Net Profit Margin Forecasting with Machine Learning Methods in Hospital Finance Management

Öz

Hospital information management systems (HIMS) were managed using paper-based systems with individual efforts in the pre-computer period. Today, in parallel with technological developments, it is carried out digitally in an electronic environment. HIMS software usually includes modules such as patient follow-up-registration-appointment, clinical, medical records, radiology, laboratory, drug management, billing, reporting, and hospital management. Accounting records are processed in the finance management submodule within the hospital management module. Artificial intelligence models used in many sectors for financial estimation in hospital finance management have been found worthy of research considering the benefits of the hospital's financial management. Financial data of private hospitals traded on the stock exchange between 2009-2023 were used in the study. A total of 97 financial reports from 5 different private hospitals and 776 raw data obtained from the reports constitute the study's data set. "Net Profit Margin" has been estimated over the data set. The most reliable and closest-to-reality algorithm was determined by making five different algorithm trials in the PHYTON programming language. The most successful result was obtained with the Random Forest algorithm. It has been seen that hospitals can make this estimation using Random Forest when they want to predict financial data for future periods.

Anahtar Kelimeler

• Financial Forecasting
• Financial Forecasting Methods
• Machine Learning
• Health İnformation Management System

Kaynakça

1. AbdelSalam, K., Hany, S., El Hady, D., Essam, M., Mahmoud, O., Mohammed, M., Samir, A., Magdy, A. (2022). Robo-nurse healthcare complete system using artificial intelligence. In International Conference on Advanced Machine Learning Technologies and Applications.
2. Abdullah, M. (2021). The implication of machine learning for financial solvency prediction: an empirical analysis on public listed companies of Bangladesh. Journal of Asian Business and Economic Studies, 28, 303–320.
3. Agirbas, İ., Turgut, M., Işıkçelik, F. (2018). Özel hastanelerde finansal analiz. III.Uluslararası Al-Farabi Sosyal Bilimler Kongresi, November.
4. Akkaya, G. C., Demireli, E., Yakut, Ü. H. (2009). İşletmelerde finansal başarisizlik tahminlemesi: yapay sinir ağlari modeli ile İMKB üzerine bir uygulama. Eskişehir Osmangazi Üniversitesi Sosyal Bilimler Dergisi, 10.
5. Sarıkale, H. İlter, B. (2018). Finansal analiz sürecindeki temel mali tablo düzeltmelerinin oran analizine etkisi. Afyon Kocatepe Üniversitesi Sosyal Bilimler Dergisi, 20, 165-184.
6. Astolfi, R., Lorenzoni, L., Oderkirk, J. (2012). A comparative analysis of health forecasting methods. OECD Health Working Papers, 59.
7. Car, Z., Baressi Šegota, S., Anđelić, N., Lorencin, I., Mrzljak, V. (2020). Modeling the spread of COVID-19 infection using a multilayer perceptron. Computational and Mathematical Methods in Medicine, 2020.
8. Davenport, T., Kalakota, R. (2020). The potential for artificial intelligence in healthcare. SSRN Electronic Journal, 6, 94–98.

9. Fletcher, T. S. (2012). Machine learning for financial market prediction. Doctoral dissertation, UCL (University College London), London.
10. Kaya, U., Yılmaz, A., Dikmen, Y. (2019). Sağlık alanında kullanılan derin öğrenme yöntemleri. European Journal of Science and Technology, 16, 792–808.
11. Koçyiğit, S., Bıyık, E., Ertaş, Ş. (2022). Özel bir sağlık işletmesinin finansal performansinin trend analizi ile değerlendirilmesi. Abant Sosyal Bilimler Dergisi, 22, 165–180.
12. Lakshmi, J. V. N., Scholar, R. (2016). Stochastic gradient descent using linear regression with Python. International Journal of Advanced Engineering Research and Applications. Access Address: www.ijaera.org
13. Lee, R., Miller, T. (2002). An approach to forecasting health expenditures, with application to the U.S. Medicare System. Health Services Research, 37, 1365–1386.
14. Özdemir, L., Bilgin, A. (2021). The use of artificial intelligence in health and ethical problems. Sağlık ve Hemşirelik Yönetimi Dergisi, 8, 439–445.
15. Pilnenskiy, N., Smetannikov, I. (2020). Feature selection algorithms as one of the Python data analytical tools. Future Internet, 12.
16. Polimis, K., Rokem, A., Hazelton, B. (2017). Confidence intervals for random forests in Python. The Journal of Open Source Software, 2, 124.
17. Samruddhi, K., Ashok Kumar, R. (2020). Used car price prediction using K-Nearest Neighbor Based Model. International Journal of Innovative Research in Applied Sciences and Engineering, 4.
18. Soyiri, I. N.,Reidpath, D. D. (2013). An overview of health forecasting. Environmental Health and Preventive Medicine, 18, 1–9.
19. Ural, K., Gürarda, Ş., Önemli, M. B. (2015). Muhasebe ve finansman dergisi Lojistik Regresyon Modeli ile finansal başarısızlık tahminlemesi: Borsa İstanbul’da faaliyet gösteren gida, içki ve tütün şirketlerinde uygulama. Muhasebe ve Finansman Dergisi.
20. Wasserbacher, H., Spindler, M. (2022). Machine learning for financial forecasting, planning and analysis: recent developments and pitfalls. Digital Finance, 4, 63–88.