Browsing by Author "Tamil, Lakshman S."
Now showing 1 - 3 of 3
- Results Per Page
- Sort Options
Item Automating Disease Management Using Answer Set Programming: Heart Failure(2017-12) Chen, Zhuo; Gupta, Gopal; Tamil, Lakshman S.Management of chronic diseases such as heart failure (HF), diabetes and chronic obstructive pulmonary disease is a major health care problem. A standard approach that the medical community has devised to manage widely prevalent chronic diseases such as heart failure is to have a committee of experts develop guidelines that all physicians should follow. These guidelines typically consist of a series of complex rules that make recommendations based on a patient's information. Due to their complexity, often the guidelines are either ignored or not complied with at all, which can result in poor medical practices. It is not even clear whether it is humanly possible to follow these clinical guidelines due to their length and complexity. In the case of heart failure management, the guidelines run nearly 80 pages. In this dissertation we describe a physician advisory system that codes the entire set of clinical practice guidelines for heart failure management using answer set programming (ASP). ASP is a form of declarative programming geared toward solving NP-hard search problems. Our approach is based on developing reasoning templates that we call knowledge patterns and using these patterns to systematically code the clinical guideline for HF management as ASP rules. Use of the knowledge patterns greatly facilitates the development of the physician advisory system. Given a patient's medical information, the system generates a set of guideline-compliant recommendations just as a human physician would. The system works even in the presence of incomplete information. Abductive reasoning is implemented in the system to find missing symptoms and conditions that the patient must exhibit in order for a treatment prescribed by a physician to work effectively. The physician advisory system is validated by using data of representative patients with heart failure.Item Hardware Implementation of Real-Time Beat Detection and Classification Algorithm for Automated ECG Analysis(2018-08) Ghosh, Ria; Tamil, Lakshman S.The epidemics of diabetes and obesity, along with unhealthy and stressful lifestyles, have highly contributed to the increased number of patients with heart failure in recent times. As the saying goes, “Prevention is better than cure”, detecting heart abnormalities accurately in initial stages can save patients from severe consequences and expensive surgeries. Hence, in the past few years there has been extensive research in beat detection and real-time cardiac monitoring to determine algorithms that can detect heart beat location and analyze whether the distance between two beats are normal or not. Such a regular check on the health of the heart using a device that could give real-time cardiac monitoring outside the hospital helps to ensure early diagnosis of any kind of abnormality that the cardiac system of an individual might be facing or is prone to face in the near future. Various QRS complex detecting algorithms have been implemented into smart watches and fitness trackers, which has led to the commercialization of various wearable heart beat monitoring devices that have been effective to quite an extent. However, various factors like unwanted noise and inconsistency in differentiating beat locations, may reduce the accuracy of such devices. Hence, it is necessary to ensure that any algorithm maintains accurate precision during both software and hardware testing. Therefore, this thesis aims towards analyzing and confirming the accuracy of the hardware implementation of a Real-time QRS complex detector and Heart Beat classifier using an algorithm based on the modified Pan Tompkins algorithm, which sets a threshold for detecting the peak locations and then classifies them as normal or ventricular. The algorithm, which is a single-lead, first derivative based heart-beat detector and classifier, has been coded in MATLAB. Then using MATLAB’s HDL Coder and System Generator applications, it was converted to VHDL. VHDL is the hardware descriptive language that can communicate with our FPGA board in Xilinx ISE 14.7. All analysis and conclusions have been verified using the SPARTAN-6 FPGA board specifications.Item Machine Learning-Based Techniques for Forecasting Emergency Department Peak Load Due to Respiratory Diseases Patients(2017-08) Khatri, Krishan Lal; 0000-0003-2263-3370 (Khatri, KL); Tamil, Lakshman S.Chronic Respiratory diseases, mainly asthma and Chronic Obstructive Pulmonary Disease (COPD), affect the lives of people by limiting their activities in various aspects. Overcrowding of hospital emergency departments (EDs) due to respiratory diseases in certain weather and environmental pollution conditions results in the degradation of quality of medical care, and even limits its availability. A useful tool for ED managers would be to forecast peak demand days so that they can take steps to improve the availability of medical care. We trained three classifier models to predict peak demand days of EDs due to respiratory patients. The first classifier is an Artificial Neural Network (ANN)-based classifier using Multi-Layer Perceptron (MLP) with back propagation algorithm that predicts Peak Event (Peak demand days) of patients with respiratory diseases, mainly asthma and COPD visiting EDs in Dallas County of Texas in the United States. We used the number of patients initially diagnosed with ICD-9-CM codes 490 to 496 (Chronic Pulmonary Obstructive Disease and Allied Conditions) in the first experiment. The precision and recall for Peak Event class were 77.1% and 78.0% respectively and those for Non-Peak Events was 83.9% and 83.2% respectively. The overall accuracy of the system is 81.0%. The second and third classifiers are Random Forests (RF)-based classifiers to predict peak days of ED visits by asthma patients. Feature-selection has been employed to develop the simplified or reduced model. Random Forests (RF) method of decision tree technique has been used for predicting daily hospital ED visits/admissions due to asthma exacerbations based on daily weather and environmental pollution measurements. For these classifiers, we used ICD-9-CM code 493 (Asthma). The base or full model uses all eight (8) predictors (historical weather and environment pollution measurements), while the other model, known hereafter as simplified model, uses only four (4) out of these eight, reduced through Correlation Feature Selection (CFS) subset evaluator. The overall accuracy of base model is 81.30%, while that of simple model was 76.59%.