Download presentation
Presentation is loading. Please wait.
1
M.Tech Major Project Presentation
PHASE - I R.V.COLLEGE OF ENGINEERING,BENGALURU
2
R. V. COLLEGE OF ENGINEERING BENGALURU – 560059
Major Project Presentation on “Recommendations for Heart Disease Patients in a Telehealth Environment” Presented by ASHWINI BIRADAR 1RV16SSE02 Under the Guidance of Prof. Sushmitha N Assistant Professor, Department of ISE, RVCE, Bengaluru-59.
3
INTRODUCTION The use of telehealth technologies to remotely monitor patients suffering chronic diseases may enable preemptive treatment of worsening health conditions before a significant deterioration in the subject’s health status occurs, requiring hospital admission. Telehealth is defined as the use of electronic information and telecommunication technologies to support and promote long-distance clinical heath-care, patient and professional health –related education, public health and health administration. E.g. Video Conferencing, the internet etc. In this project, a novel short-term recommendation system for chronic heart disease patients will be proposed. Such recommendations are established based on the prediction of their heart conditions using their time series medical data from the past few days.
4
Pulse Oximeter Automated Oscillometric Blood Pressure
Monitoring Device
5
PROBLEM STATEMENT “Coupling a Fast Fourier Transformation with a Machine Learning Ensemble Model to Support Recommendations for Heart Disease Patients in a Telehealth Environment”
6
OBJECTIVES Use of fast Fourier transformation coupled with machine learning ensemble model for short-term disease risk prediction To provide chronic heart disease patients with appropriate recommendations about the need to take a medical test or not on the coming day based on analysing their medical data. To propose an effective medical recommendation system
7
LITERATURE SURVEY Sl.No. Author Name Year Title Techniques Results 1
Tseng Vincent S, Luo YongLong,Zhang Ji 2016 An intelligent recommender system based on predictive analysis in telehealthcare environment Time Series Predictive Analysis using Logistic Regression Satisfactory Recommendation 2 Raid Lafta, Xiaohui Tao, Yan Li 2015 An Intelligent Recommender System based on Short-term Risk Prediction for Heart Disease Patients Time Series Prediction Algorithm The accuracy of the recommendations provided by the proposed system ranges from 75% to 80% across different patients
8
LITERATURE SURVEY (Cntd..)
Sl.No Author Name Year Title Techniques Results 3 Yanqin Bai, Xiao Han Tong Chen Hua Yu 2015 Quadratic kernel-free least squares support vector machine for target diseases classification Kernel-free least squares support vector machine (QLSSVM) Effective in Prediction and classification 4 Mohktar MS,Redmond SJ, Antoniades NC,Rochford PD Predicting the risk of exacerbation in patients with chronic obstructive pulmonary disease using home telehealth measurement data classification and regression tree (CART) 71.8% accuracy, 80.4% specificity and 61.1% sensitivity
9
LITERATURE SURVEY (Cntd..)
Sl.No Author Name Year Title Techniques Results 5 Jung-Gi Yang Jae-Kwon Kim Un-Gu Kang Young-Ho Lee 2014 Coronary heart disease optimization system on adaptive-network-based fuzzy inference system and linear discriminant analysis (ANFIS–LDA) Adaptive-network-based fuzzy inference system and linear discriminant analysis Prediction rate of 80.2 % 6 Junggi Yang , Youngho Lee, Un Gu Kang Cardiovascular disease prediction models on Linear Discriminant Analysis of depression The linear discriminant analysis Prediction model with linear discriminate analysis represented 69% of accuracy.
10
TABLE I: The model performance using a three-feature set.
Measurement Classifiers No. of bands Accuracy (%) Saving (%) Risk (%) Heart Rate Neural Network 5 71.60 55.54 09.72 LS-SVM 76.49 61.55 07.30 Naive Bayes 72.85 54.55 09.60 DBP 70.10 54.30 09.90 75.44 62.51 08.10 69.20 52.30 MAP 69.90 50.20 10.50 73.55 59.40 09.40 72.20 58.60 09.95 SO2 70.75 60.50 09.85 71.50 60.80 70.80 55.30 09.50
11
TABLE II: The model performance using a six-feature set.
Measurement Classifiers No. of bands Accuracy (%) Saving (%) Risk (%) Heart Rate Neural Network 5 73.50 59.50 09.30 LS-SVM 78.20 62.60 06.80 Naive Bayes 75.30 55.20 08.30 DBP 72.70 50.80 09.70 78.50 64.60 06.75 72.55 57.40 09.90 MAP 71.55 55.30 09.40 75.60 62.54 08.25 73.30 63.70 09.95 SO2 75.50 61.20 08.50 80.20 64.10 06.60 72.50 58.40 09.10
12
EXPECTED OUTCOME Appropriate recommendations for chronic heart disease patients about the need to take a medical test or not on the coming day based on analysing their medical data by providing an effective medical recommendation system. Performance Metrics Accuracy : The percentage of correctly recommended days against the total number of days for which recommendations will be provided. Workload saving : The percentage of the total number of days when recommendations will be provided for skipping the medical test against the total number of days in the training set. Risk : The percentage of incorrectly recommended days against the total number of days in the training set.
13
Thank You
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.