Journal ArticleDOI
Time to CARE: a collaborative engine for practical disease prediction
Reads0
Chats0
TLDR
This work proposes CARE, a Collaborative Assessment and Recommendation Engine, which relies only on patient’s medical history using ICD-9-CM codes in order to predict future disease risks, and describes an Iterative version, ICARE, which incorporates ensemble concepts for improved performance.Abstract:
The monumental cost of health care, especially for chronic disease treatment, is quickly becoming unmanageable. This crisis has motivated the drive towards preventative medicine, where the primary concern is recognizing disease risk and taking action at the earliest signs. However, universal testing is neither time nor cost efficient. We propose CARE, a Collaborative Assessment and Recommendation Engine, which relies only on patient's medical history using ICD-9-CM codes in order to predict future disease risks. CARE uses collaborative filtering methods to predict each patient's greatest disease risks based on their own medical history and that of similar patients. We also describe an Iterative version, ICARE, which incorporates ensemble concepts for improved performance. Also, we apply time-sensitive modifications which make the CARE framework practical for realistic long-term use. These novel systems require no specialized information and provide predictions for medical conditions of all kinds in a single run. We present experimental results on a large Medicare dataset, demonstrating that CARE and ICARE perform well at capturing future disease risks.read more
Citations
More filters
Journal ArticleDOI
Comparing different supervised machine learning algorithms for disease prediction
TL;DR: It is found that the Support Vector Machine (SVM) algorithm is applied most frequently (in 29 studies) followed by the Naïve Bayes algorithm (in 23 studies), however, the Random Forest algorithm showed superior accuracy comparatively.
Journal ArticleDOI
Bringing Big Data to Personalized Healthcare: A Patient-Centered Framework
Nitesh V. Chawla,Darcy A. Davis +1 more
TL;DR: The foundations of work that takes a Big Data driven approach towards personalized healthcare are presented, and its applicability to patient-centered outcomes, meaningful use, and reducing re-admission rates are demonstrated.
Proceedings ArticleDOI
Combining predictions for accurate recommender systems
TL;DR: It is shown that linearly combining a set of CF algorithms increases the accuracy and outperforms any single CF algorithm, and how to use ensemble methods for blending predictors in order to outperform a single blending algorithm.
Journal ArticleDOI
Limestone: High-throughput candidate phenotype generation via tensor factorization
Joyce C. Ho,Joydeep Ghosh,Steven R. Steinhubl,Walter F. Stewart,Joshua C. Denny,Bradley A. Malin,Jimeng Sun +6 more
TL;DR: The proposed Limestone, a nonnegative tensor factorization method to derive phenotype candidates with virtually no human supervision, is proposed and multiple phenotypes can be identified simultaneously from data.
Journal ArticleDOI
Recommender systems in the healthcare domain: state-of-the-art and research issues
TL;DR: This article provides a systematic overview of existing research on healthcare recommender systems, providing insights into recommendation scenarios and recommendation approaches, and develops working examples to give a deep understanding of recommendation algorithms.
References
More filters
Journal ArticleDOI
A Tutorial on Support Vector Machines for Pattern Recognition
TL;DR: There are several arguments which support the observed high accuracy of SVMs, which are reviewed and numerous examples and proofs of most of the key theorems are given.
Book
Introduction to Modern Information Retrieval
Gerard Salton,Michael J. McGill +1 more
TL;DR: Reading is a need and a hobby at once and this condition is the on that will make you feel that you must read.
