Systems and methods for training a model to predict survival time for a patient

1. A method for training one or more models to predict survival time for a patient, the method comprising:

accessing a plurality of annotated pathology images associated with a group of patients in a randomized controlled clinical trial, wherein each of the plurality of annotated pathology images is associated with survival data for a respective patient, wherein each of the plurality of annotated pathology images includes at least one annotation describing a tissue characteristic category for a portion of the image, wherein the plurality of annotated pathology images includes:

a first plurality of annotated pathology images associated with a first group of patients belonging to a first treatment group of the randomized controlled clinical trial, and

a second plurality of annotated pathology images associated with a second group of patients belonging to a second treatment group of the randomized controlled clinical trial;

training one or more models based on the survival data and the plurality of annotated pathology images, wherein the one or more trained models include a first plurality of features based in part on the first plurality of annotated pathology images and a second plurality of features based in part on the second plurality of annotated pathology images; and

storing the one or more trained models on at least one storage device.

2. The method of claim 1 , further comprising:

processing, using the one or more trained models, at least the first plurality of features to predict survival data for patients in the first group of patients; and

processing, using the one or more trained models, at least the second plurality of features to predict survival data for patients in the second group of patients.

3. The method of claim 2 , further comprising:

determining a first prognostic performance of the one or more trained models for the first treatment group based on the predicted survival data for the patients in the first group of patients and respective survival data; and

determining a second prognostic performance of the one or more trained models for the second treatment group based on the predicted survival data for the patients in the second group of patients and respective survival data.

4. The method of claim 3 , further comprising:

determining a specificity of a prognostic power of the one or more trained models by comparing the first prognostic performance of the one or more trained models for the first treatment group and the second prognostic performance of the one or more trained models for the second treatment group, wherein the specificity of the prognostic power of the one or more trained models includes a likelihood that the one or more trained models will correctly identify a subset of patients that respond to a particular treatment.

5. The method of claim 4 , wherein comparing the first prognostic performance and the second prognostic performance includes performing subset survival analyses using respective predicted survival data from the first treatment group and the second treatment group.

6. The method of claim 2 , further comprising:

selecting, based on the predicted survival data for the patients in the first group of patients, a subset of the first group of patients that responded to treatment.

7. The method of claim 1 , further comprising:

processing, using the one or more trained models, at least a third plurality of features based in part on a third plurality of annotated pathology images associated with a third group of patients belonging to a third treatment group of the randomized controlled clinical trial or a different randomized controlled clinical trial, to predict survival data for patients in the third group of patients; and

selecting a subset of the third group of patients that are expected to respond to treatment.

8. The method of claim 1 , wherein the first plurality of features and/or the second plurality of features are selected from a group consisting of area of epithelium, area of stroma, area of necrosis, area of cancer cells, area of macrophages, area of lymphocytes, number of mitotic figures, average nuclear grade, average distance between fibroblasts and lymphocytes, average distance between immunohistochemistry-positive macrophages and cancer cells, standard deviation of nuclear grade, average distance between blood vessels and tumor cells.

9. The method of claim 1 , wherein the one or more trained models include a generalized linear model, a random forest, a support vector machine, and/or a gradient boosted tree.

10. A system for training one or more models to predict survival time for a patient, the system comprising:

at least one computer hardware processor; and

at least one non-transitory computer-readable storage medium storing processor-executable instructions that, when executed by the at least one computer hardware processor, cause the at least one computer hardware processor to perform:

accessing a plurality of annotated pathology images associated with a group of patients in a randomized controlled clinical trial, wherein each of the plurality of annotated pathology images is associated with survival data for a respective patient, wherein each of the plurality of annotated pathology images includes at least one annotation describing a tissue characteristic category for a portion of the image, wherein the plurality of annotated pathology images includes:

a first plurality of annotated pathology images associated with a first group of patients belonging to a first treatment group of the randomized controlled clinical trial, and

a second plurality of annotated pathology images associated with a second group of patients belonging to a second treatment group of the randomized controlled clinical trial;

training one or more models based on the survival data and the plurality of annotated pathology images, wherein the one or more trained models include a first plurality of features based in part on the first plurality of annotated pathology images and a second plurality of features based in part on the second plurality of annotated pathology images; and

storing the one or more trained models on at least one storage device.

