informИнформатикаInformatics1816-03012617-6963UIIP NASB10.37661/1816-0301-2024-21-1-65-82inform-1274Research ArticleБИОИНФОРМАТИКАBIOINFORMATICSПрогнозирование и принятие решений на основе модели нелинейных рисков при лечении рака желудкаPrediction and decision-making based on nonlinear risks model in stomach cancer treatmenthttps://orcid.org/0000-0002-4150-282XКраськоО. В.KraskoO. V.

Красько Ольга Владимировна, кандидат технических наук, 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.comhttps://orcid.org/0009-0005-1288-2121ИвановА. В.IvanovA. V.

Иванов Андрей Владимирович, аспирант

агр Лесной, Минский район, 223040

 

Andrey V. Ivanov, Postgraduate Student

Lesnoy, Minsk Region, 223040

tennis5000@rambler.ruОбъединенный институт проблем информатики Национальной академии наук БеларусиThe United Institute of Informatics Problems of the National Academy of Sciences of BelarusУчреждение образования «Белорусский государственный медицинский университет»Belarusian State Medical UniversityРеспубликанский научно-практический центр им. Н. Н. АлександроваN. N. Alexandrov National Cancer Center of Belarus2024290320242116582Copyright © Красько О.В., Ревтович М.Ю., Иванов А.В., 20242024Красько О.В., Ревтович М.Ю., Иванов А.В.Krasko O.V., Reutovich M.Y., Ivanov A.V.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/1274Цели

Цели. В исследовании ставятся цели разработать модель нелинейных рисков развития неблагоприятных исходов и оценить ее пригодность для прогнозирования в клинической практике.

Методы

Методы. Использованы методы анализа выживаемости, регрессионные статистические модели.

Результаты

Результаты. Предложен практический подход к оценке нелинейных рисков развития неблагоприятных событий на примере лечения рака желудка. Предложена и исследована модель прогнозирования метахронной перитонеальной диссеминации у радикально оперированных по поводу рака желудка пациентов. Оценены риски в различные периоды наблюдения и клиническая пригодность разработанного подхода.

Заключение

Заключение. В клинической онкологической практике большую роль играет не только своевременное лечение, но и предупреждение неблагоприятных исходов после окончания лечения. Индивидуализация наблюдения за пациентом после лечения снижает риски фатальных исходов, затраты на дополнительные исследования и лечение в случае прогрессирования онкозаболевания. По результатам данного исследования предлагаются решения, которые должны привести к более эффективной и качественной тактике наблюдения после проведенного лечения рака желудка, к выбору оптимальных подходов и получению клинически благоприятных исходов заболевания. Предложенный метод прогноза рисков в конечном итоге приведет к индивидуализированному ведению пациента на основании его данных.

Objectives

Objectives. The goals are to develop a nonlinear risk model and examine its prediction applicability for clinical use.

Methods

Methods. Methods of survival analysis and regression statistical models were used.

Results

Results. A practical approach to assessing nonlinear risks of adverse events using the example of gastric cancer treatment is proposed. A model for predicting the metachronous peritoneal dissemination in patients undergoing radical surgery for gastric cancer was proposed and studied. Assessment of risks for various periods of observation was performed, and the clinical suitability of developed approach was assessed.

Conclusion

Conclusion. In clinical oncological practice, not only timely treatment plays an important role, but also the prevention of adverse outcomes after treatment. Individualization of patient monitoring after treatment reduces the risks of fatal outcomes and the costs of additional research and treatment in the event of cancer progression. Based on the results of this study, we propose solutions that should lead to more effective and high-quality treatment tactics and follow-up after treatment for gastric cancer, also to the selection of optimal approaches and to obtaining clinically favorable outcomes of the disease. The proposed risk prediction method will ultimately lead to individualized patient management based on the results of personal data.

