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

Measurement properties of utility-based health-related quality of life measures in cardiac rehabilitation and secondary prevention programs: a systematic review

PURPOSE

To identify utility-based patient-reported outcome measures (PROMs) for assessing health-related quality of life (HRQoL) in cardiac rehabilitation and secondary prevention programs (CR) and appraise existing evidence on their measurement properties. Secondly, to link their items to the International Classification of Functioning Disability and Health (ICF) and the International Consortium of Health Outcome Measures (ICHOM) domains for cardiovascular disease (CVD).

METHODS

Eight databases were searched. The review followed the COSMIN and JBI guidelines for measurement properties systematic reviews and PRISMA 2020 reporting guidelines. Non-experimental and observational empirical studies of patients ≥ 18 years of age with CVD undergoing CR and assessed quality of life (QoL) or HRQoL using utility-based PROMs or one accompanied by health state utilities were included.

RESULTS

Nine PROMs were identified with evidence on measurement properties for three measures: the German translations of SF-12, EQ-5D-5L, and MacNew heart disease HRQoL questionnaire. There was moderate quality evidence for responsiveness and hypothesis testing of the SF-12 and EQ-5D-5L, and high-quality evidence for responsiveness and hypothesis testing for the MacNew. All items of SF-12 and EQ-5D were linked to ICF categories, but four items of the MacNew were not classified or defined. All the PROM domains were mapped onto similar constructs from the ICHOM global sets.

CONCLUSION

Three utility-based PROMs validated in CR were identified: the German versions of the EQ-5D and SF-12 and the MacNew questionnaire. These PROMs are linked to a breadth of ICF categories and all ICHOM global sets. Additional validation studies of PROMs in CR are required.

Mapping from SIBDQ to EQ-5D-5L for patients with inflammatory bowel disease

OBJECTIVE

Clinical studies commonly use disease-specific measures to assess patients' health-related quality of life. However, economic evaluation often requires preference-based utility index scores to calculate cost per quality-adjusted life-year (QALY). When utility index scores are not directly available, mappings are useful. To our knowledge, no mapping exists for the Short Inflammatory Bowel Disease Questionnaire (SIBDQ). Our aim was to develop a mapping from SIBDQ to the EQ-5D-5L index score with German weights for inflammatory bowel disease (IBD) patients.

METHODS

We used 3856 observations of 1055 IBD patients who participated in a randomised controlled trial in Germany on the effect of introducing regular appointments with an IBD nurse specialist in addition to standard care with biologics. We considered five data availability scenarios. For each scenario, we estimated different regression and machine learning models: linear mixed-effects regression, mixed-effects Tobit regression, an adjusted limited dependent variable mixture model and a mixed-effects regression forest. We selected the final models with tenfold cross-validation based on a model subset and validated these with observations in a validation subset.

RESULTS

For the first four data availability scenarios, we selected mixed-effects Tobit regressions as final models. For the fifth scenario, mixed-effects regression forest performed best. Our findings suggest that the demographic variables age and gender do not improve the mapping, while including SIBDQ subscales, IBD disease type, BMI and smoking status leads to better predictions.

CONCLUSION

We developed an algorithm mapping SIBDQ values to EQ-5D-5L index scores for different sets of covariates in IBD patients. It is implemented in the following web application: https://www.bwl.uni-hamburg.de/hcm/forschung/mapping.html .

Mapping the 12-item World Health Organization disability assessment schedule 2.0 (WHODAS 2.0) onto the assessment of quality of life (AQoL)-4D utilities

PURPOSE

The World Health Organization Disability Assessment Schedule 2.0 (WHODAS 2.0) is a widely used disability-specific outcome measure. This study develops mapping algorithms to estimate Assessment of Quality of Life (AQoL)-4D utilities based on the WHODAS 2.0 responses to facilitate economic evaluation.

METHODS

The study sample comprises people with disability or long-term conditions (n = 3376) from the 2007 Australian National Survey of Mental Health and Wellbeing. Traditional regression techniques (i.e., Ordinary Least Square regression, Robust MM regression, Generalised Linear Model and Betamix Regression) and machine learning techniques (i.e., Lasso regression, Boosted regression, Supported vector regression) were used. Five-fold internal cross-validation was performed. Model performance was assessed using a series of goodness-of-fit measures.

RESULTS

The robust MM estimator produced the preferred mapping algorithm for the overall sample with the smallest mean absolute error in cross-validation (MAE = 0.1325). Different methods performed differently for different disability subgroups, with the subgroup with profound or severe restrictions having the highest MAE across all methods and models.

