Diabetes mellitus is a common disease of human body caused by a group of metabolic disorders where the sugar levels over a prolonged period is very high. It affects different organs of the human body which thus harm a large number of the body's system, in particular the blood veins and nerves.Early prediction in such disease can be controlled and save human life. To achieve the goal, this research work mainly explores various risk factors related to this disease using machine learning techniques. Machine learning techniques provide efficient result to extract knowledge by constructing predicting models from diagnostic medical datasets collected from the diabetic patients. Extracting knowledge from such data can be useful to predict diabetic patients. In this work, we employ four popular machine learning algorithms, namely Support Vector Machine (SVM), Naive Bayes (NB), K-Nearest Neighbor (KNN) and C4.5 Decision Tree, on adult population data to predict diabetic mellitus. Our experimental results show that C4.5 decision tree achieved higher accuracy compared to other machine learning techniques.

No abstract

Nowadays, eHealth service has become a booming area, which refers to computer-based health care and information delivery to improve health service locally, regionally and worldwide. An effective disease risk prediction model by analyzing electronic health data benefits not only to care a patient but also to provide services through the corresponding data-driven eHealth systems. In this paper, we particularly focus on predicting and analysing diabetes mellitus, an increasingly prevalent chronic disease that refers to a group of metabolic disorders characterized by a high blood sugar level over a prolonged period of time. K-Nearest Neighbor (KNN) is one of the most popular and simplest machine learning techniques to build such a disease risk prediction model utilizing relevant health data. In order to achieve our goal, we present an optimal K-Nearest Neighbor (Opt-KNN) learning based prediction model based on patient's habitual attributes in various dimensions. This approach determines the optimal number of neighbors with low error rate for providing better prediction outcome in the resultant model. The effectiveness of this machine learning eHealth model is examined by conducting experiments on the real-world diabetes mellitus data collected from medical hospitals.

Background: Coronary artery diseases are one of the major challenges faced by cardiologists. Control of certain risk factors for CAD is associated with decrease in mortality and morbidity from myocardial infarction and unstable angina. So, identification and taking appropriate measures for primary and secondary prevention of such risk factors is, therefore, of great importance. This retrospective study was carried at the newly set up cath lab in Dhaka Medical college. Materials and Methods: Total 228 consecutive case undergone diagnostic coronary angiogram from 10th January 2007 to31st January 2009 out of which 194(80%) were male and 34 (20%) were female. In both sexes most of the patients were between 41 to 60 years of age. Risk factors of the patients were evaluated. Results: In females commonest risk factor was Diabetes (58.8%) followed by dyslipidaemia (35.3%). In males commonest risk factor was hypertension (30.9%) followed by smoking (29.9%) and diabetes (28.3%). In males 44.3% patients presented with acute myocardial infarction followed by stable angina (43.3%); but in females stable angina was the commonest presentation (50.0%) followed by myocardial infarction (38.2%).CAG findings revealed that in males 33.5% had double vessel disease 26.8% followed by single vessel 26.8% and multivessel disease 25.3%. In females normal CAG was found in 35.5% followed by double vessel 23.5%, multivessel 20.6% and single vessel 20.6%. On the basis of CAG findings; in males 41.8% patients were recommended for CABG, followed by PTCA & stenting 26.3% and medical therapy 30.0%; where as in females 55.9% were recommended for medical therapy , followed by CABG 32.4% and PTCA & stenting11.8%. Conclusion: The commonest presentation of CAD was 4th and 5th decades in both sexes. Diabetes and dyslipidaemia were more common in females whereas hypertension and smoking were more common in males. Myocardial infarction and stable angina were most common presentation in both sexes though in males myocardial infarction was more common. In males the angiographic severity of CAD was more and they were more subjected for CABG in comparison to females. Key words: Risk factors; Coronary angiography. DOI: http://dx.doi.org/10.3329/cardio.v3i2.9179 Cardiovasc. J. 2011; 3(2): 122-125

Clinicians continue to face the challenges of identifying and treating the idiopathic dilated cardiomyopathy to improve symptoms and survival. A study on idiopathic dilated cardiomyopathy was done in the Department of Cardiology, University Cardiac Center, Bangabandhu Sheikh Mujib Medical University, Dhaka, from January 2004 to December 2009. The aim of this study was to examine clinical profile of patients with idiopathic dilated cardiomyopathy. The age range was 18 to 65 years and 70% subjects were male. Most common symptom was dyspnea (86%) and cough (75%). 75% subjects had sinus tachycardia, 42% had ventricular ectopics and 40% had left bundle branch block. Mean diastolic dimension was 60±9 mm, ejection fraction was 28±8%, left atrial dimension was 40±6 mm and 36% were having mitral regurgitation. Left ventricular failure (75%) and various type of arrhythmias (62%) were the main complications. 8% subjects were died during hospital stay. Hence the clinical presentation of idiopathic dilated cardiomyopathy varies from patient to patient, but most patients present later, i.e. at some point in the spectrum of heart failure.