Abstract
Intensive-care units (ICUs) treat the most critically ill patients, which is complicated by the heterogeneity of the diseases that they encounter. Severity scores based mainly on acute physiology measures collected at ICU admission are used to predict mortality, but are non-specific, and predictions for individual patients can be inaccurate. We investigated whether inclusion of long-term disease history before ICU admission improves mortality predictions. Registry data for long-term disease histories for more than 230 000 Danish ICU patients were used in a neural network to develop an ICU mortality prediction model. Long-term disease histories and acute physiology measures were aggregated to predict mortality risk for patients for whom both registry and ICU electronic patient record data were available. We compared mortality predictions with admission scores on the Simplified Acute Physiology Score (SAPS) II, the Acute Physiologic Assessment and Chronic Health Evaluation (APACHE) II, and the best available multimorbidity score, the Multimorbidity Index. An external validation set from an additional hospital was acquired after model construction to confirm the validity of our model. During initial model development data were split into a training set (85%) and an independent test set (15%), and a five-fold cross-validation was done during training to avoid overfitting. Neural networks were trained for datasets with disease history of 1 month, 3 months, 6 months, 1 year, 2·5 years, 5 years, 7·5 years, 10 years, and 23 years before ICU admission. Mortality predictions with a model based solely on disease history outperformed the Multimorbidity Index (Matthews correlation coefficient 0·265 vs 0·065), and performed similarly to SAPS II and APACHE II (Matthews correlation coefficient with disease history, age, and sex 0·326 vs 0·347 and 0·300 for SAPS II and APACHE II, respectively). Diagnoses up to 10 years before ICU admission affected current mortality prediction. Aggregation of previous disease history and acute physiology measures in a neural network yielded the most precise predictions of in-hospital mortality (Matthews correlation coefficient 0·391 for in-hospital mortality compared with 0·347 with SAPS II and 0·300 with APACHE II). These results for the aggregated model were validated in an external independent dataset of 1528 patients (Matthews correlation coefficient for prediction of in-hospital mortality 0·341). Longitudinal disease-spectrum-wide data available before ICU admission are useful for mortality prediction. Disease history can be used to differentiate mortality risk between patients with similar vital signs with more precision than SAPS II and APACHE II scores. Machine learning models can be deconvoluted to generate novel understandings of how ICU patient features from long-term and short-term events interact with each other. Explainable machine learning models are key in clinical settings, and our results emphasise how to progress towards the transformation of advanced models into actionable, transparent, and trustworthy clinical tools. Novo Nordisk Foundation and Innovation Fund Denmark.
Highlights
Intensive-care units (ICUs) handle patients from all medical and surgical specialties
Mortality risk estimates based on acute physiology scores—such as the Simplified Acute Physiology Score (SAPS) and the Acute Physiologic Assessment and Chronic Health Evaluation (APACHE)—are sometimes used in clinical practice to assess disease severity.[2,3]
The final dataset included 8817 individual patients with 10 368 ICU admissions, which were subsequently split into training (n=8812) and test sets (n=1556; figure 2), and had both long-term disease history and ICU data from electronic patient records (EPRs). 10 223 (98⋅6%) of the 10 368 admissions did not have any missing data. 3462 (33·4%) of this cohort died in hospital, 2729 (26·3%) died within 30 days of ICU admission, and 3671 (35·4%) died within 90 days of ICU admission
Summary
Intensive-care units (ICUs) handle patients from all medical and surgical specialties. Their populations are highly heterogeneous, and consist of mainly elderly patients who often have a long history of disease. Prediction of prognosis to inform decision making in the ICU is difficult because of the severity of patients’ current illness and their disease history.[1]. Mortality risk estimates based on acute physiology scores—such as the Simplified Acute Physiology Score (SAPS) and the Acute Physiologic Assessment and Chronic Health Evaluation (APACHE)—are sometimes used in clinical practice to assess disease severity.[2,3] They are based on logistic regression of specific markers of patient physiology that are recorded during the first hours after ICU admission. In the past 10 years, advanced www.thelancet.com/digital-health Vol 1 June 2019
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have