Implications of Longitudinal Data in Machine Learning for Medicine and Epidemiology

Size: px
Start display at page:

Download "Implications of Longitudinal Data in Machine Learning for Medicine and Epidemiology"

Transcription

1 Implications of Longitudinal Data in Machine Learning for Medicine and Epidemiology Billy Heung Wing Chang, Yanxian Chen, Mingguang He Zhongshan Ophthalmic Center, Sun Yat-sen University Biostatistics Seminar Dalla Lana School of Public Health Feb 3, 2015 Longitudinal Prediction Feb 3, / 33

2 Outline 1 Myopia and Myopia Prediction 2 Supervised Machine Learning and Prediction 3 Myopia Progression 4 Principal Component Analysis 5 Conclusion Longitudinal Prediction Feb 3, / 33

3 Myopia Commonly known as short-sightedness. Measured by Spherical Equivalence (SE), units = Dioptres (D). 0 D: emmetropia (no myopia). 0 D to -3 D: low myopia. Correctable by wearing glasses. Morgan et. al. (2012) Lancet 379: Longitudinal Prediction Feb 3, / 33

4 Myopia Progression COMET (2013) IOVS 54: Emmetropic at early ages. Myopia onset during elementary school. Myopia stabilization during secondary school. Age of onset, age of stabilization, and progression rates varies. Longitudinal Prediction Feb 3, / 33

5 Risk Factors for Myopia Largely believed to be genetic in the past. Prevalence in certain countries on rapid rise recently. Lin, et al (2004) Ann Acad Med Singapore, 33, Education, near work, outdoor time. Longitudinal Prediction Feb 3, / 33

6 High Myopia An extreme level of myopia. SE < -6.0 D. Increased risk of blindness. Irreversible. Prevention. Longitudinal Prediction Feb 3, / 33

7 Preventive Treatment of High Myopia To arrest myopia progression towards high myopia. Popular treatment: Atropine eye drops, specialized contact lens. Shih et. al. (2002) Acta Ophthalmologica Scandinavica 79:3, Long-term treatment with risk of severe side-effects. Idea: target only children at risk of high myopia. Longitudinal Prediction Feb 3, / 33

8 Prediction of Children At-Risk Given SE at early ages (10-13 years old). Predict the SE at age 15. Longitudinal Prediction Feb 3, / 33

9 Outline 1 Myopia and Myopia Prediction 2 Supervised Machine Learning and Prediction 3 Myopia Progression 4 Principal Component Analysis 5 Conclusion Longitudinal Prediction Feb 3, / 33

10 Supervised Machine Learning Construct a prediction model based on a training" sample of predictors and responses {x i, y i } N i=1, (x i, y i ) (X, Y ). At prediction time: input the test case x test = (x1 test, x2 test,...) into the fitted model to obtain the prediction y test. E.g. linear regression. E(Y X) = β0 + β 1 X 1 + β 2 X Training data {x i, y i } N i=1 to estimate ˆβ 0, ˆβ 1, ˆβ 2,... ŷ test = ˆβ 0 + ˆβ 1 x1 test + ˆβ 2 x2 test +... Longitudinal Prediction Feb 3, / 33

11 Criterion for a Good Prediction Model Generalization Ability: Can the model make accurate prediction for data unused for training? Can the model be applied for prediction in the future? Can the model be applied for other population? Longitudinal Prediction Feb 3, / 33

12 Existing Works Follow the above scheme: Training Data Prediction Model Prediction Issues of Generalization: Must use data from the past. Rely on population parameters. Also need Y = endpoint SE: unrealistic. Longitudinal Prediction Feb 3, / 33

13 Prediction using Longitudinal Data With longitudinal data, we can extrapolate using SE at early ages. Endpoint SE not needed for model building. But this naive approach ignores myopia stabilization. SE SE Age Age Longitudinal Prediction Feb 3, / 33

14 Change-point Model Myopia progression will stabilize during adolescence. Use a Change-point Regression Model to imitate stabilization. SE SE Age Change-Point Age Change-Point Longitudinal Prediction Feb 3, / 33

15 Mean-Matching for Change-point Selection Fit regression using the available SE measures. Mean SE at midpoint age (14 years) was estimated. Fit change-point models using a range of change-points. Choose the change-point with the averaged prediction values that best matched the regression-predicted mean at the midpoint age. change-point SE SE Age mid-point Age mid-point Longitudinal Prediction Feb 3, / 33

16 Data Set Training Data: Guangzhou Twin Eye Study pairs of twins. First-born twins are considered for analysis. inclusion: 2nd follow-up SE before age 13. Endpoint age > subjects remains. Right-eye SE is used. Validation Data: Zhongshan Ophthalmic Center Optometry Clinic Data subjects. same inclusion criterion as above. 56 subjects remains. Left-eye SE is used. Proposed methods compared with linear mixed effects model (LME). Longitudinal Prediction Feb 3, / 33

17 Results: Prediction MSE for Twin Data One Follow up Age SE follow up, Naive Endpoint SE Predicted follow up, Change Point Endpoint SE Predicted follow up, LME Endpoint SE Predicted Two Follow up Age SE follow up, Naive Endpoint SE Predicted follow up, Change Point Endpoint SE Predicted follow up, LME Endpoint SE Predicted Longitudinal Prediction Feb 3, / 33

18 Results: Validation on Optometry Clinic Data, Prediction MSE follow up, Change point Endpoint SE Predicted follow up, LME Endpoint SE Predicted Longitudinal Prediction Feb 3, / 33

19 Brief Summary A simple change-point model for future SE prediction. Higher accuracy than linear mixed effects model. Potential reason: Change-point model accounts for myopia stabilization. Linear mixed effects model contains many population parameters. Lack generalization ability. Longitudinal Prediction Feb 3, / 33

