Published on Wed Nov 07 2018

Early Prediction of Acute Kidney Injury in Critical Care Setting Using Clinical Notes

Yikuan Li, Liang Yao, Chengsheng Mao, Anand Srivastava, Xiaoqian Jiang, Yuan Luo

Acute kidney injury (AKI) in critically ill patients is associated with significant morbidity and mortality. Development of novel methods to identify patients with AKI earlier will allow for testing of novel strategies to prevent or reduce the complications of AKI.

0
0
0
Abstract

Acute kidney injury (AKI) in critically ill patients is associated with significant morbidity and mortality. Development of novel methods to identify patients with AKI earlier will allow for testing of novel strategies to prevent or reduce the complications of AKI. We developed data-driven prediction models to estimate the risk of new AKI onset. We generated models from clinical notes within the first 24 hours following intensive care unit (ICU) admission extracted from Medical Information Mart for Intensive Care III (MIMIC-III). From the clinical notes, we generated clinically meaningful word and concept representations and embeddings, respectively. Five supervised learning classifiers and knowledge-guided deep learning architecture were used to construct prediction models. The best configuration yielded a competitive AUC of 0.779. Our work suggests that natural language processing of clinical notes can be applied to assist clinicians in identifying the risk of incident AKI onset in critically ill patients upon admission to the ICU.

Wed Sep 02 2020
Machine Learning
All Data Inclusive, Deep Learning Models to Predict Critical Events in the Medical Information Mart for Intensive Care III Database (MIMIC III)
Deep learning models (DLMs) can be leveraged to learn from large complex datasets. This retrospective study was performed using 42,818 hospital admissions involving 35,348 patients. DLMs were used to predict in-hospital mortality (IHM) and length of stay (LOS)
0
0
0
Wed Apr 10 2019
Machine Learning
Identifying Sub-Phenotypes of Acute Kidney Injury using Structured and Unstructured Electronic Health Record Data with Memory Networks
Acute Kidney Injury (AKI) is a common clinical syndrome characterized by the rapid loss of kidney excretory function. Identification of AKI sub-phenotypes can lead to an improved understanding of the disease pathophysiology and development of more targeted clinical interventions.
0
0
0
Tue May 19 2020
Machine Learning
ISeeU2: Visually Interpretable ICU mortality prediction using deep learning and free-text medical notes
Accurate mortality prediction allows Intensive Care Units (ICUs) to benchmark clinical practice and identify patients with unexpected outcomes. We show a Deep Learning model trained on MIMIC-III to predict mortality.
0
0
0
Fri Sep 13 2019
Machine Learning
Dynamic survival prediction in intensive care units from heterogeneous time series without the need for variable selection or pre-processing
Data for more than 45,000 American ICU patients from the MIMIC-III database were used to develop an ICU mortality prediction model. All chart, lab and output events were treated by the model in the same manner inspired by Natural Language Processing (NLP) Patient events were discretized by percentile and mapped to learnt embeddings before being passed to a Recurrent Neural Network.
0
0
0
Mon Jul 12 2021
Machine Learning
Predicting sepsis in multi-site, multi-national intensive care cohorts using deep learning
Sepsis remains a global public health crisis with high mortality, and morbidity. An early prediction of sepsis could lead to earlier pathogen identification, resistance testing, and effective antibiotic and supportive treatment. Our analysis represents the largest multi-national, multi-centre in-ICU study using ML.
1
0
2
Fri Jun 07 2019
Machine Learning
Early detection of sepsis utilizing deep learning on electronic health record event sequences
The timeliness of detection of a sepsis event in progress is a crucial factor in the outcome for the patient. Machine learning models built from data in electronic health records can be used as an effective tool for improving this timeliness. So far the potential for clinical implementations has been largely limited to studies in intensive care units.
0
0
0