Predicting adverse health events using a measure of adherence to a testing routine

One or more non-transitory computer storage media storing instructions that are operable, when executed by one or more computers, to cause the one or more computers to perform operations for predicting an adverse health event of a subject, comprising:

• (a) obtaining a dataset from one or more sources, wherein the dataset comprises a plurality of values for health measurements of the subject;
• (b) generating metadata about the dataset, wherein the metadata comprises a measure of adherence to a testing routine comprising the health measurements;
• (c) generating a plurality of intermediate scores based on the dataset and the metadata;
• (d) using a trained machine learning algorithm to generate a risk score by applying a plurality of weights to the plurality of intermediate scores, wherein the risk score is indicative of whether the subject will experience the adverse health event;
• and
• (e) outputting the risk score on a graphical user interface of a computing device, wherein (b)-(e) are performed within 30 days of (a), and
• (f) determining whether to initiate a medical intervention for the subject based at least in part on the risk score.

A system comprising one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations for predicting an adverse health event of a subject, comprising:

• (a) obtaining a dataset from one or more sources, wherein the dataset comprises a plurality of values for health measurements of the subject;
• (b) generating metadata about the dataset, wherein the metadata comprises a measure of adherence to a testing routine comprising the health measurements;
• (c) generating a plurality of intermediate scores based on the dataset and the metadata;
• (d) using a trained machine learning algorithm to generate a risk score by applying a plurality of weights to the plurality of intermediate scores, wherein the risk score is indicative of whether the subject will experience the adverse health event;
• and
• (e) outputting the risk score on a graphical user interface of a computing device, wherein (b)-(e) are performed within 30 days of (a), and
• (f) determining whether to initiate a medical intervention for the subject based at least in part on the risk score.