IP Library › Granted Patent US 12,462,937
Granted Patent B2
US 12,462,937 · App. 17/926,272 · Granted Nov 4, 2025

Intelligent workflow analysis for treating covid-19 using exposable cloud-based registries

Inventors: Silvia Elena Molero Leon (Heredia, CR); Helene Jeanne Sahri (Basel, CH); Turap Tasoglu (Basel, CH)
Assignee: Hoffmann-La Roche Inc.
G16H50/20G06N5/01G16H10/60G16H50/70G16H50/80
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,462,937
App. No.
17/926,272
Granted
Nov 4, 2025
Kind
B2
Abstract

Disclosed herein are systems, methods, and techniques for building and using a data platform to facilitate intelligent identification of coronavirus disease 2019 (COVID-19) related diagnoses, treatment selection, and interaction tracing. The present disclosure relates to a cloud-based application that generates outputs predictive of a subject's COVID-19 diagnoses and/or suitability for COVID-19 treatments.

Claims (75)

1 . A computer-implemented method comprising:

receiving input corresponding to a selection of an identifier of a subject record associated with a subject, the identifier of the subject record being selected using an interface;

retrieving the subject record from a data store, the subject record including a set of subject attributes that medically characterize the subject, the subject attributes including at least a medical diagnosis;

generating an array representation for the subject, the array representation being generated by transforming the set of subject attributes using singular value decomposition (SVD) to generate one or more numerical representations for each attribute and combine the numerical representations into a vector representation as the array representation;

inputting the array representation for the subject into a trained machine-learning model, the trained machine-learning model comprising:

a set of parameters that were learned using a set of other subject records stored in a data registry, each other subject record of the set of other subject records being associated with another subject who was infected with COVID-19 and subsequently treated using a treatment, and each other subject record of the set of other subject records including a respective set of other subject attributes that medically characterize the associated another subject; and

one or more functions configured to transform array-representation input into size-reduced output using the set of parameters, wherein the one or more functions are configured to repeatedly monitor and aggregate large-scale data from across a plurality of institutions;

outputting, from the trained machine-learning model, an output that includes a classification for the subject based upon the input and the set of learned parameters;

determining, based on the output, that the subject record corresponds to criteria of a COVID-19 diagnosis and/or factors indicative of suitability of a particular COVID-19 treatment; and

in response to determining that the subject record corresponds to the criteria of a COVID-19 diagnosis:

determining, using a random forest model trained to iterate through the set of other subject records, one or more segmenting thresholds for segmenting the set of other subject records into one or more subject groups, each subject group corresponding to a subject outcome, where one of the subject groups corresponds to subjects who have been discharged after recovering from COVID-19;

determining a set of treatments associated with the subject group corresponding to subjects who have been discharged after recovering from COVID-19;

determining, using the random forest model and based on the one or more segmenting thresholds, a set of characteristics determined to contribute to the discharging of the subjects who have been discharged after recovering from COVID-19;

determining a respective similarity metric between the subject record and each characteristic from the set of characteristics by automatically combining numerical representations of the SVD-transformed attributes in a domain space;

determining, based on the similarity metrics, a confidence score for each treatment in the set of treatments; and

presenting, on the interface and based on the confidence scores, the set of treatments as proposed treatments for treating the subject.

2 . The computer-implemented method of claim 1 , further comprising:

causing a communication to be transmitted notifying one or more individuals associated with one or more potential interaction locations between the subject and respective ones of the one or more individuals, wherein the communication is transmitted upon receiving authorization from the subject, and wherein the communication avoids violating data-privacy rules associated with individual locations of the potential interaction locations;

receiving one or more responses to the communication;

identifying one or more potential human interactions using the one or more responses to the communication; and

generating, for each potential human interaction of the one or more potential human interactions, a test-request workflow for assigning a COVID-19 test to the potential human interaction.

