US 11,961,594 B2Granted

System and method using clinical data to predict genetic relatedness for the efficient management and reduction of healthcare-associated infections

AssigneeKoninklijke Philips N.V.

InventorsLiyi Xu, Raivo Kolde, Andrew G. Hoss

Life of this patent

Estimating the term…

Loading patent…

Abstract

A method for identifying two or more infections as related or non-related infections based on an estimated genetic relatedness of the two or more infections, comprising: (i) receiving, for each of two or more infected patients, infection-relevant information comprising an antibiotic resistance profile for the patient's infection, a geo-temporal record for the patient, and a caregiver history for the patient; (ii) estimating, using a trained genetic relatedness model, a genetic relatedness of at least two of the two or more infections; (iii) comparing the estimated genetic relatedness between at least two of the two or more infections to a predetermined threshold; (iv) identifying, based on the comparison, the at least two of the two or more infections as a related infection or a non-related infection.

Claims14

Dependent claims

A method for identifying two or more infections as related or non-related infections based on an estimated genetic relatedness of the two or more infections, comprising:

training a genetic relatedness model, comprising:
(i) receiving, from a database of infection data, infection-relevant information for a plurality of patients and pathogen sequencing data for an infection associated with each of the plurality of patients;
(ii) calculating, using the sequencing data, genetic relatedness between the infections of two or more of the plurality of patients;
and (iii) generating, from the received infection-relevant information and the calculated genetic relatedness between the infections, a predictive model designed to provide an estimate of genetic relatedness between two or more infections using only infection-relevant information;
receiving, for each of two or more infected patients, infection-relevant information comprising an antibiotic resistance profile for the patient's infection, a geo-temporal record for the patient, and a caregiver history for the patient;
estimating, using the trained genetic relatedness model analyzing the received infection-relevant information for the two or more infected patients, a genetic relatedness of at least two of the two or more infections;
comparing the estimated genetic relatedness between at least two of the two or more infections to a predetermined threshold;
and
identifying, based on the comparison, the at least two of the two or more infections as a related infection or a non-related infection, wherein the at least two of the two or more infections are identified as a related infection if the estimated genetic relatedness falls below the predetermined threshold, and wherein the at least two of the two or more infections are identified as a non-related infection if the estimated genetic relatedness exceeds the predetermined threshold.

6 more elements

A system configured to identify two or more infections as related or non-related infections based on an estimated genetic relatedness of the two or more infections, comprising:

infection-relevant information for each of two or more infected patients, comprising an antibiotic resistance profile for the patient's infection, a geo-temporal record for the patient, and a caregiver history for the patient;
a trained genetic relatedness model configured to analyze the received infection-relevant information for the two or more infected patients and to estimate based on that analysis a genetic relatedness of at least two of the two or more infections, wherein the genetic relatedness model is trained by:
(i) receiving, from a database of infection data, infection-relevant information for a plurality of patients and pathogen sequencing data for an infection associated with each of the plurality of patients;
(ii) calculating, using the sequencing data, genetic relatedness between the infections of two or more of the plurality of patients;
and (iii) generating, from the received infection-relevant information and the calculated genetic relatedness between the infections, a predictive model designed to provide an estimate of genetic relatedness between two or more infections using only infection-relevant information;
a processor configured to:
(i) compare the estimated genetic relatedness between at least two of the two or more infections to a predetermined threshold;
and
(i) identify, based on the comparison, the at least two of the two or more infections as a related infection or a non-related infection, wherein the at least two of the two or more infections are identified as a related infection if the estimated genetic relatedness falls below the predetermined threshold, and wherein the at least two of the two or more infections are identified as a non-related infection if the estimated genetic relatedness exceeds the predetermined threshold;
and
a user interface configured to display a representation of the estimated genetic relatedness between the at least two of the two or more infections.

8 more elements

Dependencies are inferred from the claim text.

Facts

Application: 16/455,985Filed 28 Jun 2019
Published: US 2020/0411133 A131 Dec 2020
Granted: 16 Apr 2024
Term ends: Not estimatedThe source records don’t support an estimate.

Classification16 codes

G16B 5/20
ICT specially adapted for modelling or simulations in systems biology, e.g. gene-regulatory networks, protein interaction networks or metabolic…:…
G06N 5/02
Computing arrangements using knowledge-based models: knowledge representation; Symbolic representation
G16B 20/20
ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations: allele or variant detection, e.g. single…
G16B 30/10
ICT specially adapted for sequence analysis involving nucleotides or amino acids: sequence alignment; Homology search