Risk prediction models for intensive care unit-acquired weakness in intensive care unit patients: A systematic review.

Background And Objectives: Intensive care unit-acquired weakness (ICU-AW) commonly occurs among intensive care unit (ICU) patients and seriously affects the survival rate and long-term quality of life for patients. In this systematic review, we synthesized the findings of previous studies in order to analyze predictors of ICU-AW and evaluate the discrimination and validity of ICU-AW risk prediction models for ICU patients.

Methods: We searched seven databases published in English and Chinese language to identify studies regarding ICU-AW risk prediction models. Two reviewers independently screened the literature, evaluated the quality of the included literature, extracted data, and performed a systematic review.

Results: Ultimately, 11 studies were considered for this review. For the verification of prediction models, internal verification methods had been used in three studies, and a combination of internal and external verification had been used in one study. The value for the area under the ROC curve for eight models was 0.7-0.923. The predictor most commonly included in the models were age and the administration of corticosteroids. All the models have good applicability, but most of the models are biased due to the lack of blindness, lack of reporting, insufficient sample size, missing data, and lack of performance evaluation and calibration of the models.

Conclusions: The efficacy of most models for the risk prediction of ICU-AW among high-risk groups is good, but there was a certain bias in the development and verification of the models. Thus, ICU medical staff should select existing models based on actual clinical conditions and verify them before applying them in clinical practice. In order to provide a reliable basis for the risk prediction of ICU-AW, it is necessary that large-sample, multi-center studies be conducted in the future, in which ICU-AW risk prediction models are verified.