PMID- 35300933
OWN - NLM
STAT- MEDLINE
DCOM- 20220908
LR  - 20221013
IS  - 1524-4733 (Electronic)
IS  - 1098-3015 (Linking)
VI  - 25
IP  - 9
DP  - 2022 Sep
TI  - Predicting Patient-Level 3-Level Version of EQ-5D Index Scores From a Large 
      International Database Using Machine Learning and Regression Methods.
PG  - 1590-1601
LID - S1098-3015(22)00101-2 [pii]
LID - 10.1016/j.jval.2022.01.024 [doi]
AB  - OBJECTIVES: This study aimed to evaluate the performance of machine learning and 
      regression methods in the prediction of 3-level version of EQ-5D (EQ-5D-3L) index 
      scores from a large diverse data set. METHODS: A total of 30 studies from 3 
      countries were combined. Predictions were performed via eXtreme Gradient Boosting 
      classification (XGBC), eXtreme Gradient Boosting regression (XGBR) and ordinary 
      least squares (OLS) regression using 10-fold cross-validation and 80%/20% 
      partition for training and testing. We evaluated 6 prediction scenarios using 3 
      samples (general population, patients, total) and 2 predictor sets: demographic 
      and disease-related variables with/without patient-reported outcomes. Model 
      performance was evaluated by mean absolute error and percent of predictions 
      within clinically irrelevant error range and within correct health severity group 
      (EQ-5D-3L index <0.45, 0.45-0.926, >0.926). RESULTS: The data set involved 26 318 
      individuals (clinical settings n = 6214, general population n = 20 104) and 26 
      predictor variables plus diagnoses. Using all predictors and the total sample, 
      mean absolute error values were 0.153, 0.126, and 0.131, percent of predictions 
      within clinically irrelevant error range were 47.6%, 39.5%, and 37.4%, and within 
      the correct health severity group were 56.3%, 64.9%, and 63.3% by XGBC, XGBR, and 
      OLS, respectively. The performance of models depended on the applied evaluation 
      criteria, the target population, the included predictors, and the EQ-5D-3L index 
      score range. CONCLUSIONS: Regression models (XGBR and OLS) outperformed XGBC, yet 
      prediction errors were outside the clinically irrelevant error range for most 
      respondents. Our results highlight the importance of systematic patient-reported 
      outcome (EQ-5D) data collection. Dialogs between artificial intelligence and 
      outcomes research experts are encouraged to enhance the value of accumulating 
      data in health systems.
CI  - Copyright (c) 2022. Published by Elsevier Inc.
FAU - Zrubka, Zsombor
AU  - Zrubka Z
AD  - Health Economics Research Center, University Research and Innovation Center, 
      Obuda University, Budapest, Hungary; Corvinus Institue for Advanced Studies, 
      Corvinus University of Budapest, Budapest, Hungary. Electronic address: 
      zrubka.zsombor@uni-obuda.hu.
FAU - Csabai, Istvan
AU  - Csabai I
AD  - Department of Physics of Complex Systems, ELTE Eotvos Lorand University, 
      Budapest, Hungary.
FAU - Hermann, Zoltan
AU  - Hermann Z
AD  - Institute of Economics, Centre for Economic and Regional Studies, Budapest, 
      Hungary; Institute of Economics, Corvinus University of Budapest, Budapest, 
      Hungary.
FAU - Golicki, Dominik
AU  - Golicki D
AD  - Department of Experimental and Clinical Pharmacology, Medical University of 
      Warsaw, Warsaw, Poland.
FAU - Prevolnik-Rupel, Valentina
AU  - Prevolnik-Rupel V
AD  - Institute for Economic Research, Ljubljana, Slovenia.
FAU - Ogorevc, Marko
AU  - Ogorevc M
AD  - Institute for Economic Research, Ljubljana, Slovenia.
FAU - Gulacsi, Laszlo
AU  - Gulacsi L
AD  - Health Economics Research Center, University Research and Innovation Center, 
      Obuda University, Budapest, Hungary; Corvinus Institue for Advanced Studies, 
      Corvinus University of Budapest, Budapest, Hungary.
FAU - Pentek, Marta
AU  - Pentek M
AD  - Health Economics Research Center, University Research and Innovation Center, 
      Obuda University, Budapest, Hungary.
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20220315
PL  - United States
TA  - Value Health
JT  - Value in health : the journal of the International Society for Pharmacoeconomics 
      and Outcomes Research
JID - 100883818
SB  - IM
MH  - *Artificial Intelligence
MH  - Health Status
MH  - Humans
MH  - Least-Squares Analysis
MH  - Machine Learning
MH  - *Quality of Life
MH  - Surveys and Questionnaires
OTO - NOTNLM
OT  - EQ-5D-3L
OT  - machine learning
OT  - prediction
EDAT- 2022/03/19 06:00
MHDA- 2022/09/09 06:00
CRDT- 2022/03/18 05:38
PHST- 2021/07/28 00:00 [received]
PHST- 2021/11/30 00:00 [revised]
PHST- 2022/01/18 00:00 [accepted]
PHST- 2022/03/19 06:00 [pubmed]
PHST- 2022/09/09 06:00 [medline]
PHST- 2022/03/18 05:38 [entrez]
AID - S1098-3015(22)00101-2 [pii]
AID - 10.1016/j.jval.2022.01.024 [doi]
PST - ppublish
SO  - Value Health. 2022 Sep;25(9):1590-1601. doi: 10.1016/j.jval.2022.01.024. Epub 
      2022 Mar 15.