Machine learning for the diagnosis of pulmonary hypertension

Objective This paper aims to investigate whether machine learning (ML) can be used to predict the state of pulmonary hypertension (PH), including pre-capillary and post-capillary, from echocardiographic data.
Methods Two hundred and seventy-five patients with PH who underwent both echocardiography and right heart catheterization were included in the study. Mean pulmonary artery pressure, pulmonary artery wedge pressure measured by right heart catheterization were used as criteria for judging pre-capillary PH and post-capillary PH. Thirteen echocardiographic indicators were used to predict whether the PH was pre-capillary or post-capillary. Nine ML models were used to make predictions. Accuracy was used as the primary reference standard, and the performance of classification model is observed in conjunction with area under curve (AUC), specificity (Sp), sensitivity (Se), Positive Prediction Value (PPV), Negative Prediction Value (NPV), Positive Likelihood Ratio (PLR) and Negative Likelihood Ratio (NLR) and other assessment protocols.
Results By comparing the accuracy (ACC), recall rate (Recall) and other model effect evaluation index of the classification under the nine ML models, it can be found that the ML model can effectively identify the pre-capillary PH and the post-capillary PH. LogitBoost performed best in nine ML models (ACC=0.87, Recall=0.83, F1score=0.85, AUC=0.87, Se=0.90, NPV=0.88, PPV=0.87, PLR=8.61 and NLR=0.18, AUC=0.83), it showed good results in identification of the pre-capillary PH (ACC=0.83, Recall=0.87, F-score=0.85); Post-vascular PH (ACC=0.90, Recall=0.88, F-score=0.89). Decision Tree (ACC=0.75, Recall=0.77, F1score=0.78, AUC=0.75, Se=0.72, NPV=0.78, PPV=0.77, PLR=3.66 and NLR=0.29, AUC=0.79) performed worst, and the accuracy of the other seven models was greater than 0.82.
Conclusion The classification results of the nine ML models in this paper indicate that the ML method can effectively identify the pre-capillary PH and post-capillary PH from echocardiographic data. Compared with medical diagnosis, ML methods can distinguish between pre-capillary PH and the post-capillary PH under non-invasive conditions.

1. Hoeper MM, Bogaard HJ, Condliffe R, Frantz R, Khanna D, Kurzyna M et al. Definitions and Diagnosis of Pulmonary Hypertension. Journal of the American College of Cardiology. 2013;62(25):D42–50. DOI: 10.1016/j.jacc.2013.10.032

2. Galiè N, Humbert M, Vachiery J-L, Gibbs S, Lang I, Torbicki A et al. 2015 ESC/ERS Guidelines for the diagnosis and treatment of pulmonary hypertension: The Joint Task Force for the Diagnosis and Treatment of Pulmonary Hypertension of the European Society of Cardiology (ESC) and the European Respiratory Society (ERS): Endorsed by: Association for European Paediatric and Congenital Cardiology (AEPC), International Society for Heart and Lung Transplantation (ISHLT). European Heart Journal. 2016;37(1):67–119. DOI: 10.1093/eurheartj/ehv317

3. Cao JY, Wales KM, Cordina R, Lau EMT, Celermajer DS. Pulmonary vasodilator therapies are of no benefit in pulmonary hypertension due to left heart disease: A meta-analysis. International Journal of Cardiology. 2018;273:213–20. DOI: 10.1016/j.ijcard.2018.09.043

4. Liu X, Chen K, Wu T, Weidman D, Lure F, Li J. Use of multimodality imaging and artificial intelligence for diagnosis and prognosis of early stages of Alzheimer’s disease. Translational Research. 2018;194:56–67. DOI: 10.1016/j.trsl.2018.01.001

5. Odajima K, Pawlovsky AP. A detailed description of the use of the kNN method for breast cancer diagnosis. 2014 7th International Conference on Biomedical Engineering and Informatics. IEEE. 688-692. 2014. [DOI: 10.1109/BMEI.2014.7002861]

6. Zheng Y, Yang C, Merkulov A, Bandari M. Early breast cancer detection with digital mammograms using Haar-like features and AdaBoost algorithm. SPIE Commercial + Scientific Sensing and Imaging. Baltimore, Maryland, United States. 2016. [DOI: 10.1117/12.2227342]

7. Kim YH, Kim M-J, Shin HJ, Yoon H, Han SJ, Koh H et al. MRI-based decision tree model for diagnosis of biliary atresia. European Radiology. 2018;28(8):3422–31. DOI: 10.1007/s00330-018-5327-0

8. Chen H, Lin Z, Wu H, Wang L, Wu T, Tan C. Diagnosis of colorectal cancer by near-infrared optical fiber spectroscopy and random forest. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy. 2015;135:185–91. DOI: 10.1016/j.saa.2014.07.005

9. Tin Kam Ho. The random subspace method for constructing decision forests. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1998;20(8):832–44. DOI: 10.1109/34.709601

10. Aduen JF, Castello R, Daniels JT, Diaz JA, Safford RE, Heckman MG et al. Accuracy and Precision of Three Echocardiographic Methods for Estimating Mean Pulmonary Artery Pressure. Chest. 2011;139(2):347–52. DOI: 10.1378/chest.10-0126

11. Aduen JF, Castello R, Lozano MM, Hepler GN, Keller CA, Alvarez F et al. An Alternative Echocardiographic Method to Estimate Mean Pulmonary Artery Pressure: Diagnostic and Clinical Implications. Journal of the American Society of Echocardiography. 2009;22(7):814–9. DOI: 10.1016/j.echo.2009.04.007