Abstract
Background
This study aims to derive country-specific EQ-5D-5L health status utility (HSU) from the MacNew Heart Disease Health-related Quality of Life questionnaire (MacNew) using both traditional regression analyses, as well as a machine learning technique.
Methods
Data were drawn from the Multi-Instrument Comparison (MIC) survey. The EQ-5D-5L was scored using 4 country-specific tariffs (United States, United Kingdom, Germany, and Canada). The traditional regression techniques, as well as a machine learning technique, deep neural network (DNN), were adopted to directly predict country-specific EQ-5D-5L HSUs (i.e. a direct mapping approach). An indirect response mapping was undertaken additionally. The optimal algorithm was identified based on three goodness-of-fit tests, namely, the mean absolute error (MAE), mean error (ME) and root mean square error (RMSE), with the first being the primary criteria. Internal validation was undertaken.
Results
Indirect response mapping and direct mapping (via betamix with MacNew items as the key predictors) were found to produce the optimal mapping algorithms with the lowest MAE when EQ-5D-5L were scored using three country-specific tariffs (United Kingdom, Canada, and Germany for the former and United Kingdom, United States, Canada and Germany for the latter approach). DNN approach generated the lowest MAE and RMSE when using the Germany-specific tariff.
Conclusions
Among different approaches been explored, there is not a conclusive conclusion regarding the optimal method for developing mapping algorithms. A machine learning approach represents an alternative mapping approach that should be explored further. The reported algorithms from response mapping have the potential to be more widely used; however, the performance needs to be externally validated.
Similar content being viewed by others
Availability of data and materials
MIC dataset is available upon request.
Code availability
Code for DNN model is publicly assessable.
References
Rumsfeld, J.S., Alexander, K.P., Goff, D.C., Jr., Graham, M.M., Ho, P.M., Masoudi, F.A., Moser, D.K., Roger, V.L., Slaughter, M.S., Smolderen, K.G., Spertus, J.A., Sullivan, M.D., Treat-Jacobson, D., Zerwic, J.J., American Heart Association Council on Quality of, C., Outcomes Research, C.o.C., Stroke Nursing, C.o.E., Prevention, C.o.P.V.D., Stroke, C.: Cardiovascular health: the importance of measuring patient-reported health status: a scientific statement from the American Heart Association. Circulation 127(22), 2233–2249 (2013). doi:https://doi.org/10.1161/CIR.0b013e3182949a2e
Hofer, S., Benzer, W., Oldridge, N.: Change in health-related quality of life in patients with coronary artery disease predicts 4-year mortality. Int. J. Cardiol. 174(1), 7–12 (2014). https://doi.org/10.1016/j.ijcard.2014.03.144
Hofer, S., Kullich, W., Graninger, U., Wonisch, M., Gassner, A., Klicpera, M., Laimer, H., Marko, C., Schwann, H., Muller, R.: Cardiac rehabilitation in Austria: long term health-related quality of life outcomes. Health Qual. Life Outcomes 7, 99 (2009). https://doi.org/10.1186/1477-7525-7-99
Longworth, L., Rowen, D.: Mapping to obtain EQ-5D utility values for use in NICE health technology assessments. Value Health 16(1), 202–210 (2013). https://doi.org/10.1016/j.jval.2012.10.010
Pharmaceutical Benefits Advisory Committee: Guidelines for preparing submissions to the Pharmaceutical Benefits Advisory Committee (PBAC), version 5.0. Available from: https://pbac.pbs.gov.au/. (2016).
Hofer, S., Lim, L., Guyatt, G., Oldridge, N.: The MacNew Heart Disease health-related quality of life instrument: a summary. Health Qual. Life Outcomes 2, 3 (2004). https://doi.org/10.1186/1477-7525-2-3
Chen, G., McKie, J., Khan, M.A., Richardson, J.R.: Deriving health utilities from the MacNew Heart Disease Quality of Life Questionnaire. Eur. J. Cardiovasc. Nurs. 14(5), 405–415 (2015). https://doi.org/10.1177/1474515114536096
Obermeyer, Z., Emanuel, E.J.: Predicting the future—Big data, machine learning, and clinical medicine. N. Engl. J. Med. 375(13), 1216–1219 (2016). https://doi.org/10.1056/NEJMp1606181
Mullainathan, S., Spiess, J.: Machine learning: an applied econometric approach. J. Econ. Perspect. 31(2), 87–106 (2017). https://doi.org/10.1257/jep.31.2.87
Rajkomar, A., Dean, J., Kohane, I.: Machine learning in medicine. N. Engl. J. Med. 380(14), 1347–1358 (2019). https://doi.org/10.1056/NEJMra1814259
Chen, P.H.C., Liu, Y., Peng, L.: How to develop machine learning models for healthcare. Nat. Mater. 18(5), 410–414 (2019). https://doi.org/10.1038/s41563-019-0345-0
Richardson J, I., Khan, M., Maxwell, A.: Cross-national comparison of twelve quality of life instruments: MIC paper1: background, questions, instruments. Melbourne, Victoria, Australia: Research Paper76, Centre for Health Economics, Monash University, 2012.