20 Outline 1 Myopia and Myopia Prediction 2 Supervised Machine Learning and Prediction 3 Myopia Progression 4 Principal Component Analysis 5 Conclusion Longitudinal Prediction Feb 3, / 33

21 Analysis of Myopia Progression To study the various aspects of myopia progression. Progression rate, myopia onset, myopia stabilization. To identify factors associated to progression rate, onset and stabilization. Longitudinal Prediction Feb 3, / 33

22 Existing Appraoch for Progression Modelling Gompertz model. A pre-defined model for modelling the entire progression. Require long term follow-up data. Lack-of-fit issues. Idea: perhaps with shorter-term follow-up data, we can still do some analysis? COMET (2013) IOVS 54: Longitudinal Prediction Feb 3, / 33

23 Outline 1 Myopia and Myopia Prediction 2 Supervised Machine Learning and Prediction 3 Myopia Progression 4 Principal Component Analysis 5 Conclusion Longitudinal Prediction Feb 3, / 33

24 Principal Component Analysis (PCA) Let x = {x 1, x 2,..., x P } F, E(x) = 0 {x i } N i=1 i.i.d. samples from F 1 Find a unit vector v 1 such that var(x ˆ T v 1 ) is maximized. Step 1 Step 2 x x2 x x2 x1 x1 2 Find a unit vector v 2, v 2 v 1, such that ˆ var(x T v 2 ) is maximized. 3 Repeat if necessary for v 3, v 4, etc... z ij = x T i v j is the jth principal component scores for x i. Longitudinal Prediction Feb 3, / 33

25 Principal Component Analysis x x2 z x z1 Longitudinal Prediction Feb 3, / 33

26 PCA on Longitudinal Data What if PCA is applied to longitudinal data? It finds major trends hidden within the data. Revisit the Twin data set. 637 first born twins with without cataract surgery history or loss of 3 consecutive visits. Right-eye SE are used. Missing data are imputed using linear regression. Purpose: to identify major trends of myopia progression, and identify potential factors associated with those trends. Longitudinal Prediction Feb 3, / 33

27 PCA on the Twin Data Set PC 1 PC 2 PC 3 PC Loading PC Loading PC Loading follow up follow up follow up Longitudinal Prediction Feb 3, / 33

28 PC Scores > 0.5 vs. < -0.5 PC2 represents rate of myopia progression. PC3 with positive scores represents myopia stabilization. PC3 with negative scores represents myopia onset. Longitudinal Prediction Feb 3, / 33

29 Using the PC Scores as Responses in Regression The PC scores z ij = x T i v j are measures of the strength of the trends. To identify risk factors for each trend. Regress z ij = x T i v j onto the predictors. Longitudinal Prediction Feb 3, / 33

30 PCA scores and Risk Factors Longitudinal Prediction Feb 3, / 33

31 PCA scores and Risk Factors Longitudinal Prediction Feb 3, / 33

32 Outline 1 Myopia and Myopia Prediction 2 Supervised Machine Learning and Prediction 3 Myopia Progression 4 Principal Component Analysis 5 Conclusion Longitudinal Prediction Feb 3, / 33

33 Conclusion Change-point model with longitudinal data: a prediction method with good generalization ability. PCA: hypothesis-free approach to analyze longitudinal trends in myopia progression. Hopefully, this presentation can suggest some ideas on how longitudinal data can be used for prediction, and how dimension reduction techniques can be used in longitudinal data analysis. Longitudinal Prediction Feb 3, / 33

Myopia is a common ocular disorder, with an estimated

Myopia is a common ocular disorder, with an estimated Clinical and Epidemiologic Research Myopia Stabilization and Associated Factors Among Participants in the Correction of Myopia Evaluation Trial (COMET) The COMET Group Department of Preventive Medicine,

More information

Machine Learning to Inform Breast Cancer Post-Recovery Surveillance

Machine Learning to Inform Breast Cancer Post-Recovery Surveillance Machine Learning to Inform Breast Cancer Post-Recovery Surveillance Final Project Report CS 229 Autumn 2017 Category: Life Sciences Maxwell Allman (mallman) Lin Fan (linfan) Jamie Kang (kangjh) 1 Introduction

More information

Myopia: Professor Chris Hammond St Thomas Hospital, London Dept Twin Research & Genetic Epidemiology

Myopia: Professor Chris Hammond St Thomas Hospital, London Dept Twin Research & Genetic Epidemiology Myopia: Cause and Cure Professor Chris Hammond St Thomas Hospital, London Dept Twin Research & Genetic Epidemiology www.twinsuk.ac.uk Common! Cost Complications Why study myopia? Retinal detachment Myopic

More information

MiSight 1 day - Live Webinar Q&A

MiSight 1 day - Live Webinar Q&A What age does the child stop needing treatment? Our current published research tracks children up to 15 years of age and the data shows that myopia is still progressing in both MiSight and single vision

More information

Utilizing Posterior Probability for Race-composite Age Estimation

Utilizing Posterior Probability for Race-composite Age Estimation Utilizing Posterior Probability for Race-composite Age Estimation Early Applications to MORPH-II Benjamin Yip NSF-REU in Statistical Data Mining and Machine Learning for Computer Vision and Pattern Recognition

More information

Myopia Control. Disclosures. Prevalence. Cost. Prevalence. Bausch + Lomb: research materials

Myopia Control. Disclosures. Prevalence. Cost. Prevalence. Bausch + Lomb: research materials Disclosures Bausch + Lomb: research materials Myopia Control Jeffrey J. Walline, OD PhD The Ohio State University College of Optometry Myopia Control Prevalence From: nature.com http://www.nature.com/news/the-myopia-boom-1.17120

More information

Myopia: How it Became a Modern Epidemic

Myopia: How it Became a Modern Epidemic Myopia: How it Became a Modern Epidemic Francesca Philips Maths 89S Duke University 1 st November 2016 1 Myopia Introduction Myopia is the most common ocular disorder with approximately 25% of the world