11. The system of claim 10 , wherein the processor-executable instructions further cause the at least one computer hardware processor to perform:

processing, using the one or more trained models, at least the first plurality of features to predict survival data for patients in the first group of patients; and

processing, using the one or more trained models, at least the second plurality of features to predict survival data for patients in the second group of patients.

12. The system of claim 11 , wherein the processor-executable instructions further cause the at least one computer hardware processor to perform:

determining a first prognostic performance of the one or more trained models for the first treatment group based on the predicted survival data for the patients in the first group of patients and respective survival data; and

determining a second prognostic performance of the one or more trained models for the second treatment group based on the predicted survival data for the patients in the second group of patients and respective survival data.

13. The system of claim 12 , wherein the processor-executable instructions further cause the at least one computer hardware processor to perform:

determining a specificity of a prognostic power of the one or more trained models by comparing the first prognostic performance of the one or more trained models for the first treatment group and the second prognostic performance of the one or more trained models for the second treatment group, wherein the specificity of the prognostic power of the one or more trained models includes a likelihood that the one or more trained models will correctly identify a subset of patients that respond to a particular treatment.

14. The system of claim 13 , wherein comparing the first prognostic performance and the second prognostic performance includes performing subset survival analyses using respective predicted survival data from the first treatment group and the second treatment group.

15. The system of claim 11 , wherein the processor-executable instructions further cause the at least one computer hardware processor to perform:

selecting, based on the predicted survival data for the patients in the first group of patients, a subset of the first group of patients that responded to treatment.

16. The system of claim 10 , wherein the processor-executable instructions further cause the at least one computer hardware processor to perform:

processing, using the one or more trained models, at least a third plurality of features based in part on a third plurality of annotated pathology images associated with a third group of patients belonging to a third treatment group of the randomized controlled clinical trial or a different randomized controlled clinical trial, to predict survival data for patients in the third group of patients; and

selecting a subset of the third group of patients that are expected to respond to treatment.

17. The system of claim 10 , wherein the first plurality of features and/or the second plurality of features are selected from a group consisting of area of epithelium, area of stroma, area of necrosis, area of cancer cells, area of macrophages, area of lymphocytes, number of mitotic figures, average nuclear grade, average distance between fibroblasts and lymphocytes, average distance between immunohistochemistry-positive macrophages and cancer cells, standard deviation of nuclear grade, average distance between blood vessels and tumor cells.

18. The system of claim 10 , wherein the one or more trained models include a generalized linear model, a random forest, a support vector machine, and/or a gradient boosted tree.

19. A non-transitory computer-readable storage medium storing processor-executable instructions that, when executed by at least one computer hardware processor, cause the at least one computer hardware processor to perform:

accessing a plurality of annotated pathology images associated with a group of patients in a randomized controlled clinical trial, wherein each of the plurality of annotated pathology images is associated with survival data for a respective patient, wherein each of the plurality of annotated pathology images includes at least one annotation describing a tissue characteristic category for a portion of the image, wherein the plurality of annotated pathology images includes:

a first plurality of annotated pathology images associated with a first group of patients belonging to a first treatment group of the randomized controlled clinical trial, and

a second plurality of annotated pathology images associated with a second group of patients belonging to a second treatment group of the randomized controlled clinical trial;

training one or more models based on the survival data and the plurality of annotated pathology images, wherein the one or more trained models include a first plurality of features based in part on the first plurality of annotated pathology images and a second plurality of features based in part on the second plurality of annotated pathology images; and

storing the one or more trained models on at least one storage device.

20. The non-transitory computer-readable storage medium of claim 19 , wherein the processor-executable instructions further cause the at least one computer hardware processor to perform:

processing, using the one or more trained models, at least the first plurality of features to predict survival data for patients in the first group of patients; and

processing, using the one or more trained models, at least the second plurality of features to predict survival data for patients in the second group of patients.