informИнформатикаInformatics1816-03012617-6963UIIP NASB10.37661/1816-0301-2024-21-2-36-53inform-1282Research ArticleБИОИНФОРМАТИКАBIOINFORMATICSДооперационное прогнозирование T-стадии рака желудка на базе моделей порядковой регрессииPreoperative prediction of gastric cancer T-staging based on ordinal regression modelshttps://orcid.org/0000-0002-4150-282XКраськоО. В.KraskoO. V.

Красько Ольга Владимировна, кандидат техническихнаук, доцент, ведущий научный сотрудник

ул. Сурганова, 6, Минск, 220012

Olga V. Krasko, Ph. D. (Eng.), Assoc. Prof., Leading Researcher

st. Surganova, 6, Minsk, 220012

krasko@NEWMAN.bas-net.byhttps://orcid.org/0000-0001-7202-6902РевтовичМ. Ю.ReutovichM. Yu.

Ревтович Михаил Юрьевич, доктор медицинских наук, доцент, декан лечебного факультета

пр. Дзержинского, 83, Минск, 220083

Mikhail Yu. Reutovich, D. Sc. (Med.), Assoc. Prof., Dean of the Faculty of General Medicine

av. Dzerzhinsky, 83, Minsk, 220083

mihail_revtovich@yahoo.comПотейкоА. И.PatseikaA. L.

Потейко Александр Иванович, врач онколог-хирург,онкологическое отделение гастроэзофагеальной патологии

аг. Лесной, Минский район, 223040

Aliaksandr I. Patseika, Surgical Oncologist, Oncology Division of Gastroesophageal Abnormalities

Lesnoy, Minsk District, 223040

drpatseika@gmail.comОбъединенный институт проблем информатики Национальной академии наук БеларусиThe United Institute of Informatics Problems of the National Academy of Sciences of BelarusБелорусский государственный медицинский университетBelarusian State Medical UniversityРеспубликанский научно-практический центр онкологии и медицинской радиологии им. Н. Н. Александрова.N. N. Alexandrov National Cancer Centre of Belarus2024280620242123653Copyright © Красько О.В., Ревтович М.Ю., Потейко А.И., 20242024Красько О.В., Ревтович М.Ю., Потейко А.И.Krasko O.V., Reutovich M.Y., Patseika A.L.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://inf.grid.by/jour/article/view/1282Цели

Цели. Исследование порядковых регрессий, представленных набором бинарных логистических регрессий, и их применение в клинической практике при Т-стадировании рака желудка.

Методы

Методы. Использовались методы статистических моделей порядковой регрессии, оценки эффективности модели и анализа выживаемости.

Результаты

Результаты. Основные модели порядковой регрессии были изучены и применены к клиническим данным рака желудка. К известным прогностическим критериям по классификации TNM в многофакторной регрессионной модели добавлены некоторые клинические предикторы, результаты представляются перспективными для персонализированного подхода при планировании объема лечения для повышения его эффективности.

Заключение

Заключение. Проведенное исследование показало, что комплексное использование порядковых моделей наряду с мультиномиальными дает дополнительную информацию, которая помогает понять поведение латентной переменной в сложных процессах онкологических заболеваний. Клиническая часть исследования создает предпосылки к дифференцированному подходу к предоперационному планированию объема лечения пациентов с одинаковой Т-стадией на основе результатов моделирования.

Objectives. Study of ordinal regressions presented via the set of binary logistic regressions and their application in clinical practice for T-staging of gastric cancer.Methods. Methods of ordinal regression statistical models, model performance assessment, and survival analysis were used.Results. Basic ordinal regression models have been studied and applied to the clinical data of gastric cancer. Some clinical predictors have been added to the well-known prognostic criteria according to the TNM classification in the multifactor regression model, results seem appropriate for a personalized approach when planning the treatment volume for improving efficacy.Conclusion. The study showed that the analysis of ordinal models, along with multinomial ones, provides additional information that helps to understand the behavior of the latent variable in the complex cancer processes. The clinical part of the study facilitates a differentiated approach to preoperative planning of the treatment volume for patients with the same T-stage, based on modeling results.