Brazier, J.E., Yang, Y., Tsuchiya, A., Rowen, D.L.: A review of studies mapping (or cross walking) non-preference based measures of health to generic preference-based measures. Eur. J. Health Econ. 11(2), 215–225 (2010). https://doi.org/10.1007/s10198-009-0168-z
Xie, F., Pullenayegum, E., Gaebel, K., Bansback, N., Bryan, S., Ohinmaa, A., Poissant, L., Johnson, J.A., Canadian, E.Q.D.L.V.S.G.: A Time Trade-off-derived Value Set of the EQ-5D-5L for Canada. Med Care 54(1), 98–105 (2016). doi:https://doi.org/10.1097/MLR.0000000000000447
Pickard, A.S., Law, E.H., Jiang, R., Pullenayegum, E., Shaw, J.W., Xie, F., Oppe, M., Boye, K.S., Chapman, R.H., Gong, C.L., Balch, A., Busschbach, J.J.V.: United States Valuation of EQ-5D-5L Health States Using an International Protocol. Value Health (2019). https://doi.org/10.1016/j.jval.2019.02.009
Ludwig, K., Graf von der Schulenburg, J.M., Greiner, W.: German Value Set for the EQ-5D-5L. Pharmacoeconomics 36(6), 663–674 (2018). doi:https://doi.org/10.1007/s40273-018-0615-8
Oldridge, N., Guyatt, G., Jones, N., Crowe, J., Singer, J., Feeny, D., Mckelvie, R., Runions, J., Streiner, D., Torrance, G.: Effects on quality-of-life with comprehensive rehabilitation after acute myocardial-infarction. Am. J. Cardiol. 67(13), 1084–1089 (1991). https://doi.org/10.1016/0002-9149(91)90870-Q
Lim, L.L.Y., Valenti, L.A., Knapp, J.C., Dobson, A.J., Plotnikoff, R., Higginbotham, N., Heller, R.F.: A self-administered quality-of-life questionnaire after acute myocardial-infarction. J. Clin. Epidemiol. 46(11), 1249–1256 (1993). https://doi.org/10.1016/0895-4356(93)90089-J
Valenti, L., Lim, L., Heller, R.F., Knapp, J.: An improved questionnaire for assessing quality of life after acute myocardial infarction. Qual. Life Res. 5(1), 151–161 (1996). https://doi.org/10.1007/Bf00435980
Dixon, T., Lim, L.L.Y., Oldridge, N.B.: The MacNew heart disease health-related quality of life instrument: reference data for users. Qual. Life Res. 11(2), 173–183 (2002). https://doi.org/10.1023/A:1015005109731
Alava, M.H., Wailoo, A.: Fitting adjusted limited dependent variable mixture models to EQ-5D. 15(3), 737–750 (2015). doi:https://doi.org/10.1177/1536867x1501500307
Hernandez Alava, M., Wailoo, A.J., Ara, R.: Tails from the peak district: adjusted limited dependent variable mixture models of EQ-5D questionnaire health state utility values. Value Health 15(3), 550–561 (2012). https://doi.org/10.1016/j.jval.2011.12.014
Gray, L.A., Alava, M.H., Wailoo, A.J.: Development of methods for the mapping of utilities using mixture models: mapping the AQLQ-S to the EQ-5D-5L and the HUI3 in Patients with Asthma. Value Health 21(6), 748–757 (2018). https://doi.org/10.1016/j.jval.2017.09.017
Wailoo, A., Alava, M.H., Martinez, A.E.: Modelling the relationship between the WOMAC osteoarthritis index and EQ-5D. Health Qual. Life Out 12 (2014). doi:https://doi.org/10.1186/1477-7525-12-37
Ward Fuller, G., Hernandez, M., Pallot, D., Lecky, F., Stevenson, M., Gabbe, B.: Health state preference weights for the Glasgow Outcome Scale following traumatic brain injury: a systematic review and mapping study. Value Health 20(1), 141–151 (2017). https://doi.org/10.1016/j.jval.2016.09.2398
Gray, L.A., Hernández Alava, M., Wailoo, A.J.: Development of methods for the mapping of utilities using mixture models: mapping the AQLQ-S to the EQ-5D-5L and the HUI3 in patients with asthma. Value Health 21(6), 748–757 (2018). https://doi.org/10.1016/j.jval.2017.09.017
Gray, L.A., Alava, M.H.: A command for fitting mixture regression models for bounded dependent variables using the beta distribution. 18(1), 51–75 (2018). doi:https://doi.org/10.1177/1536867x1801800105
Rabe Hesketh, B., Everitt, B.: A handbook of statistical analyses using Stata (fourth edition). Chapman and Hall/CRC, Boca Raton, Florida (2007)