3 . The computer-implemented method of claim 1 , further comprising:

prescribing a treatment workflow associated with the COVID-19 diagnosis, the treatment workflow including the particular COVID-19 treatment, the particular COVID-19 treatment being performable by a physician or medical professional.

4 . The computer-implemented method of claim 1 , wherein the set of subject attributes characterizing the subject includes any one or more from a group comprised of: one or more comorbidities, a smoking status of the subject, a suspected diagnosis of a viral disease, a confirmed diagnosis of a viral disease, a testing technology used to confirm a diagnosis, or a treatment for a disease or condition.

5 . A system comprising:

a memory with instructions stored thereon; and

a processing device, coupled to the memory and operable to access the memory, wherein the instructions when executed by the processing device, cause the processing device to perform operations including:

receiving input corresponding to a selection of an identifier of a subject record associated with a subject, the identifier of the subject record being selected using an interface;

retrieving the subject record from a data store, the subject record including a set of subject attributes that medically characterize the subject, the subject attributes including at least a medical diagnosis;

generating an array representation for the subject, the array representation being generated by transforming the set of subject attributes using singular value decomposition (SVD) to generate one or more numerical representations for each attribute and combine the numerical representations into a vector representation as the array representation;

inputting the array representation for the subject into a trained machine-learning model to generate an output that is size-reduced, the trained machine-learning model comprising:

a set of parameters that were learned using a set of other subject records stored in a data registry, each other subject record of the set of other subject records being associated with another subject who was infected with COVID-19 and subsequently treated using a treatment; and

one or more functions configured to transform array-representation input into size-reduced output using the set of parameters, wherein the one or more functions are configured to repeatedly monitor and aggregate large-scale data from across a plurality of institutions;

outputting, from the trained machine-learning model, an output that includes a classification for the subject based upon the input and the set of learned parameters;

determining, based on the output, that the subject record corresponds to criteria of a COVID-19 diagnosis and/or factors indicative of suitability of a particular COVID-19 treatment; and

in response to determining that the subject record corresponds to the criteria of a COVID-19 diagnosis:

determining, using a random forest model trained to iterate through the set of other subject records, one or more segmenting thresholds for segmenting the set of other subject records into one or more subject groups, each subject group corresponding to a subject outcome, where one of the subject groups corresponds to subjects who have been discharged after recovering from COVID-19;

determining a set of treatments associated with the subject group corresponding to subjects who have been discharged after recovering from COVID-19;

determining, using the random forest model and based on the one or more segmenting thresholds, a set of characteristics determined to contribute to the discharging of the subjects who have been discharged after recovering from COVID-19;

determining a respective similarity metric between the subject record and each characteristic from the set of characteristics by automatically combining the numerical representations of the SVD-transformed attributes in a domain space;

determining, based on the similarity metrics, a confidence score for each treatment in the set of treatments; and

presenting, on the interface and based on the confidence scores, the set of treatments as proposed treatments for treating the subject.

6 . The system of claim 5 , wherein the operations further comprise:

causing a communication to be transmitted notifying one or more individuals associated with one or more potential interaction locations between the subject and respective ones of the one or more individuals, wherein the communication is transmitted upon receiving authorization from the subject, and wherein the communication avoids violating data-privacy rules associated with individual locations of the potential interaction locations;

receiving one or more responses to the communication;

identifying one or more potential human interactions using the one or more responses to the communication; and

generating, for each potential human interaction of the one or more potential human interactions, a test-request workflow for assigning a COVID-19 test to the potential human interaction.

7 . The system of claim 5 , wherein the operations further comprise:

prescribing a treatment workflow associated with the COVID-19 diagnosis, the treatment workflow including the particular COVID-19 treatment, the particular COVID-19 treatment being performable by a physician or medical professional.

8 . The system of claim 5 , wherein the set of subject attributes characterizing the subject includes any one or more from a group comprised of: one or more comorbidities, a smoking status of the subject, a suspected diagnosis of a viral disease, a confirmed diagnosis of a viral disease, a testing technology used to confirm a diagnosis, or a treatment for a disease or condition.