порядковые регрессионные моделиметрики производительности и классификации моделейTNM-классификациядооперационное T-стадирование рака желудкаанализ выживаемостиordinal regression modelsmodel performance and classifications metricsTNM-descriptorspreoperative T-staging of gastric cancersurvival analysisReferencesStevens S. S. On the theory of scales of measurement. Science, 1946, vol. 103, no. 2684, рр. 677–680.Stevens S. S. On the theory of scales of measurement //Science. – 1946. – Т. 103. – №. 2684. – С. 677-680.Agresti A. Modelling ordered categorical data: recent advances and future challenges. Statistics in Medicine, 1999, vol. 18, no. 17–18, рр. 2191–2207.Agresti A. Modelling ordered categorical data: recent advances and future challenges //Statistics in medicine. – 1999. – Т. 18. – №. 17‐18. – С. 2191-2207.McCullagh P. Regression models for ordinal data. Journal of the Royal Statistical Society: Series B (Methodological), 1980, vol. 42, no. 2, рр. 109–127.McCullagh P. Regression models for ordinal data //Journal of the Royal Statistical Society: Series B (Methodological). – 1980. – Т. 42. – №. 2. – С. 109-127.Agresti A. Analysis of Ordinal Categorical Data, 2nd edition. John Wiley & Sons, 2010, 424 р.Agresti A. Analysis of ordinal categorical data. – John Wiley & Sons, 2010. – Т. 656.McCullagh P. Proportional odds model: Theoretical background. Wiley StatsRef: Statistics Reference Online, 2014. Available at: https://onlinelibrary.wiley.com/doi/abs/10.1002/9781118445112.stat05796 (accessed 27.02.2024).McCullagh P. Proportional odds model: Theoretical background //Wiley StatsRef: Statistics Reference Online. – 2014.Thompson Jr W. A. On the treatment of grouped observations in life studies. Biometrics, 1977, vol. 33, no. 3, рр. 463–470.Thompson Jr W. A. On the treatment of grouped observations in life studies //Biometrics. – 1977. – С. 463-470.Cox D. R. Regression models and life‐tables. Journal of the Royal Statistical Society: Series B (Methodological), 1972, vol. 34, no. 2, рр. 187–202.Cox D. R. Regression models and life‐tables //Journal of the Royal Statistical Society: Series B (Methodological). – 1972. – Т. 34. – №. 2. – С. 187-202.McCullagh P. Regression models for ordinal data. Journal of the Royal Statistical Society: Series B (Methodological), 1980, vol. 42, no. 2, рр. 109–127.McCullagh P. Regression models for ordinal data //Journal of the Royal Statistical Society: Series B (Methodological). – 1980. – Т. 42. – №. 2. – С. 109-127.Fienberg S. E. The Analysis of Cross-Classified Categorical Data, 2nd edition. Springer Science & Business Media, 2007, 212 р.Fienberg S. E. The analysis of cross-classified categorical data. – Springer Science & Business Media, 2007.Powers D., Xie Y. Statistical Methods for Categorical Data Analysis, 2nd edition. Emerald Group Publishing, 2008, 296 р.Powers D., Xie Y. Statistical methods for categorical data analysis. – Emerald Group Publishing, 2008.Fullerton A. S., Xu J. Constrained and unconstrained partial adjacent category logit models for ordinal response variables. Sociological Methods & Research, 2018, vol. 47, no. 2, рр. 169–206.Fullerton A. S., Xu J. Constrained and unconstrained partial adjacent category logit models for ordinal response variables //Sociological Methods & Research. – 2018. – Т. 47. – №. 2. – С. 169-206. ]Anderson J. A. Regression and ordered categorical variables. Journal of the Royal Statistical Society: Series B (Methodological), 1984, vol. 46, no. 1, рр. 1–22.Anderson J. A. Regression and ordered categorical variables //Journal of the Royal Statistical Society: Series B (Methodological). – 1984. – Т. 46. – №. 