STATISTICAL MODEL FOR PREDICTING FALLING IN HUMANS

• US 20110082672A1
• Filed: 09/30/2010
• Published: 04/07/2011
• Est. Priority Date: 10/02/2009
• Status: Active Grant

• Current Assignee: Nova Southeastern University
• Original Assignee: Nova Southeastern University
• Inventors: HARDIGAN, Patrick C.
• Granted Patent: US 8,521,490 B2
• Time in Patent Office: Days
• US Class Current: 703/2
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/50 for simulation or modelling of medical disorders
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

Dependent variables believed to contribute to a likelihood of falling are analyzed using a latent class analysis. The dependent variables are biomedical factors, which may include, for example, arthritis, high blood pressure, diabetes, foot disorders, Parkinson'"'"'s Disease, stroke, eye disorder, limb disorder, or proprioceptive disorder. Data pertaining to the biomedical factors is gathered from a population of individuals at risk of falling. Covariate data, including for example age and the number of prescriptions taken, is further analyzed against latent class data. For a particular group of at risk individuals, a set of five classes produced useful results broadly corresponding to groups representing individuals who have: good health; a range of diseases; Parkinson'"'"'s Disease; arthritis; and high blood pressure. A probability of falling is determined, relative to the group of individuals with good health.

Claims

1. A method, implemented on at least one computer, for analyzing the likelihood of biomedical factors contributing to a greater risk of falling in humans, comprising:

inputting base data into at the least one computer, the base data including dependent variables representing biomedical factors associated with the humans; and

calculating, using the at least one computer, results of a latent class analysis based on the inputted base data, using the formula

2. The method of claim 1, further comprising:

inputting covariate data into the at least one computer corresponding to the number of medications taken by humans;

calculating, using the at least one computer and said results, a changed probability of falling based on the covariate data.

3. The method of claim 1, further comprising:

inputting covariate data into the at least one computer corresponding to the age of humans;

calculating, using the at least one computer and said results, a changed probability of falling based on the covariate data.

4. The method of claim 1, further comprising:

inputting covariate data into the at least one computer corresponding to the age of humans and the number of medications taken by humans;

calculating, using the at least one computer and said results, a changed probability of falling based on the covariate data.

5. The method of claim 1, further comprising:

calculating, using the at least one computer, a posterior probability of an individual belonging to a latent class, using the formula

6. The method of claim 1, wherein said biomedical factors are selected from the group consisting of the following:

arthritis, high blood pressure, diabetes, foot disorders, Parkinson'"'"'s Disease, stroke, eye disorder, limb disorder, proprioceptive disorder, cardiovascular disease, musculoskeletal disease, neurological disease, metabolic disease, respiratory disease, diseases and disorders of the nervous system, diseases and disorders of the eye, diseases and disorders of the ear, diseases and disorders of the nose, diseases and disorders of the mouth, diseases and disorders of the throat, diseases and disorders of the respiratory system, diseases and disorders of the circulatory system, diseases and disorders of the digestive system, diseases and disorders of the hepatobiliary system, diseases and disorders of the pancreas, diseases and disorders of the musculoskeletal system, diseases and disorders of the connective tissue, diseases and disorders of the skin, diseases and disorders of the subcutaneous tissue, diseases and disorders of the breast, diseases and disorders of the endocrine system, diseases and disorders of nutrition, diseases and disorders of metabolism, diseases and disorders of the blood, diseases and disorders of blood forming organs, diseases and disorders of the immune system, myeloproliferative diseases and disorders, diseases and disorders of poorly differentiated neoplasms, and significant trauma.

7. The method of claim 1, wherein the likelihood of falling is analyzed for an individual human.

8. The method of claim 1, further comprising:

graphically displaying, using the at least one computer, probabilities of humans in each latent class being associated with the biomedical factors.

11. The method of claim 1, where xj is the response vector of individual human j taken from a sample of J individuals, xij is the presence or absence of a response 1, . . . , i/ε

, Π

ik is the probability of a positive response on variable i for an individual in class z_j=k, 1, . . . , k K ε and

η

k are the probability that a randomly chosen individual is in class k, and given the class zj=k and the j individual, independence yields

14. The method of claim 1, further including:

inputting changed data into the at least one computer, the changed data pertaining to biomedical factors associated with at least one of the humans that has changed relative to the base data;

performing said step of calculation after said step of changing;

determining a change in the likelihood of falling for the at least one human based upon a difference between said base data and said changed data.

15. The method of claim 14, wherein said biomedical factors changed includes changing a medication or a dosage of a medication of the at least one human.

16. The method of claim 14, wherein said biomedical factors changed includes remediating a disease or disorder of the at least one human.

9. A method for analyzing the likelihood of biomedical factors contributing to a greater risk of falling in humans, comprising:

calculating, based on data including dependent variables representing biomedical factors pertaining to the health of humans, results of a latent class analysis based on the inputted data, using the formula

10. A computer program product for analyzing the likelihood of biomedical factors contributing to a greater risk of falling in humans, the computer program product comprising instructions which perform the following functions when executed on at least one computer:

retrieving data from storage or memory connected to the least one computer, the data including dependent variables representing biomedical factors associated with the humans; and

calculating, using the at least one computer, results of a latent class analysis based on the inputted data, using the formula

17. The product of claim 10, further including:

retrieving changed data into the at least one computer, after said step of calculating, said changed data pertaining to biomedical factors associated with at least one of the humans that has changed since said step of calculating;

recalculating, using the at least one computer, said step of calculating after said step of retrieving changed data; and

calculating, using the at least one computer, a change in the likelihood of falling for the at least one human, between said step of calculating, and said step of recalculating.

18. The product of claim 17, wherein said biomedical factors changed includes a change in a medication or a dosage of a medication relating to the at least one human.

12. A computer system for analyzing the likelihood of biomedical factors contributing to a greater risk of falling in humans, comprising:

at least one computer;

storage or memory means connected to said at least one computer for storing base data including dependent variables representing biomedical factors associated with the humans;

a processor connected to said computer operative to calculate results of a latent class analysis based on the stored base data, using the formula

13. The computer system of claim 12, wherein said means for communicating includes means for presenting said results on a computer display screen by transforming said results from non-visible digital values stored in the memory of a computer to visible pixels corresponding to human readable characters on the display screen.

19. The system of claim 12, wherein said storage or memory means further stores changed data pertaining to biomedical factors associated with at least one of the humans that has changed relative to said base data;

and

wherein said processor connected to said computer is operative to calculate results of said latent class analysis based on the changed data, and to calculate a difference between said results of calculations based on said base data and calculations based on said changed data; and

wherein said means for communicating is operative to communicate results pertaining to said calculated difference.

20. The method of claim 19, wherein said biomedical factors changed includes a change in a medication or a dosage of a medication relating to the at least one human.