Predicting Heart Failure. Группа авторов

the entire chest CT image into numbers of anatomically significant regions that focus on the four chambers of the heart. The manual process of segmentation is becoming replaced by computer-aided techniques such as graph-based segmenting, mean-thresholding, fuzzy clustering methods, and the latest deep learning approach, which has shown promising results. The deep learning system can be trained to identify and quantify coronary artery calcium. This makes an effective early detection device for coronary calcification from atherosclerosis as it detects calcification before symptoms develop. This forms a powerful predictor of future heart problems.

One of the works proposed in the literature regarding CAC was about developing an algorithm that excludes CT scans with negative CAC scores and segments CAC in cases where positive scores are found. The segmented region can further proceed to radiologists for accurate detection. The proposed method highly reduces the workload of radiologists [32]. The proposed method utilized an integrated architecture model which consists of two CNNs where one is for classification and the other for segmentation. The model was able to exclude 86% of the negative cases and segmentation achieved a Dice coefficient of 0.63 and 0.84, for internal and external validation, respectively.

Another research group developed a deep learning model for CAC classification and segmentation [33]. The group focused on calcium quantification of chest CT scans and compared it to manual evaluation. The model was a combination of CNNs along with a ResNet architecture for image feature extraction, as well as an FCN for spatial coordinate features. Their method displayed a high correlation with the manual evaluation for detecting the presence of calcification, with results of 91% sensitivity and 92% specificity. In the case of calcium volume determination, the AI model was able to produce an excellent correlation with the manual determination with no significant difference found. The method proved to be fully automated, reducing the time for evaluation while optimizing clinical calcium scoring.

The work by Zhang et al. [34] utilized deep learning for calcium quantification from CT scan images. They developed a fully automated framework to detect CAC, using 3D CT scans as input for the model and extracting features to apply segmentation and calcification. The obtained results of the proposed method have no significant difference compared to the manual method.

Dekker et al. [35], implemented the deep learning technique to calculate the CAC score during myocardial perfusion imaging (MPI) assessment. They defined a threshold for CAC scores where it was low (<400) and high (≥400). The deep learning model used in the proposed method was previously validated in other approaches. The outcomes of the research work highlighted that high CAC scores presented higher accumulative event rates. They also proved that their method could progress risk stratification leading to customized treatments for patients.

In conclusion, AI methods showed better automation and higher accuracy in diagnosis in some applications. Some of the outcomes are even open to further enhancement which could lead to higher performance. This could help to reduce the effort of physicians and radiologists in diagnosing heart disease in the future. AI based methods can’t replace clinical methods such as ECG, EEG, or CT scans; however, they can automate the decision-making task.

      2.6 Conclusion

      Heart diseases are very common nowadays and are one of the major contributors of world mortality rate. The prompt diagnosis of heart disease can reduce the casualty as well as mortality associated with the risk of heart disease to a great extent. Today, due to the technological advancement in signal processing, medical imaging, sensors, etc., diagnosis of heart disease and finding the underlying specific reasons is not hard. Future versions of the medical devices, including the stethoscope and ECG machines, will utilize AI technologies for efficient detection of heart abnormalities in hospitals and clinics. However, conventional methods will also be used alongside advanced methods, with most of the former, including inspection and palpation, being cost-effective and not requiring any advanced devices or sensors. Recent advancements that enabled the development of neural network-based stethoscopes will reduce the effort of physicians to perform conventional auscultation examinations.

      This chapter has briefly discussed the various conventional clinical methods for heart disease prediction and has presented several physiological attributes considered by the physician for diagnosing heart disease. The clinical significance of psychological attributes has also been discussed and we provided a brief history of the devices utilized by cardiologists, physicians, and radiologists for heart examination. The chapter ended by providing a brief discussion on how AI can assist physicians as well as a radiologists in cardiovascular examination.

      References

      1 1 NCBI Bookshelf. (2004). Cardiology explained: Cardiovascular Examination. A service of the National Library of Medicine, National Institutes of Health.

      2 2 Malik, M.B.and Gopal, S. (2020). Cardiac exam. StatPearls.

      3 3 Jacob, R.and Khan, M. (2018). Cardiac biomarkers: What is and what can be. Indian Journal of Cardiovascular Disease in Women WINCARS 03 (04). https://doi.org/10.1055/s-0039-1679104.

      4 4 Peterson, P.N., Magid, D.J., Ross, C., Ho, P.M., Rumsfeld, J.S., Lauer, M.S., Lyons, E.E., Smith, S.S., and Masoudi, F.A. (2008). Association of exercise capacity on treadmill with future cardiac events in patients referred for exercise testing. Archives of Internal Medicine 168 (2). https://doi.org/10.1001/archinternmed.2007.68.

      5 5 Cole, C.R., Foody, J.A.M., Blackstone, E.H., and Lauer, M.S. (2000). Heart rate recovery after submaximal exercise testing as a predictor of mortality in a cardiovascularly healthy cohort. Annals of Internal Medicine 132 (7). https://doi.org/10.7326/0003-4819-132-7-200004040-00007.

      6 6 Jouven, X., Empana, J.-P., Schwartz, P.J., Desnos, M., Courbon, D., and Ducimetière, P. (2005). Heart-rate profile during exercise as a predictor of sudden death. New England Journal of Medicine 352 (19). https://doi.org/10.1056/nejmoa043012.

      7 7 Kolber, M.R.and Scrimshaw, C. (2014). Family history of cardiovascular disease. Canadian Family Physician 60 (11).

      8 8 Benjamin, E.J., Blaha, M.J., Chiuve, S.E., Cushman, M., Das, S.R., Deo, R., De Ferranti, S.D., Floyd, J., Fornage, M., Gillespie, C., Isasi, C.R., Jim’nez, M.C., Jordan, L.C., Judd, S.E., Lackland, D., Lichtman, J.H., Lisabeth, L., Liu, S., Longenecker, C.T., and Muntner, P. (2017). Heart disease and stroke statistics – 2017 Update: A report from the American Heart Association. Circulation 135 (10). https://doi.org/10.1161/CIR.0000000000000485.

      9 9 Franklin, S.S., Larson, M.G., Khan, S.A., Wong, N.D., Leip, E.P., Kannel, W.B., and Levy, D. (2001). Does the relation of blood pressure to coronary heart disease risk change with aging?: The Framingham heart study. Circulation 103 (9). https://doi.org/10.1161/01.CIR.103.9.1245.

      10 10 Rader, D.J.and Hovingh, G.K. (2014). HDL and cardiovascular disease. The Lancet 384 (9943). https://doi.org/10.1016/S0140-6736(14)61217-4.

      11