1. – С. 1-22.Fernandez D., Liu I., Costilla R. A method for ordinal outcomes: The ordered stereotype model. International Journal of Methods in Psychiatric Research, 2019, vol. 28, no. 4, р. e1801.Fernandez D., Liu I., Costilla R. A method for ordinal outcomes: The ordered stereotype model //International journal of methods in psychiatric research. – 2019. – Т. 28. – №. 4. – С. e1801.Long J. S., Cheng S. Regression models for categorical outcomes. Handbook of Data Analysis, 2004, рр. 259–284.Long J. S., Cheng S. Regression models for categorical outcomes //Handbook of data analysis. – 2004. – С. 259-284.Hilbe J. M. Logistic Regression Models, 1st edition. CRC press, 2009, 656 р.Hilbe J. M. Logistic regression models. – CRC press, 2009.Hauser R. M., Andrew M. 1. Another look at the stratification of educational transitions: the logistic response model with partial proportionality constraints. Sociological Methodology, 2006, vol. 36, no. 1, рр. 1–26.Hauser R. M., Andrew M. 1. Another look at the stratification of educational transitions: the logistic response model with partial proportionality constraints //Sociological Methodology. – 2006. – Т. 36. – №. 1. – С. 1-26.Tutz G. Ordinal regression: A review arn a taxoromy of models. Wiley Interdisciplinary Reviews: Computational Statistics, 2022, vol. 14, no. 2, р. e1545.Tutz G. Ordinal regression: A review arn a taxoromy of models //Wiley Interdisciplinary Reviews: Computational Statistics. – 2022. – Т. 14. – №. 2. – С. e1545.Hosmer D. W., Lemeshow S., Cook E. Applied Logistic Regression, 2nd edition. New York, John Wiley and Sons Inc., 2000, 376 р.Hosmer D. W., Lemeshow S., Cook E. Applied logistic regression 2nd edition //New York: Jhon Wiley and Sons Inc. – 2000.Lipsitz S. R., Fitzmaurice G. M., Molenberghs G. Goodness-of-fit tests for ordinal response regression models. Journal of the Royal Statistical Society Series C: Applied Statistics, 1996, vol. 45, no. 2, рр. 175–190.Lipsitz S. R., Fitzmaurice G. M., Molenberghs G. Goodness-of-fit tests for ordinal response regression models //Journal of the Royal Statistical Society Series C: Applied Statistics. – 1996. – Т. 45. – №. 2. – С. 175-190.Pulkstenis E., Robinson T. J. Goodness‐of‐fit tests for ordinal response regression models. Statistics in Medicine, 2004, vol. 23, no. 6, рр. 999–1014.Pulkstenis E., Robinson T. J. Goodness‐of‐fit tests for ordinal response regression models //Statistics in medicine. – 2004. – Т. 23. – №. 6. – С. 999-1014.Fagerland M. W., Hosmer D. W. Tests for goodness of fit in ordinal logistic regression models. Journal of Statistical Computation and Simulation, 2016, vol. 86, no. 17, рр. 3398–3418.Fagerland M. W., Hosmer D. W. Tests for goodness of fit in ordinal logistic regression models //Journal of Statistical Computation and Simulation. – 2016. – Т. 86. – №. 17. – С. 3398-3418.Tharwat A. Classification assessment methods. Applied Computing and Informatics, 2020, vol. 17, no. 1, рр. 168–192.Tharwat A. Classification assessment methods //Applied computing and informatics. – 2020. – Т. 17. – №. 1. – С. 168-192.Japanese Gastric Cancer Association. Japanese Gastric Cancer Treatment Guidelines 2021. Gastric Cancer: Official Journal of the International Gastric Cancer Association and the Japanese Gastric Cancer Association, 2023, vol. 26, no. 1, рр. 1–25.Japanese Gastric Cancer Association. Japanese Gastric Cancer Treatment Guidelines 2021 //Gastric cancer: official journal of the International Gastric Cancer Association and the Japanese Gastric Cancer Association. – 2023. – Т. 26. – №. 