Development and internal validation of the multivariable CIPHER (Collaborative Integrated Pregnancy High-dependency Estimate of Risk) clinical risk prediction model.

BACKGROUND: Intensive care unit (ICU) outcome prediction models, such as Acute Physiology And Chronic Health Evaluation (APACHE), were designed in general critical care populations and their use in obstetric populations is contentious. The aim of the CIPHER (Collaborative Integrated Pregnancy High-dependency Estimate of Risk) study was to develop and internally validate a multivariable prognostic model calibrated specifically for pregnant or recently delivered women admitted for critical care. METHODS: A retrospective observational cohort was created for this study from 13 tertiary facilities across five high-income and six low- or middle-income countries. Women admitted to an ICU for more than 24 h during pregnancy or less than 6 weeks post-partum from 2000 to 2012 were included in the cohort. A composite primary outcome was defined as maternal death or need for organ support for more than 7 days or acute life-saving intervention. Model development involved selection of candidate predictor variables based on prior evidence of effect, availability across study sites, and use of LASSO (Least Absolute Shrinkage and Selection Operator) model building after multiple imputation using chained equations to address missing data for variable selection. The final model was estimated using multivariable logistic regression. Internal validation was completed using bootstrapping to correct for optimism in model performance measures of discrimination and calibration. RESULTS: Overall, 127 out of 769 (16.5%) women experienced an adverse outcome. Predictors included in the final CIPHER model were maternal age, surgery in the preceding 24 h, systolic blood pressure, Glasgow Coma Scale score, serum sodium, serum potassium, activated partial thromboplastin time, arterial blood gas (ABG) pH, serum creatinine, and serum bilirubin. After internal validation, the model maintained excellent discrimination (area under the curve of the receiver operating characteristic (AUROC) 0.82, 95% confidence interval (CI) 0.81 to 0.84) and good calibration (slope of 0.92, 95% CI 0.91 to 0.92 and intercept of -0.11, 95% CI -0.13 to -0.08). CONCLUSIONS: The CIPHER model has the potential to be a pragmatic risk prediction tool. CIPHER can identify critically ill pregnant women at highest risk for adverse outcomes, inform counseling of patients about risk, and facilitate bench-marking of outcomes between centers by adjusting for baseline risk.

Individual and joint expert judgments as reference standards in artifact detection.

OBJECTIVE: To investigate the agreement among clinical experts in their judgments of monitoring data with respect to artifacts, and to examine the effect of reference standards that consist of individual and joint expert judgments on the performance of artifact filters. DESIGN: Individual judgments of four physicians, a majority vote judgment, and a consensus judgment were obtained for 30 time series of three monitoring variables: mean arterial blood pressure (ABPm), central venous pressure (CVP), and heart rate (HR). The individual and joint judgments were used to tune three existing automated filtering methods and to evaluate the performance of the resulting filters. MEASUREMENTS: The interrater agreement was calculated in terms of positive specific agreement (PSA). The performance of the artifact filters was quantified in terms of sensitivity and positive predictive value (PPV). RESULTS: PSA values between 0.33 and 0.85 were observed among clinical experts in their selection of artifacts, with relatively high values for CVP data. Artifact filters developed using judgments of individual experts were found to moderately generalize to new time series and other experts; sensitivity values ranged from 0.40 to 0.60 for ABPm and HR filters (PPV: 0.57-0.84), and from 0.63 to 0.80 for CVP filters (PPV: 0.71-0.86). A higher performance value for the filters was found for the three variable types when joint judgments were used for tuning the filtering methods. CONCLUSION: Given the disagreement among experts in their individual judgment of monitoring data with respect to artifacts, the use of joint reference standards obtained from multiple experts is recommended for development of automatic artifact filters.