Computing platform for establishing referrals
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a computing platform that identifies information about a trial program, where the information is related to healthcare data included in datasets, and identifies an investigator based on the information about the trial program. A data analytics model of the platform generates an initial provider score for each provider in a group of providers based on analysis of the information. The analyzed information of the datasets includes healthcare data describing interactions between patients and providers in the group and criteria for the trial program. The platform provides a request to a subset of providers using the initial provider scores. The request is an invitation to for each provider to join a referral network. The platform uses the request to establish referral connections between the trial investigator and a provider in the subset.
1. A computer-implemented method, comprising:
determining, using a predictive analytics model implemented on a hardware circuit, prospective patient referral activity of a provider based on data describing healthcare interactions between patients and the provider;
determining, based on numerical parameters computed at the hardware circuit using the predictive analytics model, weighted connections between information about a clinical trial and the data describing the healthcare interactions;
iteratively computing, by the predictive analytics model, machine-learning inferences to enhance, based on the weighted connections, a capability of the predictive analytics model to accurately predict prospective patient referral activity of different providers;
generating, using the enhanced predictive capability of the predictive analytics model, an adjusted score representing a predicted likelihood at least one of the different providers will refer candidates to a trial investigator that conducts the clinical trial;
based on the adjusted score, establishing a referral connection between the trial investigator and the provider that enables a patient referral from the provider to the trial investigator; and
generating, using the referral connection, a referral output identifying a patient for participation in the clinical trial based on data communications between the provider and the trial investigator.
2. The method of claim 1 , comprising:
generating a respective adjusted score for each provider in a listing of providers that are identified for participation in an electronic referral network.
3. The method of claim 2 , wherein generating the respective adjusted score for each provider in the listing of providers comprises:
generating the respective adjusted score based on at least one of:
a quantity of patients managed by the provider that are eligible for participation in the clinical trial;
a proximity of the provider relative to one or more of multiple trial investigators conducting the clinical trial; or
a quantity of patients managed by the provider that are shared with one or more of multiple trial investigators conducting the clinical trial.
4. The method of claim 3 , comprising:
producing, by training a neural network of a machine learning system, the predictive analytics model based on a first set of inferences determined using the neural.
5. The method of claim 4 , further comprising:
enhancing a predictive capability of the predictive analytics model based on a of machine-learning inferences computed by the machine learning system using the neural network; and
generating the respective adjusted score for each provider in the subset of providers using the enhanced prediction capability of the predictive analytics model.
6. The method of claim 5 , wherein the respective adjusted score for each provider in the subset indicates:
an increased likelihood that the provider will identify and refer, to the trial investigator, a candidate that satisfies particular criteria for participation in the clinical trial.
7. The method of claim 4 , wherein criteria for the clinical trial comprises:
inclusion criteria for identifying candidate subjects for participation in the clinical trial; and
exclusion criteria for identifying candidate subjects to be excluded from participating in the clinical trial.
8. A system, comprising:
one or more processing devices; and
one or more non-transitory machine-readable storage devices storing instructions that are executable by the one or more processing devices to cause performance of operations comprising:
determining, using scoring logic and a predictive analytics model implemented on a hardware circuit, prospective patient referral activity of a provider based on data describing healthcare interactions between patients and the provider;
determining, based on numerical parameters computed at the hardware circuit using the predictive analytics model, weighted connections between information about a clinical trial and the data describing the healthcare interactions;
iteratively computing, by the predictive analytics model, machine-learning inferences to enhance, based on the weighted connections, a capability of the predictive analytics model to accurately predict prospective patient referral activity of different providers;
generating, using the enhanced predictive capability of the predictive analytics model, an adjusted score representing a predicted likelihood at least one of the different providers will refer candidates to a trial investigator that conducts the clinical trial;
based on the adjusted score, establishing a referral connection between the trial investigator and the provider that enables a patient referral from the provider to the trial investigator; and
generating, using the referral connection, a referral output identifying a patient for participation in the clinical trial based on data communications between the provider and the trial investigator.
9. The system of claim 8 , wherein the operations comprise:
generating a respective adjusted score for each provider in a listing of providers that are identified for participation in an electronic referral network.
10. The system of claim 9 , wherein generating the respective adjusted score for each provider in the listing of providers comprises:
generating the respective adjusted score based on at least one of:
a quantity of patients managed by the provider that are eligible for participation in the clinical trial;
a proximity of the provider relative to one or more of multiple trial investigators conducting the clinical trial; or
a quantity of patients managed by the provider that are shared with one or more of multiple trial investigators conducting the clinical trial.
11. The system of claim 10 , wherein the operations comprises:
producing, by training a neural network of a machine learning system, the predictive analytics model based on a first set of inferences determined using the neural.
12. The system of claim 11 , wherein the operations further comprise:
enhancing a predictive capability of the predictive analytics model based on a set of machine-learning inferences computed by the machine learning system using the neural network; and
generating the respective adjusted score for each provider in the subset of providers using the enhanced prediction capability of the predictive analytics model.
13. The system of claim 12 , wherein the respective adjusted score for each provider in the subset indicates:
an increased likelihood that the provider will identify and refer, to the trial investigator, a candidate that satisfies particular criteria for participation in the clinical trial.
14. The system of claim 11 , wherein criteria for the clinical trial comprises:
inclusion criteria for identifying candidate subjects for participation in the clinical trial; and
exclusion criteria for identifying candidate subjects to be excluded from participating in the clinical trial.
15. One or more non-transitory machine-readable storage devices storing instructions that are executable by one or more processing devices to cause performance of operations comprising:
determining, using a predictive analytics model implemented on a hardware circuit, prospective patient referral activity of a provider based on data describing healthcare interactions between patients and the provider;
determining, based on numerical parameters computed at the hardware circuit using the predictive analytics model, weighted connections between information about a clinical trial and the data describing the healthcare interactions;
iteratively computing, by the predictive analytics model, machine-learning inferences to enhance, based on the weighted connections, a capability of the predictive analytics model to accurately predict prospective patient referral activity of different providers;
generating, using the enhanced predictive capability of the predictive analytics model, an adjusted score representing a predicted likelihood at least one of the different providers will refer candidates to a trial investigator that conducts the clinical trial;
based on the adjusted score, establishing a referral connection between the trial investigator and the provider that enables a patient referral from the provider to the trial investigator; and
generating, using the referral connection, a referral output identifying a patient for participation in the clinical trial based on data communications between the provider and the trial investigator.
16. The machine-readable storage device of claim 15 , wherein the operations comprise:
generating a respective adjusted score for each provider in a listing of providers that are identified for participation in an electronic referral network.
17. The machine-readable storage device of claim 16 , wherein generating the respective adjusted score for each provider in the listing of providers comprises:
generating the respective adjusted score based on at least one of:
a quantity of patients managed by the provider that are eligible for participation in the clinical trial;
a proximity of the provider relative to one or more of multiple trial investigators conducting the clinical trial; or
a quantity of patients managed by the provider that are shared with one or more of multiple trial investigators conducting the clinical trial.
18. The method of claim 4 , comprising:
establishing, between the trial investigator and a corresponding provider in the subset, a referral connection that enables a respective patient referral from the corresponding provider to the trial investigator.
19. The method of claim 4 , wherein the predictive analytics model represents a dynamic recommendation engine.
20. The system of claim 11 , wherein the predictive analytics model represents a dynamic recommendation engine.