CONCLUSION

The developed mapping algorithm enables cost-utility analyses of interventions for people with disability where the WHODAS 2.0 has been collected. Mapping algorithms developed from different methods should be considered in sensitivity analyses in economic evaluations.

Mapping the Seattle Angina Questionnaire to EQ-5D-5L in patients with coronary heart disease

BACKGROUND

Health economic evaluation is critical in supporting novel cardiovascular disease therapies. However, most clinical studies do not include preference-based questionnaires to calculate utilities for health economic evaluations. Thus, this study aimed to develop mapping algorithms that convert the Seattle Angina Questionnaire (SAQ) to EQ-5D-5L health utility scores for patients with coronary health disease (CHD) in China.

METHODS

Data were obtained from a longitudinal study of patients with CHD conducted at the Tianjin Medical University General Hospital in China. Convenience sampling was used to recruit patients with CHD. The inclusion criteria were having been diagnosed with CHD through a medical examination and being aged 18 years or older. The exclusion criteria were a lack of comprehension ability, serious comorbidities, mental illness, and hearing or vision impairment. All eligible patients were invited to participate, and 305 and 75 patients participated at baseline and in the follow-up, respectively. Seven regression models were developed using a direct approach. Furthermore, we predicted the five EQ-5D items using ordered logit model and derived the utility score from predicted responses using an indirect approach. Model performances were evaluated using mean absolute error (MAE), root mean squared error (RMSE), correlation coefficient (ρ), and Lin's concordance correlation coefficient (CCC). A five-fold cross-validation method was used to evaluate internal validation.

RESULTS

The average age was 63.04 years, and 53.72% of the included patients were male. Most (70.05%) patients had unstable angina pectoris, and the mean illness duration was 2.50 years. The EQ-5D scores were highly correlated with five subscales of the SAQ, with Spearman's rank correlation coefficients ranging from 0.6184 to 0.7093. The mixture beta model outperformed the other regression models in the direct approach, with the lowest MAE and RMSE and highest ρ and CCC. The ordered logit model in the indirect approach performed the same as the mixture beta regression with equal MAE, lower RMSE, and higher ρ and CCC.

CONCLUSION

Mapping algorithms developed using mixture beta and ordered logit models accurately converted SAQ scores to EQ-5D-5L health utility values, which could support health economic evaluations related to coronary heart disease.

China Health Related Outcomes Measures (CHROME): development of a descriptive system to support cardiovascular disease specific preference-based measure for the Chinese population

PURPOSE

Preference-based measures have been increasingly recommended to measure health outcomes for economic evaluation. However, none of existing cardiovascular disease (CVD)-specific health-related quality of life (HRQoL) instruments are preference-based. This study aimed to develop the descriptive system of preference-based HRQoL instrument for Chinese patients with CVDs under the Initiative of China Health Related Outcomes Measures (CHROME).

METHODS

Qualitative face-to-face interviews were conducted with Chinese patients with CVDs. Content analysis was employed to generate candidate items for the instrument. Then expert consultation and cognitive debriefing interviews were conducted to guide further selection and revision of the items.

RESULTS

We interviewed 127 CVD patients with 67.7% being male and 63.8% living in the urban area. A hierarchical code book comprised of four themes, 20 categories, 62 sub-categories, and 207 codes, was developed. Candidate items were selected based on the criteria set by the Consensus-based Standards for the selection of health Measurement Instruments (COSMIN) methodology and ISPOR PRO guidance. An online survey and meeting with an expert advisory panel (n = 15) followed by cognitive debriefing interviews with 20 patients and 13 physicians were conducted to further select and revise the candidate items. The descriptive system of CHROME-CVD consists of 14 items, namely frequency and severity of chest pain, chest tightness, palpitation, shortness of breath, dizziness, fatigue, appetite, sleeping, mobility, daily activities, depression, worry, and social relationship. Four or five level responses were selected based on cognitive debriefing results to each item.

CONCLUSION

The current study developed the descriptive system (items and response options) of CHROME-CVD, the future CVD-specific preference-based HRQoL instrument for Chinese CVD patients.

Mapping of disease-specific Oxford Knee Score onto EQ-5D-5L utility index in knee osteoarthritis

BACKGROUND

EQ5D is a generic measure of health. It provides a single index value for health status that can be used in the clinical and economic evaluation of healthcare. Oxford Knee Score (OKS) is a joint-specific outcome measure tool designed to assess symptoms and function in osteoarthritis patients after joint replacement surgery. Though widely used, it has the disadvantage of lacking health index value. To fill the gap between functional and generic questionnaires with economic value, we linked generic EQ-5D-5L to the specific OKS to give a single index value for health status in KOA patients.

