Diagnosing inapparent diseases from common clinical tests using Bayesian analysis

• US 8,068,993 B2
• Filed: 06/17/2008
• Issued: 11/29/2011
• Est. Priority Date: 05/01/2001
• Status: Expired due to Fees

• Current Assignee: Quest Diagnostics Investments Incorporated (Quest Diagnostics Incorporated)
• Original Assignee: Quest Diagnostics Investments Incorporated (Quest Diagnostics Incorporated)
• Inventors: Billingsley, Frank, Kasten, Bernard, Karlov, Valeri I., Padilla, Carlos E., Maggio, Edward T.
• Primary Examiner(s): Feliciano; Eliseo Ramos
• Assistant Examiner(s): SUAREZ, FELIX E
• Application Number:
  US12/140,880
• Publication Number:
  US 20090024332A1
• Time in Patent Office: 1,260 Days
• Field of Search: 702/19, 702/20, 702/179, 702/181, 702/185, 702/186, 702/189, 435/6, 703/11, 705/2, 707/7
• US Class Current: 702/19
• CPC Class Codes: G16H 10/20 for electronic clinical trials or questionnaires
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 15/00 ICT specially adapted for medical reports, e.g. generation or transmission thereof
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients
• CPC Class Codes: G16H 50/80 for detecting, monitoring or modelling epidemics or pandemics, e.g. flu
• CPC Class Codes: Y02A 90/10 Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Abstract

A system and method of diagnosing diseases from biological data is disclosed. A system for automated disease diagnostics prediction can be generated using a database of clinical test data. The diagnostics prediction can also be used to develop screening tests to screen for one or more inapparent diseases. The prediction method can be implemented with Bayesian probability estimation techniques. The system and method permit clinical test data to be analyzed and mined for improved disease diagnosis.

Claims

1. A computer-implemented method of processing test data, comprising:

determining, by a computer specifically programmed therefor, a set of posterior test-conditional probability density functions (pdf) p(H_k|x) for a set H of hypotheses relating to a set X of test data conditioned on the test data based on (i) an estimate for one or more hypothesis-conditional pdf p(x|H_k) for the test data conditioned on the hypotheses and (ii) a set of prior pdf p(H_k) for each hypothesis;

wherein the p(x|H_k) estimates include (a) a global estimate produced in accordance with uncertainties in the statistical characteristics of the test data relating to each hypothesis-conditional pdf p(x|H_k) and (b) a local estimate produced in accordance with a discrete neighbor counting process for the test data relative to the global estimate for the corresponding hypothesis-conditional pdf.

2. The computer-implemented method of claim 1, wherein the uncertainties in the statistical characteristics are specified as an ellipsoid about the test data for each hypothesis and each ellipsoid is defined by an m-dimensional ellipsoid E_q,k for each hypothesis H_k and is specified by:

E_q,k={x;

(x−

m_x,k)^TP<sup>−

1</sup>_x,k(x−

m_x,k)≦

μ

²_q,k}

where the in m×

1 vector x is the argument in the space of test data, the m×

1 vector m_x,k is the mean (center) of each ellipsoid, the in m×

m matrix P_x,k is a covariance matrix of the ellipsoid, and the scalar μ

²_q,k defines the size of the q-th ellipsoid, such that the global estimate of the hypothesis-conditional pdf is specified by;

{circumflex over (P)}_glob(x|H_k)=α

_q,k if xε

E_q,k∩

E_q-l,k), (E_0,k=E_l,k),k=1, . . . , N

for a selected confidence-interval parameter α

_q,k.

3. The computer-implemented method of claim 1, wherein the local estimate for a hypothesis is specified as a probability that an observed vector of tests x and an associated discrete neighbor counting pattern {C_l,k(x)}, l=1, . . . , L_k, k =1,. . ., N might actually be observed, wherein the neighbor counting pattern comprises counting neighbors in the distance layers for each class:

{C_{l,k },l=}1, . . . , L_k, wherein the integer C_l,k is the number of neighbors associated with the k-th hypothesis whose test values are distanced from a next test value within the l-th globally-transformed distance layer for the k-th class;

4. The computer-implemented method of claim 3, wherein the selected k-th class of the test data corresponds to a selected training subset class of the test data.

5. The computer-implemented method of claim 1, further including:

performing a training mode in which a training subset class of the test data is used to produce the hypothesis-conditional probability density functions p(x|H_k); and

performing a prediction mode in which a set of posterior probabilities is determined for the set H of hypotheses, wherein the hypothesis-conditional probability density functions p(x |H^k) are produced from the global estimates and from the local estimate.

6. The computer-implemented method of claim 5, wherein the selected k-th class of the test data corresponds to the training subset class of the test data.

