Application of Data Mining Techniques to Predict the Length of Stay of Hospitalized Patients with Diabetes

Diabetes is one of the most critical public health conditions worldwide. It has been shown that patients with diabetes are associated with a longer length of hospital stay (LOS) and increased associated healthcare cost. The uncertainty of diabetic patients' LOS makes it difficult for hospitals to optimize their scheduling process. In this paper, we applied the stacked ensemble method, with deep learning as the meta-learning algorithm, to predict long vs. short LOS for diabetic patients. The obtained results show that stacked ensemble technique is promising in this field because stacking multiple classification learning algorithms resulted in a better predictive performance than that obtained from any of the constituent learning algorithms. Having a reasonable estimate on LOS for patients with diabetes can help in optimizing the use of hospital resources, reducing healthcare cost, and improving diabetic patient satisfaction.

[1]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[2]  Boncho Ku,et al.  Prediction of Fasting Plasma Glucose Status Using Anthropometric Measures for Diagnosing Type 2 Diabetes , 2014, IEEE Journal of Biomedical and Health Informatics.

[3]  T. M. Ahmed.  USING DATA MINING TO DEVELOP MODEL FOR CLASSIFYING DIABETIC PATIENT CONTROL LEVEL BASED ON HISTORICAL MEDICAL RECORDS , 2016 .

[4]  E. Carter,et al.  Diabetes is predictive of longer hospital stay and increased rate of complications in spinal surgery in the UK. , 2013, Annals of the Royal College of Surgeons of England.

[5]  Sunil Kumar Khatri,et al.  Predictive risk modelling for early hospital readmission of patients with diabetes in India , 2016, International Journal of Diabetes in Developing Countries.

[6]  M. Harris,et al.  Impact of diabetes on hospital admission and length of stay among a general population aged 45 year or more: a record linkage study , 2015, BMC Health Services Research.

[7]  I. Vlahavas,et al.  Machine Learning and Data Mining Methods in Diabetes Research , 2017, Computational and structural biotechnology journal.

[8]  Nicholas Graves,et al.  Modeling length of stay in hospital and other right skewed data: comparison of phase-type, gamma and log-normal distributions. , 2009, Value in health : the journal of the International Society for Pharmacoeconomics and Outcomes Research.

[9]  Mahmoud Elbattah,et al.  Using Machine Learning to Predict Length of Stay and Discharge Destination for Hip-Fracture Patients , 2016, IntelliSys.

[10]  Vandana Pursnani Janeja,et al.  Predicting Hospital Length of Stay (PHLOS): A Multi-tiered Data Mining Approach , 2012, 2012 IEEE 12th International Conference on Data Mining Workshops.

[11]  Ioannis A. Kakadiaris,et al.  A Comparison of Supervised Machine Learning Techniques for Predicting Short-Term In-Hospital Length of Stay among Diabetic Patients , 2014, 2014 13th International Conference on Machine Learning and Applications.

[12]  N. Sambasiva Rao,et al.  Survey on clinical prediction models for diabetes prediction , 2017, Journal of Big Data.

[13]  Peyman Rezaei Hachesu,et al.  Use of Data Mining Techniques to Determine and Predict Length of Stay of Cardiac Patients , 2013, Healthcare informatics research.

[14]  Gary King,et al.  Amelia II: A Program for Missing Data , 2011 .

[15]  Michael L. Johnson,et al.  Predicting in-hospital mortality and hospital length of stay in diabetic patients , 2013 .

[16]  M. Malone,et al.  The effect of diabetes mellitus on costs and length of stay in patients with peripheral arterial disease undergoing vascular surgery. , 2014, European journal of vascular and endovascular surgery : the official journal of the European Society for Vascular Surgery.

[17]  Riccardo Bellazzi,et al.  Temporal data mining and process mining techniques to identify cardiovascular risk-associated clinical pathways in Type 2 diabetes patients , 2014, IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI).

[18]  Somayeh Alizadeh,et al.  Extract critical factors affecting the length of hospital stay of pneumonia patient by data mining (case study: an Iranian hospital) , 2017, Artif. Intell. Medicine.

[19]  Emc Education Services.  Data Science and Big Data Analytics: Discovering, Analyzing, Visualizing and Presenting Data , 2015 .

[20]  Ai Hua Zhang,et al.  Clinical pathways: effects on professional practice, patient outcomes, length of stay and hospital costs , 2011 .

[21]  Beata Strack,et al.  Impact of HbA1c Measurement on Hospital Readmission Rates: Analysis of 70,000 Clinical Database Patient Records , 2014, BioMed research international.

[22]  James Jaccard,et al.  Statistics for the Behavioral Sciences , 1983 .

[23]  Wei Zhang,et al.  wmin . ac . uk / westminsterresearch Healthcare data mining : predicting inpatient length of stay , 2007 .

[24]  Erin LeDell,et al.  Scalable Ensemble Learning and Computationally Efficient Variance Estimation , 2015 .