Machine learning for real-time prediction of complications in critical care: a retrospective study.

By A. Meyer, Dina Zverinski, B. Pfahringer, J. Kempfert, T. Kuehne, S. Sündermann, C. Stamm, Thomas Hofmann, Volkmar Falk, Carsten Eickhoff. The Lancet Respiratory Medicine, 2018

309 citations recorded by the source corpus.

BACKGROUND The large amount of clinical signals in intensive care units can easily overwhelm health-care personnel and can lead to treatment delays, suboptimal care, or clinical errors. The aim of this study was to apply deep machine learning methods to predict severe complications during critical care in real time after cardiothoracic surgery. METHODS We used deep learning methods (recurrent neural networks) to predict several severe complications (mortality, renal failure with a need for renal replacement therapy, and postoperative bleeding leading to operative revision) in post cardiosurgical care in real time. Adult patients who underwent major open heart surgery from Jan 1, 2000, to Dec 31, 2016, in a German tertiary care centre for cardiovascular diseases formed the main derivation dataset. We measured the accuracy and timeliness of the deep learning model's forecasts and compared predictive quality to that of established standard-of-care clinical reference tools (clinical rule for postoperative bleeding, Simplified Acute Physiology Score II for mortality, and the Kidney Disease: Improving Global Outcomes staging criteria for acute renal failure) using positive predictive value (PPV), negative predictive value, sensitivity, specificity, area under the curve (AUC), and the F1 measure (which computes a harmonic mean of sensitivity and PPV). Results were externally retrospectively validated with 5898 cases from the published MIMIC-III dataset. FINDINGS Of 47 559 intensive care admissions (corresponding to 42 007 patients), we included 11 492 (corresponding to 9269 patients). The deep learning models yielded accurate predictions with the following PPV and sensitivity scores: PPV 0·90 and sensitivity 0·85 for mortality, 0·87 and 0·94 for renal failure, and 0·84 and 0·74 for bleeding. The predictions significantly outperformed the standard clinical reference tools, improving the absolute complication prediction AUC by 0·29 (95% CI 0·23-0·35) for bleeding, by 0·24 (0·19-0·29) for mortality, and by 0·24 (0·13-0·35) for renal failure (p<0·0001 for all three analyses). The deep learning methods showed accurate predictions immediately after patient admission to the intensive care unit. We also observed an increase in performance in our validation cohort when the machine learning approach was tested against clinical reference tools, with absolute improvements in AUC of 0·09 (95% CI 0·03-0·15; p=0·0026) for bleeding, of 0·18 (0·07-0·29; p=0·0013) for mortality, and of 0·25 (0·18-0·32; p<0·0001) for renal failure. INTERPRETATION The observed improvements in prediction for all three investigated clinical outcomes have the potential to improve critical care. These findings are noteworthy in that they use routinely collected clinical data exclusively, without the need for any manual processing. The deep machine learning method showed AUC scores that significantly surpass those of clinical reference tools, especially soon after admission. Taken together, these properties are encouraging for prospective deployment in critical care settings to direct the staff's attention towards patients who are most at risk. FUNDING No specific funding.

Subfields: Artificial Intelligence, Epidemiology, Health Informatics

View Paper: https://www.semanticscholar.org/paper/24d6ec4497e9c59ef1fb2da969b19443eeec00f4

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Epidemiology

Citations in the corpus

Dynamic and explainable machine learning prediction of mortality in patients in the intensive care unit: a retrospective study of high-frequency data in electronic patient records. (2020, unknown): “37 As in our study, they base their model on routinely collected data.”
Early prediction of circulatory failure in the intensive care unit using machine learning (2020, methodology): “ML techniques have been applied to tasks in radiology 44 , pathology 45 and critical care 46,47 in retrospective clinical studies.”
Development, Implementation, and Evaluation of an In-Hospital Optimized Early Warning Score for Patient Deterioration (2020, methodology): “It is likely that more sophisticated machine learning methods, for example, deep learning, would yield a better model, as has been developed by others.(27) In parallel, we are actively assessing the added value of these methods and hope to implement them when newer versions of EPIC become available.”
Use of Machine Learning to Develop and Evaluate Models Using Preoperative and Intraoperative Data to Identify Risks of Postoperative Complications (2021, unknown): “8) Height, median (IQR), cm 170 (163-178) Weight, median (IQR), kg 83 (69-100) BMI, median (IQR) 28 (24-34) Functional capacity, METS”