More information

Research Article Association of Birth Parameters with Refractive Status in a Sample of Caucasian Children Aged 4 17 Years

Research Article Association of Birth Parameters with Refractive Status in a Sample of Caucasian Children Aged 4 17 Years Ophthalmology Volume 2015, Article ID 635682, 5 pages http://dx.doi.org/10.1155/2015/635682 Research Article Association of Birth Parameters with Refractive Status in a Sample of Caucasian Children Aged

More information

EECS 433 Statistical Pattern Recognition

EECS 433 Statistical Pattern Recognition EECS 433 Statistical Pattern Recognition Ying Wu Electrical Engineering and Computer Science Northwestern University Evanston, IL 60208 http://www.eecs.northwestern.edu/~yingwu 1 / 19 Outline What is Pattern

More information

Ophthalmology. Ophthalmology Services

Ophthalmology. Ophthalmology Services Ophthalmology Ophthalmology Services The Ophthalmology service offers the latest and most comprehensive eye care for patients. With a dedicated team of eye surgeons and consultants, we treat vision problems

More information

Machine Learning Statistical Learning. Prof. Matteo Matteucci

Machine Learning Statistical Learning. Prof. Matteo Matteucci Machine Learning Statistical Learning Pro. Matteo Matteucci Statistical Learning Outline o What Is Statistical Learning? Why estimate? How do we estimate? The trade-o between prediction accuracy & model

More information

Myopia Control. Disclosures. Myopia Control Summary. End of Lecture, You Will Be Able To. Soft Multifocal Myopia Control

Myopia Control. Disclosures. Myopia Control Summary. End of Lecture, You Will Be Able To. Soft Multifocal Myopia Control Disclosures Bausch + Lomb: research materials Myopia Control Jeffrey J. Walline, OD PhD The Ohio State University College of Optometry End of Lecture, You Will Be Able To Talk to parents about myopia control

More information

A Comparison of Methods for Determining HIV Viral Set Point

A Comparison of Methods for Determining HIV Viral Set Point STATISTICS IN MEDICINE Statist. Med. 2006; 00:1 6 [Version: 2002/09/18 v1.11] A Comparison of Methods for Determining HIV Viral Set Point Y. Mei 1, L. Wang 2, S. E. Holte 2 1 School of Industrial and Systems

More information

Association of Ocular Dominance and Myopia Development: A 2-Year Longitudinal Study

Association of Ocular Dominance and Myopia Development: A 2-Year Longitudinal Study Association of Ocular Dominance and Myopia Development: A 2-Year Longitudinal Study Zhikuan Yang, Weizhong Lan, Wen Liu, Xiang Chen, Haohui Nie, Minbin Yu, and Jian Ge From the State Key Laboratory of

More information

Math 215, Lab 7: 5/23/2007

Math 215, Lab 7: 5/23/2007 Math 215, Lab 7: 5/23/2007 (1) Parametric versus Nonparamteric Bootstrap. Parametric Bootstrap: (Davison and Hinkley, 1997) The data below are 12 times between failures of airconditioning equipment in

More information

The focus of this paper is the

The focus of this paper is the Refraction planning in cataract: avoid creating an unhappy patient BY ROBERT H TAYLOR, ROGER B ELLINGHAM It is much more important to know what sort of a patient has a disease than what sort of a disease

More information

Outcomes of Cataract Surgery in Urban Southern China: The Liwan Eye Study METHODS

Outcomes of Cataract Surgery in Urban Southern China: The Liwan Eye Study METHODS Clinical and Epidemiologic Research Outcomes of Cataract Surgery in Urban Southern China: The Liwan Eye Study Wenyong Huang, 1 Guofu Huang, 1 Dandan Wang, 1 Qiuxia Yin, 1 Paul J. Foster, 2 and Mingguang

More information

STATISTICS 201. Survey: Provide this Info. How familiar are you with these? Survey, continued IMPORTANT NOTE. Regression and ANOVA 9/29/2013

STATISTICS 201. Survey: Provide this Info. How familiar are you with these? Survey, continued IMPORTANT NOTE. Regression and ANOVA 9/29/2013 STATISTICS 201 Survey: Provide this Info Outline for today: Go over syllabus Provide requested information on survey (handed out in class) Brief introduction and hands-on activity Name Major/Program Year

More information

18 Myopia Prevention. Healthy eyes, c lear vision Here are some good eye care habits you can share with your child

18 Myopia Prevention. Healthy eyes, c lear vision Here are some good eye care habits you can share with your child 18 Myopia Prevention Healthy eyes, c lear vision Here are some good eye care habits you can share with your child Myopia Prevention 19 About half the children in Singapore have myopia also known as short-sightedness

More information

IOL Power Calculation for Children

IOL Power Calculation for Children 1 IOL Power Calculation for Children Rupal H. Trivedi, MD MSCR M. Edward Wilson, MD The authors have no financial interest in the subject matter of this presentation. Intraocular lens (IOL) implantation

More information

12/30/2017. PSY 5102: Advanced Statistics for Psychological and Behavioral Research 2

12/30/2017. PSY 5102: Advanced Statistics for Psychological and Behavioral Research 2 PSY 5102: Advanced Statistics for Psychological and Behavioral Research 2 Selecting a statistical test Relationships among major statistical methods General Linear Model and multiple regression Special

More information

Clinically Meaningful

Clinically Meaningful Myopia Control Myopia Control -19% -7% 18% 40% 42% 46% 76% Jeffrey J. Walline, OD PhD The Ohio State University College of Optometry Undercorrection GP Bifocal / PAL Pirenzepine Specs OK What is Clinically

More information

Chapter 11: Advanced Remedial Measures. Weighted Least Squares (WLS)

Chapter 11: Advanced Remedial Measures. Weighted Least Squares (WLS) Chapter : Advanced Remedial Measures Weighted Least Squares (WLS) When the error variance appears nonconstant, a transformation (of Y and/or X) is a quick remedy. But it may not solve the problem, or it

