Brain & spine · 2026
Mapping between EQ-5D-5L and EQ-5D-3L in lumbar spine surgery patients: Machine learning compared to crosswalk algorithms.
СтатьяНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Chang Natalie Hong Siu, Pedersen Casper Friis, Andersen Mikkel Østerheden, Carreon Leah Yacat
Аннотация
INTRODUCTION: The transition from EQ-5D-3L to EQ-5D-5L poses challenges for comparing health-related quality of life across studies and clinical settings. Although official EuroQol crosswalk algorithms are commonly used to map between versions, alternative mapping approaches may be relevant for disease-specific populations.
RESEARCH QUESTION: This study evaluated the performance of machine-learning models for bidirectional mapping between EQ-5D-3L and EQ-5D-5L in patients undergoing evaluation for elective lumbar spine surgery for degenerative conditions.
MATERIAL AND METHODS: Paired EQ-5D-3L and EQ-5D-5L single-center responses (n = 766) were analyzed using repeated cross-validation. Response-level mapping was performed using parametric ordinal regression models (VGAM, ordinalNet) and tree-based machine-learning models (XGBoost, CatBoost, ordinalForest). Both hard and soft prediction approaches were evaluated on held-out data and compared with the official crosswalk algorithms using RMSE, MAE, bias (mean signed error), R2, and CCC.
RESULTS: Soft predictions generally showed lower prediction errors and higher predictive R2 than official crosswalk algorithms, particularly for 3L-to-5L mapping, while improvements were smaller for 5L-to-3L mapping, and CCC favored the official crosswalk algorithms. Hard predictions showed similar improvements for 3L-to-5L mapping, except for CatBoost, but higher errors and lower predictive R2 for 5L-to-3L mapping. Differences between machine-learning models were generally small across all evaluation metrics.
DISCUSSION AND CONCLUSION: Machine-learning models provided alternative approaches to the official EuroQol crosswalk algorithms, with performance varying by mapping direction and prediction approach. Soft prediction generally showed more favorable predictive performance, particularly for 3L-to-5L mapping. Overall, these findings support further investigation of response-level mapping machine-learning approaches to harmonize mixed-format EQ-5D data.
RESEARCH QUESTION: This study evaluated the performance of machine-learning models for bidirectional mapping between EQ-5D-3L and EQ-5D-5L in patients undergoing evaluation for elective lumbar spine surgery for degenerative conditions.
MATERIAL AND METHODS: Paired EQ-5D-3L and EQ-5D-5L single-center responses (n = 766) were analyzed using repeated cross-validation. Response-level mapping was performed using parametric ordinal regression models (VGAM, ordinalNet) and tree-based machine-learning models (XGBoost, CatBoost, ordinalForest). Both hard and soft prediction approaches were evaluated on held-out data and compared with the official crosswalk algorithms using RMSE, MAE, bias (mean signed error), R2, and CCC.
RESULTS: Soft predictions generally showed lower prediction errors and higher predictive R2 than official crosswalk algorithms, particularly for 3L-to-5L mapping, while improvements were smaller for 5L-to-3L mapping, and CCC favored the official crosswalk algorithms. Hard predictions showed similar improvements for 3L-to-5L mapping, except for CatBoost, but higher errors and lower predictive R2 for 5L-to-3L mapping. Differences between machine-learning models were generally small across all evaluation metrics.
DISCUSSION AND CONCLUSION: Machine-learning models provided alternative approaches to the official EuroQol crosswalk algorithms, with performance varying by mapping direction and prediction approach. Soft prediction generally showed more favorable predictive performance, particularly for 3L-to-5L mapping. Overall, these findings support further investigation of response-level mapping machine-learning approaches to harmonize mixed-format EQ-5D data.