합성 데이터를 활용한 폐암 환자의 생존분석 가능성 검정
A Study on the Availability of Survival Analysis of Lung Cancer Patients Using Synthetic Data
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Objectives: This was a pilot study to investigate the possibility of clinical analysis to support the lack of sample size of real data and to generate synthetic data. Since real data has many limitations, such as ethical issues and costly issues, there have been many attempts to create realistic synthetic data. The focus is on whether synthetic data can be used instead of real data. Methods: This study analyzed 11,978 lung cancer patients who used anticancer drug therapy using synthetic data as a quasi-experimental study. Clinically significant variables were extracted and some tables containing patient status and treatment records were preprocessed. This experiment was applied to the propensity score matching technique to prevent the bias of covariates. Then, the preprocessed data were analyzed using Kaplan-Meier estimation and Cox proportional hazards model. Results: When plotting the survival curves, the curves from the synthetic data did not match the curves for the actual data of the other covariates. In Cohort 1, Gen I had a better 5-year OS than Gen II [S1 = 0.973, S2 = 0.953, p < 0.05]. Similarly, Gen I anti-cancer was better than Gen III in Cohort 2 [S1 = 0.990, S3 = 0.884, p < 0.05]. In the exploratory sub- group analysis using the Cox regression model, the risk ratio was estimated. We found that Gen I had a better effect on HR than Gen II and III. However, those results were different from the actual trend. Conclusions: It was found that the analysis based on the DATA-FREE-BOX data was different from the trend of the survival analysis conducted with the real data. The trend of this analysis could be different from the real trend. It will be able to contribute to data-validation. Moreover, it is expected that the same methodology can be applied in clinical studies based on actual data by utilizing the technique used in this study.
Abstract
Objectives: This was a pilot study to investigate the possibility of clinical analysis to support the lack of sample size of real data and to generate synthetic data. Since real data has many limitations, such as ethical issues and costly issues, there have been many attempts to create realistic synthetic data. The focus is on whether synthetic data can be used instead of real data. Methods: This study analyzed 11,978 lung cancer patients who used anticancer drug therapy using synthetic data as a quasi-experimental study. Clinically significant variables were extracted and some tables containing patient status and treatment records were preprocessed. This experiment was applied to the propensity score matching technique to prevent the bias of covariates. Then, the preprocessed data were analyzed using Kaplan-Meier estimation and Cox proportional hazards model. Results: When plotting the survival curves, the curves from the synthetic data did not match the curves for the actual data of the other covariates. In Cohort 1, Gen I had a better 5-year OS than Gen II [S1 = 0.973, S2 = 0.953, p < 0.05]. Similarly, Gen I anti-cancer was better than Gen III in Cohort 2 [S1 = 0.990, S3 = 0.884, p < 0.05]. In the exploratory sub- group analysis using the Cox regression model, the risk ratio was estimated. We found that Gen I had a better effect on HR than Gen II and III. However, those results were different from the actual trend. Conclusions: It was found that the analysis based on the DATA-FREE-BOX data was different from the trend of the survival analysis conducted with the real data. The trend of this analysis could be different from the real trend. It will be able to contribute to data-validation. Moreover, it is expected that the same methodology can be applied in clinical studies based on actual data by utilizing the technique used in this study.
참고문헌 (26)
- "National Cancer Information Center"[URL]
- "Differential Privacy: A Q&A With NIST’s Mary Theofanos"[URL]
- Chen J, "The validity of synthetic clinical data : a validation study of a leading synthetic data generator(synthea)using clinical quality measures", BMC Med Inform Decis Mak, 19(1), pp.44~ (2019)[DOI]
- "Service ‘DATA-FREE-BOX’ at CONNECT"[URL]
- Nagano T, "Molecular mechanisms and targeted therapies including immunotherapy for non-small cell lung cancer", Curr Cancer Drug Targets, 19(8), pp.595~630 (2019)[DOI]
- Gandhi L, "Pembrolizumab plus chemotherapy in metastatic nonsmall-cell lung cancer", N Engl J Med, 378(22), pp.2078~2092 (2018)[DOI]
- Reck M, "Pembrolizumab versus chemotherapy for PD-L1-positive nonsmall-cell lung cancer", N Engl J Med, 375(19), pp.1823~1833 (2016)[DOI]
- Hellmann MD, "Nivolumab plus ipilimumab in lung cancer with a high tumor mutational burden", N Engl J Med, 378(22), pp.2093~2104 (2018)[DOI]
- Gadgeel S, "Updated analysis from KEYNOTE-189 : pembrolizumab or placebo plus pemetrexed and platinum for previously untreated metastatic nonsquamous non-small-cell lung cancer", J Clin Oncol, 38(14), pp.1505~1517 (2020)[DOI]
- Paz-Ares L, "Pembrolizumab plus chemotherapy for squamous non-small-cell lung cancer", N Engl J Med, 379(21), pp.2040~2051 (2018)
- Bae SH, "Study on assessing the proportional hazard assumption in the Cox model", pp.2012
- Reiffel JA, "Propensity-score matching : optimal, adequate, or incomplete", J Atr Fibrillation, 11(4), pp.2130~ (2018)[DOI]
- 이동규, "Propensity score matching method의 소개", Anesthesia and Pain Medicine, 11(2), pp.130~148 (2016), 대한마취통증의학회
- "PyPi-psmpy 0.3.5"[URL]
- "Special cancer immunotherapy"[URL]
- "American College of Surgeons"[URL]
- Rami-Porta R, "Lung cancer-major changes in the American Joint Committee on Cancer eighth edition cancer staging manual", CA Cancer J Clin, 67(2), pp.138~155 (2017)[DOI]
- Schabath MB, "Cancer progress and priorities : lung cancer", Cancer Epidemiol Biomarkers Prev, 28(10), pp.1563~1579 (2019)[DOI]
- van Meerbeeck JP, "The seventh tumour-node-metastasis staging system for lung cancer: Sequel or prequel?", EJC Suppl, 11(2), pp.150~158 (2013)[DOI]
- Song H, "Application of N descriptors proposed by the international association for the study of lung cancer in clinical staging", Radiology, 300(2), pp.450~457 (2021)[DOI]
- Detterbeck FC, "The eighth edition TNM stage classification for lung cancer: What does it mean on main street?", J Thorac Cardiovasc Surg, 155(1), pp.356~359 (2018)[DOI]
- Page P, "Beyond statistical significance : clinical interpretation of rehabilitation research literature", Int J Sports Phys Ther, 9(5), pp.726~736 (2014)
- Das Sarma A, "Synthesizing view definitions from data", ICDT ‘10: Proceedings of the 13th International Conference on Database Theory, pp.89~103 (2010)
- Howard AF, "Clinical significance in pediatric oncology randomized controlled treatment trials : a systematic review", Trials, 19(1), pp.539~ (2018)[DOI]
- Man-Son-Hing M, "Determination of the clinical importance of study results", J Gen Intern Med, 17(6), pp.469~476 (2002)[DOI]
- Collins GS, "Sample size considerations for the external validation of a multivariable prognostic model : a resampling study", Stat Med, 35(2), pp.214~226 (2016)[DOI]