Dynamically determining risk of clinical condition
Systems, methods and computer-readable media are provided for facilitating clinical decision support and managing patient population health by health-related entities including caregivers, health care administrators, insurance providers, and patients. Embodiments of the invention provide decision support services including providing timely contextual patient information including condition risks, risk factors and relevant clinical information that are dynamically updatable; imputing missing patient information; dynamically generating assessments for obtaining additional patient information based on context; data-mining and information discovery services including discovering new knowledge; identifying or evaluating treatments or sequences of patient care actions and behaviors, and providing recommendations based on this; intelligent, adaptive decision support services including identifying critical junctures in patient care processes, such as points in time that warrant close attention by caregivers; near-real time querying across diverse health records data sources, which may use diverse clinical nomenclatures and ontologies; improved natural language processing services; and other decision support services.
1. A computer system having one or more hardware processors configured to facilitate a plurality of operations, the operations comprising:
receiving a portion of patient health data associated with a patient, the portion of patient health data including a first set of clinical concepts encoded in a first clinical nomenclature;
determining, from the portion of patient health data and based at least on an identification of a location in a traversable state machine via a finite state machine agent or solver, a current state of the patient;
based on the determined current state of the patient and based further on the portion of patient health data, performing via the one or more hardware processors:
(a) utilizing the portion of patient health data and information corresponding to one or both of the location in the traversable state machine and a state in the traversable state machine to access a library of clinical condition programs that are encoded in the second nomenclature and stored at one or more physical data stores distributed across multiple physical locations;
(b) based on accessing the library and based further on identifying at least one clinical condition program in the library, utilizing one or more distributed electronic adaptive agents to dynamically construct a clinical condition computer program routine for the patient based on the determined current state of the patient; and
(c) executing the clinical condition computer program routine to determine a set of clinical concepts relevant to the determined current state of the patient, the set of clinical concepts including at least one clinical concept encoded in the second clinical nomenclature;
converting, via the one or more hardware processors, the at least one clinical concept encoded in the second clinical nomenclature from the second clinical nomenclature to the first clinical nomenclature; and
presenting, via the one or more hardware processors and via an electronic user interface, information associated with the at least one clinical concept in the first clinical nomenclature after the at least one clinical concept encoded in the second clinical nomenclature is converted from the second clinical nomenclature to the first clinical nomenclature.
2. The computer system of claim 1 , wherein the clinical condition program is implemented by an autonomous software agent, and herein the operations further comprise causing the electronic user interface to display a condition risk area responsive to selection of a clinical condition of a set of one or more clinical conditions, the condition risk area comprising:
a computed likelihood of the clinical condition;
a set of risk factors associated with the clinical condition; and
a clinical value associated with at least a portion of the set of risk factors.
3. The computer system of claim 2 , wherein: (a) the clinical value comprises a patient-specific value corresponding to a clinical variable associated with the portion of patient health data, (b) a presented computed likelihood of the clinical condition and the set of risk factors are dynamically responsive to changes in the clinical condition computer program routine, and (c) the operations further comprise: (i) displaying, via the electronic user interface, a clinical information area including a set of clinical information elements associated with the clinical condition from the portion of patient health data, (ii) receiving patient health information relevant to concurrent clinical conditions, and (iii) updating a likelihood of the patient having each of the concurrent clinical conditions based on the received patient health information.
4. The computer system of claim 2 , wherein the operations further comprise:
receiving an indication of a change in the set of risk factors associated with a condition; and
based on the indication, dynamically updating the set of risk factors presented in the condition risk area.
5. The computer system of claim 1 , wherein the first set of clinical concepts comprises lab results, test results, patient conditions, patient health history, patient demographic information, or other discretized health-related information.
6. The computer system of claim 1 , wherein the clinical condition computer program routine is dynamically constructed by multiple geographically distributed electronic adaptive agents operating on a cloud based computing platform.
7. One or more non-transitory media having computer-readable instructions that, when executed by one or more hardware processors, cause the one or more hardware processors to facilitate a plurality of operations, the operations comprising:
receiving a portion of patient health data associated with a patient, the portion of patient health data including a first set of clinical concepts encoded in a first clinical nomenclature;
determining, from the portion of patient health data and based at least on an identification of a location in a traversable state machine via a finite state machine agent or solver, a current state of the patient;
based on the determined current state of the patient and based further on the portion of patient health data, performing via a set of the one or more hardware processors:
(a) utilizing the portion of patient health data and information corresponding to one or both of the location in the traversable state machine and a state in the traversable state machine to access a library of clinical condition programs that are encoded in the second nomenclature and stored at one or more physical data stores distributed across multiple physical locations;
(b) based on accessing the library and based further on identifying at least one clinical condition program in the library, dynamically constructing, by one or more distributed electronic adaptive agents, a clinical condition computer program routine for use with information associated with at least the portion of patient health data; and
(c) executing the clinical condition computer program routine to determine a set of clinical concepts relevant to the determined current state of the patient, the set of clinical concepts including at least one clinical concept encoded in the second clinical nomenclature;
converting, via the one or more hardware processors, the at least one clinical concept encoded in the second clinical nomenclature from the second clinical nomenclature to the first clinical nomenclature; and
presenting, via the one or more hardware processors and via an electronic user interface, information associated with the at least one clinical concept in the first clinical nomenclature after the at least one clinical concept encoded in the second clinical nomenclature is converted from the second clinical nomenclature to the first clinical nomenclature.
