Advanced

Predicting and Analyzing Osteoarthritis Patient Outcomes with Machine Learning

Persson, Per-Victor LU and Rietz, Hans (2017) In LU-CS-EX 2017-10 EDA920 20171
Department of Computer Science
Abstract
The use of machine learning as a tool in medicine is increasing and has provided new avenues for research into a number of diseases.
Creating better predictive models for these diseases could provide opportunities for better care, which we have applied to osteoarthritis, a degenerative disease that affects a large part of the older population.
We have sought to answer ``Is it possible to predict patient outcomes?'' and ``What factors contribute to the patient outcome?'' by constructing and evaluating machine learning models.
In order to do this, a dataset containing 75,366 patients who have participated in an osteoarthritis treatment program was used and analyzed.
The selection of models included neural networks, logistic regression,... (More)
The use of machine learning as a tool in medicine is increasing and has provided new avenues for research into a number of diseases.
Creating better predictive models for these diseases could provide opportunities for better care, which we have applied to osteoarthritis, a degenerative disease that affects a large part of the older population.
We have sought to answer ``Is it possible to predict patient outcomes?'' and ``What factors contribute to the patient outcome?'' by constructing and evaluating machine learning models.
In order to do this, a dataset containing 75,366 patients who have participated in an osteoarthritis treatment program was used and analyzed.
The selection of models included neural networks, logistic regression, and gradient boosting machines among others in order to capture the performance of several types of machine learning models.
Our results show that it is possible to predict patient outcomes on a test set with ~60% accuracy. (Less)
Please use this url to cite or link to this publication:
author
Persson, Per-Victor LU and Rietz, Hans
supervisor
organization
course
EDA920 20171
year
type
H3 - Professional qualifications (4 Years - )
subject
keywords
MSc, machinelearning, neuralnetworks, osteoarthritis
publication/series
LU-CS-EX 2017-10
report number
LU-CS-EX 2017-10
ISSN
1650-2884
language
English
id
8919345
date added to LUP
2017-06-28 10:12:23
date last changed
2017-06-28 10:12:23
@misc{8919345,
  abstract     = {The use of machine learning as a tool in medicine is increasing and has provided new avenues for research into a number of diseases. 
Creating better predictive models for these diseases could provide opportunities for better care, which we have applied to osteoarthritis, a degenerative disease that affects a large part of the older population. 
We have sought to answer ``Is it possible to predict patient outcomes?'' and ``What factors contribute to the patient outcome?'' by constructing and evaluating machine learning models.
In order to do this, a dataset containing 75,366 patients who have participated in an osteoarthritis treatment program was used and analyzed.
The selection of models included neural networks, logistic regression, and gradient boosting machines among others in order to capture the performance of several types of machine learning models.
Our results show that it is possible to predict patient outcomes on a test set with ~60% accuracy.},
  author       = {Persson, Per-Victor and Rietz, Hans},
  issn         = {1650-2884},
  keyword      = {MSc,machinelearning,neuralnetworks,osteoarthritis},
  language     = {eng},
  note         = {Student Paper},
  series       = {LU-CS-EX 2017-10},
  title        = {Predicting and Analyzing Osteoarthritis Patient Outcomes with Machine Learning},
  year         = {2017},
}