A machine‐learning algorithm to grade heart murmurs and stage preclinical myxomatous mitral valve disease in dogs
Abstract Background The presence and intensity of heart murmurs are sensitive indicators of several cardiac diseases in dogs, particularly myxomatous mitral valve disease (MMVD), but accurate interpretation requires substantial clinical expertise. Objectives Assess if a machine‐learning algorithm ca...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-11-01
|
| Series: | Journal of Veterinary Internal Medicine |
| Subjects: | |
| Online Access: | https://doi.org/10.1111/jvim.17224 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846157552192061440 |
|---|---|
| author | Andrew McDonald Jose Novo Matos Joel Silva Catheryn Partington Eve J. Y. Lo Virginia Luis Fuentes Lara Barron Penny Watson Anurag Agarwal |
| author_facet | Andrew McDonald Jose Novo Matos Joel Silva Catheryn Partington Eve J. Y. Lo Virginia Luis Fuentes Lara Barron Penny Watson Anurag Agarwal |
| author_sort | Andrew McDonald |
| collection | DOAJ |
| description | Abstract Background The presence and intensity of heart murmurs are sensitive indicators of several cardiac diseases in dogs, particularly myxomatous mitral valve disease (MMVD), but accurate interpretation requires substantial clinical expertise. Objectives Assess if a machine‐learning algorithm can be trained to accurately detect and grade heart murmurs in dogs and detect cardiac disease in electronic stethoscope recordings. Animals Dogs (n = 756) with and without cardiac disease attending referral centers in the United Kingdom. Methods All dogs received full physical and echocardiographic examinations by a cardiologist to grade any murmurs and identify cardiac disease. A recurrent neural network algorithm, originally trained for heart murmur detection in humans, was fine‐tuned on a subset of the dog data to predict the cardiologist's murmur grade from the audio recordings. Results The algorithm detected murmurs of any grade with a sensitivity of 87.9% (95% confidence interval [CI], 83.8%‐92.1%) and a specificity of 81.7% (95% CI, 72.8%‐89.0%). The predicted grade exactly matched the cardiologist's grade in 57.0% of recordings (95% CI, 52.8%‐61.0%). The algorithm's prediction of loud or thrilling murmurs effectively differentiated between stage B1 and B2 preclinical MMVD (area under the curve [AUC], 0.861; 95% CI, 0.791‐0.922), with a sensitivity of 81.4% (95% CI, 68.3%‐93.3%) and a specificity of 73.9% (95% CI, 61.5%‐84.9%). Conclusion and Clinical Importance A machine‐learning algorithm trained on humans can be successfully adapted to grade heart murmurs in dogs caused by common cardiac diseases, and assist in differentiating preclinical MMVD. The model is a promising tool to enable accurate, low‐cost screening in primary care. |
| format | Article |
| id | doaj-art-ae7dba21a96c4da3b4aefdf52dec1e95 |
| institution | Kabale University |
| issn | 0891-6640 1939-1676 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Veterinary Internal Medicine |
| spelling | doaj-art-ae7dba21a96c4da3b4aefdf52dec1e952024-11-25T08:31:40ZengWileyJournal of Veterinary Internal Medicine0891-66401939-16762024-11-013862994300410.1111/jvim.17224A machine‐learning algorithm to grade heart murmurs and stage preclinical myxomatous mitral valve disease in dogsAndrew McDonald0Jose Novo Matos1Joel Silva2Catheryn Partington3Eve J. Y. Lo4Virginia Luis Fuentes5Lara Barron6Penny Watson7Anurag Agarwal8Department of Engineering University of Cambridge Cambridge United KingdomDepartment of Veterinary Medicine University of Cambridge Cambridge United KingdomDepartment of Veterinary Medicine University of Cambridge Cambridge United KingdomDepartment of Veterinary Medicine University of Cambridge Cambridge United KingdomRoyal Veterinary College Hertfordshire United KingdomRoyal Veterinary College Hertfordshire United KingdomDavies Veterinary Specialists Hitchin United KingdomDepartment of Veterinary Medicine University of Cambridge Cambridge United KingdomDepartment of Engineering University of Cambridge Cambridge United KingdomAbstract Background The presence and intensity of heart murmurs are sensitive indicators of several cardiac diseases in dogs, particularly myxomatous mitral valve disease (MMVD), but accurate interpretation requires substantial clinical expertise. Objectives Assess if a machine‐learning algorithm can be trained to accurately detect and grade heart murmurs in dogs and detect cardiac disease in electronic stethoscope recordings. Animals Dogs (n = 756) with and without cardiac disease attending referral centers in the United Kingdom. Methods All