SCALABLE ARCHITECTURE SYSTEM FOR CLINICIAN DEFINED ANALYTICS
A method and system of a scalable modular architecture for enabling clinicians to define clinical inputs, operators, and notifications on a per patient and enterprise basis for screening any pathological condition per the clinical practice
1 . A method for a scalable modular architecture for clinician defined analytics, comprising:
measuring, by one or more sensors of one or more devices, one or more clinical measurements of a patient;
aggregating, by a command center, the one or more clinical measurements;
extracting, by the command center, clinical measurement vectors from the aggregated clinical measurements for one or more decision system;
selecting, by the command center, appropriate clinical measurements relevant to triggering one or more decision systems from a pool of incoming data; and
performing computations, by the command center, to define an analytics engine per analytics specifications and operations.
2 . The method of claim 1 , wherein one or more decision support systems are triggered using the defined analytics engine.
3 . The method of claim 2 , wherein the defined analytics engine further performs evaluation tasks, optimization process, and computation process of the decision support system based on the definitions of the clinician.
4 . The method of claim 3 , wherein the evaluation tasks include evaluation and compilation of the definitions into a mathematical form used for computation, and verification of syntax involving automated compilation rules or a manual input table of operand values run through a mathematical form to ensure correct output.
5 . The method of claim 4 , wherein the optimization process includes minimization of states or declarative statements by reducing unreachable states or statements.
6 . The method of claim 5 , wherein the computation process uses data vectors for the operands and the optimized mathematical structure for computing the elements of the decision support system.
7 . The method of claim 1 , further comprising, defining and setting, by a clinician, the analytics specifications and operations.
8 . The method of claim 7 , wherein the defining and setting the analytics specifications and operation includes:
setting, by a clinician portal, processes of a decision layer for defining explicit explanatory mathematical structure of a decision support system;
defining operands required for the decision support system in the definition layer,
wherein the operand includes sensor inputs including at least one of vital sign measurements or lab results.
9 . The method of claim 8 , wherein the decision layer includes at least one of a Boolean process, scoring process, dynamic process, or mixed process.
10 . The method of claim 9 , wherein the Boolean process defines a decision structure whose result may trigger a single alert.
11 . The method of claim 9 , wherein the scoring process that defines a decision structure whose result generates scores that may trigger a multiple alert.
12 . The method of claim 9 , wherein the dynamic process defines a decision structure where the process transitions from one state to a next state until the process reaches a final state that may trigger a single alert.
13 . The method of claim 9 , wherein the mixed process is a dynamic process with each state being a Boolean process or a scoring process.
14 . The method of claim 1 , further comprising assisting a clinician in selecting definitions of the analytics specifications and operations by learning optimal decisions based on outcomes of prior definitions and operations.
15 . The method of claim 1 , further comprising integrating the one or more clinical measurements into an electronic health record (EHR).
16 . A non-transitory computer-readable medium storing executable instructions for clinician defined analytics that, in response to execution, cause a computer to perform operations comprising:
measuring, by one or more sensors of one or more devices, one or more clinical measurements of a patient;
aggregating, by a command center, the one or more clinical measurements;
extracting, by the command center, clinical measurement vectors from the aggregated clinical measurements for one or more decision system;
selecting, by the command center, appropriate clinical measurements relevant to triggering one or more decision systems from a pool of incoming data; and
performing computations, by the command center, to define an analytics engine per analytics specifications and operations.
17 . The non-transitory computer-readable medium of claim 16 , further comprising:
defining and setting, by a clinician, the analytics specifications and operations, wherein the defining and setting the analytics specifications and operation includes:
setting, by a clinician portal, processes of a decision layer for defining explicit explanatory mathematical structure of a decision support system;
defining operands required for the decision support system in the definition layer,
wherein the operand includes sensor inputs including at least one of vital sign measurements or lab results.
18 . The non-transitory computer-readable medium of claim 17 , wherein the decision layer includes at least one of a Boolean process, scoring process, dynamic process, or mixed process.
19 . The non-transitory computer-readable medium of claim 18 ,
wherein the Boolean process defines a decision structure whose result may trigger a single alert,
wherein the scoring process that defines a decision structure whose result generates scores that may trigger a multiple alert,
wherein the dynamic process defines a decision structure where the process transitions from one state to a next state until the process reaches a final state that may trigger a single alert, and
wherein the mixed process is a dynamic process with each state being a Boolean process
20 . The non-transitory computer-readable medium of claim 16 ,
wherein one or more decision support systems are triggered using the defined analytics engine.