 |
 |
 |
 |
 |
 |
Sains Malaysiana 55(9)(2026): 1579-1591
http://doi.org/10.17576/jsm-2026-5509-14
Cost Estimation for a Single
Episode of Lung Cancer Treatment in a Malaysian Tertiary Hospital: A Generalised Linear Model Approach
(Anggaran Kos bagi Satu Episod Rawatan Kanser Paru-paru di Hospital Tertier Malaysia: Pendekatan Model Linear Teritlak)
NORIZA MAJID1,*, AZIMATUN NOOR
AIZUDDIN2 & YI HUI CHENG1
1Department of Mathematical Sciences,
Faculty of Science and Technology, Universiti Kebangsaan Malaysia, 43600 UKM Bangi, Selangor, Malaysia
2Department of Community Health, Faculty of
Medicine, Hospital Canselor Tuanku Muhriz,
Universiti Kebangsaan Malaysia, 56000 Kuala Lumpur, Malaysia
Received: 13 April 2026/Accepted: 8 September 2026
*Corresponding author;
email: nm@ukm.edu.my
Abstract
Lung cancer is a leading cause of cancer-related
mortality in Malaysia and imposes a substantial financial burden on patients
and the healthcare system. This study identifies key determinants of lung
cancer treatment costs and develops cost estimates for a single episode of care
using Generalised Linear Models (GLM). A total of 1,132 lung cancer patient
records from the International Casemix and Clinical
Coding Centre (ITCC), Hospital Canselor Tuanku Muhriz (HCTM), spanning
2019 to 2023, were analysed. Patient demographics (age, gender, smoking status)
and clinical variables (cancer severity, length of hospitalisation, treatment
type, metastatic status, comorbidities, and discharge status) were examined.
The GLM with Gamma distribution and logarithmic link function showed the best
goodness-of-fit when compared to the Gamma-Log, Gaussian-Log, and Lognormal
models. This was based on the Akaike Information Criterion (AIC), Bayesian
Information Criterion (BIC), deviance, and predictive accuracy metrics. The final
model identified 17 significant predictors, including length of
hospitalisation, cancer severity, brain metastasis, surgical and biopsy
procedures, age group, and discharge status, together with seven significant
interaction variables. These interaction effects indicate that the
co-occurrence of specific clinical factors amplifies treatment costs beyond
their individual contributions. The Gamma-Log model provided accurate cost
estimates for mild-to-moderate cases but exhibited underestimation for patients
with extensive comorbidities who did not receive primary cancer treatment,
suggesting that future models should incorporate palliative and supportive care
variables. These results offer practical data for the allocation of healthcare
resources and cost assessment in Malaysia.
Keywords: Gamma distribution; generalised linear
model; lung cancer; treatment costs
Abstrak
Kanser paru-paru merupakan punca utama kematian akibat kanser di Malaysia dan memberi tekanan ekonomi yang ketara kepada pesakit serta sistem kesihatan negara. Kajian ini mengenal pasti faktor penentu utama kos rawatan kanser paru-paru dan membangunkan anggaran kos bagi satu episod rawatan menggunakan Model Linear Teritlak (GLM). Sebanyak 1,132 rekod pesakit kanser paru-paru dari Pusat Antarabangsa Casemix dan Pengekodan Klinikal (ITCC),
Hospital Canselor Tuanku Muhriz (HCTM) bagi tahun 2019 hingga 2023 telah dianalisis. Pemboleh ubah demografi pesakit (umur, jantina, tabiat merokok) dan klinikal (tahap ketenatan kanser, tempoh penghospitalan, jenis rawatan, status metastasis, komorbid dan status discaj) dikaji.
GLM dengan taburan Gamma
dan fungsi pautan logaritma menunjukkan kesesuaian terbaik berbanding model Gamma-Log, Gaussian-Log dan Lognormal. Ini berdasarkan Kriteria Maklumat Akaike (AIC), Kriteria Maklumat Bayesian (BIC), devians dan metrik ketepatan ramalan. Model akhir mengenal pasti 17 peramal signifikan termasuk tempoh penghospitalan, tahap ketenatan kanser, metastasis otak, pembedahan dan biopsi, kumpulan umur serta status discaj, bersama-sama tujuh pemboleh ubah interaksi yang signifikan. Model Gamma-Log menghasilkan anggaran kos yang tepat bagi kes ringan hingga sederhana, tetapi cenderung merendah anggaran bagi pesakit dengan komorbid meluas yang tidak menerima rawatan kanser utama. Keputusan ini menawarkan data praktikal untuk peruntukan sumber penjagaan kesihatan dan penilaian kos di
Malaysia.