More information

Original Article Downloaded from jhs.mazums.ac.ir at 22: on Friday October 5th 2018 [ DOI: /acadpub.jhs ]

Original Article Downloaded from jhs.mazums.ac.ir at 22: on Friday October 5th 2018 [ DOI: /acadpub.jhs ] Iranian journal of health sciences 213;1(3):58-7 http://jhs.mazums.ac.ir Original Article Downloaded from jhs.mazums.ac.ir at 22:2 +33 on Friday October 5th 218 [ DOI: 1.18869/acadpub.jhs.1.3.58 ] A New

More information

Part [2.1]: Evaluation of Markers for Treatment Selection Linking Clinical and Statistical Goals

Part [2.1]: Evaluation of Markers for Treatment Selection Linking Clinical and Statistical Goals Part [2.1]: Evaluation of Markers for Treatment Selection Linking Clinical and Statistical Goals Patrick J. Heagerty Department of Biostatistics University of Washington 174 Biomarkers Session Outline

More information

Genomic Biomarkers for Depression: Feature-specific and Joint Biomarkers

Genomic Biomarkers for Depression: Feature-specific and Joint Biomarkers Genomic Biomarkers for Depression: Feature-specific and Joint Biomarkers Helena Geys, Dan Lin, Ziv Shkedy, Abel Tilahun, Luc Bijnens, Willem Talloen hgeys@its.jnj.com Janssen Pharmaceutical Companies Research

More information

Application of Artificial Neural Network-Based Survival Analysis on Two Breast Cancer Datasets

Application of Artificial Neural Network-Based Survival Analysis on Two Breast Cancer Datasets Application of Artificial Neural Network-Based Survival Analysis on Two Breast Cancer Datasets Chih-Lin Chi a, W. Nick Street b, William H. Wolberg c a Health Informatics Program, University of Iowa b

More information

Capturing myopia and hypermetropia phenotypes without formal refraction

Capturing myopia and hypermetropia phenotypes without formal refraction (2008) 22, 939 943 & 2008 Nature Publishing Group All rights reserved 0950-222X/08 $30.00 www.nature.com/eye Capturing myopia and hypermetropia phenotypes without formal refraction PM Cumberland 1, CS

More information

Applications. DSC 410/510 Multivariate Statistical Methods. Discriminating Two Groups. What is Discriminant Analysis

Applications. DSC 410/510 Multivariate Statistical Methods. Discriminating Two Groups. What is Discriminant Analysis DSC 4/5 Multivariate Statistical Methods Applications DSC 4/5 Multivariate Statistical Methods Discriminant Analysis Identify the group to which an object or case (e.g. person, firm, product) belongs:

More information

Review: Logistic regression, Gaussian naïve Bayes, linear regression, and their connections

Review: Logistic regression, Gaussian naïve Bayes, linear regression, and their connections Review: Logistic regression, Gaussian naïve Bayes, linear regression, and their connections New: Bias-variance decomposition, biasvariance tradeoff, overfitting, regularization, and feature selection Yi

More information

NEPTUNE RED BANK BRICK

NEPTUNE RED BANK BRICK NEPTUNE RED BANK BRICK Diabetes & The Eye Diabetics are more likely to develop Cataracts at a younger age. Diabetics are twice as likely to develop Glaucoma when compared to non-diabetics. The primary

More information

Information-theoretic stimulus design for neurophysiology & psychophysics

Information-theoretic stimulus design for neurophysiology & psychophysics Information-theoretic stimulus design for neurophysiology & psychophysics Christopher DiMattina, PhD Assistant Professor of Psychology Florida Gulf Coast University 2 Optimal experimental design Part 1

More information

The progression of corrected myopia

The progression of corrected myopia Graefes Arch Clin Exp Ophthalmol (2015) 253:1273 1277 DOI 10.1007/s00417-015-2991-5 BASIC SCIENCE The progression of corrected myopia Antonio Medina 1,2 Received: 23 December 2014 /Revised: 4 March 2015

More information

Original Article Correlation of axial length and corneal curvature with diopter in eyes of adults with anisometropia

Original Article Correlation of axial length and corneal curvature with diopter in eyes of adults with anisometropia Int J Clin Exp Med 2015;8(8):13639-13643 www.ijcem.com /ISSN:1940-5901/IJCEM0010322 Original Article Correlation of axial length and corneal curvature with diopter in eyes of adults with anisometropia

More information

Accuracy and Utility of Self-Report of Refractive Error: the UK Biobank study

Accuracy and Utility of Self-Report of Refractive Error: the UK Biobank study Accuracy and Utility of Self-Report of Refractive Error: the UK Biobank study Phillippa M Cumberland, BA, MSc 1, 2 Antonietta Chianca, BSc, PhD 1, 2 Jugnoo S Rahi, PhD, FRCOphth 1, 2, 3, 4 For the UK Biobank

More information

Using a signature-based machine learning model to analyse a psychiatric stream of data

Using a signature-based machine learning model to analyse a psychiatric stream of data Using a signature-based machine learning model to analyse a psychiatric stream of data Imanol Perez (Joint work with T. Lyons, K. Saunders and G. Goodwin) Mathematical Institute University of Oxford Rough

More information

UNIVERSITY of PENNSYLVANIA CIS 520: Machine Learning Final, Fall 2014

UNIVERSITY of PENNSYLVANIA CIS 520: Machine Learning Final, Fall 2014 UNIVERSITY of PENNSYLVANIA CIS 520: Machine Learning Final, Fall 2014 Exam policy: This exam allows two one-page, two-sided cheat sheets (i.e. 4 sides); No other materials. Time: 2 hours. Be sure to write

More information

The effectiveness of progressive addition lenses on the progression of myopia in Chinese children

