Method and process for predicting and analyzing patient cohort response, progression, and survival

A method for implementing a prediction model, comprising:

• 1) receiving a plurality of data for a plurality of patients, the plurality of data covering a period of time;
• 2) normalizing the plurality of data relative to a common anchor point shared by the plurality of patients;
• identifying, for each of the plurality of patients, a plurality of patient timepoints within the period of time, the plurality of patient timepoints including at least one timepoint after the common anchor point, each patient timepoint associated with a respective piece of data of the plurality of data;
• 4) for each patient of the plurality of patients and for each patient timepoint of the plurality of patient timepoints and based on the plurality of data for the plurality of patients:
• a) determining whether an outcome target for an outcome event occurs within a horizon time window measured from the patient timepoint;
• b) generating a prior feature set comprising a plurality of prior features, and
• c) determining a state of each of the plurality of prior features at the patient timepoint;
• 5) identifying, for each patient timepoint of the plurality of timepoints having a valid outcome target and for each combination of horizon time window and outcome event, a plurality of forward features;
• 6) generating a plurality of sets of predictions for the plurality of patients based on the plurality of prior features and the plurality of forward features;
• 7) selecting a cohort of patients comprising a group of patients of the plurality of patients;
• 8) identifying a common anchor point in time from a set of anchor points associated with each of the group of patients, the common anchor point being shared by each of the group of patients in the cohort;
• 9) aligning, for each patient of the group of patients, a timeline associated with each patient of the group of patients to the common anchor point;
• 10) identifying an outcome target;
• 11) retrieving, for each patient of the group of patients and for each of the plurality of forward features and the plurality of prior features, the generated plurality of sets of predictions each comprising a predicted target value;
• and
• 12) generating a classification model based on the plurality of sets of predictions each comprising a predicted target value;
• wherein at least one of the prior features or the forward features comprises genetic data comprising sequence information of a patient's tumor sample, the sequence information derived from hundreds of nucleotide sequences.