Granted Patent B2

US 12,211,624 · App. 17/107,407 · Granted Jan 28, 2025

Inventors: Ajay Kumar Gupta (Potomac, MD); Ramani Peruvemba (McLean, VA)

Assignee: Health Solutions Research, Inc.

G16H50/30G16H40/40G16H50/20G16H50/80

Abstract

Claims (70)

1. A method of tracking a disease, comprising:

generating a predictive model, wherein the predictive model includes a plurality of analyzer channels to customize or fine tune the predictive model to the disease,

wherein the generating of the predictive model includes training the predictive model by iteratively adjusting a weight of one or more of the plurality of analyzer channels until the predictive model passes the training by:

acquiring data based on population data and condition data by extracting data from a plurality of data sources,

identifying a first subset of the population data based on at least one criterion in which the first subset includes patients who tested positive for the disease,

identifying a second subset of the population data that includes patients who have at least developed antibodies to the disease based on the first subset and the condition data,

determining a correlation between the first subset and the second subset, wherein the correlation includes identifying which individuals are in the first subset and in the second subset,

determining whether the correlation between the first subset and the second subset meets or exceeds a predetermined threshold,

wherein if the correlation does not meet or exceed the predetermined threshold, adjusting the weight for the one or more of the plurality of analyser channels by modifying, deleting, or adding the one or more of the plurality of analyser channels and feeding the predictive model, iteratively, to re-test the predictive model to customize or fine tune the predictive model to the disease, in which at least one of the plurality of analyser channels corresponds to an observable condition with respect to the disease that places a patient at a greater risk of being affected by the infectious disease, and repeating the identification of which of the individuals are in the first subset and in the second subset until the correlation meets or exceeds the predetermined threshold in accordance with the adjustment, wherein the one or more of the plurality of analyser channels is broken down into analyzer features to provide additional sensitivity in identifying the patient at the greater risk of being affected by the infectious disease, and

when the correlation meets or exceeds the predetermined threshold, outputting the predictive model;

obtaining a set of resource data, using the predictive model to predict a number of active patients for the disease, a hospitalization rate for the disease, and a number of resources from the plurality of data sources;

determining a number of PPE users, a first burn rate, and a second burn rate for a type of PPE based on the predictive model of the disease and the set of resource data;

predicting a first PPE consumption rate for the type of PPE based on the number of PPE users, the first burn rate for the type of PPE, the hospitalization rate for the disease, the number of active patients for the disease, and the number of resources based on the predictive model of the disease;

predicting a second PPE consumption rate for the type of PPE based on the number of PPE users, the second burn rate for the type of PPE, the hospitalization rate for the disease, the number of active patients for the disease, and the number of resources based on the predictive model of the disease;

determining an index PPE rate based on a pandemic risk index, the first PPE consumption rate for the type of PPE, the second PPE consumption rate for the type of PPE, and the first burn rate;

geocoding the index PPE rate and loading the geocoded index PPE rate into a geospatial data analytic response engine;

displaying the geocoded index PPE on a spatial data infrastructure;

triggering a resource allocation and/or procurement based on the index PPE rate on the spatial data infrastructure; and

adjusting the set of resource data based on the resource allocation and/or procurement.

2. The method according to claim 1 , further comprising:

determining a transmission risk index;

determining a mortality risk index; and

determining the pandemic risk index based on the transmission risk index and the mortality risk index.

3. The method according to claim 2 , wherein determining the transmission risk index includes:

determining a patient density for the disease;

determining a patient density inverse distance weight for the disease;

determining a patient density mobility for the disease; and

determining the transmission risk index based on the patient density, the patient density inverse distance weight, and the patient density mobility.

4. The method according to claim 3 , wherein the patient density for the disease is a number of cases for the disease per a predetermined number of people in a predetermined area.

5. The method according to claim 4 , wherein the number of cases is determined based on the number of active patients in the predetermined area and a percentage of daily increases of the number of active patients in a predetermined period of time.

6. The method according to claim 5 , wherein the predetermined period of time is a week.

7. The method according to claim 3 , wherein determining the patient density inverse distance weight for the disease includes:

determining a plurality of inverse distance weights for the patient density in a geographical area;

determining the patient density inverse distance weight for the disease based on the plurality of inverse distance weights and the patient density for the geographical area.

8. The method according to claim 7 , wherein determining the plurality of inverse distance weights for the patient density in the geographical area includes:

determining a predetermined number of neighbours for the geographical area;

determining an inverse distance weight for each of the neighbours for the geographical area.

9. The method according to claim 8 , wherein the predetermined number of neighbours is a constant and the geographical area is a county.

10. The method according to claim 8 , wherein the predetermined number of neighbours is a constant and the geographical area is an area covered by a ZIP Code.

11. The method according to claim 3 , wherein determining the patient density mobility for the disease includes:

determining a plurality of areas a route passes through;

determining the patient density for each of the plurality of areas;

determining mobility factors based on predetermined regulations;

determining the patient density mobility for the disease based on the mobility factors, and the patient density for each of the plurality of areas.

12. The method according to claim 11 , wherein each of the plurality of areas is an area covered by a ZIP Code.

13. The method according to claim 11 , wherein the predetermined regulations include a predetermined distance between persons.

14. The method according to claim 2 , wherein determining the mortality risk index includes:

determining a mortality rate for a range of ages and a mortality rate for all ages;

determining a percentage in population for the range of ages;

determining a mortality rate for a comorbidity;

determining a percentage in population for the comorbidity; and

determining the mortality risk index based on the mortality rate for the range of ages, the percentage in population for the range of ages, the mortality rate for the comorbidity, the percentage in population for the comorbidity, and the mortality rate for all ages.

15. The method according to claim 1 , further comprising:

obtaining a number of the type of PPE;

determining PPE needs based on the number of the type of PPE, the index PPE rate, the first PPE consumption rate, and the second PPE consumption rate;

procuring the type of PPE based on the determined PPE needs.

16. The method according to claim 1 , further comprising:

obtaining a number of the type of PPE;

determining PPE needs based on the number of the type of PPE, the index PPE rate, the first PPE consumption rate, and the second PPE consumption rate;

allocating the type of PPE based on the determined PPE needs.

17. The method according to claim 1 , further comprising:

obtaining a number of the type of PPE;

determining PPE needs based on the number of the type of PPE, the index PPE rate, the first PPE consumption rate, and the second PPE consumption rate;

supplying the type of PPE based on the determined PPE needs.

18. The method according to claim 1 , further comprising:

obtaining a number of the type of PPE;

determining phases of a lifecycle of a pandemic for the disease;

for each phases, determining PPE needs based on the number of the type of PPE, the index PPE rate, the first PPE consumption rate, and the second PPE consumption rate.

19. The method according to claim 1 , wherein the disease includes COVID-19.

20. A non-transitory computer-readable medium having computer-readable instructions that, if executed by a computing device, cause the computing device to perform operations comprising the method of claim 1 .

Assignments (2)

Continuity (5)

References Cited (70)