Machine learning teaching method determination

A computer program product comprising a non-transitory computer readable storage medium storing computer program code executable to perform operations, the operations comprising:

• electronically recording an individual diagnosed with a neurodevelopmental disorder, the electronic recording comprising an audio recording of a voice of the individual or a video recording of the individual;
• processing multimodal information associated with the individual using a plurality of machine learning models, the multimodal information comprising demographic information, survey responses, and the electronic recording of the individual;
• generating a list of one or more teaching methods selected from established evidence-based practices for neurodevelopmental disorders based on a combination of predictions from the plurality of machine learning models, wherein the plurality of machine learning models comprise different machine learning models for predicting different teaching methods, and wherein a teaching method is included in the list of one or more teaching methods in response to a number of the plurality of machine learning models that predict the teaching method satisfying a threshold;
• selecting a teaching method for the individual diagnosed with the neurodevelopmental disorder from the list of teaching methods based on a combination of predictions from the plurality of machine learning models, wherein the plurality of machine learning models comprise a plurality of different machine learning models for one or more different demographics, wherein predictions are ranked based on accuracy of past predictions of the respective machine learning model and demographic similarity between training data of the respective machine learning model and the individual, and wherein the teaching method having a highest ranked prediction is selected;
• determining a personalized learning plan for the individual based on the predictions from the plurality of machine learning models and the selected teaching method;
• receiving access control information from a user for viewing the selected teaching method and the personalized learning plan;
• displaying, to the user in response to authenticating the user based on the access control information, the selected teaching method and the personalized learning plan on an electronic display screen for a hardware computing device;
• tracking measured effectiveness outcomes associated with the selected teaching method for the individual over time, the measured effectiveness outcomes comprising information indicating an effectiveness of the selected teaching method for the individual diagnosed with the neurodevelopmental disorder;
• and
• retraining the plurality of machine learning models using the measured effectiveness outcomes associated with the selected teaching method.

A method comprising:

• electronically recording an individual diagnosed with a neurodevelopmental disorder, the electronic recording comprising an audio recording of a voice of the individual or a video recording of the individual;
• processing multimodal information associated with the individual using a plurality of machine learning models, the multimodal information comprising demographic information, survey responses, and the electronic recording of the individual;
• generating a list of one or more teaching methods selected from established evidence-based practices for neurodevelopmental disorders based on a combination of predictions from the plurality of machine learning models, wherein the plurality of machine learning models comprise different machine learning models for predicting different teaching methods, and wherein a teaching method is included in the list of one or more teaching methods in response to a number of the plurality of machine learning models that predict the teaching method satisfying a threshold;
• selecting a teaching method for the individual diagnosed with the neurodevelopmental disorder from the list of teaching methods based on a combination of predictions from the plurality of machine learning models, wherein the plurality of machine learning models comprise a plurality of different machine learning models for one or more different demographics, wherein predictions are ranked based on accuracy of past predictions of the respective machine learning model and demographic similarity between training data of the respective machine learning model and the individual, and wherein the teaching method having a highest ranked prediction is selected;
• determining a personalized learning plan for the individual based on the predictions from the plurality of machine learning models and the selected teaching method;
• receiving access control information from a user for viewing the selected teaching method and the personalized learning plan;
• displaying, to the user in response to authenticating the user based on the access control information, the selected teaching method and the personalized learning plan on an electronic display screen for a hardware computing device;
• tracking measured effectiveness outcomes associated with the selected teaching method for the individual over time, the measured effectiveness outcomes comprising information indicating an effectiveness of the selected teaching method for the individual diagnosed with the neurodevelopmental disorder;
• and
• retraining the plurality of machine learning models using the measured effectiveness outcomes associated with the selected teaching method.