Methods for determining treatment for cancer patients
Methods for determining treatments for cancer patients are disclosed.
1. A computing system comprising:
computer memory configured to store model training data, wherein the model training data involves a first set of cancer patients that underwent cancer treatments, wherein the model training data includes and associates (i) input of results from 20 or more laboratory tests conducted on the first set of cancer patients and tumor types of the first set of cancer patients with (ii) output of whether individuals from the first set of cancer patients died within a threshold number of weeks from initiation of the cancer treatments, wherein the tumor types include two or more of non-small cell lung cancer, urothelial carcinoma, squamous cell carcinoma of head and neck, gastric cancer, renal cell carcinoma, or Hodgkin's lymphoma; and
one or more processors in communication with the computer memory and configured to execute program instructions to:
for each respective laboratory test, train a respective variation of a gradient boosting machine learning model on the 20 or more laboratory tests with the respective laboratory test removed;
determine predictive values of each of the 20 or more laboratory tests by comparing accuracies of the variations of the gradient boosting machine learning model;
select a subset of laboratory tests from the 20 or more laboratory tests with the highest predictive values for at least some of the tumor types; and
train a final gradient boosting machine learning model on the subset of laboratory tests, wherein the final gradient boosting machine learning model predicts whether a further cancer patient dies within the threshold number of weeks based on results from the subset of laboratory tests as conducted on the further cancer patient and a tumor type of the further cancer patient, and wherein predicting whether the further cancer patient dies within the threshold number of weeks comprises:
determining a probability that the further cancer patient dies within the threshold number of weeks, and
based on the probability and a cutoff value, placing the further cancer patient into either a high risk of death category or a low risk of death category, wherein the cutoff value is selected so that there is no more than a false positive rate of 5-20% when predicting whether the first set of cancer patients die within the threshold number of weeks.
2. The computing system of claim 1 , wherein results of the subset of laboratory tests include: a neutrophil to lymphocyte ratio, a neutrophil level, an albumin level, a lactate dehydrogenase level, an aspartate amino transferase level, and a gamma-glutamyl transferase level.
3. The computing system of claim 1 , wherein cancer patients placed in the high risk of death category are excluded from a clinical trial for treatment of cancer, and wherein cancer patients placed in the low risk of death category are included in the clinical trial for treatment of cancer.
4. The computing system of claim 1 , wherein the computer memory is further configured to store model tuning data, wherein the model tuning data involves a second set of cancer patients that underwent cancer treatments, wherein the model tuning data associates (i) results from the laboratory tests as conducted on the second set of cancer patients and tumor types of the second set of cancer patients with (ii) whether the second set of cancer patients died within the threshold number of weeks from initiation of the cancer treatments, and
wherein the one or more processors are further configured to execute further program instructions to:
generate two or more further variations of the gradient boosting machine learning model by training a sequential series of decision trees for each further variation with different sets of hyperparameters;
apply the further variations to the model training data and the model tuning data; and
select, as the gradient boosting machine learning model, a particular variation from the further variations that provides predictions of whether the first set of cancer patients and the second set of cancer patients die within the threshold number of weeks from initiation of the cancer treatments within a threshold degree of accuracy.
5. The computing system of claim 4 , wherein the hyperparameters include one or more of: maximum depth of the decision trees set to 2, 3, 4, 5, or 6, minimum loss reduction required to split a node in the decision trees set to 0, 1, 2, 3, or 4, minimum sum of weights of all observations required in a child node in the decision trees set between 3.0 and 7.0, fraction of input parameters to be randomly sampled for each of the decision trees set between 0.7 and 1.0, fraction of observations to be randomly sampled for each of the decision trees set between 0.4 and 0.8, number of decision trees in the sequential series of decision trees set between 10 and 25.
