Abstract: A system may receive a plurality of digital histology images, wherein each of the plurality of digital histology images is labeled with a respective image-level classification. A system may extract a plurality of tiles from each of the plurality of digital histology images. A system may create a first dataset comprising the plurality of tiles and respective image-level classifications. A system may train a first machine learning model using the first dataset. A system may create a second dataset by sampling the first dataset based on respective classifications and respective uncertainty measures for each of the plurality of tiles output by the trained first machine learning model. A system may train a second machine learning model using the second dataset, wherein the trained second machine learning model is configured to classify one or more tiles of a digital histology image.

Abstract: Methods and systems for predicting prognosis of a patient are provided. An example method can comprise determining a target set, wherein the target set comprises patient data from a target patient, determining a reference set, wherein the reference set comprises patient data from a plurality of patients, and the plurality of patients have one or more features in common with the target patient, determining common comparison features, normalizing common comparison feature data by a normalization method, weighting the normalized common comparison feature data, and determining one or more best matches by applying a classification method to the weighted normalized common comparison feature data. Finally, the prognosis of the patient in the target set is predicted.

Abstract: Methods and systems for predicting prognosis of a patient are provided. An example method can comprise determining a target set, wherein the target set comprises patient data from a target patient, determining a reference set, wherein the reference set comprises patient data from a plurality of patients, and the plurality of patients have one or more features in common with the target patient, determining common comparison features, normalizing common comparison feature data by a normalization method, weighting the normalized common comparison feature data, and determining one or more best matches by applying a classification method to the weighted normalized common comparison feature data. Finally, the prognosis of the patient in the target set is predicted.