Mortality Prediction of ICU patients using Machine Leaning: A survey

Recently health care researchers are working a lot on outcome prediction on Intensive Care Unit (ICU) and trauma. Outcome prediction in intensive care is a difficult process. Accurate synthesis of quality data and application of prior experience to the analysis is required to solve it. In this paper we will review some of the recent advancements in the mortality prediction of ICU patients using machine learning techniques. Mainly the research covered in this survey will be on predicting readmission in Intensive care unit, mortality rate after ICU discharge and life expectancy rate for 5 years. In order to analyse how much a patient will survive in next five years, this expectancy rate is used. These predictions are very useful because using these results doctors can take decision about extending the stay of patient in hospital and also helps in taking decision about the particular treatment needed. An extensive survey of the related research is presented with a stress on the major novelties of their work. At last, the research gaps inferred after analyzing the previous works are highlighted along with the future prospects in the field of research.

[1]  B. A. Mobley,et al.  Artificial neural network predictions of lengths of stay on a post-coronary care unit. , 1995, Heart & lung : the journal of critical care.

[2]  R. Dybowski,et al.  Prediction of outcome in critically ill patients using artificial neural network synthesised by genetic algorithm , 1996, The Lancet.

[3]  John W. Williams,et al.  Common comorbidity scales were similar in their ability to predict health care costs and mortality. , 2004, Journal of clinical epidemiology.

[4]  B. Cuthbertson,et al.  Predicting death and readmission after intensive care discharge. , 2008, British journal of anaesthesia.

[5]  Yoav Freund,et al.  The Alternating Decision Tree Learning Algorithm , 1999, ICML.

[6]  T. Buchman,et al.  A comparison of statistical and connectionist models for the prediction of chronicity in a surgical intensive care unit , 1994, Critical care medicine.

[7]  Juan José Rodríguez Diez,et al.  Rotation Forest: A New Classifier Ensemble Method , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  J. Civetta,et al.  Therapeutic intervention scoring system: a method for quantitative comparison of patient care. , 1974, Critical care medicine.

[9]  Jimeng Sun,et al.  Using recurrent neural network models for early detection of heart failure onset , 2016, J. Am. Medical Informatics Assoc..

[10]  João Miguel da Costa Sousa,et al.  Data mining using clinical physiology at discharge to predict ICU readmissions , 2012, Expert Syst. Appl..

[11]  W. Knaus,et al.  APACHE II: a severity of disease classification system. , 1985 .

[12]  R G Mark,et al.  MIMIC II: a massive temporal ICU patient database to support research in intelligent patient monitoring , 2002, Computers in Cardiology.

[13]  R. Lippmann,et al.  Coronary artery bypass risk prediction using neural networks. , 1997, Annals of Thoracic Surgery.

[14]  J. Savino,et al.  An artificial neural network as a model for prediction of survival in trauma patients: validation for a regional trauma area. , 1998, The Journal of trauma.

[15]  João Miguel da Costa Sousa,et al.  Decision tree search methods in fuzzy modeling and classification , 2007, Int. J. Approx. Reason..

[16]  G S Doig,et al.  Modeling mortality in the intensive care unit: comparing the performance of a back-propagation, associative-learning neural network with multivariate logistic regression. , 1993, Proceedings. Symposium on Computer Applications in Medical Care.

[17]  Charles Elkan,et al.  Learning to Diagnose with LSTM Recurrent Neural Networks , 2015, ICLR.

[18]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[19]  Jürgen Paetz.  Some remarks on choosing a method for outcome prediction. , 2002, Critical care medicine.

[20]  R. Orr,et al.  Use of a Probabilistic Neural Network to Estimate the Risk of Mortality after Cardiac Surgery , 1997, Medical decision making : an international journal of the Society for Medical Decision Making.

[21]  A. Choudhary,et al.  Development of a 5 year life expectancy index in older adults using predictive mining of electronic health record data. , 2013, Journal of the American Medical Informatics Association : JAMIA.

[22]  G. Clermont,et al.  Predicting hospital mortality for patients in the intensive care unit: A comparison of artificial neural networks with logistic regression models , 2001, Critical care medicine.

[23]  M. Frize,et al.  Clinical decision support systems for intensive care units: using artificial neural networks. , 2001, Medical engineering & physics.

[24]  H. Akaike.  A new look at the statistical model identification , 1974 .

[25]  J. L. Gall,et al.  APACHE II--a severity of disease classification system. , 1986, Critical care medicine.

[26]  S. Lemeshow,et al.  A new Simplified Acute Physiology Score (SAPS II) based on a European/North American multicenter study. , 1993, JAMA.

[27]  Michio Sugeno,et al.  Fuzzy identification of systems and its applications to modeling and control , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[28]  Benjamin M. Marlin,et al.  Unsupervised pattern discovery in electronic health care data using probabilistic clustering models , 2012, IHI '12.

[29]  L. Walter,et al.  Cancer screening in elderly patients: a framework for individualized decision making. , 2001, JAMA.

[30]  Andrew P. Bradley,et al.  The use of the area under the ROC curve in the evaluation of machine learning algorithms , 1997, Pattern Recognit..

[31]  D. Hosmer,et al.  Goodness of fit tests for the multiple logistic regression model , 1980 .

[32]  W. Knaus,et al.  The APACHE III prognostic system. Risk prediction of hospital mortality for critically ill hospitalized adults. , 1991, Chest.

[33]  Jean-François Timsit,et al.  A model to predict short-term death or readmission after intensive care unit discharge. , 2012, Journal of critical care.

[34]  J. Wyatt,et al.  Commentary: Prognostic models: clinically useful or quickly forgotten? , 1995 .