Kata kunci: Kanser paru-paru;
kos rawatan; model linear teritlak; taburan Gamma
REFERENCES
Ab Manan, A., Basri, H., Kaur, N., Abd Rahman, S.Z.,
Amir, P.N., Ali, N., Raman, S. & Bahtiar, B.
2019. Malaysia National Cancer Registry Report (MNCR) 2012-2016.
Agresti, A. 2015. Foundation of Linear and Generalized
Linear Models. 1st ed. New Jersey: John Wiley & Sons.
American Cancer Society. 2024. What is Lung Cancer? https://www.cancer.org/cancer/types/lung-cancer/about/what-is.html Accessed on
7 July 2025.
Bade, B.C. & Dela Cruz, C.S. 2020. Lung cancer
2020: Epidemiology, etiology, and prevention. Clin.
Chest. Med. 41(1): 1-24. DOI: 10.1016/j.ccm.2019.10.001
Breiman,
L. 2001. Random forests. Machine Learning 45(1): 5-32. DOI: 10.1023/A:1010933404324
Buchinsky,
M. 1998. Recent advances in quantile regression models: A practical guideline
for empirical research. Journal of Human Resources 33(1): 88-126. DOI:
10.2307/146316
Buja, A., Rivera, M., De Polo, A., Brino,
E.D., Marchetti, M., Scioni, M., Pasello,
G., Bortolami, A., Rebba, V., Schiavon, M.,
Calabrese, F., Mandoliti, G., Baldo, V. & Conte,
P. 2021. Estimated direct costs of non-small cell lung cancer by stage at
diagnosis and disease management phase: A whole-disease model. Thorac Cancer 12(1): 13-20. DOI:
10.1111/1759-7714.13616
Cancer Council. 2019. What is Lung Cancer? https://www.cancer.org.au/cancer-information/types-of-cancer/lung-cancer Accessed
on 21 May 2025.
Cancer Research UK. 2022. Lung Cancer. https://www.cancerresearchuk.org/about-cancer/lung-cancer Accessed on 21 May 2025.
Chen,
T. & Guestrin, C. 2016. XGBoost:
A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD
International Conference on Knowledge Discovery and Data Mining. pp. 785-794.
DOI:10.1145/2939672.2939785
Corral, J., Espinàs, J.A.,
Cots, F., Pareja, L., Solà, J., Font, R. & Borràs, J.M. 2015. Estimation of lung cancer diagnosis and
treatment costs based on a patient-level analysis in Catalonia (Spain). BMC
Health Services Research 15(1): 70. DOI: 10.1186/s12913-015-0725-3
Deb, P. & Norton, E.C. 2018. Modeling health care expenditures and use. Annual Review of Public Health 39: 489-505.
DOI: 10.1146/annurev-publhealth-040617-013517
Ding, R., Zhu, D., He, P., Ma, Y., Chen, Z. & Shi,
X. 2020. Comorbidity in lung cancer patients and its association with medical
service cost and treatment choice in China. BMC Cancer 20(1): 250. DOI:
10.1186/s12885-020-06759-8
Duan, N., Manning Jr. W.G., Morris, C.N. &
Newhouse, J.P. 1983. A comparison of alternative models for the demand for
medical care. Journal of Business & Economic Statistics 1(2):
115-126.
Dunn, P.K. & Smyth, G.K. 2018. Generalized
Linear Models with Examples in R. New York/Berlin: Springer Nature.
Fox, K.M., Brooks, J.M. & Kim, J. 2008. Metastatic
non-small cell lung cancer: Costs associated with disease progression. Am. J.
Manag. Care 14(9): 565-571.
Gallucci, M. 2011. Best practices for using median
splits, artificial categorization, and their continuous alternatives. Journal
of Experimental Psychopathology 2(2): 197-209. DOI: 10.5127/jep.008310
Girard, N., Cozzone, D., De Leotoing,
L., Tournier, C., Vainchtock, A., Tehard,
B. & Cortot, A.B. 2018. Extra cost of brain
metastases (BM) in patients with non-squamous non-small cell lung cancer
(NSCLC): A French national hospital database analysis. ESMO Open 3(6):
e000414.
Global Cancer Observatory (GLOBOCAN). 2022. Global
Cancer Observatory: Cancer Today: Lung.
Hernandez, D., Cheng, C.Y., Hernandez-Villafuerte, K.
