Development of a practically usable prediction model for quality of life of ICU survivors: A sub-analysis of the MONITOR-IC prospective cohort study

Wubben, Nina; Boogaard, Mark van den; Ramjith, Jordache; Bisschops, Laurens L. A.; Frenzel, Tim; Hoeven, Johannes G. van der; Zegers, Marieke

doi:10.1016/j.jcrc.2021.04.019

Cited by 13 publications

(35 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All in all, pre-ICU QoL has high-predictive value in predicting longterm QoL. 10,18 Our findings here suggest that the incorporation of pre-ICU QoL information in prediction models for long-term QoL renders the inclusion of more comprehensive physiological data unnecessary.…”

Section: Discussionmentioning

confidence: 79%

“…The importance of pre-ICU QoL as a predictor, compared to the other predictors used in this study, might explain our finding of no improvement of predictive performance. 10,18 This study has some limitations. First, over two thirds of the study population were included after elective surgery.…”

Section: Discussionmentioning

confidence: 95%

“…The PREPARE model was first replicated with machine learning techniques: the baseline model. 10 Then, several machine learning techniques used for prediction were applied to the 24-hour PREPARE data as well as to the data pertaining to the entire ICU stay in order to find the best performing prediction model. The 10 machine learning models that were compared are Ordinary Least Squares (OLS), Random Forest (RF) Regressor, Multilayer Perceptron (MLP) Regressor, Lasso(CV), Least Angle Regression (LARS), Elastic net regularization (ElasticNet), Huber Regressor, Ridge Regression, Automatic Relevance Determination (ARD) Regression, and Support Vector Regression (SVR) (Additional File 3, Table S3).…”

Section: Prediction Modelingmentioning

confidence: 99%

“…The further improvement may increase the validity and reliability of the model that could then be used to improve the quality of communication between physicians, patients and family members concerning long-term ICU outcomes that takes place at the end of a patient's ICU stay. Therefore, we aimed to improve the performance of the existing PREPARE prediction model 10 for long-term QoL by incorporating additional physiological, pathological, drug and treatment data from the EHR, including bedside monitor data, pertaining to the entire ICU stay. To facilitate the incorporation of the new data originating from several sources, machine learning methodology was used.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Optimizing an existing prediction model for quality of life one‐year post‐intensive care unit: An exploratory analysis

Jonge¹,

Wubben²,

Kaam³

et al. 2022

Acta Anaesthesiol Scand

Self Cite

View full text Add to dashboard Cite

Background This study aimed to improve the PREPARE model, an existing linear regression prediction model for long‐term quality of life (QoL) of intensive care unit (ICU) survivors by incorporating additional ICU data from patients' electronic health record (EHR) and bedside monitors. Methods The 1308 adult ICU patients, aged ≥16, admitted between July 2016 and January 2019 were included. Several regression‐based machine learning models were fitted on a combination of patient‐reported data and expert‐selected EHR variables and bedside monitor data to predict change in QoL 1 year after ICU admission. Predictive performance was compared to a five‐feature linear regression prediction model using only 24‐hour data (R2 = 0.54, mean square error (MSE) = 0.031, mean absolute error (MAE) = 0.128). Results The 67.9% of the included ICU survivors was male and the median age was 65.0 [IQR: 57.0–71.0]. Median length of stay (LOS) was 1 day [IQR 1.0–2.0]. The incorporation of the additional data pertaining to the entire ICU stay did not improve the predictive performance of the original linear regression model. The best performing machine learning model used seven features (R2 = 0.52, MSE = 0.032, MAE = 0.125). Pre‐ICU QoL, the presence of a cerebro vascular accident (CVA) upon admission and the highest temperature measured during the ICU stay were the most important contributors to predictive performance. Pre‐ICU QoL's contribution to predictive performance far exceeded that of the other predictors. Conclusion Pre‐ICU QoL was by far the most important predictor for change in QoL 1 year after ICU admission. The incorporation of the numerous additional features pertaining to the entire ICU stay did not improve predictive performance although the patients' LOS was relatively short.

show abstract

Section: Discussionmentioning

confidence: 79%

Section: Discussionmentioning

confidence: 95%

Section: Prediction Modelingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Optimizing an existing prediction model for quality of life one‐year post‐intensive care unit: An exploratory analysis

Jonge¹,

Wubben²,

Kaam³

et al. 2022

Acta Anaesthesiol Scand

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, prediction modelling studies showed that pre-ICU health (mental and physical) status and comorbidities are the most important predictors for quality of life (QoL) after ICU admission. 9 Several Dutch ICUs provide some kind of post-ICU care. 5 Because of the lack of evidence, these current post-ICU clinics are pragmatically set up, without focusing on patients with a high risk for long-term sequelae, who will likely benefit the most of post-ICU care.…”

Section: Strengths and Limitations Of This Studymentioning

confidence: 99%

MiCare study, an evaluation of structured, multidisciplinary and personalised post-ICU care on physical and psychological functioning, and quality of life of former ICU patients: a study protocol of a stepped-wedge cluster randomised controlled trial

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

Development and validation of early prediction models for new-onset functional impairment at hospital discharge of ICU admission

et al. 2022

View full text Add to dashboard Cite

Development of a practically usable prediction model for quality of life of ICU survivors: A sub-analysis of the MONITOR-IC prospective cohort study

Cited by 13 publications

References 40 publications

Optimizing an existing prediction model for quality of life one‐year post‐intensive care unit: An exploratory analysis

Optimizing an existing prediction model for quality of life one‐year post‐intensive care unit: An exploratory analysis

MiCare study, an evaluation of structured, multidisciplinary and personalised post-ICU care on physical and psychological functioning, and quality of life of former ICU patients: a study protocol of a stepped-wedge cluster randomised controlled trial

Development and validation of early prediction models for new-onset functional impairment at hospital discharge of ICU admission

Contact Info

Product

Resources

About