9 . The system of claim 5 , wherein the subject was admitted to a medical facility as a suspected case of COVID-19.

10 . A non-transitory computer-readable medium with instructions stored thereon that, responsive to execution by a processing device, causes the processing device to perform operations comprising:

receiving input corresponding to a selection of an identifier of a subject record associated with a subject, the identifier of the subject record being selected using an interface;

retrieving the subject record from a data store, the subject record including a set of subject attributes that medically characterize the subject, the subject attributes including at least a medical diagnosis;

generating an array representation for the subject, the array representation being generated by transforming the set of subject attributes using singular value decomposition (SVD) to generate one or more numerical representations for each attribute and combine the numerical representations into a vector representation as the array representation;

inputting the array representation for the subject into a trained machine-learning model, the trained machine-learning model comprising:

a set of parameters that were learned using a set of other subject records stored in a data registry, each other subject record of the set of other subject records being associated with another subject who was infected with COVID-19 and subsequently treated using a treatment, and each other subject record of the set of other subject records including a respective set of other subject attributes that medically characterize the associated another subject; and

one or more functions configured to transform array-representation input into size-reduced output using the set of parameters, wherein the one or more functions are configured to repeatedly monitor and aggregate large-scale data from across a plurality of institutions;

outputting, from the trained machine-learning model, an output that includes a classification for the subject based upon the input and the set of learned parameters;

determining, based on the output, that the subject record corresponds to criteria of a COVID-19 diagnosis and/or factors indicative of suitability of a particular COVID-19 treatment; and

in response to determining that the subject record corresponds to the criteria of a COVID-19 diagnosis:

determining, using a random forest model trained to iterate through the set of other subject records, one or more segmenting thresholds for segmenting the set of other subject records into one or more subject groups, each subject group corresponding to a subject outcome, where one of the subject groups corresponds to subjects who have been discharged after recovering from COVID-19;

determining, using the random forest model, one or more segmenting thresholds for segmenting the set of other subject records into one or more subject groups, each subject group corresponding to a subject outcome, where one of the subject groups corresponds to subjects who have been discharged after recovering from COVID-19;

determining a set of treatments associated with the subject group corresponding to subjects who have been discharged after recovering from COVID-19;

determining, using the random forest model and based on the one or more segmenting thresholds, a set of characteristics determined to contribute to the discharging of the subjects who have been discharged after recovering from COVID-19;

determining a respective similarity metric between the subject record and each characteristic from the set of characteristics by automatically combining the numerical representations of the SVD-transformed attributes in a domain space;

determining, based on the similarity metrics, a confidence score for each treatment in the set of treatments; and

presenting, on the interface and based on the confidence scores, the set of treatments as proposed treatments for treating the subject.

11 . The non-transitory computer-readable medium of claim 10 , wherein the operations further comprise:

causing a communication to be transmitted notifying one or more individuals associated with one or more potential interaction locations between the subject and respective ones of the one or more individuals, wherein the communication is transmitted upon receiving authorization from the subject, and wherein the communication avoids violating data-privacy rules associated with individual locations of the potential interaction locations;

receiving one or more responses to the communication;

identifying one or more potential human interactions using the one or more responses to the communication; and

generating, for each potential human interaction of the one or more potential human interactions, a test-request workflow for assigning a COVID-19 test to the potential human interaction.

