Machine-learning based query construction and pattern identification for amyotrophic lateral sclerosis
A method, computer program product, and system identifying a probability of a medical condition in a patient. The method includes a processor obtaining data set(s) related to a patient population diagnosed with a medical condition and based on a frequency of features in the data set(s), identifying common features and weighting the common features based on frequency of occurrence in the data set(s) to generate mutual information. The processor generates pattern(s) including a portion of the common features to generate a machine learning algorithm(s). The processor compiles a training set of data to use to tune the machine learning algorithm(s). The processor dynamically adjusts common features in the pattern(s) such that the machine learning algorithm(s) can distinguish patient data indicating the medical condition from patient data not indicating the medical condition. The processor applies the machine learning algorithm(s) to data related to the undiagnosed patient, to determine the probability.
1. A computer-implemented method, comprising:
obtaining, by one or more processors in a distributed computing environment, one or more machine-readable data sets related to a patient population diagnosed with an orphan disease from one or more databases;
based on a frequency of features in the one or more data sets, identifying, by the one or more processors, common features in the one or more data sets and weighting the common features based on frequency of occurrence in the one or more data sets, wherein the common features comprise mutual information;
generating, by the one or more processors, one or more patterns comprising a portion of the common features, wherein the portion of the features comprises a smallest number of the common features that is a largest number of differentiating characteristics of the patient population diagnosed with the orphan disease, wherein the portion of the common features is identified based on comparing members of a general population, wherein the general population comprises the patient population and an additional population, wherein the patient population comprises patients diagnosed with the orphan disease and the additional population comprises patients not diagnosed with the orphan disease, wherein a portion of the patient population diagnosed with the medical condition has the differentiating characteristics, and wherein the portion comprises fewer patients than the patients comprising the patient population;
generating, by the one or more processors, one or more machine learning algorithms based on the one or more patterns, the one or more machine learning algorithms to identify presence or absence of the given orphan disease in an undiagnosed patient based on absence or presence of features comprising the one or more patterns in data related to the undiagnosed patient;
utilizing, by the one or more processors, statistical sampling to compile a training set of data, wherein the training set comprises data from the one or more data sets related to the patient population diagnosed with the orphan disease and at least one additional data set comprising data related to a population without the orphan disease, wherein the statistical sampling comprises proportionally selecting representative electronic medical records from two data sources, the two data sources comprising: one or more data sets related to the patient population diagnosed with the orphan disease, and at least one additional data set comprising data related to the population without the orphan disease, wherein the representative electronic medical records from the data from the one or more data sets related to the patient population diagnosed with the orphan disease comprise a target population, and wherein the representative electronic medical records from the at least one additional data set comprising data related to the population without the orphan disease comprise a control population, and wherein utilizing the statistical sampling comprises formulating and obtaining queries based on the data set and processing and responding to the queries, the processing comprising, for each query:
evaluating, by the one or more processors, the query to determine if a prospective response to the query is a single value pulled from a single data set;
based on determining that the prospective response to the query is the single value pulled from the single data set assigning, by the one or more processors, the query to a given computing resource in the distributed computing environment; and
based on determining that the prospective response to the query is not the single value pulled from the single data set, distributing, by the one or more processors, the query over a group of computing resources of the distributed computing environment to maximize efficiency, wherein the distributing comprises assigning each computing resource of the group of computing resources a portion of the query to execute in parallel with at least one other computing resource of the group of computing resources executing another portion of the query;
tuning, by the one or more processors, the one or more machine learning algorithms by applying the one or more machine learning algorithms to the training set of data;
dynamically adjusting, by the one or more processors, the common features comprising the one or more patterns to improve accuracy such that the one or more machine learning algorithms can distinguish patient data indicating the orphan disease from patient data that does not indicate the orphan disease, wherein the dynamically adjusting narrows the target population; and
determining, by the one or more processors, based on applying the one or more machine learning algorithms to data related to the undiagnosed patient, a probability, wherein the probability is a numerical value indicating a percentage of commonality between the data related to the undiagnosed patient and the one or more patterns, wherein the probability indicates a probability that the undiagnosed patient will be diagnosed with the orphan disease in the future.
2. The method of claim 1 , wherein the generating the one or more patterns comprises:
ranking, by the one or more processors, the common features based on the weighting; and
retaining, by the one or more processors, the portion of the common features wherein the portion comprises common features of a pre-defined weight, wherein the portion comprises the one or more patterns.
3. The method of claim 1 , wherein the identifying of the common features is also based on a commonality in timestamps associated with the occurrence of the common features in the data set.
4. The method of claim 1 , wherein the mutual information comprises features from a plurality of feature categories and wherein each pattern of the one or more patterns comprising a portion of the common features comprises features in one feature category of the plurality of feature categories.
5. The method of claim 4 , wherein the orphan disease is amyotrophic lateral sclerosis and the features are selected from the group consisting of: connective tissue diseases, nervous system disorders, joint disorders, hereditary and degenerative nervous system conditions, multiple sclerosis, malaise and fatigue, and gastrointestinal disorders.
