Abstract
Healthcare systems find it difficult to decide on how long they should wait between submitting insurance claims and following up on the Accounts Receivables (AR) for the submitted claims. The solution to this can be the study of payer-specific historical data to understand payment trends of the submitted claims. This data may include censored data points where the responses were not received from the payers and hence is appropriate to be analyzed with Survival Analysis. To aid the follow-up process on submitted claims, we developed and validated a Time to Response (TTR) survival models using the machine learning method Random Survival Forests (RSF) for Medicare, Medicaid, and Commercial payers. TTR models aim to streamline the insurance claim follow-up process for smoother functioning of healthcare systems. These models capture the previous response time patterns based on the covariates and predict the probability of getting a response for each claim filed, from the day of claim file submission. We studied the effect of demographic, geographic, date-time related field, diagnoses, procedural and clean claim covariates on TTR. The model performance was assessed in terms of Concordance Index (C-index) and Integrated Brier score (IBS). Train and test C-index of Medicare was 0.68 and 0.67, Medicaid 0.74 and 0.74, Commercial 0.76 and 0.75 respectively. Test IBS was reported as 0.02, 0.01 and 0.06 for Medicare, Medicaid and Commercial payers respectively.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Kamenetzky, S.A.: Cash flow management. Arch. Ophthalmol. 111(6), 757–60 https://doi.org/10.1001/archopht.1993.01090060045021, PMID:8512475
Manley, R., Satiani, B.: Revenue cycle management. J. Vasc. Surg. 50(5), 1232 (2009). ISSN:0741–5214 PMID: 19782521 https://doi.org/10.1016/j.jvs.2009.07.065
McDaniel, J.W., Baum, N.: Putting the receive in accounts receivable. J. Med. Pract. Manag. 22(1), 31–33 (2006). PMID: 16986638
Beaulieu-volk, D.: Accounts receivable. Strategies for better management. From eligibility verification to patient engagement, managing accounts receivable is a vital process to maintaining financial health. Med. Econ. 92(11), 38 42–4 (2015). PMID:26298962
Center for Medicare and Medicaid Services(CMS) Medicare Billing Form CMS- 1450 and the 837 Institutional Medicare Learning Network Booklet. https://www.cms.gov/Outreach-andEducation/Medicare-Learning-Network-MLN/MLNProducts/Downloads/837I-FormCMS-1450-ICN006926.pdf
Center for Medicare and Medicaid Services (CMS) Medicare Billing Form CMS- and the 837 Professional Medicare Learning Network Booklet: https://www.cms.gov/Outreach-and-Education/Medicare-Learning-Network-MLN/MLNProducts/Downloads/837P-CMS-1500.pdf
Center for Medicare and Medicaid Services(CMS) CMS Manual System Medicare Claims Processing. https://www.cms.gov/Regulations-and-Guidance/Guidance/Transmittals/Downloads/R114CP.pdf
Romo, E.: Adapting to the ANSI 835 transaction set. Healthc. Financ. Manage 47(1), 54–56 (1993). PMID:10145738
Moynihan, J.J.: Improving the claims process with EDI. Healthc. Financ. Manage 47(1), 48–49 (1993). PMID: 10145737
Clement, J.M., Marc, O.J., Paul, D., Blaine, T., Jeffrey, G.S.: What is done, what is needed and what is realistic to expect from medical informatics standards. Int. J. Med. Inform. 48(1–3), 5-12. ISSN 1386-5056 (1998). https://doi.org/10.1016/S1386-5056(97)00102-0
Prinja, S., Gupta, N., Verma, R.: Censoring in clinical trials: review of survival analysis techniques. Indian J. Comm. Med. Official Publ. Indian Assoc. Prev. Soc. Med. 35(2), 217–221 (2010). https://doi.org/10.4103/0970-0218.66859
Wikipedia Survival Analysis. https://en.wikipedia.org/wiki/Survival_analysis
Rich, J.T., et al.: A practical guide to understanding Kaplan-Meier curves. Otolaryngol Head Neck Surg. 143(3), 331–336 (2010). https://doi.org/10.1016/j.otohns.2010.05.007
Enrique, B., Laura, B.: Effect of right censoring bias on survival analysis. arXiv2012.08649 (2020)
Lifelines Documentation. https://lifelines.readthedocs.io/en/latest/
Ishwaran, H., Kogalur, U.B., Blackstone, E.H., Lauer, M.S.: Random survival forests. Ann. Appl. Stat. 2, 841–860 (2008). https://doi.org/10.1214/08-AOAS169
Breiman, L.: Random forests. Mach. Learn. 45, 5–32 (2001)
Janika, S.: Modelling Late Invoice Payment Times Using Survival Analysis and Random Forests Techniques. Financial and Actuarial Mathematics Curriculum Master’s thesis, Institute of Mathematics and Statistics, University of Tartu
Eli5 Package Document. https://eli5.readthedocs.io/en/latest/blackbox/ permutation_importance.html
Lars, B., Gilles, L., et al.: API design for machine learning software: experiences from the scikit-learn project. In: ECML PKDD Workshop: Languages for Data Mining and Machine Learning, pp. 108–122 (2013)
Ørnulf, B.: Nelson-aalen estimator. Encycl. Biostatis. (2005). https://doi.org/10.1002/0470011815.b2a11054
Pölsterl, S.: scikit-survival: a library for time-to-event analysis built on top of scikit-learn. J. Mach. Learn. Res. 21(212), 1–6 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Chaudhuri, R., Parsa, S.P.K., Nagpal, D., R, K. (2022). Time to Response Prediction for Following up on Account Receivables in Healthcare Revenue Cycle Management. In: Singh, M., Tyagi, V., Gupta, P.K., Flusser, J., Ören, T. (eds) Advances in Computing and Data Sciences. ICACDS 2022. Communications in Computer and Information Science, vol 1614. Springer, Cham. https://doi.org/10.1007/978-3-031-12641-3_11
Download citation
DOI: https://doi.org/10.1007/978-3-031-12641-3_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-12640-6
Online ISBN: 978-3-031-12641-3
eBook Packages: Computer ScienceComputer Science (R0)