Diagnosis of stage B2 DMVD
The invention relates to method of diagnosing stage B2 degenerative mitral valve disease (DMVD) in a dog, a method of determining the probability of a dog having stage B2 DMVD, a method of training a model to predict stage B2 DMVD in a dog, and a related computer program and system.
1 . A method of diagnosing or screening for stage B2 degenerative mitral valve disease (DMVD) in a dog, the method comprising the steps of:
(a) receiving characteristic data relating to the dog, the characteristic data comprising appetite, creatinine concentration, murmur intensity, and NT-proBNP concentration; and
(b) processing the characteristic data using a model, wherein an output of the model is an output value associated with the probability of the dog having stage B2 DMVD.
2 . The method of claim 1 , wherein the dog has received a diagnosis of DMVD prior to step (a).
3 . The method of claim 1 , wherein the model is derived using a regression process.
4 . The method of claim 3 , wherein the model is derived using multivariable logistic regression or regularised regression.
5 . The method of claim 1 , wherein the model is derived using a machine learning process.
6 . The method of claim 5 , wherein the model is derived using a support vector machines (SVM) process, a random forest process, or a gradient boosting process.
7 . A non-transitory computer-readable medium comprising code that, when executed by a computer system, instructs the computer system to perform the method of claim 1 .
8 . The method of claim 1 , further comprising:
(c) diagnosing the presence or absence of stage B2 DMVD in the dog based on a comparison of the output value to a predetermined value.
9 . The method of claim 8 , wherein the presence of stage B2 DMVD is indicated by an output value associated with a probability of the dog having stage B2 DMVD of greater than or equal to 0.872, and the absence of stage B2 DMVD is indicated by an output value associated with a probability of the dog having stage B2 DMVD of less than 0.106.
10 . A method of training a model to predict stage B2 DMVD in a dog, the method comprising:
(i) processing characteristic data relating to a dog using the model to output an output value, the characteristic data comprising appetite, creatinine concentration, murmur intensity, and NT-proBNP concentration;
(ii) comparing the output value to a diagnosis of presence or absence of stage B2 DMVD in the dog; and
(iii) adjusting the parameters of the model based on the result of the comparison.
11 . The method of claim 10 , wherein the diagnosis of presence or absence of stage B2 DMVD is based on echocardiographic examination.
12 . The method of claim 10 , further comprising:
(iv) repeating steps (i) to (iii) one or more times, wherein the characteristic data relate to a different dog each time steps (i) to (iii) are performed.
13 . The method of claim 10 , wherein the model is derived using a regression process.
14 . The method of claim 13 , wherein the model is derived using multivariable logistic regression or regularised regression.
15 . The method of claim 10 , wherein the model is derived using a machine learning process.
16 . The method of claim 15 , wherein the model is derived using a support vector machines (SVM) process, a random forest process, or a gradient boosting process.
17 . A non-transitory computer-readable medium comprising code that, when executed by a computer system, instructs the computer system to perform the method of claim 10 .
18 . A system for diagnosing stage B2 DMVD in dogs, the system comprising:
an input device configured to receive characteristic data relating to a dog, the characteristic data comprising appetite, creatinine concentration, murmur intensity, and NT-proBNP concentration;
a model configured to receive the characteristic data and generate an output value associated with the probability of the dog having stage B2 DMVD; and
an output device configured to output the output value.