6. The method of claim 4 , wherein the one feature category is selected from the group consisting of: diagnosis codes, procedures, drug treatments, providers, and locations.
7. The method of claim 1 , wherein the one or more machine learning algorithms comprise a linear Support Vector Machines classification algorithm.
8. The method of claim 1 , wherein the one or more machine learning algorithms comprise at least two machine learning algorithms and wherein the tuning further comprises:
compiling results of the tuning of each of the at least two machine learning algorithms and utilizing ensemble learning to consolidate portions of the at least two machine learning algorithms into a single machine learning algorithm.
9. The method of claim 1 , the tuning further comprising:
associating, by the one or more processors, based on applying the one or more machine learning algorithms to the training set of test data, probabilities to a portion of the records in the training set of test data, wherein the probabilities reflect a likelihood of presence of the orphan disease for each record training set of test data; and
completing the dynamically adjusting of the common features when the probabilities are within a pre-defined accuracy threshold.
10. The method of claim 1 , wherein the orphan disease is amyotrophic lateral sclerosis.
11. The method of claim 1 , wherein the determining the probability:
obtaining, by the one or more processors, from a computing resource, electronic medical records for the undiagnosed patient for a defined temporal period, wherein the electronic medical records comprise electronic contact information for a healthcare provider to the undiagnosed patient;
applying, by the one or more processors, the one or more machine learning algorithms to the electronic medical records;
determining, by the one or more processors, based on the applying, if the probability is within a predetermined range; and
based on determining that the probability exceeds a predetermined threshold, electronically alerting, in real time, the healthcare provider to the undiagnosed patient of the probability.
12. The method of claim 11 , further comprising:
retaining, by the one or more processors, in a memory resource communicatively coupled to the one or more processors, the one or more patterns;
obtaining, by the one or more processors, an indication regarding accuracy of the probability; and
updating, by the one or more processors, the one or more patterns based on the indication.
13. The method of claim 11 , wherein the probability indicates a probability that the undiagnosed patient has the orphan disease.
14. A computer program product comprising:
a non-transitory computer readable storage medium readable by one or more processors in a distributed computing environment, and storing instructions for execution by the one or more processors for performing a method comprising:
obtaining, by the one or more processors in a distributed computing environment, one or more machine-readable data sets related to a patient population diagnosed with an orphan disease from one or more databases;
based on a frequency of features in the one or more data sets, identifying, by the one or more processors, common features in the one or more data sets and weighting the common features based on frequency of occurrence in the one or more data sets, wherein the common features comprise mutual information;
generating, by the one or more processors, one or more patterns comprising a portion of the common features, wherein the portion of the features comprises a smallest number of the common features that is a largest number of differentiating characteristics of the patient population diagnosed with the orphan disease, wherein the portion of the common features is identified based on comparing members of a general population, wherein the general population comprises the patient population and an additional population, wherein the patient population comprises patients diagnosed with the orphan disease and the additional population comprises patients not diagnosed with the orphan disease, wherein a portion of the patient population diagnosed with the medical condition has the differentiating characteristics, and wherein the portion comprises fewer patients than the patients comprising the patient population;
generating, by the one or more processors, one or more machine learning algorithms based on the one or more patterns, the one or more machine learning algorithms to identify presence or absence of the given orphan disease in an undiagnosed patient based on absence or presence of features comprising the one or more patterns in data related to the undiagnosed patient;
utilizing, by the one or more processors, statistical sampling to compile a training set of data, wherein the training set comprises data from the one or more data sets related to the patient population diagnosed with the orphan disease and at least one additional data set comprising data related to a population without the orphan disease, wherein the statistical sampling comprises proportionally selecting representative electronic medical records from two data sources, the two data sources comprising: one or more data sets related to the patient population diagnosed with the orphan disease, and at least one additional data set comprising data related to the population without the orphan disease, wherein the representative electronic medical records from the data from the one or more data sets related to the patient population diagnosed with the orphan disease comprise a target population, and wherein the representative electronic medical records from the at least one additional data set comprising data related to the population without the orphan disease comprise a control population, and wherein utilizing the statistical sampling comprises formulating and obtaining queries based on the data set and processing and responding to the queries, the processing comprising, for each query:
evaluating, by the one or more processors, the query to determine if a prospective response to the query is a single value pulled from a single data set;
based on determining that the prospective response to the query is the single value pulled from the single data set, assigning, by the one or more processors, the query to a given computing resource in the distributed computing environment; and
based on determining that the prospective response to the query is not the single value pulled from the single data set, distributing, by the one or more processors, the query over a group of computing resources of the distributed computing environment to maximize efficiency, wherein the distributing comprises assigning each computing resource of the group of computing resources a portion of the query to execute in parallel with at least one other computing resource of the group of computing resources executing another portion of the query;
tuning, by the one or more processors, the one or more machine learning algorithms by applying the one or more machine learning algorithms to the training set of data;
dynamically adjusting, by the one or more processors, the common features comprising the one or more patterns to improve accuracy such that the one or more machine learning algorithms can distinguish patient data indicating the orphan disease from patient data that does not indicate the orphan disease, wherein the dynamically adjusting narrows the target population; and
determining, by the one or more processors, based on applying the one or more machine learning algorithms to data related to the undiagnosed patient, a probability, wherein the probability is a numerical value indicating a percentage of commonality between the data related to the undiagnosed patient and the one or more patterns, wherein the probability indicates a probability that the undiagnosed patient will be diagnosed with the orphan disease in the future.