The effectiveness of progressive addition lenses on the progression of myopia in Chinese children Ophthal. Physiol. Opt. 2009 29: 41 48 The effectiveness of progressive addition lenses on the progression of myopia in Chinese children Zhikuan Yang, Weizhong Lan, Jian Ge, Wen Liu, Xiang Chen, Linxin

More information

Longitudinal data monitoring for Child Health Indicators

Longitudinal data monitoring for Child Health Indicators Longitudinal data monitoring for Child Health Indicators Vincent Were Statistician, Senior Data Manager and Health Economist Kenya Medical Research institute [KEMRI] Presentation at Kenya Paediatric Association

More information

Myopia Control An Update

Myopia Control An Update Lyndon Jones PhD, DSc, FCAHS, FCOptom, FAAO Financial Disclosures Myopia Control An Update Lyndon Jones PhD DSc FCAHS FCOptom FAAO Over the past three years, members of CORE have received research funding

More information

Saving Eyes Without a Topographer:

Saving Eyes Without a Topographer: Saving Eyes Without a Topographer: Myopia Control in General Practice Alex Petty BOptom, FIAO Saving Eyes Without a Topographer: Myopia Control in General Practice Alex Petty BOptom, FIAO Alex s Background

More information

Predicting Breast Cancer Survival Using Treatment and Patient Factors

Predicting Breast Cancer Survival Using Treatment and Patient Factors Predicting Breast Cancer Survival Using Treatment and Patient Factors William Chen wchen808@stanford.edu Henry Wang hwang9@stanford.edu 1. Introduction Breast cancer is the leading type of cancer in women

More information

Lecture 13: Finding optimal treatment policies

Lecture 13: Finding optimal treatment policies MACHINE LEARNING FOR HEALTHCARE 6.S897, HST.S53 Lecture 13: Finding optimal treatment policies Prof. David Sontag MIT EECS, CSAIL, IMES (Thanks to Peter Bodik for slides on reinforcement learning) Outline

More information

A Vision-based Affective Computing System. Jieyu Zhao Ningbo University, China

A Vision-based Affective Computing System. Jieyu Zhao Ningbo University, China A Vision-based Affective Computing System Jieyu Zhao Ningbo University, China Outline Affective Computing A Dynamic 3D Morphable Model Facial Expression Recognition Probabilistic Graphical Models Some

More information

Learning in neural networks

Learning in neural networks http://ccnl.psy.unipd.it Learning in neural networks Marco Zorzi University of Padova M. Zorzi - European Diploma in Cognitive and Brain Sciences, Cognitive modeling", HWK 19-24/3/2006 1 Connectionist

More information

An overview of the myopia problem in China

An overview of the myopia problem in China Preface Page 1 of 5 An overview of the myopia problem in China It is now generally accepted that several locations in East and Southeast Asia, specifically the Republic of Korea, Japan, Singapore, mainland

More information

Measurement. Reliability vs. Validity. Reliability vs. Validity

Measurement. Reliability vs. Validity. Reliability vs. Validity MEASUREMENT Outline 1. Measurement - Reliability vs. Validity - Validity - Threats to Internal Validity - Construct Validity (measurement validity) - Face validity - Content validity - Predictive validity

More information

Rare Variant Burden Tests. Biostatistics 666

Rare Variant Burden Tests. Biostatistics 666 Rare Variant Burden Tests Biostatistics 666 Last Lecture Analysis of Short Read Sequence Data Low pass sequencing approaches Modeling haplotype sharing between individuals allows accurate variant calls

More information

GENERALIZED ESTIMATING EQUATIONS FOR LONGITUDINAL DATA. Anti-Epileptic Drug Trial Timeline. Exploratory Data Analysis. Exploratory Data Analysis

GENERALIZED ESTIMATING EQUATIONS FOR LONGITUDINAL DATA. Anti-Epileptic Drug Trial Timeline. Exploratory Data Analysis. Exploratory Data Analysis GENERALIZED ESTIMATING EQUATIONS FOR LONGITUDINAL DATA 1 Example: Clinical Trial of an Anti-Epileptic Drug 59 epileptic patients randomized to progabide or placebo (Leppik et al., 1987) (Described in Fitzmaurice

More information

Pediatric Lens Diseases

Pediatric Lens Diseases Pediatric Lens Diseases Yizhi Liu Editor Pediatric Lens Diseases Editor Yizhi Liu State Key Laboratory of Ophthalmology Zhongshan Ophthalmic Center Guangzhou, Guangdong, China ISBN 978-981-10-2626-3 ISBN

More information

Recent decades have seen a rapid rise in the

Recent decades have seen a rapid rise in the LIGHT EXPOSURE AND CHILDHOOD MYOPIA There is evidence in many countries globally that the prevalence of myopia is on the rise. Advances in measurement technology now allow many environmental factors potentially

More information

COMP90049 Knowledge Technologies

COMP90049 Knowledge Technologies COMP90049 Knowledge Technologies Introduction Classification (Lecture Set4) 2017 Rao Kotagiri School of Computing and Information Systems The Melbourne School of Engineering Some of slides are derived

More information

A novel approach to estimation of the time to biomarker threshold: Applications to HIV

A novel approach to estimation of the time to biomarker threshold: Applications to HIV A novel approach to estimation of the time to biomarker threshold: Applications to HIV Pharmaceutical Statistics, Volume 15, Issue 6, Pages 541-549, November/December 2016 PSI Journal Club 22 March 2017

More information

The prevalence rates of refractive errors among children, adolescents, and adults in Germany

The prevalence rates of refractive errors among children, adolescents, and adults in Germany ORIGINAL RESEARCH The prevalence rates of refractive errors among children, adolescents, and adults in Germany Sandra Jobke 1 Erich Kasten 2 Christian Vorwerk 3 1 Institute of Medical Psychology, 3 Department

