Predictive Performance Engineering for Patient Accounting Systems: An AI-Augmented LoadRunner Framework for Proactive Bottleneck Forecasting in Healthcare Revenue Cycle Management

This paper presented a Predictive Performance Engineering framework that augments conventional LoadRunner-based testing of Patient Accounting Systems with a short-horizon machine-learning forecasting layer and a feedback controller. Representative experimental results across normal, peak, and surge load scenarios show that the predictive layer can surface impending resource bottlenecks several minutes before a conventional reactive cycle would detect the same breach, giving healthcare IT teams a practical window to intervene and reducing the number of full test iterations required to reach a stable capacity recommendation. Future work includes validating the framework against a larger set of production-representative PAS deployments, extending the forecasting layer to multivariate models that capture cross-resource interactions (e.g., database contention driving downstream CPU pressure), and evaluating the approach against fully automated, closed-loop auto-scaling infrastructure.

Practitioner's Approach, 9th ed. New York, NY, USA: McGraw-Hill Education, 2019. [2] I. Sommerville, Software Engineering, 10th ed. Boston, MA, USA: Pearson Education, 2015. [3] M. G. Nanda and D. P. R. Rao, "Performance testing of web applications: A survey," International Journal of Computer Applications, vol. 70, no. 18, pp. 1–5, 2013. [4] S. Elbaum, S. Karre, and G. Rothermel, "Improving web application testing with user session data," IEEE Transactions on Software Engineering, vol. 29, no. 8, pp. 756–770, Aug. 2003. [5] F. I. Vokolos and E. J. Weyuker, "Performance testing of software systems," in Proc. Workshop on Software and Performance, 1998, doi: 10.1145/287318.287337. [6] C. Patel and R. Gulati, "Identifying ideal values of parameters for software performance testing," 2015, doi: 10.1109/cccs.2015.7374125. [7] C. Patel and R. Gulati, "Software performance testing measures," Int. J. Multidisciplinary and Current Research, vol. 8, no. 2, pp. 1297–1300, 2014. [8] E. Foster, M. R. Hosking, and S. Ziya, "A spoonful of math helps the medicine go down: An illustration of how healthcare can benefit from mathematical modeling and analysis," BMC Medical Research Methodology, vol. 10, no. 1, 2010, doi: 10.1186/1471-2288-10-60. [9] P. Åhlin, P. Almström, and C. Wänström, "When patients get stuck: A systematic literature review on throughput barriers in hospital-wide patient processes," Health Policy, vol. 126, no. 2, pp. 87–98, 2022, doi: 10.1016/j.healthpol.2021.12.002. [10] A. Altalhi, A. Alghamdi, Z. Ullah, and F. Saleem, "Developing a framework and algorithm for scalability to evaluate the performance and throughput of CRM systems," J. Applied Statistics, vol. 23, no. 1, pp. 149–152, 2016, doi: 10.1080/10798587.2016.1184830.