Predicting a Need for Financial Assistance in Emergency Department Care

Identifying patients with a low likelihood of paying their bill serves the needs of patients and providers alike: aligning government programs with their target beneficiaries while minimizing patient frustration and reducing waste among emergency physicians by streamlining the billing process. The g...

Full description

Bibliographic Details
Main Authors: Samuel Davis, Sara Nourazari, Rachel Granovsky, Nasser Fard
Format: Article
Language:English
Published: MDPI AG 2021-05-01
Series:Healthcare
Subjects:
Online Access:https://www.mdpi.com/2227-9032/9/5/556
id doaj-3f38aa25bbbf4ffb99b7ca42328c76f4
record_format Article
spelling doaj-3f38aa25bbbf4ffb99b7ca42328c76f42021-05-31T23:32:35ZengMDPI AGHealthcare2227-90322021-05-01955655610.3390/healthcare9050556Predicting a Need for Financial Assistance in Emergency Department CareSamuel Davis0Sara Nourazari1Rachel Granovsky2Nasser Fard3Department of Mechanical and Industrial Engineering, Northeastern University, Boston, MA 02115, USADepartment of Health Care Administration, California State University, Long Beach, CA 90840, USASchool of General Studies, Columbia University, New York, NY 10027, USADepartment of Mechanical and Industrial Engineering, Northeastern University, Boston, MA 02115, USAIdentifying patients with a low likelihood of paying their bill serves the needs of patients and providers alike: aligning government programs with their target beneficiaries while minimizing patient frustration and reducing waste among emergency physicians by streamlining the billing process. The goal of this study was to predict the likelihood of patients paying the balance of their emergency department visit bill within 90 days of receipt. Three machine learning methodologies were applied to predict payment: logistic regression, decision tree, and random forest. Models were trained and performance was measured using 1,055,941 patients with non-zero balances across 27 EDs from 1 August 2015 to 31 July 2017. The decision tree accurately predicted 87% of unsuccessful payments, providing significant opportunities to identify patients in need of financial assistance.https://www.mdpi.com/2227-9032/9/5/556healthcare financehealth equityemergency departmentpredictive modelingMedicaid
collection DOAJ
language English
format Article
sources DOAJ
author Samuel Davis
Sara Nourazari
Rachel Granovsky
Nasser Fard
spellingShingle Samuel Davis
Sara Nourazari
Rachel Granovsky
Nasser Fard
Predicting a Need for Financial Assistance in Emergency Department Care
Healthcare
healthcare finance
health equity
emergency department
predictive modeling
Medicaid
author_facet Samuel Davis
Sara Nourazari
Rachel Granovsky
Nasser Fard
author_sort Samuel Davis
title Predicting a Need for Financial Assistance in Emergency Department Care
title_short Predicting a Need for Financial Assistance in Emergency Department Care
title_full Predicting a Need for Financial Assistance in Emergency Department Care
title_fullStr Predicting a Need for Financial Assistance in Emergency Department Care
title_full_unstemmed Predicting a Need for Financial Assistance in Emergency Department Care
title_sort predicting a need for financial assistance in emergency department care
publisher MDPI AG
series Healthcare
issn 2227-9032
publishDate 2021-05-01
description Identifying patients with a low likelihood of paying their bill serves the needs of patients and providers alike: aligning government programs with their target beneficiaries while minimizing patient frustration and reducing waste among emergency physicians by streamlining the billing process. The goal of this study was to predict the likelihood of patients paying the balance of their emergency department visit bill within 90 days of receipt. Three machine learning methodologies were applied to predict payment: logistic regression, decision tree, and random forest. Models were trained and performance was measured using 1,055,941 patients with non-zero balances across 27 EDs from 1 August 2015 to 31 July 2017. The decision tree accurately predicted 87% of unsuccessful payments, providing significant opportunities to identify patients in need of financial assistance.
topic healthcare finance
health equity
emergency department
predictive modeling
Medicaid
url https://www.mdpi.com/2227-9032/9/5/556
work_keys_str_mv AT samueldavis predictinganeedforfinancialassistanceinemergencydepartmentcare
AT saranourazari predictinganeedforfinancialassistanceinemergencydepartmentcare
AT rachelgranovsky predictinganeedforfinancialassistanceinemergencydepartmentcare
AT nasserfard predictinganeedforfinancialassistanceinemergencydepartmentcare
_version_ 1721417269730344960