Chen, G., Garcia-Gordillo, M.A., Collado-Mateo, D., del Pozo-Cruz, B., Adsuar, J.C., Cordero-Ferrera, J.M., Abellán-Perpiñán, J.M., Sánchez-Martínez, F.I.: Converting Parkinson-specific scores into health state utilities to assess cost-utility analysis. Patient Patient-Centered Outcomes Res. 11(6), 665–675 (2018). https://doi.org/10.1007/s40271-018-0317-5
Freese J, JS, L.: Regression models for categorical dependent variables using Stata. Austin: Stata. (2006)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436 (2015). https://doi.org/10.1038/nature14539
Esteva, A., Robicquet, A., Ramsundar, B., Kuleshov, V., DePristo, M., Chou, K., Cui, C., Corrado, G., Thrun, S., Dean, J.: A guide to deep learning in healthcare. Nat. Med. 25(1), 24–29 (2019). https://doi.org/10.1038/s41591-018-0316-z
Willmott, C.J., Matsuura, K.: Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate Res. 30(1), 79–82 (2005). https://doi.org/10.3354/cr030079
van Hout, B., Janssen, M.F., Feng, Y.S., Kohlmann, T., Busschbach, J., Golicki, D., Lloyd, A., Scalone, L., Kind, P., Pickard, A.S.: Interim scoring for the EQ-5D-5L: mapping the EQ-5D-5L to EQ-5D-3L value sets. Value Health 15(5), 708–715 (2012). https://doi.org/10.1016/j.jval.2012.02.008
Alava, M.H., Wailoo, A.: Fitting adjusted limited dependent variable mixture models to EQ-5D. Stata J 15(3), 737–750 (2015). https://doi.org/10.1177/1536867x1501500307
Alava, M.H., Wailoo, A.J., Ara, R.: Tails from the Peak district: adjusted limited dependent variable mixture models of EQ-5D Questionnaire Health State Utility Values. Value Health 15(3), 550–561 (2012). https://doi.org/10.1016/j.jval.2011.12.014
Kaambwa, B., Chen, G., Ratcliffe, J., Iezzi, A., Maxwell, A., Richardson, J.: Mapping between the Sydney Asthma Quality of Life Questionnaire (AQLQ-S) and Five Multi-Attribute Utility Instruments (MAUIs). Pharmacoeconomics 35(1), 111–124 (2017). https://doi.org/10.1007/s40273-016-0446-4
Basu, A., Manca, A.: Regression estimators for generic health-related quality of life and quality-adjusted life years. Med. Decis. Making 32(1), 56–69 (2012). https://doi.org/10.1177/0272989x11416988
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015). https://doi.org/10.1038/nature14539
Hays, R.D., Revicki, D.A., Feeny, D., Fayers, P., Spritzer, K.L., Cella, D.: Using Linear Equating to Map PROMIS((R)) Global Health Items and the PROMIS-29 V2.0 Profile Measure to the Health Utilities Index Mark 3. Pharmacoeconomics 34(10), 1015–1022 (2016). doi:https://doi.org/10.1007/s40273-016-0408-x
Thompson, N.R., Lapin, B.R., Katzan, I.L.: Mapping PROMIS Global Health Items to EuroQol (EQ-5D) Utility Scores using linear and equipercentile equating. Pharmacoeconomics 35(11), 1167–1176 (2017). https://doi.org/10.1007/s40273-017-0541-1
Chen, G., Khan, M.A., Iezzi, A., Ratcliffe, J., Richardson, J.: Mapping between 6 multiattribute utility instruments. Med. Decis. Making 36(2), 160–175 (2016). https://doi.org/10.1177/0272989x15578127
Funding
No funding is received.
Author information
Authors and Affiliations
Contributions
LG, WL and GC conceived the project; LG, WL and UT conducted the data analysis; LG, WL, UT, MM and GC interpreted the results; LG drafted the manuscript and all the other authors reviewed and approved the final version for submission.
Corresponding author
Ethics declarations
Conflict of interest
All authors affirm that there is nothing to declare.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Gao, L., Luo, W., Tonmukayakul, U. et al. Mapping MacNew Heart Disease Quality of Life Questionnaire onto country-specific EQ-5D-5L utility scores: a comparison of traditional regression models with a machine learning technique. Eur J Health Econ 22, 341–350 (2021). https://doi.org/10.1007/s10198-020-01259-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10198-020-01259-9