Neural networks for longitudinal studies in Alzheimer's disease

Reeti Tandon, Sudeshna Adak, Jeffrey Kaye

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

Objective: Alzheimer's disease affects a growing population of elderly people today. The predictions about the course of the disease is a key component of health care decision making for patients with Alzheimer's. The physician's prognosis and predicted trajectory of cognitive decline often form the basis of treatment and health care decisions taken by patients and their families. These predictions are difficult to make because of the high variability and non-linearity exhibited by individual patterns of cognitive decline. This paper presents a new method of predicting the course of a disease using longitudinal data collected through multiple clinic visits. Longitudinal databases are similar to temporal databases, with some important differences - data is collected at irregular time intervals that are patient specific and also a varying number of observations are made for each patient, depending upon the number of times the patient visited the clinic. We propose a new type of neural network called the mixed effects neural network (MENN) model that can incorporate this type of longitudinal information. Material and methods: We have used longitudinal data on 704 subjects enrolled at the Layton aging and research center (LAARC) at Oregon Health and Science University. A back-propagation algorithm, modified for longitudinal data is used to obtain the weight parameters of the MENN. The modified back-propagation algorithm is further embedded in an iterative procedure that estimates the noise variance and the parameters that capture the longitudinal (temporal) correlation structure. Results: We have compared the performance of the MENN with linear mixed effects models and standard neural networks (NN). MENN show better performance (misclassification rate = 0.13 and relative MSE = 0.35) as compared to standard NN (misclassification rate = 0.34 and relative MSE = 2.74) and linear mixed effects models (misclassification rate = 0.14 and relative MSE = 0.4). Conclusion: The results show that this method can be a useful tool for predicting non-linear disease trajectories and uncovering significant prognostic factors in longitudinal databases.

Original languageEnglish (US)
Pages (from-to)245-255
Number of pages11
JournalArtificial Intelligence in Medicine
Volume36
Issue number3
DOIs
StatePublished - Mar 2006

Fingerprint

Longitudinal Studies
Alzheimer Disease
Neural networks
Neural Networks (Computer)
Databases
Backpropagation algorithms
Health care
Delivery of Health Care
Trajectories
Ambulatory Care
Noise
Decision Making
Physicians
Weights and Measures
Health
Aging of materials
Decision making
Research
Population
Cognitive Dysfunction

Keywords

  • Disease course
  • Longitudinal
  • Misclassification
  • Mixed effects
  • Neurodegenerative diseases
  • Prognosis
  • Random effects

ASJC Scopus subject areas

  • Artificial Intelligence
  • Medicine(all)

Cite this

Neural networks for longitudinal studies in Alzheimer's disease. / Tandon, Reeti; Adak, Sudeshna; Kaye, Jeffrey.

In: Artificial Intelligence in Medicine, Vol. 36, No. 3, 03.2006, p. 245-255.

Research output: Contribution to journalArticle

Tandon, Reeti ; Adak, Sudeshna ; Kaye, Jeffrey. / Neural networks for longitudinal studies in Alzheimer's disease. In: Artificial Intelligence in Medicine. 2006 ; Vol. 36, No. 3. pp. 245-255.
@article{ca2365c9ec3a492592045c1218556c6f,
title = "Neural networks for longitudinal studies in Alzheimer's disease",
abstract = "Objective: Alzheimer's disease affects a growing population of elderly people today. The predictions about the course of the disease is a key component of health care decision making for patients with Alzheimer's. The physician's prognosis and predicted trajectory of cognitive decline often form the basis of treatment and health care decisions taken by patients and their families. These predictions are difficult to make because of the high variability and non-linearity exhibited by individual patterns of cognitive decline. This paper presents a new method of predicting the course of a disease using longitudinal data collected through multiple clinic visits. Longitudinal databases are similar to temporal databases, with some important differences - data is collected at irregular time intervals that are patient specific and also a varying number of observations are made for each patient, depending upon the number of times the patient visited the clinic. We propose a new type of neural network called the mixed effects neural network (MENN) model that can incorporate this type of longitudinal information. Material and methods: We have used longitudinal data on 704 subjects enrolled at the Layton aging and research center (LAARC) at Oregon Health and Science University. A back-propagation algorithm, modified for longitudinal data is used to obtain the weight parameters of the MENN. The modified back-propagation algorithm is further embedded in an iterative procedure that estimates the noise variance and the parameters that capture the longitudinal (temporal) correlation structure. Results: We have compared the performance of the MENN with linear mixed effects models and standard neural networks (NN). MENN show better performance (misclassification rate = 0.13 and relative MSE = 0.35) as compared to standard NN (misclassification rate = 0.34 and relative MSE = 2.74) and linear mixed effects models (misclassification rate = 0.14 and relative MSE = 0.4). Conclusion: The results show that this method can be a useful tool for predicting non-linear disease trajectories and uncovering significant prognostic factors in longitudinal databases.",
keywords = "Disease course, Longitudinal, Misclassification, Mixed effects, Neurodegenerative diseases, Prognosis, Random effects",
author = "Reeti Tandon and Sudeshna Adak and Jeffrey Kaye",
year = "2006",
month = "3",
doi = "10.1016/j.artmed.2005.10.007",
language = "English (US)",
volume = "36",
pages = "245--255",
journal = "Artificial Intelligence in Medicine",
issn = "0933-3657",
publisher = "Elsevier",
number = "3",

