A machine learning model to classify aortic dissection patients in the early diagnosis phase

Aortic dissection is one of the most clinical-challenging and life-threatening cardiovascular diseases associated with high morbidity and mortality. Aortic dissection requires fast diagnosis and timely therapy. Any delay or misdiagnosis can cause severe consequence to aortic dissection patients with even higher mortality. To better help physicians identify the potential dissection within the scope of all misdiagnosed patients, this paper describes a method which is developed with data mining methods for aortic dissection patient classification and prediction in the phase of early diagnosis. Various machine learning algorithms were used to build the models which were all trained and tested on the patient dataset with cross validation. Among them, Bayesian Network model achieved the best performance by predicting at a precision rate of 84.55% with Area Under the Curve (AUC) value of 0.857. On this basis, the Bayesian Network model can help physicians better with early diagnosis of aortic dissection in clinical practice. Beyond this study, more data from diverse regions and the internal pathology can be crucial to further build a universal model with broader predictive power.

[1]  Patricia A. H. Williams,et al.  Big data in healthcare: What is it used for? , 2014 .

[2]  C. Macaya,et al.  Aortic dissection occurring during coronary angioplasty: angiographic and transesophageal echocardiographic findings. , 1997, Catheterization and cardiovascular diagnosis.

[3]  Long-Term Outcome and Quality of Life in Aortic Type A Dissection Survivors. , 2015, The Thoracic and cardiovascular surgeon.

[4]  Rema Padman,et al.  Tabu Search-Enhanced Graphical Models for Classification in High Dimensions , 2008, INFORMS J. Comput..

[5]  J. Swanevelder,et al.  Diagnosis and management of aortic dissection , 2009 .

[6]  Rema Padman,et al.  Machine Learning Approaches for Early DRG Classification and Resource Allocation , 2015, INFORMS J. Comput..

[7]  T. Kamp,et al.  Myocardial infarction, aortic dissection, and thrombolytic therapy. , 1994, American heart journal.

[8]  A Evangelista,et al.  The International Registry of Acute Aortic Dissection (IRAD): new insights into an old disease. , 2000, JAMA.

[9]  L. Svensson,et al.  Aortic dissection and aortic aneurysm surgery: clinical observations, experimental investigations, and statistical analyses. Part III. , 1993, Current problems in surgery.

[10]  Leu Hj.  Classification of vasculitides. A survey. , 1995 .

[11]  L. Svensson,et al.  Aortic dissection and aortic aneurysm surgery: clinical observations, experimental investigations, and statistical analyses. Part I. , 1992, Current problems in surgery.

[12]  W R Webb,et al.  Management of acute aortic dissection. , 1975, The Annals of thoracic surgery.

[13]  D Kromhout,et al.  The burden of cardiovascular diseases mortality in Europe. Task Force of the European Society of Cardiology on Cardiovascular Mortality and Morbidity Statistics in Europe. , 1997, European heart journal.

[14]  Ian H. Witten,et al.  Data mining - practical machine learning tools and techniques, Second Edition , 2005, The Morgan Kaufmann series in data management systems.

[15]  Pedro Larrañaga,et al.  A review of feature selection techniques in bioinformatics , 2007, Bioinform..

[16]  Lijue Liu,et al.  A study of aortic dissection screening method based on multiple machine learning models , 2020, Journal of thoracic disease.

[17]  J. Oh,et al.  Presence of simple renal cysts is associated with increased risk of aortic dissection: a common manifestation of connective tissue degeneration? , 2010, Heart.

[18]  Frank J Criado,et al.  Aortic dissection: a 250-year perspective. , 2011, Texas Heart Institute journal.

[19]  Xiang Ma,et al.  Sex-Related Differences Between Patients With Symptomatic Acute Aortic Dissection , 2016, Medicine.

[20]  R. Desanctis,et al.  The clinical recognition of dissecting aortic aneurysm. , 1976, The American journal of medicine.

[21]  LarrañagaPedro,et al.  A review of feature selection techniques in bioinformatics , 2007 .

[22]  Ya-Ju Fan,et al.  Optimizing feature selection to improve medical diagnosis , 2010, Ann. Oper. Res..

[23]  W. Melrose.  Lymphatic filariasis: new insights into an old disease. , 2002, International journal for parasitology.

[24]  Martti Juhola,et al.  Classification of Otoneurological Cases According to Bayesian Probabilistic Models , 2010, Journal of Medical Systems.

[25]  Mark A. Hall,et al.  Correlation-based Feature Selection for Machine Learning , 2003 .

[26]  Guifang Yang,et al.  Potential biomarkers for early diagnosis of acute aortic dissection. , 2015, Heart & lung : the journal of critical care.

[27]  A. Tajik,et al.  Clinical features and differential diagnosis of aortic dissection: experience with 236 cases (1980 through 1990). , 1993, Mayo Clinic proceedings.

[28]  B. Matthews.  Comparison of the predicted and observed secondary structure of T4 phage lysozyme. , 1975, Biochimica et biophysica acta.