Forecasting of subject-related attributes using generative machine-learning models

A computer-implemented method of determining an efficacy and/or safety of a trial therapeutic intervention in a clinical trial, the computer-implemented method comprising:

• receiving electronic data comprising results of a clinical trial relating to a trial therapeutic intervention;
• receiving control data, the control data generated by:
• receiving input data comprising:
• a medical history of a subject, the medical history comprising values of a plurality of subject-related attributes of a subject;
• and
• data specifying a requested output, the data comprising one or more specified subject-related attributes of the subject and a time frame;
• and
• applying a trained generative machine-learning model to the received input data, the trained generative machine-learning model configured to generate control data based on the input data, the control data comprising:
• respective values of the one or more specified subject-related attributes of the subject in the specified time frame
• wherein the trained generative machine-learning model is a trained large language model, wherein the computer-implemented method further comprises converting the received input data into converted input data having a predetermined syntax which is appropriate for input into the generative machine-learning model;
• and
• determining an efficacy and/or safety of the trial therapeutic intervention based on a comparison of the electronic data comprising the results of the clinical trial with the control data comprising the generated data.