US 2022/0189638 A1 · Method for predicting risk of unfavorable outcomes, e.g., in COVID-19 hospitalization, from clinical characteristics and basic laboratory findings

Abstract

A method for predicting an unfavorable outcome for a patient admitted to a hospital, e.g., with a COVID-19 infection is described. Attributes from an electronic health record for the patient are obtained including at least findings obtained at admission, basic patient characteristics, and laboratory data. The attributes are supplied to a classifier implemented in a programmed computer which is trained to predict a risk of the unfavorable outcome. The classifier is arranged as a hierarchical combination of (a) an initial binary classifier stratifying the patient into either a high risk group or a low risk group, and (b) child classifiers further classifying the patient in a lowest risk group or a highest risk group depending how the initial binary classifier stratified the patient as either a member of the high risk or low risk group. The initial binary classifier is configured as a combination of a trained classification decision tree and a logistical combination of atomic classifiers with drop-out regularization.

Claims19

Dependent claims

A method for predicting an unfavorable outcome for a hospitalized COVID-19 patient, comprising the steps of:

a) obtaining attributes from a health record for the patient comprising at least findings obtained at admission, basic patient characteristics and laboratory data,
b) training initial binary classifiers from a development set and child classifiers from development subsets comprising data obtained from records for a set of hospitalized COVID-19 patients including at least findings obtained at admission, basic patient characteristics, and laboratory data for each of such patient;
c) supplying the attributes obtained in step a) to a classifier iteratively using the trained set of initial binary and child classifiers implemented in a programmed computer trained to predict a risk of the unfavorable outcome, wherein:
1) the classifier is arranged as a hierarchical combination of (a) the initial binary classifier stratifying the patient into either a high risk group or a low risk group, and (b) the child classifiers further classifying the patient in a lowest risk group or a highest risk group depending how the initial binary classifier stratified the patient as either a member of the high risk or low risk group,
2) the initial binary classifier is configured as a combination of a trained classification decision tree and a logistical combination of atomic classifiers with drop-out regularization;
and
3) the child classifiers are configured as a logistical combination of atomic classifiers with drop-out regularization.

4 more elements

A computer system implementing trained classifiers to predict risk of an unfavorable outcome of a hospitalized COVID-19 patient from attributes from the health record for a patient comprising at least findings obtained at admission, basic patient characteristics and laboratory data, comprising

a) a memory storing parameters of an initial binary classifier stratifying the patient into either a high risk group or a low risk group, and child classifiers further classifying the patient in a lowest risk group or a highest risk group depending how the binary classifier stratified the patient as either a member of the high risk or low risk group,
b) a processor implementing program code executing the initial binary and child classifiers iteratively on the attributes in the health record for the hospitalized COVID-19 patient in a hierarchical manner, wherein the initial binary classifier is configured as a combination of a trained classification decision tree and a logistical combination of atomic classifiers with drop-out regularization, and wherein the child classifiers are configured as a logistical combination of atomic classifiers with drop-out regularization, and
c) code for generating an output from one of the child classifiers in the form of a prediction of a risk of the unfavorable outcome.

A method for developing a classifier for predicting risk of an unfavorable outcome of a patient admitted to a hospital, comprising the steps of:

a) obtaining a development set comprising data from records for a multitude of patients admitted to one or more hospitals, wherein the data includes laboratory data, findings obtained at admission, basic patient characteristics, and clinical data including data indicating whether or not the unfavorable outcome occurred during hospitalization of the patients;
b) training an initial binary classifier from the development set to stratify members of the development set into high and low risk groups;
c) training child classifiers to further stratify high and low risk groups into at least highest and lowest risk groups;
d) supplying the development set to the classifier iteratively using the trained set of initial binary and child classifiers;
e) configuring a test for predicting risk of unfavorable outcome as a hierarchical combination of the initial binary classifier and the child classifiers, and
wherein:
1) the initial binary classifier is configured as a combination of a trained classification decision tree and a logistical combination of atomic classifiers with drop-out regularization, and
2) the child classifiers are configured as a logistical combination of atomic classifiers with drop-out regularization.

5 more elements

Dependencies are inferred from the claim text.

Method for predicting risk of unfavorable outcomes, e.g., in COVID-19 hospitalization, from clinical characteristics and basic laboratory findings

Life of this patent

Method for predicting risk of unfavorable outcomes, e.g., in COVID-19 hospitalization, from clinical characteristics and basic laboratory findings

Life of this patent

Abstract

Claims19