Performance Improvement of Decision Trees for Diagnosis of Coronary Artery Disease Using Multi Filtering Approach

Penyakit arteri koroner (coronary artery disease) menjadi penyebab utama kematian penduduk di dunia setidaknya selama dua dekade (2000-2019) dan mengalami peningkatan kematian terbesar dalam rentang waktu tersebut dibandingkan dengan penyebab kematian lainnya. Keberhasilan memprediksi penyakit arteri koroner secara dini berdasarkan data medis bermanfaat bagi pasien dan juga bagi kestabilan perekonomian negara. Tujuan penelitian ini adalah memprediksi penyakit arteri koroner jantung dengan mengimplementasikan dua metode statistical learning yaitu Multinomial Naïve Bayes dan pohon keputusan dengan validasi silang 10-fold, dimana variabel-variabel numerik didiskritisasi untuk memperoleh variabel-variabel kategorik. Hasil penelitian menunjukkan bahwa metode Pohon Keputusan memiliki kinerja yang lebih baik dibandingkan metode Multinomial Naïve Bayes dalam memprediksi penyakit arteri koroner. Ukuran kinerja metode Pohon Keputusan memperoleh tingkat akurasi 99,63 %, sensitivitas 100 %, spesifisitas 99,33%, presisi 99,23 %, dan nilai prediksi negatif (NPV) 100 %. Ukuran-ukuran ini mengindikasikan bahwa metode Pohon Keputusan layak digunakan untuk memprediksi penyakit arteri coroner, termasuk data independent berupa data penyakit arteri coroner lainnya dengan variable predictor yang sama. Hasil penelitian ini juga menunjukkan bahwa perbedaan rujukan dengan penelitian-penelitian sebelumnya dalam mendiskritisasi variabel numerik mampu meningkatkan kinerja metode dalam memprediksi penyakit arteri coroner.

Download Full-text

Elevated level of circulatory sTLT1 induces inflammation through SYK/MEK/ERK signalling in coronary artery disease

Clinical Science ◽

10.1042/cs20190999 ◽

2019 ◽

Vol 133 (22) ◽

pp. 2283-2299

Author(s):

Apabrita Ayan Das ◽

Devasmita Chakravarty ◽

Debmalya Bhunia ◽

Surajit Ghosh ◽

Prakash C. Mandal ◽

...

Keyword(s):

Risk Factors ◽

Coronary Artery Disease ◽

Coronary Artery ◽

Chronic Inflammation ◽

Ex Vivo ◽

Human Subjects ◽

Critical Role ◽

Atherosclerotic Cardiovascular Disease ◽

Tnf Α ◽

Artery Disease

Abstract The role of inflammation in all phases of atherosclerotic process is well established and soluble TREM-like transcript 1 (sTLT1) is reported to be associated with chronic inflammation. Yet, no information is available about the involvement of sTLT1 in atherosclerotic cardiovascular disease. Present study was undertaken to determine the pathophysiological significance of sTLT1 in atherosclerosis by employing an observational study on human subjects (n=117) followed by experiments in human macrophages and atherosclerotic apolipoprotein E (apoE)−/− mice. Plasma level of sTLT1 was found to be significantly (P<0.05) higher in clinical (2342 ± 184 pg/ml) and subclinical cases (1773 ± 118 pg/ml) than healthy controls (461 ± 57 pg/ml). Moreover, statistical analyses further indicated that sTLT1 was not only associated with common risk factors for Coronary Artery Disease (CAD) in both clinical and subclinical groups but also strongly correlated with disease severity. Ex vivo studies on macrophages showed that sTLT1 interacts with Fcɣ receptor I (FcɣRI) to activate spleen tyrosine kinase (SYK)-mediated downstream MAP kinase signalling cascade to activate nuclear factor-κ B (NF-kB). Activation of NF-kB induces secretion of tumour necrosis factor-α (TNF-α) from macrophage cells that plays pivotal role in governing the persistence of chronic inflammation. Atherosclerotic apoE−/− mice also showed high levels of sTLT1 and TNF-α in nearly occluded aortic stage indicating the contribution of sTLT1 in inflammation. Our results clearly demonstrate that sTLT1 is clinically related to the risk factors of CAD. We also showed that binding of sTLT1 with macrophage membrane receptor, FcɣR1 initiates inflammatory signals in macrophages suggesting its critical role in thrombus development and atherosclerosis.

Download Full-text