Peter Moore 10/05/051 ANN survival prediction for cancer patients Peter Moore High Energy Physics University of Manchester.

Slides:



Advertisements
Similar presentations
Regulation of Consumer Tests in California AAAS Meeting June 1-2, 2009 Beatrice OKeefe Acting Chief, Laboratory Field Services California Department of.
Advertisements

1 Statistical Modeling  To develop predictive Models by using sophisticated statistical techniques on large databases.
Neural Network Approach to Modeling the Laser Material-Removal Process By Basem. F. Yousef London, Canada, N6A 5B9 December 2001.
Departments of Medicine and Biostatistics
Artificial Neural Networks
Recursive Partitioning Method on Survival Outcomes for Personalized Medicine 2nd International Conference on Predictive, Preventive and Personalized Medicine.
RBF Neural Networks x x1 Examples inside circles 1 and 2 are of class +, examples outside both circles are of class – What NN does.
Model and Variable Selections for Personalized Medicine Lu Tian (Northwestern University) Hajime Uno (Kitasato University) Tianxi Cai, Els Goetghebeur,
1 Learning to Detect Objects in Images via a Sparse, Part-Based Representation S. Agarwal, A. Awan and D. Roth IEEE Transactions on Pattern Analysis and.
I welcome you all to this presentation On: Neural Network Applications Systems Engineering Dept. KFUPM Imran Nadeem & Naveed R. Butt &
Neural Networks. R & G Chapter Feed-Forward Neural Networks otherwise known as The Multi-layer Perceptron or The Back-Propagation Neural Network.
Learning From Data Chichang Jou Tamkang University.
Machine Learning Motivation for machine learning How to set up a problem How to design a learner Introduce one class of learners (ANN) –Perceptrons –Feed-forward.
Artificial Neural Networks
EVIDENCE BASED MEDICINE
Radial-Basis Function Networks
Gene based diagnostic prediction of cancers by using Artificial Neural Network Liya Wang ECE/CS/ME539.
Prognostic Modelling and Profiling of Breast Cancer Patients after Surgery Ian Jarman School of Computer and Mathematical Sciences Liverpool John Moores.
CHAPTER 12 ADVANCED INTELLIGENT SYSTEMS © 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition, Turban, Aronson, and Liang.
NATIONAL INSTITUTE OF SCIENCE & TECHNOLOGY Presented by:Manoj Kumar Gantayat CS: Technical Seminar Presentation by MANOJ KUMAR GANTAYAT.
ENDA MOLLOY, ELECTRONIC ENG. FINAL PRESENTATION, 31/03/09. Automated Image Analysis Techniques for Screening of Mammography Images.
Classification Part 3: Artificial Neural Networks
C. Benatti, 3/15/2012, Slide 1 GA/ICA Workshop Carla Benatti 3/15/2012.
Using Neural Networks in Database Mining Tino Jimenez CS157B MW 9-10:15 February 19, 2009.
Introduction to Neural Networks Debrup Chakraborty Pattern Recognition and Machine Learning 2006.
Neural Networks AI – Week 23 Sub-symbolic AI Multi-Layer Neural Networks Lee McCluskey, room 3/10
Data Mining Techniques in Stock Market Prediction
Introduction to Artificial Neural Network Models Angshuman Saha Image Source: ww.physiol.ucl.ac.uk/fedwards/ ca1%20neuron.jpg.
Using Neural Networks to Predict Claim Duration in the Presence of Right Censoring and Covariates David Speights Senior Research Statistician HNC Insurance.
Michigan REU Final Presentations, August 10, 2006Matt Jachowski 1 Multivariate Analysis, TMVA, and Artificial Neural Networks Matt Jachowski
LINEAR CLASSIFICATION. Biological inspirations  Some numbers…  The human brain contains about 10 billion nerve cells ( neurons )  Each neuron is connected.
ARTIFICIAL NEURAL NETWORKS. Overview EdGeneral concepts Areej:Learning and Training Wesley:Limitations and optimization of ANNs Cora:Applications and.
Artificial Neural Networks An Introduction. What is a Neural Network? A human Brain A porpoise brain The brain in a living creature A computer program.
1 Introduction to Neural Networks And Their Applications.
Gap filling of eddy fluxes with artificial neural networks
Applying Neural Networks Michael J. Watts
EMBC2001 Using Artificial Neural Networks to Predict Malignancy of Ovarian Tumors C. Lu 1, J. De Brabanter 1, S. Van Huffel 1, I. Vergote 2, D. Timmerman.
Statistical Tools for Solar Resource Forecasting Vivek Vijay IIT Jodhpur Date: 16/12/2013.
© 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition, Turban, Aronson, and Liang 12-1 Chapter 12 Advanced Intelligent Systems.
A.N.N.C.R.I.P.S The Artificial Neural Networks for Cancer Research in Prediction & Survival A CSI – VESIT PRESENTATION Presented By Karan Kamdar Amit.
Multivariate Data Analysis Chapter 1 - Introduction.
Neural Networks Presented by M. Abbasi Course lecturer: Dr.Tohidkhah.
Image Source: ww.physiol.ucl.ac.uk/fedwards/ ca1%20neuron.jpg
24 Nov 2007Data Management and Exploratory Data Analysis 1 Yongyuth Chaiyapong Ph.D. (Mathematical Statistics) Department of Statistics Faculty of Science.
Introduction to Neural Networks Freek Stulp. 2 Overview Biological Background Artificial Neuron Classes of Neural Networks 1. Perceptrons 2. Multi-Layered.
CHEE825 Fall 2005J. McLellan1 Nonlinear Empirical Models.
Artificial Neural Networks (ANN). Artificial Neural Networks First proposed in 1940s as an attempt to simulate the human brain’s cognitive learning processes.
Perceptrons Michael J. Watts
Bab 5 Classification: Alternative Techniques Part 4 Artificial Neural Networks Based Classifer.
Introduction Background Medical decision support systems based on patient data and expert knowledge A need to analyze the collected data in order to draw.
國立雲林科技大學 National Yunlin University of Science and Technology Intelligent Database Systems Lab 1 Self-organizing map for cluster analysis of a breast cancer.
Retrospective Chart Reviews: How to Review a Review Adam J. Singer, MD Professor and Vice Chairman for Research Department of Emergency Medicine Stony.
Kim HS Introduction considering that the amount of MRI data to analyze in present-day clinical trials is often on the order of hundreds or.
Data Mining: Concepts and Techniques1 Prediction Prediction vs. classification Classification predicts categorical class label Prediction predicts continuous-valued.
A Presentation on Adaptive Neuro-Fuzzy Inference System using Particle Swarm Optimization and it’s Application By Sumanta Kundu (En.R.No.
Phenotyping youth depression
Deep Learning Amin Sobhani.
Introduction to Neural Networks And Their Applications
Chapter 12 Advanced Intelligent Systems
Artificial Intelligence Methods
Incorporating Statistical Methodology for a Research Proposal
XOR problem Input 2 Input 1
Introduction to Neural Networks And Their Applications - Basics
Department of Electrical Engineering
Lecture Notes for Chapter 4 Artificial Neural Networks
Recurrence-Associated Long Non-coding RNA Signature for Determining the Risk of Recurrence in Patients with Colon Cancer  Meng Zhou, Long Hu, Zicheng.
Prediction of in-hospital mortality after ruptured abdominal aortic aneurysm repair using an artificial neural network  Eric S. Wise, MD, Kyle M. Hocking,
Neural Networks II Chen Gao Virginia Tech ECE-5424G / CS-5824
III. Introduction to Neural Networks And Their Applications - Basics
Neural Networks II Chen Gao Virginia Tech ECE-5424G / CS-5824
Presentation transcript:

