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

1 . A method, comprising:

determining whether a trained model accurately identifies a subset of prostate cancer patients that is likely to benefit from an experimental treatment compared to a standard treatment or a control treatment, wherein the determining comprises:

processing, using the trained model, a first plurality of values for a plurality of features extracted from a first plurality of annotated prostate images associated with a first group of prostate cancer patients, to predict survival data for prostate cancer patients in the first group of prostate cancer patients, wherein the first group of prostate cancer patients belongs to an experimental treatment group of a randomized controlled clinical trial;

processing, using the trained model, a second plurality of values for the plurality of features extracted from a second plurality of annotated prostate images associated with a second group of prostate cancer patients, to predict survival data for prostate cancer patients in the second group, wherein the second group of prostate cancer patients belongs to a control treatment group of the randomized controlled clinical trial; and

determining whether the trained model accurately identifies a subset of prostate cancer patients that is likely to benefit from the experimental treatment compared to the standard treatment or the control treatment based on the predicted survival data for the prostate cancer patients in the first group and the predicted survival data for the prostate cancer patients in the second group.

2 . The method of claim 1 , wherein determining whether the trained model accurately identifies the subset of prostate cancer patients that is likely to benefit from the experimental treatment compared to the standard treatment or the control treatment further comprises performing subset survival analyses using respective predicted survival data from the experimental treatment group and the control treatment group.

3 . The method of claim 1 , further comprising:

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

4 . The method of claim 3 , further comprising:

selecting, based on the predicted survival data for the prostate cancer patients in the first group, a subset of the plurality of features indicative of the subset of the first group of prostate cancer patients that responded to the experimental treatment.

5 . The method of claim 1 , further comprising:

processing, using the trained model, a third plurality of values for the plurality of features extracted from a third plurality of annotated pathology images associated with a third group of prostate cancer patients, to predict survival data for the prostate cancer patients in the third group, wherein the third group belongs to a treatment group in another clinical trial; and

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

6 . The method of claim 1 , wherein the 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.

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

8 . A 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:

determining whether a trained model accurately identifies a subset of prostate cancer patients that is likely to benefit from an experimental treatment compared to a standard treatment or a control treatment, wherein the determining comprises:

processing, using the trained model, a first plurality of values for a plurality of features extracted from a first plurality of annotated prostate images associated with a first group of prostate cancer patients, to predict survival data for prostate cancer patients in the first group of prostate cancer patients, wherein the first group of prostate cancer patients belongs to an experimental treatment group of a randomized controlled clinical trial;

processing, using the trained model, a second plurality of values for the plurality of features extracted from a second plurality of annotated prostate images associated with a second group of prostate cancer patients, to predict survival data for prostate cancer patients in the second group, wherein the second group of prostate cancer patients belongs to a control treatment group of the randomized controlled clinical trial; and

determining whether the trained model accurately identifies a subset of prostate cancer patients that is likely to benefit from the experimental treatment compared to the standard treatment or the control treatment based on the predicted survival data for the prostate cancer patients in the first group and the predicted survival data for the prostate cancer patients in the second group.

9 . The system of claim 8 , wherein determining whether the trained model accurately identifies the subset of prostate cancer patients that is likely to benefit from the experimental treatment compared to the standard treatment or the control treatment further comprises performing subset survival analyses using respective predicted survival data from the experimental treatment group and the control treatment group.

10 . The system of claim 8 , further comprising:

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

11 . The system of claim 10 , further comprising:

selecting, based on the predicted survival data for the prostate cancer patients in the first group, a subset of the plurality of features indicative of the subset of the first group of prostate cancer patients that responded to the experimental treatment.

12 . The system of claim 8 , further comprising:

processing, using the trained model, a third plurality of values for the plurality of features extracted from a third plurality of annotated pathology images associated with a third group of prostate cancer patients, to predict survival data for the prostate cancer patients in the third group, wherein the third group belongs to a treatment group in another clinical trial; and

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

13 . The system of claim 8 , wherein the 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.

14 . The system of claim 8 , wherein the trained model includes one or more of a generalized linear model, a random forest, a support vector machine, and a gradient boosted tree.

15 . 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:

determining whether a trained model accurately identifies a subset of prostate cancer patients that is likely to benefit from an experimental treatment compared to a standard treatment or a control treatment, wherein the determining comprises:

processing, using the trained model, a first plurality of values for a plurality of features extracted from a first plurality of annotated prostate images associated with a first group of prostate cancer patients, to predict survival data for prostate cancer patients in the first group of prostate cancer patients, wherein the first group of prostate cancer patients belongs to an experimental treatment group of a randomized controlled clinical trial;

processing, using the trained model, a second plurality of values for the plurality of features extracted from a second plurality of annotated prostate images associated with a second group of prostate cancer patients, to predict survival data for prostate cancer patients in the second group, wherein the second group of prostate cancer patients belongs to a control treatment group of the randomized controlled clinical trial; and

determining whether the trained model accurately identifies a subset of prostate cancer patients that is likely to benefit from the experimental treatment compared to the standard treatment or the control treatment based on the predicted survival data for the prostate cancer patients in the first group and the predicted survival data for the prostate cancer patients in the second group.

16 . The non-transitory computer-readable storage medium of claim 15 , wherein determining whether the trained model accurately identifies the subset of prostate cancer patients that is likely to benefit from the experimental treatment compared to the standard treatment or the control treatment further comprises performing subset survival analyses using respective predicted survival data from the experimental treatment group and the control treatment group.

17 . The non-transitory computer-readable storage medium of claim 15 , further comprising:

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

18 . The non-transitory computer-readable storage medium of claim 17 , further comprising:

selecting, based on the predicted survival data for the prostate cancer patients in the first group, a subset of the plurality of features indicative of the subset of the first group of prostate cancer patients that responded to the experimental treatment.

19 . The non-transitory computer-readable storage medium of claim 15 , further comprising:

processing, using the trained model, a third plurality of values for the plurality of features extracted from a third plurality of annotated pathology images associated with a third group of prostate cancer patients, to predict survival data for the prostate cancer patients in the third group, wherein the third group belongs to a treatment group in another clinical trial; and

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

20 . The non-transitory computer-readable storage medium of claim 15 , wherein the 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.