TY - JOUR
T1 - A decision-making framework for adaptive pain management
AU - Lin, Ching Feng
AU - LeBoulluec, Aera Kim
AU - Zeng, Li
AU - Chen, Victoria C.P.
AU - Gatchel, Robert Joseph
PY - 2014/9/1
Y1 - 2014/9/1
N2 - Pain management is a critical international health issue. The Eugene McDermott Center for Pain Management at The University of Texas Southwestern Medical Center conducted a two-stage interdisciplinary pain management program that considers a wide variety of treatments. Prior to treatment (beginning of Stage 1), an evaluation records the patient’s pain characteristics, medical history and related health parameters. A treatment regime is then determined. At the midpoint of the program (beginning of Stage 2), an evaluation is conducted to determine if an adjustment in the treatment should be made. A final evaluation is conducted at the end of the program to assess final outcomes. We structure this decision-making process using dynamic programming (DP) to generate adaptive treatment strategies for this two-stage program. An approximate DP solution method is employed in which state transition models are constructed empirically based on data from the pain management program, and the future value function is approximated using state space discretization based on a Latin hypercube design and artificial neural networks. The optimization seeks for treatment plans that minimize treatment dosage and pain levels simultaneously.
AB - Pain management is a critical international health issue. The Eugene McDermott Center for Pain Management at The University of Texas Southwestern Medical Center conducted a two-stage interdisciplinary pain management program that considers a wide variety of treatments. Prior to treatment (beginning of Stage 1), an evaluation records the patient’s pain characteristics, medical history and related health parameters. A treatment regime is then determined. At the midpoint of the program (beginning of Stage 2), an evaluation is conducted to determine if an adjustment in the treatment should be made. A final evaluation is conducted at the end of the program to assess final outcomes. We structure this decision-making process using dynamic programming (DP) to generate adaptive treatment strategies for this two-stage program. An approximate DP solution method is employed in which state transition models are constructed empirically based on data from the pain management program, and the future value function is approximated using state space discretization based on a Latin hypercube design and artificial neural networks. The optimization seeks for treatment plans that minimize treatment dosage and pain levels simultaneously.
KW - Adaptive treatment strategies
KW - Dynamic programming
KW - Pain management
UR - http://www.scopus.com/inward/record.url?scp=84907734573&partnerID=8YFLogxK
U2 - 10.1007/s10729-013-9252-0
DO - 10.1007/s10729-013-9252-0
M3 - Article
C2 - 23974825
AN - SCOPUS:84907734573
SN - 1386-9620
VL - 17
SP - 270
EP - 283
JO - Health Care Management Science
JF - Health Care Management Science
IS - 3
ER -