Method and apparatus for real time predictive modeling for chronically ill patients

• US 20060025931A1
• Filed: 03/08/2005
• Published: 02/02/2006
• Est. Priority Date: 07/30/2004
• Status: Abandoned Application

• Current Assignee: Intermed Advisor Incorporated
• Original Assignee: Intermed Advisor Incorporated
• Inventors: Hunter, Ian, Rosen, Richard
• Application Number:
  US11/074,425
• Publication Number:
  US 20060025931A1
• Time in Patent Office: Days
• US Class Current: 702/19
• 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

Abstract

Various embodiments of the present invention are directed to a method and apparatus for improving the care of patients (e.g., chronically ill patients). In one example (which example is intended to be illustrative and not restrictive), the invention may be designed to improve such care through real time output (e.g., periodic, such as hourly, daily, weekly or monthly) to deter development of co-morbidities associated with many chronic diseases. Various embodiments of the invention may improve the care of chronically ill patients by: easing data collection, simplifying data transmission, efficiently interpreting chronically ill patient information, providing time series to form the basis of subsequent analysis, expanding the ability of the chronically ill patient or other user of the invention to understand the relationship between the medical practice and the patient'"'"'s own lifestyle and/or easing the workload of healthcare providers (such as the patient'"'"'s physician). In this regard, the invention may help in creating dialogue between chronically ill patients and healthcare providers that otherwise would be impossible.

Claims

1. A computer implemented method for predictive modeling of a condition of a patient, comprising:

making a plurality of measurements of a physical parameter exhibited by the patient;

organizing the plurality of measurements into time series data; and

applying a variance detection algorithm to the time series data to predict a future condition of the patient.

2. The method of claim 1, wherein the variance detection algorithm comprises an algorithm selected from the group including:

(a) an ARIMA Model;

(b) a D-Statistic Procedure; and

(c) a Non-Parametric Approach.

3. The method of claim 2, wherein the ARIMA Model comprises a formula specified at least in part as:

Y_t=α

₁Y<sub>t−

1</sub>+ . . . +α

_pY<sub>t−

p</sub>+e_t+e_t+β

₁e<sub>t−

1</sub>+ . . . +β

_qe<sub>t−

q</sub>.

4. The method of claim 2, wherein the D-Statistic Procedure comprises a formula specified at least in part as:

$D_k=\frac{C_k}{C_T}-\frac{k}{T}.$

5. The method of claim 2, wherein the Non-Parametric Approach comprises a formula specified at least in part as:

U_t,T=2W_t−

t(T+1).

6. The method of claim 1, wherein the prediction of the future condition of the patient is carried out in real time, as additional measurements are made and organized into time series data.

7. The method of claim 6, wherein the prediction of the future condition of the patient is provided to at least one of:

(a) the patient;

(b) a caregiver associated with the patient; and

(c) a healthcare provider associated with the patent.

8. The method of claim 7, wherein the healthcare provider is selected from the group including:

(a) a doctor; and

(b) a nurse.

9. The method of claim 1, wherein the physical parameter is selected from the group including:

(a) blood glucose level;

(b) blood pressure;

(c) blood oxygen saturation;

(d) electrical activity;

(e) weight; and

(f) physical activity.

10. The method of claim 1, wherein a plurality of measurements are made of each of a plurality of physical parameters exhibited by the patient.

11. The method of claim 10, wherein the patient is a chronically ill patient.

34. The method of claim 1, wherein the steps are carried out in the order recited.

12. A computer implemented method for predictive modeling of a condition of a patient, comprising:

making a plurality of measurements of a physical parameter exhibited by the patient;

organizing the plurality of measurements into time series data; and

applying a prediction algorithm to the time series data to predict a future condition of the patient;

wherein the prediction algorithm comprises an algorithm selected from the group including;

(a) a General ARMAX Model;

(b) a GARCH Model;

(c) Kalman Filtering;

(d) a Markov Model;

(e) a Random Walk Model;

(f) a Multilayer Neural Network; and

(g) an Extreme Value Analysis.