15. The computer program product of claim 14 , wherein the generating the one or more patterns comprises:
ranking, by the one or more processors, the common features based on the weighting; and
retaining, by the one or more processors, the portion of the common features wherein the portion comprises common features of a pre-defined weight, wherein the portion comprises the one or more patterns.
16. The computer program product of claim 14 , wherein the mutual information comprises features from a plurality of feature categories and wherein each pattern of the one or more patterns comprising a portion of the common features comprises features in one feature category of the plurality of feature categories.
17. The computer program product of claim 14 , wherein the one feature category is selected from the group consisting of: diagnosis codes, procedures, drug treatments, and locations.
18. The computer program product of claim 14 , wherein the machine learning algorithm comprises a linear Support Vector Machines classification algorithm.
19. A system comprising:
one or more memory;
one or more processors in communication with the memory; and
program instructions executable by the one or more processors in a distributed computed environment via the one or more memory to perform a method, the method comprising:
obtaining, by the one or more processors in a distributed computing environment, one or more machine-readable data sets related to a patient population diagnosed with an orphan disease from one or more databases;
based on a frequency of features in the one or more data sets, identifying, by the one or more processors, common features in the one or more data sets and weighting the common features based on frequency of occurrence in the one or more data sets, wherein the common features comprise mutual information;
generating, by the one or more processors, one or more patterns comprising a portion of the common features, wherein the portion of the features comprises a smallest number of the common features that is a largest number of differentiating characteristics of the patient population diagnosed with the orphan disease, wherein the portion of the common features is identified based on comparing members of a general population, wherein the general population comprises the patient population and an additional population, wherein the patient population comprises patients diagnosed with the orphan disease and the additional population comprises patients not diagnosed with the orphan disease, wherein a portion of the patient population diagnosed with the medical condition has the differentiating characteristics, and wherein the portion comprises fewer patients than the patients comprising the patient population;
generating, by the one or more processors, one or more machine learning algorithms based on the one or more patterns, the one or more machine learning algorithms to identify presence or absence of the given orphan disease in an undiagnosed patient based on absence or presence of features comprising the one or more patterns in data related to the undiagnosed patient;
utilizing, by the one or more processors, statistical sampling to compile a training set of data, wherein the training set comprises data from the one or more data sets related to the patient population diagnosed with the orphan disease and at least one additional data set comprising data related to a population without the orphan disease, wherein the statistical sampling comprises proportionally selecting representative electronic medical records from two data sources, the two data sources comprising: one or more data sets related to the patient population diagnosed with the orphan disease, and at least one additional data set comprising data related to the population without the orphan disease, wherein the representative electronic medical records from the data from the one or more data sets related to the patient population diagnosed with the orphan disease comprise a target population, and wherein the representative electronic medical records from the at least one additional data set comprising data related to the population without the orphan disease comprise a control population, and wherein utilizing the statistical sampling comprises formulating and obtaining queries based on the data set and processing and responding to the queries, the processing comprising, for each query:
evaluating, by the one or more processors, the query to determine if a prospective response to the query is a single value pulled from a single data set;
based on determining that the prospective response to the query is the single value pulled from the single data set, assigning, by the one or more processors, the query to a given computing resource in the distributed computing environment; and
based on determining that the prospective response to the query is not the single value pulled from the single data set, distributing, by the one or more processors, the query over a group of computing resources of the distributed computing environment to maximize efficiency, wherein the distributing comprises assigning each computing resource of the group of computing resources a portion of the query to execute in parallel with at least one other computing resource of the group of computing resources executing another portion of the query;
tuning, by the one or more processors, the one or more machine learning algorithms by applying the one or more machine learning algorithms to the training set of data;
dynamically adjusting, by the one or more processors, the common features comprising the one or more patterns to improve accuracy such that the one or more machine learning algorithms can distinguish patient data indicating the orphan disease from patient data that does not indicate the orphan disease, wherein the dynamically adjusting narrows the target population; and
determining, by the one or more processors, based on applying the one or more machine learning algorithms to data related to the undiagnosed patient, a probability, wherein the probability is a numerical value indicating a percentage of commonality between the data related to the undiagnosed patient and the one or more patterns, wherein the probability indicates a probability that the undiagnosed patient will be diagnosed with the orphan disease in the future.