More information

Ophthalmology. Glaucoma

Ophthalmology. Glaucoma Ophthalmology Glaucoma The Ophthalmology service offers the latest and most comprehensive eye care for patients. With a dedicated team of eye surgeons and consultants, we treat vision problems ranging

More information

Trends in the Lifetime Risk of Developing Cancer in Ontario, Canada

Trends in the Lifetime Risk of Developing Cancer in Ontario, Canada Trends in the Lifetime Risk of Developing Cancer in Ontario, Canada Huan Jiang 1,2, Prithwish De 1, Xiaoxiao Wang 2 1 Surveillance and Cancer Registry, Analytic and Informatics, Cancer Care Ontario 2 Dalla

More information

Effects of Photorefractive Keratectomy-Induced Defocus on Emmetropization of Infant Rhesus Monkeys

Effects of Photorefractive Keratectomy-Induced Defocus on Emmetropization of Infant Rhesus Monkeys Effects of Photorefractive Keratectomy-Induced Defocus on Emmetropization of Infant Rhesus Monkeys Xingwu Zhong, Jian Ge, Haohui Nie, Xiaolian Chen, Juan Huang, and Nian Liu PURPOSE. To investigate whether

More information

도시초등학교 4 학년의굴절이상과안계측치변화

도시초등학교 4 학년의굴절이상과안계측치변화 도시초등학교 4 학년의굴절이상과안계측치변화 1119 1120 Table 1. Comparison of uncorrected visual acuity using logmar between March and December [No. of eyes (%)] March December Difference p-value Total Uncorrected visual acuity

More information

Predicting Sleep Using Consumer Wearable Sensing Devices

Predicting Sleep Using Consumer Wearable Sensing Devices Predicting Sleep Using Consumer Wearable Sensing Devices Miguel A. Garcia Department of Computer Science Stanford University Palo Alto, California miguel16@stanford.edu 1 Introduction In contrast to the

More information

Treatment effect estimates adjusted for small-study effects via a limit meta-analysis

Treatment effect estimates adjusted for small-study effects via a limit meta-analysis Treatment effect estimates adjusted for small-study effects via a limit meta-analysis Gerta Rücker 1, James Carpenter 12, Guido Schwarzer 1 1 Institute of Medical Biometry and Medical Informatics, University

More information

On cows and test construction

On cows and test construction On cows and test construction NIELS SMITS & KEES JAN KAN Research Institute of Child Development and Education University of Amsterdam, The Netherlands SEM WORKING GROUP AMSTERDAM 16/03/2018 Looking at

More information

Effect of Time Spent Outdoors at School on the Development of Myopia Among Children in China A Randomized Clinical Trial

Effect of Time Spent Outdoors at School on the Development of Myopia Among Children in China A Randomized Clinical Trial Research Original Investigation Effect of Time Spent Outdoors at School on the Development of Myopia Among Children in China A Randomized Clinical Trial Mingguang He, MD, PhD; Fan Xiang, MD, PhD; Yangfa

More information

Generational difference of refractive error in the baseline study of the Beijing Myopia Progression Study

Generational difference of refractive error in the baseline study of the Beijing Myopia Progression Study 1 Beijing Ophthalmology and Visual Science Key Lab, Beijing Tongren Eye Center, Beijing Tongren Hospital, Capital Medical University, Beijing, China 2 The Affiliated Eye Hospital and School of Optometry

More information

Lecture 14: Adjusting for between- and within-cluster covariates in the analysis of clustered data May 14, 2009

Lecture 14: Adjusting for between- and within-cluster covariates in the analysis of clustered data May 14, 2009 Measurement, Design, and Analytic Techniques in Mental Health and Behavioral Sciences p. 1/3 Measurement, Design, and Analytic Techniques in Mental Health and Behavioral Sciences Lecture 14: Adjusting

More information

Ridge regression for risk prediction

Ridge regression for risk prediction Ridge regression for risk prediction with applications to genetic data Erika Cule and Maria De Iorio Imperial College London Department of Epidemiology and Biostatistics School of Public Health May 2012

More information

Generalized Estimating Equations for Depression Dose Regimes

Generalized Estimating Equations for Depression Dose Regimes Generalized Estimating Equations for Depression Dose Regimes Karen Walker, Walker Consulting LLC, Menifee CA Generalized Estimating Equations on the average produce consistent estimates of the regression

More information

Dynamic prediction using joint models for recurrent and terminal events: Evolution after a breast cancer

Dynamic prediction using joint models for recurrent and terminal events: Evolution after a breast cancer Dynamic prediction using joint models for recurrent and terminal events: Evolution after a breast cancer A. Mauguen, B. Rachet, S. Mathoulin-Pélissier, S. Siesling, G. MacGrogan, A. Laurent, V. Rondeau

More information

LINEAR REGRESSION FOR BIVARIATE CENSORED DATA VIA MULTIPLE IMPUTATION

LINEAR REGRESSION FOR BIVARIATE CENSORED DATA VIA MULTIPLE IMPUTATION STATISTICS IN MEDICINE Statist. Med. 18, 3111} 3121 (1999) LINEAR REGRESSION FOR BIVARIATE CENSORED DATA VIA MULTIPLE IMPUTATION WEI PAN * AND CHARLES KOOPERBERG Division of Biostatistics, School of Public

More information

Error Detection based on neural signals

Error Detection based on neural signals Error Detection based on neural signals Nir Even- Chen and Igor Berman, Electrical Engineering, Stanford Introduction Brain computer interface (BCI) is a direct communication pathway between the brain

More information

PRODUCT MYOPIA AND EFFECTIVE MANAGEMENT SOLUTIONS

PRODUCT MYOPIA AND EFFECTIVE MANAGEMENT SOLUTIONS MYOPIA AND EFFECTIVE MANAGEMENT SOLUTIONS Myopia is becoming a real public health concern across the world. The number of myopic people is increasing rapidly. The prevalence of high myopia is also expected

More information

Kelvin Chan Feb 10, 2015

Kelvin Chan Feb 10, 2015 Underestimation of Variance of Predicted Mean Health Utilities Derived from Multi- Attribute Utility Instruments: The Use of Multiple Imputation as a Potential Solution. Kelvin Chan Feb 10, 2015 Outline

More information

Ocular Biometric Measurements In Emmetropic And Myopic Malaysian Children - A Population-Based Study

Ocular Biometric Measurements In Emmetropic And Myopic Malaysian Children - A Population-Based Study ORIGINAL ARTICLE Ocular Biometric Measurements In Emmetropic And Myopic Malaysian Children - A Population-Based Study Azura Ramlee, MS Ophthalmology, Goh Pik Pin, MS Ophthalmology, Clinical Research Centre,

More information

Supplementary Materials Are taboo words simply more arousing?

