Back to results
US 12,763,209 B2Granted
Methods and systems for determining assessments of cardiovascular, metabolic, and renal syndromes, diseases, and disorders
AssigneeEmpallo, Inc.
InventorsRuizhi Liao, Claire Beskin
Life of this patent
Estimating the term…
Abstract
In an aspect, the present disclosure provides a method for determining an assessment of a cardiovascular, metabolic, or renal syndrome, disease, or disorder. The method comprises obtaining a dataset comprising a set of clinical health data of a subject, computer processing the dataset with a trained machine learning algorithm, and based at least in part on the computer processing, determining the assessment of the cardiovascular, metabolic, or renal syndrome, disease, or disorder over a retrospective or future period of time.
Claims23
A computer-implemented method of treating a no-hemoconcentration subject at risk of a cardiovascular, metabolic, or renal syndrome, disease, or disorder, or heart failure, the method comprising:
- (a) receiving, by a computing system comprising at least a processor and a memory, a dataset comprising a set of clinical health data of a no hemoconcentration subject, the set of clinical health data including at least one parameter selected from the group consisting of:
- B-type natriuretic peptide (BNP), N-terminal (NT)-pro hormone BNP (NT-proBNP), creatinine, a hemoconcentration marker, potassium, troponin, body weight, ejection fraction (EF), estimated glomerular filtration rate (eGFR), medication history, and vital sign measurements or a combination thereof;
- (b) transforming, by the computing system, the dataset into a vector using a predefined data processing sequence stored in the memory;
- (c) processing, by the computing system, the dataset transformed into the vector containing the set of clinical health data of the subject using a trained machine learning model configured to minimize a loss function, wherein the training data contains inputs including subject numerical clinical data correlated to outputs containing subject outcomes;
- (d) applying, by the computing system, the dataset transformed into the vector as input to the trained machine learning model, wherein the trained machine learning model is configured to generate an output containing a treatment recommendation that the subject requires an increased dose of a diuretic therapy;
- (e) generating, by the computing system, the treatment recommendation of the dataset containing the set of clinical health data of the no hemoconcentration subject, wherein the treatment recommendation identifies an adjustment to the dose of a diuretic therapy for the no hemoconcentration subject with an area under the curve of 0.70 and greater, and wherein the diuretic therapy is a loop diuretic or a thiazide diuretic;
- (f) outputting, by the computing system, a treatment recommendation, the recommendation comprising increasing the dose of the loop diuretic or the thiazide diuretic for the no hemoconcentration subject with an area under the curve of 0.70 and greater;
- and
- (g) administering the increased dose of the loop diuretic or the thiazide diuretic to the no hemoconcentration subject to mitigate a predicted adverse clinical outcome.
6 more elements
A computer-implemented method of treating a transthyretin amyloidosis with cardiac manifestation (ATTR-CM) subject, the method comprising:
- (a) receiving, by a computing system comprising at least a processor and a memory, a dataset comprising a set of clinical health data of a transthyretin amyloidosis with cardiac manifestation (ATTR-CM) subject, the clinical health data including at least one parameter selected from the group consisting of B-type natriuretic peptide (BNP), N-terminal (NT)-pro hormone BNP (NT-proBNP), creatinine, a marker, potassium, troponin, body weight, ejection fraction (EF), estimated glomerular filtration rate (eGFR), medication history, vital sign measurements, left ventricular systolic stroke volume index, a presence or an absence of a chronic pulmonary disease of the subject, or age or a combination thereof;
- (b) transforming, by the computing system, the dataset into a vector using a predefined data processing sequence stored in the memory;
- (c) processing, by the computing system, the dataset using a trained machine learning model configured to minimize a loss function, wherein the training data contains inputs including subject numerical clinical data correlated to outputs containing ATTR-CM assessments;
- (d) applying, by the computing system, the dataset transformed into the vector as input to the trained machine learning model, wherein the trained machine learning model is configured to generate an output containing a treatment recommendation that the subject requires an increased dose of a TTR silencer, a TTR stabilizer, or a diuretic therapy;
- (e) generating, by the computing system, the treatment recommendation of the dataset containing the set of clinical health data of a transthyretin amyloidosis with cardiac manifestation (ATTR-CM) subject wherein the treatment recommendation identifies an increase to the dose of the TTR silencer, the TTR stabilizer, or the diuretic therapy when a B-type natriuretic peptide (BNP) is greater than 600 picograms per milliliter;
- (f) outputting, by the computing system, the treatment recommendation wherein the treatment recommendation comprises increasing the dose of the TTR silencer, the TTR stabilizer, or the diuretic therapy when the B-type natriuretic peptide (BNP) is greater than 600 picograms per milliliter adjusting a medical therapy of the subject to mitigate a predictive ATTR CM assessment risk;
- and
- (g) administering the increased dose of the TTR silencer, the TTR stabilizer, or the diuretic therapy when the B-type natriuretic peptide (BNP) is greater than 600 picograms per milliliter to the transthyretin amyloidosis with cardiac manifestation (ATTR-CM) subject to mitigate a clinical outcome.
5 more elements
Dependencies are inferred from the claim text.