dogs received full physical and echocardiographic examinations by a cardiologist to grade any murmurs and identify cardiac disease. A recurrent neural network algorithm, originally trained for heart murmur detection in humans, was fine‐tuned on a subset of the dog data to predict the cardiologist's murmur grade from the audio recordings. Results The algorithm detected murmurs of any grade with a sensitivity of 87.9% (95% confidence interval [CI], 83.8%‐92.1%) and a specificity of 81.7% (95% CI, 72.8%‐89.0%). The predicted grade exactly matched the cardiologist's grade in 57.0% of recordings (95% CI, 52.8%‐61.0%). The algorithm's prediction of loud or thrilling murmurs effectively differentiated between stage B1 and B2 preclinical MMVD (area under the curve [AUC], 0.861; 95% CI, 0.791‐0.922), with a sensitivity of 81.4% (95% CI, 68.3%‐93.3%) and a specificity of 73.9% (95% CI, 61.5%‐84.9%). Conclusion and Clinical Importance A machine‐learning algorithm trained on humans can be successfully adapted to grade heart murmurs in dogs caused by common cardiac diseases, and assist in differentiating preclinical MMVD. The model is a promising tool to enable accurate, low‐cost screening in primary care.https://doi.org/10.1111/jvim.17224auscultationcardiologydogelectronic stethoscopestage B |
| spellingShingle | Andrew McDonald Jose Novo Matos Joel Silva Catheryn Partington Eve J. Y. Lo Virginia Luis Fuentes Lara Barron Penny Watson Anurag Agarwal A machine‐learning algorithm to grade heart murmurs and stage preclinical myxomatous mitral valve disease in dogs Journal of Veterinary Internal Medicine auscultation cardiology dog electronic stethoscope stage B |
| title | A machine‐learning algorithm to grade heart murmurs and stage preclinical myxomatous mitral valve disease in dogs |
| title_full | A machine‐learning algorithm to grade heart murmurs and stage preclinical myxomatous mitral valve disease in dogs |
| title_fullStr | A machine‐learning algorithm to grade heart murmurs and stage preclinical myxomatous mitral valve disease in dogs |
| title_full_unstemmed | A machine‐learning algorithm to grade heart murmurs and stage preclinical myxomatous mitral valve disease in dogs |
| title_short | A machine‐learning algorithm to grade heart murmurs and stage preclinical myxomatous mitral valve disease in dogs |
| title_sort | machine learning algorithm to grade heart murmurs and stage preclinical myxomatous mitral valve disease in dogs |
| topic | auscultation cardiology dog electronic stethoscope stage B |
| url | https://doi.org/10.1111/jvim.17224 |
| work_keys_str_mv | AT andrewmcdonald amachinelearningalgorithmtogradeheartmurmursandstagepreclinicalmyxomatousmitralvalvediseaseindogs AT josenovomatos amachinelearningalgorithmtogradeheartmurmursandstagepreclinicalmyxomatousmitralvalvediseaseindogs AT joelsilva amachinelearningalgorithmtogradeheartmurmursandstagepreclinicalmyxomatousmitralvalvediseaseindogs AT catherynpartington amachinelearningalgorithmtogradeheartmurmursandstagepreclinicalmyxomatousmitralvalvediseaseindogs AT evejylo amachinelearningalgorithmtogradeheartmurmursandstagepreclinicalmyxomatousmitralvalvediseaseindogs AT virginialuisfuentes amachinelearningalgorithmtogradeheartmurmursandstagepreclinicalmyxomatousmitralvalvediseaseindogs AT larabarron amachinelearningalgorithmtogradeheartmurmursandstagepreclinicalmyxomatousmitralvalvediseaseindogs AT pennywatson amachinelearningalgorithmtogradeheartmurmursandstagepreclinicalmyxomatousmitralvalvediseaseindogs AT anuragagarwal amachinelearningalgorithmtogradeheartmurmursandstagepreclinicalmyxomatousmitralvalvediseaseindogs AT andrewmcdonald machinelearningalgorithmtogradeheartmurmursandstagepreclinicalmyxomatousmitralvalvediseaseindogs AT josenovomatos machinelearningalgorithmtogradeheartmurmursandstagepreclinicalmyxomatousmitralvalvediseaseindogs AT joelsilva machinelearningalgorithmtogradeheartmurmursandstagepreclinicalmyxomatousmitralvalvediseaseindogs AT catherynpartington machinelearningalgorithmtogradeheartmurmursandstagepreclinicalmyxomatousmitralvalvediseaseindogs AT evejylo machinelearningalgorithmtogradeheartmurmursandstagepreclinicalmyxomatousmitralvalvediseaseindogs AT virginialuisfuentes machinelearningalgorithmtogradeheartmurmursandstagepreclinicalmyxomatousmitralvalvediseaseindogs AT larabarron machinelearningalgorithmtogradeheartmurmursandstagepreclinicalmyxomatousmitralvalvediseaseindogs AT pennywatson machinelearningalgorithmtogradeheartmurmursandstagepreclinicalmyxomatousmitralvalvediseaseindogs AT anuragagarwal machinelearningalgorithmtogradeheartmurmursandstagepreclinicalmyxomatousmitralvalvediseaseindogs |