learning models that are provided with the input comprising the at least one radiograph of the patient, wherein the output of the one or more machine learning models identifies at least one dental condition determined by the one or more machine learning models to be depicted in the at least one radiograph of the patient;
• comparing conditions identified in radiographs by the one or more machine learning models with treatments identified in corresponding patient records from the practice management system;
• based at least in part on instances in which a condition identified by the one or more machine learning models does not match corresponding data from records in the practice management system, identifying a plurality of missed periodontal opportunities associated with the dental provider, wherein the instances are identified based at least in part on data mapping each of a plurality of dental conditions to a corresponding dental treatment;
• generating provider performance data regarding the dental provider for a time period, wherein the provider performance data comprises a numeric score or percentage representing how often, based on the instances in which the condition identified by the one or more machine learning models does not match the corresponding data from records in the practice management system, the dental provider missed periodontal opportunities among a plurality of patients that visited the dental provider over the time period;
• and
• generating a user interface that presents the provider performance data regarding the dental provider over the time period.