Machine learning framework for detection of chronic health conditions

A system for detecting health conditions, comprising:

• one or more processors;
• and
• a non-transitory computer-readable medium having processor-executable instructions stored thereon, wherein the processor-executable instructions, when executed by the one or more processors, facilitate:
• receiving monitored parameter data corresponding to data points collected over a number of days from a wearable device associated with a user through a network;
• generating a plurality of tensors based on applying a convolutional neural network (CNN) to the monitored parameter data, wherein each of the plurality of tensors corresponds to a different day in the number of days;
• processing, in a time sequential manner, the plurality of tensors using a long short-term memory (LSTM) network, wherein processing the plurality of tensors in the time sequential manner corresponds to processing the plurality of tensors in chronological order by the LSTM based on the days corresponding to each tensor;
• in response to processing the plurality of tensors, generating an embedding vector for the monitored parameter data;
• generating an output vector that indicates a prediction related to a plurality of health conditions for the user of the wearable device based on using an artificial intelligence algorithm and the embedding vector;
• and
• transmitting, to the user of the wearable device or to a healthcare provider, a notification message that is based on the prediction.

A non-transitory computer-readable medium having processor-executable instructions stored thereon, wherein the processor-executable instructions, when executed, facilitate:

• receiving monitored parameter data corresponding to data points collected over a number of days from a wearable device associated with a user through a network;
• generating a plurality of tensors based on applying a convolutional neural network (CNN) to the monitored parameter data, wherein each of the plurality of tensors corresponds to a different day in the number of days;
• processing, in a time sequential manner, the plurality of tensors using a long short-term memory (LSTM) network, wherein processing the plurality of tensors in the time sequential manner corresponds to processing the plurality of tensors in chronological order by the LSTM based on the days corresponding to each tensor;
• in response to processing the plurality of tensors, generating an embedding vector for the monitored parameter data;
• generating an output vector that indicates a prediction related to a plurality of health conditions for the user of the wearable device based on using an artificial intelligence algorithm and the embedding vector;
• and
• transmitting, to the user of the wearable device or to a healthcare provider, a notification message that is based on the prediction.