1. – С. 1-25.Götze T. O., Piso P., Lorenzen S., Bankstahl U. S., Pauligk C., …, Königsrainer A. Preventive HIPEC in combination with perioperative FLOT versus FLOT alone for resectable diffuse type gastric and gastroesophageal junction type II/III adenocarcinoma – the phase III "PREVENT"-(FLOT9) trial of the AIO/CAOGI/ACO. BMC Cancer, 2021, vol. 21, no. 1, рр. 1–9.Götze T. O. et al. Preventive HIPEC in combination with perioperative FLOT versus FLOT alone for resectable diffuse type gastric and gastroesophageal junction type II/III adenocarcinoma–the phase III “PREVENT”-(FLOT9) trial of the AIO/CAOGI/ACO //BMC cancer. – 2021. – Т. 21. – №. 1. – С. 1-9.Cohen J. A coefficient of agreement for nominal scales. Educational and Psychological Measurement, 1960, vol. 20, no. 1, рр. 37–46.Cohen J. A coefficient of agreement for nominal scales //Educational and psychological measurement. – 1960. – Т. 20. – №. 1. – С. 37-46.Lin M., Chen Q.-Y., Zheng C.-H., Li P., Xie J.-W., …, Huang C.-M. Effect of preoperative tumor under-staging on the long-term survival of patients undergoing radical gastrectomy for gastric cancer. Cancer Research and Treatment: Official Journal of Korean Cancer Association, 2021, vol. 53, no. 4, рр. 1123–1133.Lin M. et al. Effect of Preoperative Tumor Under-Staging on the Long-term Survival of Patients Undergoing Radical Gastrectomy for Gastric Cancer //Cancer Research and Treatment: Official Journal of Korean Cancer Association. – 2021. – Т. 53. – №. 4. – С. 1123-1133.Mcfadden D. Conditional logit analysis of qualitative choice behavior. Frontier in Econometrics, New York, Academic press, 1973, рр. 105–142.Mcfadden D. Conditional Logit Analysis of Qualitative Choice Behavior //Frontier in Econometrics. – 1973.Rosa F., Costamagna G., Doglietto G. B., Alfieri S. Classification of nodal stations in gastric cancer. Translational Gastroenterology and Hepatology, 2017, vol. 2. Available at: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5313280/pdf/tgh-02-2016.12.03.pdf (accessed 27.02.2024).Rosa F. et al. Classification of nodal stations in gastric cancer //Translational gastroenterology and hepatology. – 2017. – Т. 2.Deng J., Zhang R., Pan Y., Ding X., Cai M., …, Liang H. Tumor size as a recommendable variable for accuracy of the prognostic prediction of gastric cancer: a retrospective analysis of 1,521 patients. Annals of Surgical Oncology, 2015, vol. 22, рр. 565–572.Dai N. et al. Expression of phosphatase regenerating liver 3 is an independent prognostic indicator for gastric cancer //World journal of gastroenterology. – 2009. – Т. 15. – №. 12. – С. 1499-1505.Dai N., Lu A.-P., Shou C.-C., Li J.-Y. Expression of phosphatase regenerating liver 3 is an independent prognostic indicator for gastric cancer. World Journal of Gastroenterology, 2009, vol. 15, no. 12, рр. 1499–1505.Kim E. Y. et al. The platelet-to-lymphocyte ratio versus neutrophil-to-lymphocyte ratio: which is better as a prognostic factor in gastric cancer? //Annals of surgical oncology. – 2015. – Т. 22. – С. 4363-4370.Kim E. Y. Lee J. W., Yoo H. M., Park C. H., Song K. Y. The platelet-to-lymphocyte ratio versus neutrophil-to-lymphocyte ratio: which is better as a prognostic factor in gastric cancer? Annals of Surgical Oncology, 2015, vol. 22, рр. 4363–4370.Kim E. Y. Lee J. W., Yoo H. M., Park C. H., Song K. Y. The platelet-to-lymphocyte ratio versus neutrophil-to-lymphocyte ratio: which is better as a prognostic factor in gastric cancer? Annals of Surgical Oncology, 2015, vol. 22, рр. 4363–4370.

The authors declare that there are no conflicts of interest present.