Predicting Patient-Level 3-Level Version of EQ-5D Index Scores From a Large International Database Using Machine Learning and Regression Methods

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.

The burden of informal caregiving in Hungary, Poland and Slovenia: results from national representative surveys

BACKGROUND

We aimed to investigate the burden of informal care in Hungary (HU), Poland (PL) and Slovenia (SI).

METHODS

A cross-sectional online survey was performed involving representative samples of 1000 respondents per country. Caregiving situations were explored; health status of informal caregivers/care recipients and care-related quality of life were assessed using the EQ-5D-5L and CarerQol-7D.

RESULTS

The proportion of caregivers was (HU/PL/SI) 14.9, 15.0 and 9.6%, respectively. Their mean age was 56.1, 45.6 and 48.0, and the average time spent on informal care was 27.6, 35.5 and 28.8 h/week. Chronic care was dominant (> 1 year: 78.5%, 72.0%, 74.0%) and care recipients were mainly (own/in-law) parents. Average EQ-5D-5L scores of care recipients were 0.53, 0.49 and 0.52. For Poland and Slovenia, EQ-5D-5L scores of informal care providers were significantly lower than of other respondents. Average CarerQol-7D scores were (HU/PL/SI) 76.0, 69.6 and 70.9, and CarerQol-VAS was 6.8, 6.4 and 6.6, respectively. Overall, 89, 87, and 84% of caregivers felt some or a lot fulfilment related to caring. Problems with combining tasks with daily activities were most important in Hungary and Slovenia. Women had a higher probability of being a caregiver in Hungary. CarerQol-7D scores were significantly associated with caregivers' EQ-5D-5L scores. In Hungary and Poland, living in a larger household was positively, while caring for patients with mental health problems was negatively associated with CarerQol-7D scores.

CONCLUSIONS

These first results from the Central and Eastern European region using preference-based measures for the evaluation of informal care can serve as a valuable input for health economic analyses.

Towards a Central-Eastern European EQ-5D-3L population norm: comparing data from Hungarian, Polish and Slovenian population studies

BACKGROUND

EQ-5D-3L population data are available only from Hungary, Poland and Slovenia in Central and Eastern Europe (CEE). We aimed to compare the accessible studies and estimate a regional EQ-5D-3L population norm for CEE.

METHODS

A combined dataset using patient-level data of 8850 respondents was created. Based on the European Census of 2011, regional population norm estimates were calibrated by gender, age and education for the joint citizenry of 11 CEE countries.

RESULTS

EQ-5D-3L health states were available for 6926 and EQ VAS scores for 6569 respondents. Demographic characteristics of the samples reflected the recruitment methods (Hungary: online; Slovenia: postal survey, Poland: personal interviews). Occurrence of problems differed significantly by educational level in all the five dimensions (p < 0.001). The inter-country differences persisted after controlling for demographic variables. The estimated EQ-5D-3L index CEE norms with UK tariffs for age groups 18-24, 25-34, 35-44, 45-54, 55-64, 65-74 and 75 + were 0.911, 0.912, 0.871, 0.817, 0.762, 0.743 and 0.636 for males and 0.908, 0.888, 0.867, 0.788, 0.752, 0.68 and 0.584 for females, respectively. Estimates were provided also using Polish, European and Slovenian value sets.

CONCLUSIONS

Besides gender and age, education should be considered during the design and interpretation of quality-of-life studies in CEE. The estimated regional EQ-5D-3L population norm may be used as a benchmark by CEE countries with lack of local dataset. However, the substantial inter-country differences in health status and scarcity of data over age 65 call for harmonized country-specific EQ-5D-3L population norm studies in the CEE region.

A comparison of European, Polish, Slovenian and British EQ-5D-3L value sets using a Hungarian sample of 18 chronic diseases

BACKGROUND

In the Central and Eastern European region, the British EQ-5D-3L value set is used commonly in quality of life (QoL) studies. Only Poland and Slovenia have country-specific weights. Our study aimed to investigate the impact of value set choice on the evaluation of 18 chronic conditions in Hungary.

METHODS

Patients' EQ-5D-3L index scores were calculated using the VAS-based Slovenian and European and the time-trade-off-based Polish and British value sets. We performed pairwise comparisons of mean index values by dimensions, diagnoses and age groups. We evaluated disease burden by comparing index values matched by age and gender in each condition with those of the general population of the CEE region in all four value sets.

RESULTS

Altogether, 2421 patients (55% female) were included in our sample with the average age of 55.87 years (SD = 17.75). The average Slovenian, European, Polish and British EQ-5D-3L scores were 0.598 (SD = 0.279), 0.661 (SD = 0.257), 0.770 (SD = 0.261) and 0.644 (SD = 0.279), respectively. We found highly significant differences in most diagnoses, with the greatest difference between the Polish and Slovenian index values in Parkinson's disease (0.265). Systematic pairwise comparison across all conditions and value sets revealed greatest differences between the time-trade-off (TTO) and VAS-based value sets as well as varying sensitivity of the disease burden evaluations of chronic disease conditions to the choice of value sets.

CONCLUSIONS

Our results suggest that the choice of value set largely influences the health state utility results in chronic diseases, and might have a significant impact on health policy decisions.