6. A computer-implemented method comprising:
obtaining model training data, wherein the model training data involves a first set of cancer patients that underwent cancer treatments, wherein the model training data includes and associates (i) input of results from 20 or more laboratory tests conducted on the first set of cancer patients and tumor types of the first set of cancer patients with (ii) output of whether individuals from the first set of cancer patients died within a threshold number of weeks from initiation of the cancer treatments, wherein the tumor types include two or more of non-small cell lung cancer, urothelial carcinoma, squamous cell carcinoma of head and neck, gastric cancer, renal cell carcinoma, or Hodgkin's lymphoma;
for each respective laboratory test, training a respective variation of a gradient boosting machine learning model on the 20 or more laboratory tests with the respective laboratory test removed;
determining predictive values of each of the 20 or more laboratory tests by comparing accuracies of the variations of the gradient boosting machine learning model;
selecting a subset of laboratory tests from the 20 or more laboratory tests with the highest predictive values for at least some of the tumor types; and
training a final gradient boosting machine learning model on the subset of laboratory tests, wherein the final gradient boosting machine learning model predicts whether a further cancer patient dies within the threshold number of weeks based on results from the subset of laboratory tests as conducted on the further cancer patient and a tumor type of the further cancer patient, and wherein predicting whether the further cancer patient dies within the threshold number of weeks comprises:
determining a probability that the further cancer patient dies within the threshold number of weeks, and
based on the probability and a cutoff value, placing the further cancer patient into either a high risk of death category or a low risk of death category, wherein the cutoff value is selected so that there is no more than a false positive rate of 5-20% when predicting whether the first set of cancer patients die within the threshold number of weeks.
7. The computer-implemented method of claim 6 , wherein result of the subset of laboratory tests include a neutrophil to lymphocyte ratio, a neutrophil level, an albumin level, a lactate dehydrogenase level, an aspartate amino transferase level, and a gamma-glutamyl transferase level.
8. The computer-implemented method of claim 6 , wherein cancer patients placed in the high risk of death category are excluded from a clinical trial for treatment of cancer, and wherein cancer patients placed in the low risk of death category are included in the clinical trial for treatment of cancer.
9. A computer-implemented method comprising:
obtaining a gradient boosting machine learning model, wherein the gradient boosting machine learning model was trained on model training data, wherein the model training data involves a first set of cancer patients that underwent cancer treatments, wherein the model training data includes and associates (i) input of results from 20 or more laboratory tests conducted on the first set of cancer patients and tumor types of the first set of cancer patients with (ii) output of whether individuals from the first set of cancer patients died within a threshold number of weeks from initiation of the cancer treatments, wherein training the gradient boosting machine learning model involved: (i) for each respective laboratory test, training a respective variation of a gradient boosting machine learning model on the 20 or more laboratory tests with the respective laboratory test removed, (ii) determining predictive values of each of the 20 or more laboratory tests by comparing accuracies of the variations of the gradient boosting machine learning model, (iii) selecting a subset of laboratory tests from the 20 or more laboratory tests with the highest predictive values for at least some of the tumor types, and (iv) training a final gradient boosting machine learning model on the subset of laboratory tests, wherein the tumor types include two or more of non-small cell lung cancer, urothelial carcinoma, squamous cell carcinoma of head and neck, gastric cancer, renal cell carcinoma, or Hodgkin's lymphoma;
obtaining results from the subset of laboratory tests as conducted on a further cancer patient;
obtaining a tumor type of the further cancer patient;
applying the final gradient boosting machine learning model to results from the subset of laboratory tests as conducted on the further cancer patient and the tumor type of the further cancer patient; and
receiving, from the final gradient boosting machine learning model, a prediction of whether the further cancer patient dies within the threshold number of weeks, wherein predicting whether the further cancer patient dies within the threshold number of weeks comprises:
determining a probability that the further cancer patient dies within the threshold number of weeks, and
based on the probability and a cutoff value, placing the further cancer patient into either a high risk of death category or a low risk of death category, wherein the cutoff value is selected so that there is no more than a false positive rate of 5-20% when predicting whether the first set of cancer patients die within the threshold number of weeks.
10. The computer-implemented method of claim 9 , wherein results of the subset of laboratory tests include a neutrophil to lymphocyte ratio, a neutrophil level, an albumin level, a lactate dehydrogenase level, an aspartate amino transferase level, and a gamma-glutamyl transferase level.
11. The computer-implemented method of claim 9 , wherein cancer patients placed in the high risk of death category are excluded from a clinical trial for treatment of cancer, and wherein cancer patients placed in the low risk of death category are included in the clinical trial for treatment of cancer.