Peter Moore 10/05/051 ANN survival prediction for cancer patients Peter Moore High Energy Physics University of Manchester

Peter Moore 10/05/052 Project Overview Funded by MRC And PPARC…… me Collaboration: –HEP at University of Manchester ANN and Software development GRID security –Ninewells Hospital Dundee. Data Clinical expertise

Peter Moore 10/05/053 Main Aims To set up ANN based on several available DBs to predict the probable survival outcome for the patients suffering with breast or colorectal cancers Make the ANN available via secure Internet access (GRID) for clinicians nationwide Investigate the possibilities of designing better management plans and improving cancer patients quality of life after treatment.

Peter Moore 10/05/054 Data Colorectal and Breast Cancer Patients Sets of records do not share parameters 50,000 records, 100+ variables Data inconsistency Noise Missing or incomplete data Filling by hand leads to errors

Peter Moore 10/05/055 Artificial Neural Networks Mathematical model based on neurons Many variations Multilayer Feed Forward ANN Approximate any function Inputs x i  xi wj xi wj  w1w1 w3w3 w2w2 wjwj Input summator Nonlinear converter Output

Peter Moore 10/05/056 General Methodology 1.Forming a training set adequately describing the survival function. 2.Tuning the synapse weights (training). 3.Testing. 4.Evaluating and Validating 5.Recommendation for patient management plan. Training set Selecting & coding Genetic Algorithm (global estimation) Gradient based Alg. (local improvement)

Peter Moore 10/05/057 Our Methodology PLANN Cascade Architecture Scaled Conjugate Gradient training algorithm 200 times bootstrap re- sampling 1 j 0 time J bias H 1 hh i1i1 ihih iHiH K  HK  hK  1K 0 KK

Peter Moore 10/05/058 Results analysis Separate (unseen by ANN) records Known as a validation set Interpreting the ANN outputs –Individual patient testing –Group testing Cancer management

Peter Moore 10/05/059 Individual Patient Results

Peter Moore 10/05/0510 ROC Curve Receiver Operating Characteristic Probability of Detection Probability of False Alarm

Peter Moore 10/05/0511 Kaplan Meier Survival Standard method used in medicine Actual Survival probability for any group of patients Grouping patients together by specific diagnostic factors Takes into account censoring

Peter Moore 10/05/0512 Kaplan Meier Example

Peter Moore 10/05/0513 Prognostic groupings Colon Cancer A : Dukes Stage A, node negative, no liver deposits and curative operation B : Dukes Stage B, node negative, no liver deposits and potentially curative operation C: Dukes Stage C, no liver deposits and potentially curative operation D: Dukes Stage D, multiple lymph node involvement or hepatic deposits

Peter Moore 10/05/0514 Prognostic groups A, B

Peter Moore 10/05/0515 Prognostic groups C,D

Peter Moore 10/05/0516 Visions Web interface Accessible by medical personnel Improved Data New Databases sources Patient management profiles Requires improved hospital patient data collection methods Medical trials data Genome and Molecular data

Peter Moore 10/05/0517 Visions Online Dynamic ANN training? Continuously updates with latest research results and data –( would currently fail ethics approval ) Automatic relevance determination –Problems with reliability of unsupervised ANN training Remote data uploading Confidentiality and Enforcement of privacy protection Security Healthgrid?

Peter Moore 10/05/0518 More info

Peter Moore 10/05/0519

Peter Moore 10/05/0520