QUESTIONS/PURPOSES

Developing and evaluating an algorithm to estimate EuroQoL generic health utility scores (EQ-5D-5L) from the disease-specific OKS using data from patients with knee osteoarthritis (KO).

PATIENTS AND METHODS

This is a cross-sectional study of 571 patients with KO. We used four distinct mapping algorithms: Cumulative Probability for Ordinal Data, Penalized Ordinal Regression, CART (Classification and Regression Trees), and Ordinal random forest. We compared the resultant models' degrees of accuracy.

RESULTS

Mobility was best predicted by penalized regression with pre-processed predictors, usual activities by random forest, pain/discomfort by cumulative probability with pre-processed predictors, self-care by random forest with RFE (recursive feature elimination) predictors, and anxiety/depression by CART with RFE predictors. Model accuracy was lowest with anxiety/depression and highest with mobility and usual activities. Using available country value sets, the average MAE was 0.098 ± 0.022, ranging from 0.063 to 0.142; and the average MSE was 0.020 ± 0.008 ranging from 0.008 to 0.042.

CONCLUSIONS

The current study derived accurate mapping techniques from OKS to the domains of EQ-5D-5L, allowing for the computation of QALYs in economic evaluations. A machine learning-based strategy offers a viable mapping alternative that merits further exploration.

Gradient Boosted Tree Approaches for Mapping European Organization for Research and Treatment of Cancer Quality of Life Questionnaire Core 30 Onto 5-Level Version of EQ-5D Index for Patients With Cancer

OBJECTIVES

This study aimed to develop direct and response mapping algorithms from the European Organization for Research and Treatment of Cancer Quality of Life Questionnaire Core 30 onto the 5-level version of EQ-5D index based on the gradient boosted tree (GBT), a promising modern machine learning method.

METHODS

We used the Quality of Life Mapping Algorithm for Cancer study data (903 observations from 903 patients) for training GBTs and testing their predictive performance. In the Quality of Life Mapping Algorithm for Cancer study, patients with advanced solid tumor were enrolled, and the European Organization for Research and Treatment of Cancer Quality of Life Questionnaire Core 30 and 5-level version of EQ-5D were simultaneously evaluated. The Japanese value set was used for direct mapping, whereas the Japanese and US value sets were used for response mapping. We trained the GBTs in the training data set (80%) with cross-validation and tested the predictive performance measured by the root mean squared error (RMSE), mean absolute error (MAE), and mean error in the test data set (20%).

RESULTS

The RMSE and MAE in the test data set were larger in the GBT approaches than in the previously developed regression-based approaches. The mean error in the test data set tended to be smaller in the GBT approaches than in the previously developed regression-based approaches.

CONCLUSIONS

The predictive performances in the RMSE and MAE did not improve by the GBT approaches compared with regression approaches. The flexibility of the GBT approaches had the potential to reduce overprediction and underprediction in poor and good health, respectively. Further research is needed to establish the role of machine learning methods in mapping a nonpreference-based measure onto health utility.

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.

Mapping the Memorial Anxiety Scale for Prostate Cancer to the SF-6D

PURPOSE

To create a crosswalk that predicts Short Form 6D (SF-6D) utilities from Memorial Anxiety Scale for Prostate Cancer (MAX-PC) scores.

METHODS

The data come from prostate cancer patients enrolled in the North Carolina Prostate Cancer Comparative Effectiveness & Survivorship Study (NC ProCESS, N = 1016). Cross-sectional data from 12- to 24-month follow-up were used as estimation and validation datasets, respectively. Participants' SF-12 scores were used to generate SF-6D utilities in both datasets. Beta regression mixture models were used to evaluate SF-6D utilities as a function of MAX-PC scores, race, education, marital status, income, employment status, having health insurance, year of cancer diagnosis and clinically significant prostate cancer-related anxiety (PCRA) status in the estimation dataset. Models' predictive accuracies (using mean absolute error [MAE], root mean squared error [RMSE], Akaike information criterion [AIC] and Bayesian information criterion [BIC]) were examined in both datasets. The model with the highest prediction accuracy and the lowest prediction errors was selected as the crosswalk.

RESULTS

The crosswalk had modest prediction accuracy (MAE = 0.092, RMSE = 0.114, AIC = - 2708 and BIC = - 2595.6), which are comparable to prediction accuracies of other SF-6D crosswalks in the literature. About 24% and 52% of predictions fell within ± 5% and ± 10% of observed SF-6D, respectively. The observed mean disutility associated with acquiring clinically significant PCRA is 0.168 (standard deviation = 0.179).

CONCLUSION

This study provides a crosswalk that converts MAX-PC scores to SF-6D utilities for economic evaluation of clinically significant PCRA treatment options for prostate cancer survivors.