8. The one or more non-transitory media of claim 7 , wherein the operations further comprise causing the electronic user interface to display a clinical conditions menu including clinical conditions for which the patient is at risk.
9. The one or more non-transitory media of claim 8 , wherein the operations further comprise causing the electronic user interface to display a condition risk area responsive to selection of a clinical condition of the clinical conditions, the condition risk area comprising:
a computed likelihood of the clinical condition;
a set of risk factors associated with the clinical condition; and
a clinical value associated with at least a portion of the set of risk factors.
10. The one or more non-transitory media of claim 7 , wherein at least one operation of the operations is carried out by applying one or more adaptive agents configured to facilitate performance of the at least one operation.
11. The one or more non-transitory media of claim 10 , wherein the operations further comprise updating the one or more configured adaptive agents based on information associated with additional health data associated with the patient.
12. The one or more non-transitory media of claim 7 , wherein multiple clinical condition programs are dynamically constructed, based at least in part on the library of clinical condition programs and the portion of patient health data associated with the patient, via the operations performed by the one or more hardware processors.
13. The one or more non-transitory media of claim 7 , wherein the operations further comprise:
dynamically creating, via at least one processor of the one or more hardware processors and in the second clinical nomenclature, multiple clinical condition programs from corresponding clinical condition programs in an electronic data library of clinical condition programs; and
storing at least a portion of the multiple of clinical condition programs, associated with a corresponding set of clinical conditions, in the electronic data library.
14. The one or more non-transitory media of claim 7 , wherein the performing includes:
identifying via the one or more hardware processors, a plurality of states in the traversable state machine based on utilizing the finite state machine agent or solver; and
identifying, via the one or more hardware processors, a particular state of the plurality of states in the traversable state machine.
15. The one or more non-transitory media of claim 14 , wherein the particular state corresponds to a particular location of a plurality of locations in the traversable state machine.
16. The one or more non-transitory media of claim 7 , wherein the operations further comprise:
determining, via at least one processor of the one or more hardware processors, at least two concurrent clinical conditions relevant to the patient.
17. The one or more non-transitory media of claim 16 , wherein the operations further comprise:
determining, based on the at least two concurrent clinical conditions relevant to the patient, the current state of the patient.
18. The one or more non-transitory media of claim 17 , wherein the operations further comprise:
utilizing the clinical condition computer program routine to determine a set of risk factors specifically associated with the at least two concurrent clinical conditions relevant to the patient.
19. A computer-implemented method, comprising:
receiving a portion of patient health data associated with a patient, the portion of patient health data including a first set of clinical concepts encoded in a first clinical nomenclature;
determining, from the portion of patient health data and based at least on an identification of a location in a traversable state machine via a finite state machine agent or solver, a current state of the patient;
based on the determined current state of the patient and based further on the portion of patient health data, performing via one or more hardware processors:
(a) utilizing the portion of patient health data and information corresponding to one or both of the location in the traversable state machine and a state in the traversable state machine to access a library of clinical condition programs that are encoded in the second nomenclature and stored at one or more physical data stores distributed across multiple physical locations;
(b) based on the accessing the library and based further on identifying at least one clinical condition program in the library, dynamically constructing, by one or more distributed electronic adaptive agents, a clinical condition computer program routine for use with information associated with at least the portion of patient health data; and
(c) executing the clinical condition computer program routine to determine a set of clinical concepts relevant to the determined current state of the patient, the set of clinical concepts including at least one clinical concept encoded in the second clinical nomenclature;
converting, via the one or more hardware processors, the at least one clinical concept encoded in the second clinical nomenclature from the second clinical nomenclature to the first clinical nomenclature; and
presenting, via the one or more hardware processors and via an electronic user interface, information associated with the at least one clinical concept in the first clinical nomenclature after the at least one clinical concept encoded in the second clinical nomenclature is converted from the second clinical nomenclature to the first clinical nomenclature.
20. The computer-implemented method of claim 19 , further comprising causing the electronic user interface to display a condition assessment area for presenting a contextually-driven assessment based on patient information relevant to diagnosing or treating a clinical condition, and for receiving patient information in response to presenting the contextually-driven assessment, wherein the received patient information includes one or more clinical concepts encoded in the first clinical nomenclature.
21. The computer-implemented method of claim 19 , further comprising causing the electronic user interface to display a condition assessment area for presenting a contextually-driven assessment based on patient information relevant to diagnosing or treating a clinical condition and determining whether the patient information is absent or stale.