Supplementary Materials Are taboo words simply more arousing? Supplementary Materials Are taboo words simply more arousing? Our study was not designed to compare potential differences on memory other than arousal between negative and taboo words. Thus, our data cannot

More information

Selected Topics in Biostatistics Seminar Series. Missing Data. Sponsored by: Center For Clinical Investigation and Cleveland CTSC

Selected Topics in Biostatistics Seminar Series. Missing Data. Sponsored by: Center For Clinical Investigation and Cleveland CTSC Selected Topics in Biostatistics Seminar Series Missing Data Sponsored by: Center For Clinical Investigation and Cleveland CTSC Brian Schmotzer, MS Biostatistician, CCI Statistical Sciences Core brian.schmotzer@case.edu

More information

The Utility of Three Predictors of Childhood Myopia: a Bayesian Analysis

The Utility of Three Predictors of Childhood Myopia: a Bayesian Analysis Pergamon 0042-6989(94)00225-8 Vision Res. Vol. 35, No. 9, pp. 1345-1352, 1995 Copyright 1995 Elsevier Science Ltd Printed in Great Britain. All rights reserved 0042-6989/95 $9.50 + 0.00 The Utility of

More information

Cocktail Preference Prediction

Cocktail Preference Prediction Cocktail Preference Prediction Linus Meyer-Teruel, 1 Michael Parrott 1 1 Department of Computer Science, Stanford University, In this paper we approach the problem of rating prediction on data from a number

More information

Small-area estimation of prevalence of serious emotional disturbance (SED) in schools. Alan Zaslavsky Harvard Medical School

Small-area estimation of prevalence of serious emotional disturbance (SED) in schools. Alan Zaslavsky Harvard Medical School Small-area estimation of prevalence of serious emotional disturbance (SED) in schools Alan Zaslavsky Harvard Medical School 1 Overview Detailed domain data from short scale Limited amount of data from

More information

Small-area estimation of mental illness prevalence for schools

Small-area estimation of mental illness prevalence for schools Small-area estimation of mental illness prevalence for schools Fan Li 1 Alan Zaslavsky 2 1 Department of Statistical Science Duke University 2 Department of Health Care Policy Harvard Medical School March

More information

Gender Based Emotion Recognition using Speech Signals: A Review

Gender Based Emotion Recognition using Speech Signals: A Review 50 Gender Based Emotion Recognition using Speech Signals: A Review Parvinder Kaur 1, Mandeep Kaur 2 1 Department of Electronics and Communication Engineering, Punjabi University, Patiala, India 2 Department

More information

Methods for Computing Missing Item Response in Psychometric Scale Construction

Methods for Computing Missing Item Response in Psychometric Scale Construction American Journal of Biostatistics Original Research Paper Methods for Computing Missing Item Response in Psychometric Scale Construction Ohidul Islam Siddiqui Institute of Statistical Research and Training

More information

10CS664: PATTERN RECOGNITION QUESTION BANK

10CS664: PATTERN RECOGNITION QUESTION BANK 10CS664: PATTERN RECOGNITION QUESTION BANK Assignments would be handed out in class as well as posted on the class blog for the course. Please solve the problems in the exercises of the prescribed text

More information

Paraxial Schematic Eye Models for 7- and 14-Year-Old Chinese Children

Paraxial Schematic Eye Models for 7- and 14-Year-Old Chinese Children Anatomy and Pathology/Oncology Paraxial Schematic Eye Models for 7- and 14-Year-Old Chinese Children Shi-Ming Li, 1 Ningli Wang, 1 Yuehua Zhou, 1 Si-Yuan Li, 1 Meng-Tian Kang, 1 Luo-Ru Liu, 2 He Li, 2

More information

F1: Introduction to Econometrics

F1: Introduction to Econometrics F1: Introduction to Econometrics Feng Li Department of Statistics, Stockholm University General information Homepage of this course: http://gauss.stat.su.se/gu/ekonometri.shtml Lecturer F1 F7: Feng Li,

More information

The Effects of Maternal Alcohol Use and Smoking on Children s Mental Health: Evidence from the National Longitudinal Survey of Children and Youth

The Effects of Maternal Alcohol Use and Smoking on Children s Mental Health: Evidence from the National Longitudinal Survey of Children and Youth 1 The Effects of Maternal Alcohol Use and Smoking on Children s Mental Health: Evidence from the National Longitudinal Survey of Children and Youth Madeleine Benjamin, MA Policy Research, Economics and

More information

Supplemental Materials

Supplemental Materials Supplemental Materials Programmed death one homolog maintains the pool size of regulatory T cells by promoting their differentiation and stability Qi Wang 1, Jianwei He 1, Dallas B. Flies 2, Liqun Luo

More information

Searching for flu. Detecting influenza epidemics using search engine query data. Monday, February 18, 13

Searching for flu. Detecting influenza epidemics using search engine query data. Monday, February 18, 13 Searching for flu Detecting influenza epidemics using search engine query data By aggregating historical logs of online web search queries submitted between 2003 and 2008, we computed time series of

