Development and Validation of a Prediction Model for 1-Year Mortality in Patients With a Hematologic Malignancy Admitted to the ICU

Abstract

Objectives: To develop and validate a prediction model for 1-year mortality in patients with a hematologic malignancy acutely admitted to the ICU.

Design: A retrospective cohort study.

Setting: Five university hospitals in the Netherlands between 2002 and 2015.

Patients: A total of 1097 consecutive patients with a hematologic malignancy were acutely admitted to the ICU for at least 24 h.

Interventions: None.

Measurements and main results: We created a 13-variable model from 22 potential predictors. Key predictors included active disease, age, previous hematopoietic stem cell transplantation, mechanical ventilation, lowest platelet count, acute kidney injury, maximum heart rate, and type of malignancy. A bootstrap procedure reduced overfitting and improved the model's generalizability. This involved estimating the optimism in the initial model and shrinking the regression coefficients accordingly in the final model. We assessed performance using internal-external cross-validation by center and compared it with the Acute Physiology and Chronic Health Evaluation II model. Additionally, we evaluated clinical usefulness through decision curve analysis. The overall 1-year mortality rate observed in the study was 62% (95% CI, 59-65). Our 13-variable prediction model demonstrated acceptable calibration and discrimination at internal-external validation across centers (C-statistic 0.70; 95% CI, 0.63-0.77), outperforming the Acute Physiology and Chronic Health Evaluation II model (C-statistic 0.61; 95% CI, 0.57-0.65). Decision curve analysis indicated overall net benefit within a clinically relevant threshold probability range of 60-100% predicted 1-year mortality.

Conclusions: Our newly developed 13-variable prediction model predicts 1-year mortality in hematologic malignancy patients admitted to the ICU more accurately than the Acute Physiology and Chronic Health Evaluation II model. This model may aid in shared decision-making regarding the continuation of ICU care and end-of-life considerations.

Keywords: clinical decision rules; hematologic neoplasms; intensive care units; mortality; prognosis.

Figure 1.

Calibration plot of 13-variable model to predict 1-year mortality in ICU patients diagnosed with a hematologic malignancy. Positioned at the bottom of the graph, small bars depict the comparative numbers of patients who either died within a year or survived. This plot contrasts the model’s predicted mortality probabilities against a perfectly calibrated reference line. Triangular markers on the plot represent distinct patient subgroups by predicted mortality risk.

Figure 2.

Decision curve analysis of four predictive models: the greater than or equal to two organ failure model, the APACHE II model, the 13-predictor model, and 8-predictor model for prediction of 1-year mortality in patients with hematologic malignancy admitted to the ICU. For clarity, we have displayed a threshold probability range between 50% and 100%. The 8-predictor model exhibits the highest net benefit within the clinically relevant threshold probability range of 60–100%, assisting in the potential decision 24-hour postadmission to discontinue ICU care. The solid line represents the net benefit if all ICU patients were to discontinue care, whereas the faint dashed horizontal line indicates the net benefit if ICU care is continued in all patients. The distinct dashed lines trace the performance of each of the prediction models. APACHE II = Acute Physiology and Chronic Health Evaluation II.

Figure 3.

Nomogram, based on a 13-predictor model, is designed to calculate the estimated risk of 1-year mortality for patients with hematologic malignancy who are acutely admitted to the ICU. Refer to the main text for a specific usage example. CVA = cerebrovascular accident, HSCT = hematopoietic stem cell transplantation.