13. The method of claim 12, wherein the General ARMAX Model comprises a formula specified at least in part as:

$Y_t=C+\underset{i=1}{\overset{R}{\sum <br><br>}}<br><br>{\mathrm{\alpha <br><br>}}_i<br><br>Y_{t-i}+{\mathrm{\varepsilon <br><br>}}_t+\underset{j=1}{\overset{M}{\sum <br><br>}}<br><br>{\mathrm{\beta <br><br>}}_j<br><br>{\mathrm{\varepsilon <br><br>}}_{t-j}+\underset{k=1}{\overset{N}{\sum <br><br>}}<br><br>{\mathrm{\varphi <br><br>}}_k<br><br>X<br><br>\left(t,k\right).$

14. The method of claim 12, wherein the GARCH Model comprises a formula specified at least in part as:

$h_t={\mathrm{\alpha <br><br>}}_0+\underset{i=1}{\overset{q}{\sum <br><br>}}<br><br>{\mathrm{\alpha <br><br>}}_i<br><br>X_{t-i}^2+\underset{j=1}{\overset{p}{\sum <br><br>}}<br><br>{\mathrm{\beta <br><br>}}_j<br><br>h_{t-j}.$

15. The method of claim 12, wherein the Kalman Filtering comprises a formula specified at least in part as:

X_t=AX<sub>t−

1</sub>+Bμ

<sub>t−

1</sub>+ω

<sub>t−

1</sub>.

16. The method of claim 12, wherein the Markov Model comprises a formula specified at least in part as:

P(X_t=j|X₀=i₀,X₁=i₁, . . . X<sub>t−

1</sub>=i<sub>t−

1</sub>)=P(X_t=j|X<sub>t−

1</sub>=i<sub>t−

1</sub>).

17. The method of claim 12, wherein the Random Walk Model comprises a formula specified at least in part as:

Y_t=Y<sub>t−

1</sub>+α

.

18. The method of claim 12, wherein the Multilayer Neural Network comprises a formula specified at least in part as:

${\mathrm{net}}_j=\underset{i=1}{\overset{d}{\sum <br><br>}}<br><br>x_i<br><br>w_{\mathrm{ji}}+w_{\mathrm{j0}}=\underset{i=0}{\overset{d}{\sum <br><br>}}<br><br>x_i<br><br>w_{\mathrm{ji}}\equiv <br><br>W^t<br><br>X.$

19. The method of claim 12, wherein the Extreme Value Analysis includes Parameter Fitting and comprises a formula specified at least in part as:

$p<br><br>\left(D❘<br><br>\mathrm{\theta <br><br>}\right)=\underset{k=1}{\overset{n}{\prod <br><br>}}<br><br>p<br><br>\left(x_k❘<br><br>\mathrm{\theta <br><br>}\right).$

20. The method of claim 12, wherein the Extreme Value Analysis includes Goodness-Of-Fit Testing and comprises a formula specified at least in part as:

${\mathrm{\chi <br><br>}}^2=\underset{i=1}{\overset{k}{\sum <br><br>}}<br><br>{\left(O_i-E_i\right)}^2/E_i.$

21. The method of claim 12, wherein the prediction of the future condition of the patient is carried out in real time, as additional measurements are made and organized into time series data.

22. The method of claim 21, wherein the prediction of the future condition of the patient is provided to at least one of:

(a) the patient;

(b) a caregiver associated with the patient; and

(c) a healthcare provider associated with the patent.

23. The method of claim 22, wherein the healthcare provider is selected from the group including:

(a) a doctor; and

(b) a nurse.

24. The method of claim 12, wherein the physical parameter is selected from the group including:

(a) blood glucose level;

(b) blood pressure;

(c) blood oxygen saturation;

(d) electrical activity;

(e) weight; and

(f) physical activity.

25. The method of claim 12, wherein a plurality of measurements are made of each of a plurality of physical parameters exhibited by the patient.

26. The method of claim 25, wherein the patient is a chronically ill patient.

35. The method of claim 12, wherein the steps are carried out in the order recited.

27. A computer implemented method for predictive modeling of a condition of a patient, comprising:

making a plurality of measurements of a physical parameter exhibited by the patient;

organizing the plurality of measurements into time series data; and

applying a trend detection algorithm to the time series data to predict a future condition of the patient;

wherein the trend detection algorithm comprises an algorithm selected from the group including;

(a) a Piece-Wise Linear Model; and

(b) Pattern Recognition.

28. The method of claim 27, wherein the prediction of the future condition of the patient is carried out in real time, as additional measurements are made and organized into time series data.

29. The method of claim 28, wherein the prediction of the future condition of the patient is provided to at least one of:

(a) the patient;

(b) a caregiver associated with the patient; and

(c) a healthcare provider associated with the patent.

30. The method of claim 29, wherein the healthcare provider is selected from the group including:

(a) a doctor; and

(b) a nurse.

31. The method of claim 27, wherein the physical parameter is selected from the group including:

(a) blood glucose level;

(b) blood pressure;

(c) blood oxygen saturation;

(d) electrical activity;

(e) weight; and

(f) physical activity.

32. The method of claim 27, wherein a plurality of measurements are made of each of a plurality of physical parameters exhibited by the patient.

33. The method of claim 32, wherein the patient is a chronically ill patient.

36. The method of claim 27, wherein the steps are carried out in the order recited.