Advanced

Using hidden Markov models to characterize disease trajectories

Peterson, Carsten LU and Ohlsson, Mattias LU (2001) p.324-326
Abstract
A novel approach is developed for predicting body trajectories for cancer progression, where conditional probabilities of clinical data are modeled using Hidden Markov Model techniques. Basically, each potential body site is encoded by an N-letter code, and a disease trajectory is described in terms of a string of letters. Patient data base records are then represented by such strings with different lengths, start points and end points. The approach is explored using pathology data for non-Hodgkin lymphoma augmented with an artificial data base generated according to observed distributions in the clinical data. For the Hidden Markov Models a Bayesian approach is taken using the Hybrid Monte Carlo method, producing an ensemble of models... (More)
A novel approach is developed for predicting body trajectories for cancer progression, where conditional probabilities of clinical data are modeled using Hidden Markov Model techniques. Basically, each potential body site is encoded by an N-letter code, and a disease trajectory is described in terms of a string of letters. Patient data base records are then represented by such strings with different lengths, start points and end points. The approach is explored using pathology data for non-Hodgkin lymphoma augmented with an artificial data base generated according to observed distributions in the clinical data. For the Hidden Markov Models a Bayesian approach is taken using the Hybrid Monte Carlo method, producing an ensemble of models rather than a single one. Using a test set consisting of both real and random trajectories, we estimate the performance of our Hidden Markov Model models and also extract most probable profiles. Given the limited data set size the results are very encouraging. (Less)
Please use this url to cite or link to this publication:
author
and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
host publication
Proceedings of the Neural Networks and Expert Systems in Medicine and Healthcare Conference, 324-326 (2001), eds. G.M. Papadourakis
editor
Papadourakis, G. M.
pages
3 pages
language
English
LU publication?
yes
id
3c5c31cd-a269-4937-b698-0c096af73448
date added to LUP
2019-05-31 10:44:32
date last changed
2020-01-14 14:03:27
@inbook{3c5c31cd-a269-4937-b698-0c096af73448,
  abstract     = {A novel approach is developed for predicting body trajectories for cancer progression, where conditional probabilities of clinical data are modeled using Hidden Markov Model techniques. Basically, each potential body site is encoded by an N-letter code, and a disease trajectory is described in terms of a string of letters. Patient data base records are then represented by such strings with different lengths, start points and end points. The approach is explored using pathology data for non-Hodgkin lymphoma augmented with an artificial data base generated according to observed distributions in the clinical data. For the Hidden Markov Models a Bayesian approach is taken using the Hybrid Monte Carlo method, producing an ensemble of models rather than a single one. Using a test set consisting of both real and random trajectories, we estimate the performance of our Hidden Markov Model models and also extract most probable profiles. Given the limited data set size the results are very encouraging.},
  author       = {Peterson, Carsten and Ohlsson, Mattias},
  booktitle    = {Proceedings of the Neural Networks and Expert Systems in Medicine and Healthcare Conference, 324-326 (2001), eds. G.M. Papadourakis},
  editor       = {Papadourakis, G. M.},
  language     = {eng},
  pages        = {324--326},
  title        = {Using hidden Markov models to characterize disease trajectories},
  year         = {2001},
}