12 . The non-transitory computer-readable medium of claim 10 , wherein the operations further comprise:

prescribing a treatment workflow associated with the COVID-19 diagnosis, the treatment workflow including the particular COVID-19 treatment of the set of treatments, the particular COVID-19 treatment being performable by a physician or medical professional.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 18, 2022
From: MOLERO LEON, SILVIA ELENA; SAHRI, HELENE JEANNE; TASOGLU, TURAP
To: F. HOFFMANN-LA ROCHE AG
Reel/Frame 061823/0097 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 18, 2022
From: F. HOFFMANN-LA ROCHE AG
To: HOFFMANN-LA ROCHE INC.
Reel/Frame 061823/0135 →
Priority Claims (1)
EP 20175835 · May 20, 2020 · regional
Continuity (1)
Related Publication 20230207126A1 · Jun 29, 2023
References Cited (26)
US 11676722B1 · Adib · 2023 [cited by examiner]
US 20170000422A1 · Moturu · 2017 [cited by examiner]
US 20200365270A1 · Kazemi Oskooei · 2020 [cited by examiner]
US 20200373018A1 · Segal · 2020 [cited by examiner]
US 20220087591A1 · Costa · 2022 [cited by examiner]
JP 2006178903 · 2006 [cited by applicant]
JP 2017527399 · 2017 [cited by applicant]
WO WO2015118529A1 · 2015 [cited by examiner]
WO 2016040295 · 2016 [cited by applicant]
WO 2017023556A1 · 2017 [cited by applicant]
WO 2017106770A1 · 2017 [cited by applicant]
WO 2020091053 · 2020 [cited by applicant]
WO WO2021231274A1 · 2021 [cited by examiner]
Alimadadi et al., “Artificial intelligence and machine learning to fight COVID-19,” Physiol Genomics 52: 200-202, 2020; First published Mar. 27, 2020; doi: 10.1152/physiolgenomics.00029.2020. (Year: 2020). [cited by examiner]
Beck et al., “Predicting commercially available antiviral drugs that may act on the novel coronavirus (SARS-CoV-2) through a drug-target interaction deep learning model,” Computational and Structural Biotechnology Journ… [cited by examiner]
Prakash et al., “Analysis, Prediction and Evaluation of COVID-19 Datasets using Machine Learning Algorithms,” vol. 8. No. 5, May 2020; International Journal of Emerging Trends in Engineering Research; https://doi.org/10… [cited by examiner]
Shi et al., “Large-Scale Screening of COVID-19 from Community Acquired Pneumonia using Infection Size-Aware Classification,” arXiv:2003.09860. (Year: 2020). [cited by examiner]
Wu et al., “Rapid and accurate identification of COVID-19 infection through machine learning based on clinical available blood test results,” medRxiv; https://doi.org/10.1101/2020.04.02.20051136. (Year: 2020). [cited by examiner]
JPO, Notice of Rejection (with English translation) for Japanese Patent Application No. 2022-570601, Feb. 13, 2024, 8 pages. [cited by applicant]
EPO, International Search Report for International Patent Application No. PCT/US2021/028647, Dec. 21, 2021, 8 pages. [cited by applicant]
EPO, Written Opinion for International Patent Application No. PCT/US2021/028647, Dec. 21, 2021, 19 pages. [cited by applicant]
Schwab, Patrick et al., “preCOVID-19: A Systematic Study of Clinical Predictive Models for Coronavirus Disease 2019,” arXiv preprint arXiv:2005.08302 76, Cornell University Library (2020), 8 pages. [cited by applicant]
Mei, Xueyan et al., “Artificial intelligence-enabled rapid diagnosis of patients with COVID-19,” Nature medicine 26.8 (2020), pp. 1224-1228. [cited by applicant]
Alsdurf, Hannah et al., “COVI White Paper,” arXiv preprint arXiv:2005.08502, Cornell University Library (2020), 64 pages. [cited by applicant]
Sandhu, Rajinder et al., “An intelligent system for predicting and preventing MERS-CoV infection outbreak,” The Journal of supercomputing 72.8 (2016), pp. 3033-3056. [cited by applicant]
Wang, Kun et al., “Clinical Infectious Diseases Clinical Infectious Diseases and Laboratory Predictions of In-hospital Mortality in Patients with Coronavirus Disease—2019: a Cohort Study in Wuhan, China,” Clinical infec… [cited by applicant]