Dataset Information

Using Machine Learning to Predict Early Onset Acute Organ Failure in Critically Ill Intensive Care Unit Patients With Sickle Cell Disease: Retrospective Study.

ABSTRACT: BACKGROUND:Sickle cell disease (SCD) is a genetic disorder of the red blood cells, resulting in multiple acute and chronic complications, including pain episodes, stroke, and kidney disease. Patients with SCD develop chronic organ dysfunction, which may progress to organ failure during disease exacerbations. Early detection of acute physiological deterioration leading to organ failure is not always attainable. Machine learning techniques that allow for prediction of organ failure may enable early identification and treatment and potentially reduce mortality. OBJECTIVE:The aim of this study was to test the hypothesis that machine learning physiomarkers can predict the development of organ dysfunction in a sample of adult patients with SCD admitted to intensive care units (ICUs). METHODS:We applied diverse machine learning methods, statistical methods, and data visualization techniques to develop classification models to distinguish SCD from controls. RESULTS:We studied 63 sequential SCD patients admitted to ICUs with 163 patient encounters (mean age 30.7 years, SD 9.8 years). A subset of these patient encounters, 22.7% (37/163), met the sequential organ failure assessment criteria. The other 126 SCD patient encounters served as controls. A set of signal processing features (such as fast Fourier transform, energy, and continuous wavelet transform) derived from heart rate, blood pressure, and respiratory rate was identified to distinguish patients with SCD who developed acute physiological deterioration leading to organ failure from patients with SCD who did not meet the criteria. A multilayer perceptron model accurately predicted organ failure up to 6 hours before onset, with an average sensitivity and specificity of 96% and 98%, respectively. CONCLUSIONS:This retrospective study demonstrated the viability of using machine learning to predict acute organ failure among hospitalized adults with SCD. The discovery of salient physiomarkers through machine learning techniques has the potential to further accelerate the development and implementation of innovative care delivery protocols and strategies for medically vulnerable patients.

SUBMITTER: Mohammed A

PROVIDER: S-EPMC7254279 | biostudies-literature | 2020 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Using Machine Learning to Predict Early Onset Acute Organ Failure in Critically Ill Intensive Care Unit Patients With Sickle Cell Disease: Retrospective Study.

Mohammed Akram A Podila Pradeep S B PSB Davis Robert L RL Ataga Kenneth I KI Hankins Jane S JS Kamaleswaran Rishikesan R

Journal of medical Internet research 20200513 5

<h4>Background</h4>Sickle cell disease (SCD) is a genetic disorder of the red blood cells, resulting in multiple acute and chronic complications, including pain episodes, stroke, and kidney disease. Patients with SCD develop chronic organ dysfunction, which may progress to organ failure during disease exacerbations. Early detection of acute physiological deterioration leading to organ failure is not always attainable. Machine learning techniques that allow for prediction of organ failure may ena ...[more]

PMID: 32401216

Similar Datasets

Project description:BackgroundPrevalence of multiple organ failure (MOF) in critically ill patients is increasing and associated mortality remains high. Extracorporeal organ support is a cornerstone in the management of MOF. We report data of an advanced hemodialysis system based on albumin dialysis (ADVOS multi device) that can regulate acid-base balance in addition to the established properties of renal replacement therapy and albumin dialysis systems in critically ill patients with MOF.Methods34 critically ill patients with MOF received 102 ADVOS treatment sessions in the Department of Intensive Care Medicine of the University Medical Center Hamburg-Eppendorf. Markers of metabolic detoxification and acid-base regulation were collected and blood gas analyses were performed. A subgroup analyses were performed in patients with severe acidemia (pH < 7.2).ResultsMedian number of treatment sessions was 2 (range 1-9) per patient. Median duration of treatment was 17.5 (IQR 11-23) hours per session. Treatment with the ADVOS multi-albumin dialysis device caused a significant decrease in bilirubin levels, serum creatinine, BUN and ammonia levels. The relative elimination rate of bilirubin was concentration dependent. Furthermore, a significant improvement in blood pH, HCO3- and PaCO2, was achieved during ADVOS treatment including six patients that suffered from severe metabolic acidosis refractory to continuous renal replacement therapy. Delta pH, HCO3- and PaCO2 were significantly affected by the ADVOS blood flow rate and pH settings. This improvement in the clinical course during ADVOS treatments allowed a reduction in norepinephrine during ADVOS therapy. Treatments were well tolerated. Mortality rates were 50% and 62% for 28 and 90 days, respectively.ConclusionsIn this case series in patients with MOF, ADVOS was able to eliminate water-soluble and albumin-bound substances. Furthermore, the device corrected severe metabolic and respiratory acid-base disequilibrium. No major adverse events associated with the ADVOS treatments were observed.

Dataset Information

Using Machine Learning to Predict Early Onset Acute Organ Failure in Critically Ill Intensive Care Unit Patients With Sickle Cell Disease: Retrospective Study.

Publications

Using Machine Learning to Predict Early Onset Acute Organ Failure in Critically Ill Intensive Care Unit Patients With Sickle Cell Disease: Retrospective Study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets