Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Predicting the inpatient hospital cost using a machine learning approach

Predicting the inpatient hospital cost using a machine learning approach Increasing health-care costs are a major concern, especially in the USA. The purpose of this paper is to predict the hospital charges of a patient before being admitted. This will help a patient who is getting admitted: “electively” can plan his/her finance. Also, this can be used as a tool by payers (insurance companies) to better forecast the amount that a patient might claim.Design/methodology/approachThis research method involves secondary data collected from New York state’s patient discharges of 2017. A stratified sampling technique is used to sample the data from the population, feature engineering is done on categorical variables. Different regression techniques are being used to predict the target value “total charges.”FindingsTotal cost varies linearly with the length of stay. Among all the machine learning algorithms considered, namely, random forest, stochastic gradient descent (SGD) regressor, K nearest neighbors regressor, extreme gradient boosting regressor and gradient boosting regressor, random forest regressor had the best accuracy with R2 value 0.7753. “Age group” was the most important predictor among all the features.Practical implicationsThis model can be helpful for patients who want to compare the cost at different hospitals and can plan their finances accordingly in case of “elective” admission. Insurance companies can predict how much a patient with a particular medical condition might claim by getting admitted to the hospital.Originality/valueHealth care can be a costly affair if not planned properly. This research gives patients and insurance companies a better prediction of the total cost that they might incur. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png International Journal of Innovation Science Emerald Publishing

Predicting the inpatient hospital cost using a machine learning approach

Download PDF
18 pages

Loading next page...
 
/lp/emerald-publishing/predicting-the-inpatient-hospital-cost-using-a-machine-learning-SegQyedLdo
Publisher
Emerald Publishing
Copyright
© Emerald Publishing Limited
ISSN
1757-2223
DOI
10.1108/ijis-09-2020-0175
Publisher site
See Article on Publisher Site

Abstract

Increasing health-care costs are a major concern, especially in the USA. The purpose of this paper is to predict the hospital charges of a patient before being admitted. This will help a patient who is getting admitted: “electively” can plan his/her finance. Also, this can be used as a tool by payers (insurance companies) to better forecast the amount that a patient might claim.Design/methodology/approachThis research method involves secondary data collected from New York state’s patient discharges of 2017. A stratified sampling technique is used to sample the data from the population, feature engineering is done on categorical variables. Different regression techniques are being used to predict the target value “total charges.”FindingsTotal cost varies linearly with the length of stay. Among all the machine learning algorithms considered, namely, random forest, stochastic gradient descent (SGD) regressor, K nearest neighbors regressor, extreme gradient boosting regressor and gradient boosting regressor, random forest regressor had the best accuracy with R2 value 0.7753. “Age group” was the most important predictor among all the features.Practical implicationsThis model can be helpful for patients who want to compare the cost at different hospitals and can plan their finances accordingly in case of “elective” admission. Insurance companies can predict how much a patient with a particular medical condition might claim by getting admitted to the hospital.Originality/valueHealth care can be a costly affair if not planned properly. This research gives patients and insurance companies a better prediction of the total cost that they might incur.

Journal

International Journal of Innovation Science – Emerald Publishing

Published: Jan 22, 2021

Keywords: Health care; Prediction; Machine learning; Hospital cost

References

  • Clinical classifications software (ccs) 2015
  • Methodology overview: all patient refined diagnosis related groups (APR-DRGs) version 20.0
    Averill, F.R.; Goldfield, N.; Hughes, J.S.; Bonazelli, J.; McCullough, E.C.; Steinbeck, B.A.; Mullin, R.; Tang, A.M.
  • Algorithmic prediction of health-care costs
    Bertsimas, D.; Bjarnadóttir, M.V.; Kane, M.A.; Kryder, J.C.; Pandey, R.; Vempala, S.; Wang, G.
  • Random forests
    Breiman, L.
  • National health expenditure projections 2019-2028
  • National health expenditures
  • Previous cost model: testing alternative regression frameworks for predictive modeling of health care costs
    Duncan, I.; Loginov, M.; Ludkovski, M.
  • A comparison of comorbidity measurements to predict healthcare expenditures
    Farley, J.F.; Harley, C.R.; Devine, J.W.
  • Why your ZIP code matters more than your genetic code: promoting healthy outcomes from mother to child
    Graham, G.N.
  • Models for Health Care. Technical report Department of Economics
    Jones, A.
  • AI in healthcare: time-series forecasting using statistical, neural, and ensemble architectures
    Kaushik, S.; Choudhury, A.; Sheron, P.K.; Dasgupta, N.; Natarajan, S.; Pickett, L.A.; Dutt, V.
  • Effects of multiple chronic conditions on health care costs: an analysis based on an advanced tree-based regression model
    Konig, H.; Leicht, H.; Bickel, H.
  • CDPS – medicare: the chronic illness and disability payment system modified to predict expenditures for medicare beneficiaries
    Kronick, R.; Gilmer, T.P.; Dreyfus, T.; Ganiats, T.G.
  • Predicting healthcare expenditure increase for an individual from medicare data
    Lahiri, B.; Agarwal, N.
  • Comparison of hospital charge prediction models for colorectal cancer patients: neural network vs. decision tree models
    Lee, S.M.; Kang, J.O.; Suh, Y.M.
  • Generalized modeling approaches to risk adjustment of skewed outcomes data
    Manning, W.G.; Basu, A.; Mullahy, J.
  • Supervised learning methods for predicting healthcare costs: systematic literature review and empirical evaluation
    Morid, M.A.; Kawamoto, K.; Ault, T.; Dorius, J.; Abdelrahman, S.
  • Gradient boosting machines
    Natekin, A.; Knoll, A.
  • Hospital inpatient discharges (SPARCS De-Identified
  • DATA DICTIONARY: Hospital inpatient discharges (SPARCS De-Identified file): CY 2017
  • Bulletin UASVM agriculture: comparing linear regression and regression trees for spatial modeling of soil reaction in dobrovăt basin (Eastern Romania)
    Patriche, C.V.; Pirnau, R.G.; Rosca, B.
  • Scikit-learn: machine learning in python
    Pedregosa, F.; Varoquaux, G.; Gramfort, A.; Michel, V.; Thirion, B.; Grisel, O.; Vanderplas, J.
  • Prevalence, expenditures, utilization, and payment for persons with MS in insured populations
    Pope, G.C.; Urato, C.J.; Kulas, E.D.; Kronick, R.; Gilmer, T.
  • A stochastic approximation method
    Robbins, H.E.
  • Sklearn.model_selection.train_test_split
  • Source of payment typology. Version 9.0
  • What is the difference between medicare and medicaid?
  • Health insurance coverage in the United States 2018