7. The computer-implemented method of claim 1, wherein the posterior test-condition probabilities provide a diagnosis or risk of developing a disease or diseases.

8. The computer-implemented method of claim 7, wherein the data comprises biochemical data from a subject.

9. The computer-implemented method of claim 7, wherein the data comprises medical history data from a subject.

10. The computer-implemented method of claim 7, wherein the data comprises physiological data from a subject.

11. The computer-implemented method of claim 7, wherein the data comprises clinical data from a subject.

12. The computer-implemented method of claim 7, wherein the diseases are selected from the group consisting of cardiovascular diseases, diabetes, neurodegenerative diseases, malignancies, ophthalmic diseases, blood diseases, respiratory diseases, endocrine diseases, bacterial, parasitic, fungal or viral infections, inflammatory diseases, autoimmune diseases, and reproductive diseases.

13. A non-transitory computer readable medium containing instructions stored therein for causing a computer processor to perform a method comprising:

determining a set of posterior test-conditional probability density functions (pdf) p(H_k |x) for a set H of hypotheses relating to a set X of test data conditioned on the test data based on (i) an estimate for one or more hypothesis-conditional pdf p(x|H_k) for the test data conditioned on the hypotheses and (ii) a set of prior pdf p(H_k) for each hypothesis;

wherein the p(x|H_k) estimates include (a) a global estimate produced in accordance with uncertainties in the statistical characteristics of the test data relating to each hypothesis-conditional pdf p(x|H_k) and (b) a local estimate produced in accordance with a discrete neighbor counting process for the test data relative to the global estimate for the corresponding hypothesis-conditional pdf.

14. The non-transitory computer readable medium as defined in claim 13, wherein the uncertainties in the statistical characteristics are specified as an ellipsoid about the test data for each hypothesis and each ellipsoid is defined by an m-dimensional ellipsoid E_q,k for each hypothesis H_k and is specified by:

E_q,k={x;

(x−

m_x,k)^TP_x,k<sup>−

1</sup>(x−

m_x,k)≦

μ

_q,k²}

where the m×

1 vector x is the argument in the space of test data, the m×

1 vector m_x,k is the mean (center) of each ellipsoid, the m×

m matrix P_x,k is a covariance matrix of the ellipsoid, and the scalar μ

² _q,k defines the size of the q-th ellipsoid, such that the global estimate of the hypothesis-conditional pdf is specified by;

{circumflex over (P)}_glob(x|H_k)=α

_q,k if xε

E_q,k∩

E_q-1,k), (E_0,k=E_l,k),k=1, . . . , N

for a selected confidence interval parameter α

_q,k.

15. The non-transitory computer readable medium as defined in claim 13, wherein the local estimate for a hypothesis is specified as a probability that an observed vector of tests x and an associated discrete neighbor counting pattern {C_l,k(x)},l=1, . . ., L_k, k =1,. . .,N might actually be observed, wherein the neighbor counting pattern comprises counting neighbors in the distance layers for each class:

{C_l,k}, l=1, . . ., L_k, wherein the integer C_l,k is the number of test elements associated with the k-th hypothesis whose test values are distanced from a next test value within the l-th globally-transformed distance layer for the k-th class;

16. The non-transitory computer readable medium as defined in claim 15, wherein the selected k-th class of the test data corresponds to a selected training subset class of the test data.

17. The non-transitory computer readable medium as defined in claim 13, further including:

performing a training mode in which a training subset class of the test data is used to produce the hypothesis-conditional probability density functions p(x|H_k); and

performing a prediction mode in which a set of posterior probabilities is determined for the set H of hypotheses, wherein the hypothesis-conditional probability density functions p(x|H_k) are produced from the global estimates and from the local estimate.

18. The non-transitory computer readable medium as defined in claim 17, wherein the selected k-th class of the test data corresponds to the training subset class of the test data.

19. The non-transitory computer readable medium as defined in claim 13, wherein the posterior test-condition probabilities provide a diagnosis or risk of developing a disease or diseases.

20. The non-transitory computer readable medium as defined in claim 19, wherein the data comprises biochemical data from a subject.

21. The non-transitory computer readable medium as defined in claim 19, wherein the data comprises medical history data from a subject.

22. The non-transitory computer readable medium as defined in claim 19, wherein the data comprises physiological data from a subject.

23. The non-transitory computer readable medium as defined in claim 19, wherein the data comprises clinical data from a subject.

24. The non-transitory computer readable medium as defined in claim 19, wherein the diseases are selected from the group consisting of cardiovascular diseases, diabetes, neurodegenerative diseases, malignancies, ophthalmic diseases, blood diseases, respiratory diseases, endocrine diseases, bacterial, parasitic, fungal or viral infections, inflammatory diseases, autoimmune diseases, and reproductive diseases.