A neural network approach for noninvasive detection of coronary artery disease
Başlık çevirisi mevcut değil.
- Tez No: 364482
- Danışmanlar: DOÇ. DR. HALİL ÖZCAN GÜLÇÜR
- Tez Türü: Yüksek Lisans
- Konular: Tıbbi Biyoloji, Medical Biology
- Anahtar Kelimeler: CAD, noninvasive techniques, angiography, diastolic heart sounds, adaptive filtering, periodogram, artificial neural networks
- Yıl: 1994
- Dil: İngilizce
- Üniversite: Boğaziçi Üniversitesi
- Enstitü: Biyomedikal Mühendislik Enstitüsü
- Ana Bilim Dalı: Biyomedikal Mühendisliği Ana Bilim Dalı
- Bilim Dalı: Belirtilmemiş.
- Sayfa Sayısı: Belirtilmemiş.
Özet
Özet yok.
Özet (Çeviri)
The major cause of death in many cases is Coronary Artery Disease (CAD). This disease can be detected by angiography. However, this technique is expensive, risky and invasive. Another noninvasive technique for detecting coronary occlusion before they become serious enough to induce symptoms is based on the knowledge that coronary stenoses produce sounds due to the tulTbulent flow in partially occluded arteries. Recently, experimental systems that make use of the heart sounds for noninvasive detection of CAD have been the subject of active investigation by some research groups. In this study, we intended to improve on the previous studies concernmg noninvasive detection of CAD, using some adaptive noise canceling schemes and artificial neural networks for automatizing detection. For this purpose, using a system developed in the Institute, which includes a PC, two sensitive sound channels and an ECG channel, a number of clinical studies have been performed. Heart sounds from 60 patients (22 healthy and 38 diseased) were recorded in a relatively quiet hospital room, while ambient sounds and patient's ECG were also simultaneously recorded. A sampling frequency of 4 kHz was used for data acquisition. Using ECG information, diastolic portions of the sound signals were isolated manually. The sound signals were first passed through an analog band-pass filter with 150 Hz and 1200 Hz cut-off frequencies and then an adaptive frequency domain filter was used to eliminate the background noise. Window functions of periodogram were employed to achieve better spectral estimation. Frequency regions that were related with the coronary flow was defined. A two layer neural network with eight hidden nodes was trained using data from 20 patients. The neural network was then used for the diagnosis of the remaining 40 patients and gave correct classification rate of 62. 5%.
Benzer Tezler
- EKG verilerinden yapay zeka ile koroner lezyon tespiti ve SYNTAX skoruna göre sınıflandırma
Coronary lesion detection from ECG data with artificial intelligence and classification according to SYNTAX score
ÖMER IŞIK
Tıpta Uzmanlık
Türkçe
2026
KardiyolojiFırat ÜniversitesiKardiyoloji Ana Bilim Dalı
PROF. DR. MEHMET ALİ KOBAT
- Koroner arter hastalığının makine öğrenmesi teknikleriyle teşhisi
Diagnosis of coronary artery disease using machine learning techniques
ŞÜKRÜ ALKAN
Yüksek Lisans
Türkçe
2025
Elektrik ve Elektronik MühendisliğiSakarya ÜniversitesiElektrik-Elektronik Mühendisliği Ana Bilim Dalı
DOÇ. DR. MUHAMMED KÜRŞAD UÇAR
- Kardiyopulmoner bypass cerrahisi sonrası nörokognitif durumların matematiksel yöntemlerle analizi
Analysis of neurocognitive status after cardiopulmonary bypass surgery using mathematical methods
FARUK SANBERK KIZILTAŞ
Doktora
Türkçe
2025
Elektrik ve Elektronik MühendisliğiSakarya ÜniversitesiElektrik ve Elektronik Mühendisliği Ana Bilim Dalı
DR. ÖĞR. ÜYESİ ÖZHAN ÖZKAN
PROF. DR. ALİ FUAT ERDEM
- Deep learning methods for classification Alzheimer's disease
Alzheimer hastalığının sınıflandırılmasına yönelik derin öğrenme yöntemleri
HUSAM MOHAMMED ABDULFATTAH SAIF AL-HAMMADI
Yüksek Lisans
İngilizce
2023
Bilim ve TeknolojiFatih Sultan Mehmet Vakıf ÜniversitesiBiyomedikal Mühendisliği Ana Bilim Dalı
DR. ÖĞR. ÜYESİ EBUBEKİR KOÇ
- Detection and classification of QRS complexes from the ECR recordings
ECG sinyallerinden QRS kompleks bulma ve sınıflandırma
BENGİ KOÇ
Yüksek Lisans
İngilizce
2008
Elektrik ve Elektronik MühendisliğiOrta Doğu Teknik ÜniversitesiElektrik ve Elektronik Mühendisliği Bölümü
YRD. DOÇ. DR. YEŞİM SERİNAĞAOĞLU DOĞRUSÖZ