Method and system for processing large amounts of real world evidence
A computer-based real-world evidence (CRWE) solution that can handle disparities in real-world data (RWD) that might otherwise not be combinable or that might originate from disparate or heterogeneous sources. The CRWE solution is designed such that it can build up RWD data from the ground up (for example, from the atomic level) into a canonical relational database by converting or linking the raw RWD data to its canonical versions such that reliable canonical answers can be mined from large datasets and consistently provided in response to queries to the solution for an answer. The CRWE solution is designed to gather and analyze large amounts of RWD data from heterogeneous, multi-national, and unverifiable data sources, and provide canonical results that are constituently reliable and can expose, for example, clinically-significant correlations between medical products or treatments and outcomes.
1 . A computer-implemented method for building a relational database of clinical information concerning medical treatment of patients, the method comprising:
maintaining, by a processor, within a database,
one or more lists of canonical questions and canonical answers, wherein each canonical answer is associated with one or more of the canonical questions, and
a hierarchy of protocols each protocol comprising a respective set of canonical questions, and wherein the hierarchy of protocols includes a first circle protocol associated with a first circle and a first set of canonical questions, and a second circle protocol associated with a second circle and a second set of canonical questions,
a first circle associated with the first circle protocol, a first group of users and patient cases enrolled in the first circle by any of the first group of users, and
a second circle associated with the second circle protocol, a second group of users and patient cases enrolled in the second circle by any of the second group of users;
receiving, by a processor, real-world data, wherein the real-world data includes questions and answers obtained for patient cases enrolled in the first circle by a first user among the first group of users;
mapping, by the processor, the received questions to canonical questions in the first set of canonical questions, and converting the received answers into canonical answers based on the mapping;
storing, by the processor, at least the converted canonical answers in a data structure, wherein each converted canonical answer is stored in the data structure in association with a corresponding canonical question, the first circle protocol, the first user and a respective patient case; and
selectively providing, by the processor, a second user associated with the first circle access to canonical answers from the data structure according to data sharing rules defined by the first circle protocol and the first user.
2 . The method of claim 1 , further comprising: storing, by the processor, in the data structure, the real-world data corresponding to the converted canonical answers.
3 . The method of claim 2 ,
wherein the data sharing rules provide the first user full access to any data stored in the data structure and associated with the first user, and
wherein the data sharing rules provide the second user limited access to data stored in the data structure as defined by the first user and the first circle protocol.
4 . The method of claim 1 , wherein the step of selectively providing the second user access comprises:
receiving, by the processor, a query input by the second user including information identifying a canonical question from among the first set of canonical questions;
retrieving, by the processor according to the data sharing rules, one or more canonical answers in the data structure that corresponds to the query, and
send, to a computing device of the second user for display, at least one of:
the retrieved one or more canonical answers, and
the real-world data corresponding to the retrieved one or more canonical answers.
5 . The method of claim 4 , further comprising,
removing, by the processor according to the data sharing rules, personally identifiable information from the retrieved one or more canonical answers that are sent to the computing device of the second user.
6 . The method of claim 1 , the hierarchy of protocols further comprising a first circle sub-protocol, wherein the circle sub-protocol is a child protocol of the first circle protocol in the hierarchy, wherein the first circle sub-protocol comprises a third set of canonical questions including at least a subset of the first set of canonical questions and optionally one or more additional canonical questions.
7 . The method of claim 1 , wherein, according to the data sharing rules, canonical answers to a canonical question common to the first circle protocol and the second circle protocol is accessible to users within the first and second groups of users.
8 . A system for building a relational database containing clinical information concerning medical treatment of patients, the system comprising:
a database including a list of canonical questions and canonical answers, wherein each canonical answer is associated with one or more of the canonical questions, and
a circle processor arranged to create and manage access to circles by respective groups of one or more users, wherein the circle processor is configured to associate canonical questions and corresponding canonical answers in the list with one or more circles and one or more protocols within a hierarchy of protocols stored within the database,
wherein the hierarchy of protocols includes a first circle protocol associated with a first circle and a first set of canonical questions, and a second circle protocol associated with a second circle and a second set of canonical questions,
the circles comprising:
a first circle associated with the first circle protocol, a first group of users and patient cases enrolled in the first circle by any of the first group of users, and
a second circle associated with the second circle protocol, a second group of users and patient cases enrolled in the second circle by any of the second group of users; and
a real-world data processor, configured to:
receive real-world data, wherein the real-world data includes questions and answers obtained for patient cases enrolled in the first circle by a first user among the first group of users,
map the received questions to canonical questions in the first set of canonical questions and convert the received answers into canonical answers based on the mapping, and
store at least the converted canonical answers in a data structure, wherein each converted canonical answer is stored in the data structure in association with a corresponding canonical question, the first circle protocol, the first user and a respective patient case, and
wherein the circle processor is further configured to selectively provide a second user associated with the first circle access to canonical answers from the data structure according to data sharing rules defined by the first circle protocol and the first user.
9 . The system of claim 8 , wherein the real-world data processor is configured to store the real-world data corresponding to the converted canonical answers in the data structure.
10 . The system of claim 8 ,
wherein the data sharing rules provide the first user full access to any data stored in the data structure and associated with the first user, and
wherein the data sharing rules provide the second user limited access to data stored in the data structure as defined by the first user and the first circle protocol.
11 . The system of claim 8 , wherein the circle processor is configured to selectively provide the second user access to canonical answers from the data structure by:
receiving a query input by the second user including information identifying a canonical question from among the first set of canonical questions,
executing the query against the data structure such that one or more canonical answers in the data structure that corresponds to the query are returned according to the data sharing rules and sent to a computing device of the second user for display.
12 . The system of claim 11 , wherein personally identifiable information is removed from the retrieved one or more canonical answers sent to the computing device of the second user.
13 . The system of claim 8 , wherein the hierarchy of protocols further comprise a first circle sub-protocol, wherein the circle sub-protocol is a child protocol of the first circle protocol in the hierarchy, wherein the first circle sub-protocol comprises a third set of canonical questions including at least a subset of the first set of canonical questions and optionally one or more additional canonical questions.
14 . The system of claim 8 , wherein, according to the data sharing rules, canonical answers to a canonical question common to the first circle protocol and the second circle protocol are accessible to users within the first and second groups of users.
15 . The system of claim 8 , wherein one or more of the database, the circle processor, the real-world data processor and the data structure are distributed across one or more computing resources.