More information

Distribution and Severity of Myopic Maculopathy Among Highly Myopic Eyes

Distribution and Severity of Myopic Maculopathy Among Highly Myopic Eyes Clinical and Epidemiologic Research Distribution and Severity of Myopic Maculopathy Among Highly Myopic Eyes Ou Xiao, 1 Xinxing Guo, 1,2 Decai Wang, 1 Monica Jong, 3,4 Pei Ying Lee, 5 Linxing Chen, 1 Ian

More information

Myopia Research. Primary Care Treatment of Myopia 10/30/11. Prevalence. An Evidence-Based Approach. Mitchell Scheiman, OD

Myopia Research. Primary Care Treatment of Myopia 10/30/11. Prevalence. An Evidence-Based Approach. Mitchell Scheiman, OD Primary Care Treatment of Myopia An Evidence-Based Approach Mitchell Scheiman, OD 1 Myopia Research Prevalence US: 33% of individuals over the age of 12 years Taiwan, Honk Kong, Singapore: 60% to 80% High

More information

Cost-aware Pre-training for Multiclass Cost-sensitive Deep Learning

Cost-aware Pre-training for Multiclass Cost-sensitive Deep Learning Cost-aware Pre-training for Multiclass Cost-sensitive Deep Learning Yu-An Chung 1 Hsuan-Tien Lin 1 Shao-Wen Yang 2 1 Dept. of Computer Science and Information Engineering National Taiwan University, Taiwan

More information

CRITERIA FOR USE. A GRAPHICAL EXPLANATION OF BI-VARIATE (2 VARIABLE) REGRESSION ANALYSISSys

CRITERIA FOR USE. A GRAPHICAL EXPLANATION OF BI-VARIATE (2 VARIABLE) REGRESSION ANALYSISSys Multiple Regression Analysis 1 CRITERIA FOR USE Multiple regression analysis is used to test the effects of n independent (predictor) variables on a single dependent (criterion) variable. Regression tests

More information

THE data used in this project is provided. SEIZURE forecasting systems hold promise. Seizure Prediction from Intracranial EEG Recordings

THE data used in this project is provided. SEIZURE forecasting systems hold promise. Seizure Prediction from Intracranial EEG Recordings 1 Seizure Prediction from Intracranial EEG Recordings Alex Fu, Spencer Gibbs, and Yuqi Liu 1 INTRODUCTION SEIZURE forecasting systems hold promise for improving the quality of life for patients with epilepsy.

More information

M yopia is a growing public health problem with visual,

M yopia is a growing public health problem with visual, 341 CLINICAL SCIENCE Utility values and myopia in teenage school students S-M Saw, G Gazzard, K-G Au Eong, D Koh... See end of article for authors affiliations... Correspondence to: Dr Seang-Mei Saw, Department

More information

COMP9444 Neural Networks and Deep Learning 5. Convolutional Networks

COMP9444 Neural Networks and Deep Learning 5. Convolutional Networks COMP9444 Neural Networks and Deep Learning 5. Convolutional Networks Textbook, Sections 6.2.2, 6.3, 7.9, 7.11-7.13, 9.1-9.5 COMP9444 17s2 Convolutional Networks 1 Outline Geometry of Hidden Unit Activations

More information

Patient information leaflet. Royal Surrey County Hospital. NHS Foundation Trust. Amblyopia (Lazy Eye) Orthoptic Department

Patient information leaflet. Royal Surrey County Hospital. NHS Foundation Trust. Amblyopia (Lazy Eye) Orthoptic Department Patient information leaflet Royal Surrey County Hospital NHS Foundation Trust Amblyopia (Lazy Eye) Orthoptic Department Information for parents This leaflet covers information about vision treatment in

More information

Keywords Artificial Neural Networks (ANN), Echocardiogram, BPNN, RBFNN, Classification, survival Analysis.

Keywords Artificial Neural Networks (ANN), Echocardiogram, BPNN, RBFNN, Classification, survival Analysis. Design of Classifier Using Artificial Neural Network for Patients Survival Analysis J. D. Dhande 1, Dr. S.M. Gulhane 2 Assistant Professor, BDCE, Sevagram 1, Professor, J.D.I.E.T, Yavatmal 2 Abstract The

More information

Comparison of discrimination methods for the classification of tumors using gene expression data

Comparison of discrimination methods for the classification of tumors using gene expression data Comparison of discrimination methods for the classification of tumors using gene expression data Sandrine Dudoit, Jane Fridlyand 2 and Terry Speed 2,. Mathematical Sciences Research Institute, Berkeley

More information

Falls before and after cataract surgery: a prospective cohort study evaluating determinants of risk

Falls before and after cataract surgery: a prospective cohort study evaluating determinants of risk Falls before and after cataract surgery: a prospective cohort study evaluating determinants of risk Lisa Keay 1, Anna Palagyi 1, Kris Rogers 1, Lynn Meuleners 2, Peter McCluskey 3, Andrew White 3,4, Ecosse

More information

Glaucoma is the leading cause of irreversible blindness in

Glaucoma is the leading cause of irreversible blindness in Glaucoma Does Myopia Affect Angle Closure Prevalence Guangming Jin, 1 Xiaohu Ding, 1 Xinxing Guo, 1 Billy Heung Wing Chang, 1 Capucine Odouard, 1,2 and Mingguang He 1,3 1 State Key Laboratory of Ophthalmology,

More information

Validating the Accuracy of a Model to Predict the Onset of Myopia in Children METHODS

Validating the Accuracy of a Model to Predict the Onset of Myopia in Children METHODS Clinical and Epidemiologic Research Validating the Accuracy of a Model to redict the Onset of Myopia in Children Mingzhi Zhang, 1 Gus Gazzard, 2 Zhifu Fu, 3 Liping Li, 4 Bin Chen, 1 Seang Mei Saw, 5 and

More information