& Schlander, M. 2023. Survival and comorbidities in lung cancer patients:
Evidence from administrative claims data in Germany. Oncol. Res. 30(4):
173-185. DOI: 10.32604/or.2022.027262
Jovanoski, N., Abogunrin,
S., Di Maio, D., Belleli, R., Hudson, P., Bhadti, S. & Jones, L.G. 2023. Systematic literature
review to identify cost and resource use data in patients with early-stage
non-small cell lung cancer (NSCLC). Pharmacoeconomics 41(11): 1437-1452.
Kennedy, M.P., Hall, P.S. & Callister, M.E. 2016.
Factors affecting hospital costs in lung cancer patients in the United Kingdom. Lung Cancer 97: 8-14. DOI: 10.1016/j.lungcan.2016.04.009
Khalib, A., Ab Manan, A., Amir, P.N., Ali, N., Raman,
S., Bahtiar, S. & Raman, R.K. 2018. Malaysian
Study on Cancer Survival (MySCan). Putrajaya:
Ministry of Health.
Kim, D., Kim, S.Y., Suh, B. & Park, J.H. 2018.
Trend analysis for the choice and cost of lung cancer treatment in South Korea,
2003-2013. Cancer Res. Treat. 50(3): 757-767. DOI: 10.4143/crt.2017.050
Ku Abdul Rahim, K.N. & Hanin Farhana, K. 2018.
Systematic review of healthcare economic evaluation on Malaysia: An overview on
cancer-related economic studies. Journal of Global Oncology 4(Supplement
2): 76s-76s. DOI: 10.1200/jgo.18.20800
Manning, W.G. & Mullahy, J. 2001. Estimating log
models: To transform or not to transform? Journal of Health Economics 20(4): 461-494. DOI: 10.1016/s0167-6296(01)00086-8
Mellor, M. 2019. Kanser Paru-Paru Memiliki Kadar
'Survival' Terendah. https://subangjayamedicalcentre.com/blog-content/kanser-paru-paru-memiliki-kadar-survival-terendah-sjmc-dr-matin-mellor
Accessed on 21 May 2025.
Park, J.H., Kim, S.J., Medina, M., Prochnow, T., Min,
K. & Chang, J. 2024. Are comorbidities associated with differences in
healthcare charges among lung cancer patients in US hospitals? Focusing on
variances by patient and socioeconomic factors. Chronic Illn. 20(3): 434-444. DOI: 10.1177/17423953241241759
Rajkomar, A., Dean, J. & Kohane,
I. 2019. Machine learning in medicine. New England Journal of Medicine 380(14): 1347-1358. DOI:
10.1056/NEJMra1814259
Sari, A.A., Rezaei, S., Arab, M., Majdzadeh,
R., Matin, B.K. & Zandian, H. 2016. Effects of smoking
on cost of hospitalization and length of stay among patients with lung cancer
in Iran: A hospital-based study. Asian Pac. J. Cancer Prev. 17(9):
4421-4426. DOI: 10.7314/APJCP.2016.17.9.4421
Schabath, M.B. & Cote, M.L. 2019. Cancer progress and priorities:
Lung cancer. Cancer Epidemiol. Biomarkers Prev. 28(10): 1563-1579. DOI: 10.1158/1055-9965.EPI-19-0221
Umeda, Y., Matsumoto, S., Hagiwara, K., Yoshikawa, S.
& Chen, A. 2024. Evaluation of the factors affecting higher hospitalization
cost of lung resection for primary lung cancer: A retrospective cohort study. Ann. Thorac Cardiovasc. Surg. 30(1): 23-00180. DOI:
10.5761/atcs.oa.23-00180
World Health Organization (WHO). 2024. Global cancer
burden growing, amidst mounting need for services.
https://www.who.int/news/item/01-02-2024-global-cancer-burden-growing--amidst-mounting-need-for-services
Accessed on 21 May 2025.
Yousefi, M., Jalilian, H., Heydari, S., Seyednejad, F. & Mir, N. 2023. Cost of lung cancer: A systematic
review. Value Health Reg. Issues 33: 17-26. DOI: 10.1016/j.vhri.2022.07.007
Yu, T., He, Z., Zhou, Q., Ma, J. & Wei, L. 2015.
Analysis of the factors influencing lung cancer hospitalization expenses using
data mining. Thorac Cancer 6(3):
338-345. DOI: 10.1111/1759-7714.12147
Zhao, L. & Tang, J. 2024. Analysis of the
composition and influencing factors of hospitalization expenses for 1517
patients with lung malignant tumors in Beijing. Medicine (Baltimore) 103(11): e37385. DOI: 10.1097/MD.0000000000037385
|
|||
|