Journal ArticleDOI
Genome-wide association study of 14,000 cases of seven common diseases and 3,000 shared controls
Paul Burton,David Clayton,Lon R. Cardon,Nicholas John Craddock,Panos Deloukas,Audrey Duncanson,Dominic P. Kwiatkowski,Mark I. McCarthy,Willem H. Ouwehand,Nilesh J. Samani,John A. Todd,Peter Donnelly,Jeffrey C. Barrett,Dan Davison,Doug Easton,David M. Evans,H. T. Leung,Jonathan Marchini,Andrew P. Morris,Chris C. A. Spencer,Martin D. Tobin,Antony P. Attwood,James P. Boorman,Barbara Cant,Ursula Everson,Judith M. Hussey,Jennifer Jolley,Alexandra S. Knight,Kerstin Koch,Elizabeth Meech,Sarah Nutland,Christopher Prowse,Helen Stevens,Niall C. Taylor,Graham R. Walters,Neil Walker,Nicholas A. Watkins,Thilo Winzer,Richard Jones,Wendy L. McArdle,Susan M. Ring,David P. Strachan,Marcus Pembrey,Gerome Breen,David St Clair,Sian Caesar,Katherine Gordon-Smith,Lisa Jones,Christine Fraser,Elaine K. Green,Detelina Grozeva,Marian L. Hamshere,Peter Holmans,Ian Jones,George Kirov,Valentina Moskvina,Ivan Nikolov,Michael Conlon O'Donovan,Michael John Owen,David A. Collier,Amanda Elkin,Anne Farmer,Richard Williamson,Peter McGuffin,Allan H. Young,I. Nicol Ferrier,Stephen G. Ball,Anthony J. Balmforth,Jennifer H. Barrett,D. Timothy Bishop,Mark M. Iles,Azhar Maqbool,Nadira Yuldasheva,Alistair S. Hall,Peter S. Braund,Richard J. Dixon,Massimo Mangino,Suzanne Stevens,John R. Thompson,Francesca Bredin,Mark Tremelling,Miles Parkes,Hazel E. Drummond,Charlie W. Lees,Elaine R. Nimmo,Jack Satsangi,Sheila A. Fisher,Alastair Forbes,Cathryn M. Lewis,Clive M. Onnie,Natalie J. Prescott,Jeremy D. Sanderson,Christopher G. Mathew,Jamie Barbour,M. Khalid Mohiuddin,Catherine E. Todhunter,John C. Mansfield,Tariq Ahmad,Fraser Cummings,Derek P. Jewell,John Webster,Morris J. Brown,G. Mark Lathrop,John M. C. Connell,Anna F. Dominiczak,Carolina A. Braga Marcano,Beverley Burke,Richard Dobson,Johannie Gungadoo,Kate L. Lee,Patricia B. Munroe,Stephen Newhouse,Abiodun Onipinla,Chris Wallace,Mingzhan Xue,Mark J. Caulfield,Martin Farrall,Anne Barton,Ian N. Bruce,Hannah Donovan,Steve Eyre,Paul D. Gilbert,Samantha L. Hider,Anne Hinks,Sally John,Catherine Potter,Alan J. Silman,Deborah P M Symmons,Wendy Thomson,Jane Worthington,David B. Dunger,Barry Widmer,Timothy M. Frayling,Rachel M. Freathy,Hana Lango,John R. B. Perry,Beverley M. Shields,Michael N. Weedon,Andrew T. Hattersley,Graham A. Hitman,Mark Walker,Kate S. Elliott,Christopher J. Groves,Cecilia M. Lindgren,Nigel W. Rayner,Nicholas J. Timpson,Eleftheria Zeggini,Melanie J. Newport,Giorgio Sirugo,Emily J. Lyons,Fredrik O. Vannberg,Adrian V. S. Hill,Linda A. Bradbury,C Farrar,J J Pointon,Paul Wordsworth,Matthew A. Brown,Jayne A. Franklyn,Joanne M. Heward,Matthew J. Simmonds,Stephen C. L. Gough,Sheila Seal,Michael R. Stratton,Nazneen Rahman,Maria Ban,An Goris,Stephen Sawcer,Alastair Compston,David J. Conway,Muminatou Jallow,Kirk A. Rockett,Suzannah Bumpstead,Amy Chaney,Kate Downes,Mohammed J. R. Ghori,Rhian Gwilliam,Sarah E. Hunt,Michael Inouye,Andrew Keniry,Emma King,Ralph McGinnis,Simon C. Potter,Rathi Ravindrarajah,Pamela Whittaker,Claire Widden,David Withers,Niall Cardin,Teresa Ferreira,Joanne Pereira-Gale,Ingileif B. Hallgrímsdóttir,Bryan Howie,Zhan Su,Yik Ying Teo,Damjan Vukcevic,David Bentley,A Compston +195 more
TL;DR: This study has demonstrated that careful use of a shared control group represents a safe and effective approach to GWA analyses of multiple disease phenotypes; generated a genome-wide genotype database for future studies of common diseases in the British population; and shown that, provided individuals with non-European ancestry are excluded, the extent of population stratification in theBritish population is generally modest.
Journal ArticleDOI
Evaluating collaborative filtering recommender systems
TL;DR: The key decisions in evaluating collaborative filtering recommender systems are reviewed: the user tasks being evaluated, the types of analysis and datasets being used, the ways in which prediction quality is measured, the evaluation of prediction attributes other than quality, and the user-based evaluation of the system as a whole.
Book ChapterDOI
Ensemble Methods in Machine Learning
TL;DR: Some previous studies comparing ensemble methods are reviewed, and some new experiments are presented to uncover the reasons that Adaboost does not overfit rapidly.