}

TY - JOUR

T1 - Neural networks for longitudinal studies in Alzheimer's disease

AU - Tandon, Reeti

AU - Adak, Sudeshna

AU - Kaye, Jeffrey

PY - 2006/3

Y1 - 2006/3

N2 - Objective: Alzheimer's disease affects a growing population of elderly people today. The predictions about the course of the disease is a key component of health care decision making for patients with Alzheimer's. The physician's prognosis and predicted trajectory of cognitive decline often form the basis of treatment and health care decisions taken by patients and their families. These predictions are difficult to make because of the high variability and non-linearity exhibited by individual patterns of cognitive decline. This paper presents a new method of predicting the course of a disease using longitudinal data collected through multiple clinic visits. Longitudinal databases are similar to temporal databases, with some important differences - data is collected at irregular time intervals that are patient specific and also a varying number of observations are made for each patient, depending upon the number of times the patient visited the clinic. We propose a new type of neural network called the mixed effects neural network (MENN) model that can incorporate this type of longitudinal information. Material and methods: We have used longitudinal data on 704 subjects enrolled at the Layton aging and research center (LAARC) at Oregon Health and Science University. A back-propagation algorithm, modified for longitudinal data is used to obtain the weight parameters of the MENN. The modified back-propagation algorithm is further embedded in an iterative procedure that estimates the noise variance and the parameters that capture the longitudinal (temporal) correlation structure. Results: We have compared the performance of the MENN with linear mixed effects models and standard neural networks (NN). MENN show better performance (misclassification rate = 0.13 and relative MSE = 0.35) as compared to standard NN (misclassification rate = 0.34 and relative MSE = 2.74) and linear mixed effects models (misclassification rate = 0.14 and relative MSE = 0.4). Conclusion: The results show that this method can be a useful tool for predicting non-linear disease trajectories and uncovering significant prognostic factors in longitudinal databases.

AB - Objective: Alzheimer's disease affects a growing population of elderly people today. The predictions about the course of the disease is a key component of health care decision making for patients with Alzheimer's. The physician's prognosis and predicted trajectory of cognitive decline often form the basis of treatment and health care decisions taken by patients and their families. These predictions are difficult to make because of the high variability and non-linearity exhibited by individual patterns of cognitive decline. This paper presents a new method of predicting the course of a disease using longitudinal data collected through multiple clinic visits. Longitudinal databases are similar to temporal databases, with some important differences - data is collected at irregular time intervals that are patient specific and also a varying number of observations are made for each patient, depending upon the number of times the patient visited the clinic. We propose a new type of neural network called the mixed effects neural network (MENN) model that can incorporate this type of longitudinal information. Material and methods: We have used longitudinal data on 704 subjects enrolled at the Layton aging and research center (LAARC) at Oregon Health and Science University. A back-propagation algorithm, modified for longitudinal data is used to obtain the weight parameters of the MENN. The modified back-propagation algorithm is further embedded in an iterative procedure that estimates the noise variance and the parameters that capture the longitudinal (temporal) correlation structure. Results: We have compared the performance of the MENN with linear mixed effects models and standard neural networks (NN). MENN show better performance (misclassification rate = 0.13 and relative MSE = 0.35) as compared to standard NN (misclassification rate = 0.34 and relative MSE = 2.74) and linear mixed effects models (misclassification rate = 0.14 and relative MSE = 0.4). Conclusion: The results show that this method can be a useful tool for predicting non-linear disease trajectories and uncovering significant prognostic factors in longitudinal databases.

KW - Disease course

KW - Longitudinal

KW - Misclassification

KW - Mixed effects

KW - Neurodegenerative diseases

KW - Prognosis

KW - Random effects

UR - http://www.scopus.com/inward/record.url?scp=33644857555&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33644857555&partnerID=8YFLogxK

U2 - 10.1016/j.artmed.2005.10.007

DO - 10.1016/j.artmed.2005.10.007

M3 - Article

C2 - 16427257

AN - SCOPUS:33644857555

VL - 36

SP - 245

EP - 255

JO - Artificial Intelligence in Medicine

JF - Artificial Intelligence in Medicine

SN - 0933-3657

IS - 3

ER -