нелинейные рискимодель Файна – Греярак желудкаперитонеальная диссеминацияпрогнозированиеnonlinear hazardFine – Grey modelgastric cancerperitoneal disseminationpredictReferencesAlonzo, T. A. Clinical prediction models: a practical approach to development, validation, and updating: by Ewout W. Steyerberg / T. A. Alonzo // American J. of Epidemiology. – 2009. – Vol. 170, iss. 4. – Р. 528. https://doi.org/10.1093/aje/kwp129Alonzo T. A. Clinical prediction models: a practical approach to development, validation, and updating: by Ewout W. Steyerberg. – 2009.]A novel clinical risk prediction model for sudden cardiac death in hypertrophic cardiomyopathy (HCM risk-SCD) / C. O'Mahony [et al.] // European Heart J. – 2014. – Vol. 35, no. 30. – Р. 2010–2020.O'Mahony C. et al. A novel clinical risk prediction model for sudden cardiac death in hypertrophic cardiomyopathy (HCM risk-SCD) //European heart journal. – 2014. – Т. 35. – №. 30. – С. 2010-2020]Scrucca, L. Competing risk analysis using R: an easy guide for clinicians / L. Scrucca, A. Santucci, F. Aversa // Bone Marrow Transplantation. – 2007. – Vol. 40, no. 4. – P. 381–387.Scrucca L., Santucci A., Aversa F. Competing risk analysis using R: an easy guide for clinicians //Bone marrow transplantation. – 2007. – Т. 40. – №. 4. – С. 381-387.Prognostic models with competing risks: methods and application to coronary risk prediction / M. Wolbers [et al.] // Epidemiology. – 2009. – Vol. 20, iss. 4 – Р. 555–561.Wolbers M. et al. Prognostic models with competing risks: methods and application to coronary risk prediction //Epidemiology. – 2009. – С. 555-561.Cox, D. R. Regression models and life‐tables / D. R. Cox // J. of the Royal Statistical Society: Series B (Methodological). – 1972. – Vol. 34, no. 2. – Р. 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.Hosmer, Jr. D. W. Applied Survival Analysis: Regression Modeling of Time-to-Event Data / Jr. D. W. Hosmer, S. Lemeshow, S. May. – John Wiley & Sons, 2011. – 416 р.Hosmer Jr D. W., Lemeshow S., May S. Applied survival analysis: regression modeling of time-to-event data. – John Wiley & Sons, 2011. – Т. 618.Therneau, T. Using time dependent covariates and time dependent coefficients in the cox model / T. Therneau, C. Crowson, E. Atkinson // Survival Vignettes. – 2017. – Vol. 2, no. 3. – Р. 1–25.Therneau T., Crowson C., Atkinson E. Using time dependent covariates and time dependent coefficients in the cox model //Survival Vignettes. – 2017. – Т. 2. – №. 3. – С. 1-25.Murphy, S. A. Time-dependent coefficients in a Cox-type regression model / S. A. Murphy, P. K. Sen // Stochastic Processes and their Applications. – 1991. – Vol. 39, no. 1. – Р. 153–180.Murphy S. A., Sen P. K. Time-dependent coefficients in a Cox-type regression model //Stochastic Processes and their Applications. – 1991. – Т. 39. – №. 1. – С. 153-180.Thomas, L. Tutorial: survival estimation for Cox regression models with time-varying coefficients using SAS and R / L. Thomas, E. M. Reyes // J. of Statistical Software. – 2014. – Vol. 61. – Р. 1–23.Thomas L., Reyes E. M. Tutorial: survival estimation for Cox regression models with time-varying coefficients using SAS and R //Journal of Statistical Software. – 2014. – Т. 61. – С. 1-23.Redmond, C. The methodologic dilemma in retrospectively correlating the amount of chemotherapy received in adjuvant therapy protocols with disease-free survival / C. Redmond, B. Fisher, H. S. Wieand // Cancer Treatment Reports. – 1983. – Vol. 67, no. 6. – Р. 519–526.Redmond C., Fisher B., Wieand H. S. The methodologic dilemma in retrospectively correlating the amount of chemotherapy received in adjuvant therapy protocols with disease-free survival //Cancer Treatment Reports. – 1983. – Т. 67. – №. 6. – С. 519-526.Suissa, S. Immortal time bias in pharmacoepidemiology / S. Suissa // American J. of Epidemiology. – 2008. – Vol. 167, no. 4. – Р. 492–499.Suissa S. Immortal time bias in pharmacoepidemiology //American journal of epidemiology. – 2008. – Т. 167. – №. 4. – С. 492-499.Fine, J. P. A proportional hazards model for the subdistribution of a competing risk / J. P. Fine, R. J. Gray // J. of the American Statistical Association. – 1999. – Vol. 94, no. 446. – Р. 496–509.Fine J. P., Gray R. J. A proportional hazards model for the subdistribution of a competing risk //Journal of the American statistical association. – 1999. – Т. 94. – №. 446. – С. 496-509.Li, J. Checking Fine and Gray subdistribution hazards model with cumulative sums of residuals / J. Li, T. H. Scheike, M. J. Zhang // Lifetime Data Analysis. – 2015. – Vol. 21, no. 2. – Р. 197–217.Li J., Scheike T. H., Zhang M. J. Checking Fine and Gray subdistribution hazards model with cumulative sums of residuals //Lifetime data analysis. – 2015. – Т. 21. – №. 2. – С. 197-217.A detailed analysis of the recurrence timing and pattern after curative surgery in patients undergoing neoadjuvant therapy or upfront surgery for gastric cancer / A. Agnes [et al.] // J. of Surgical Oncology. – 2020. – Vol. 122, no. 2. – Р. 293–305.Agnes A. et al. A detailed analysis of the recurrence timing and pattern after curative surgery in patients undergoing neoadjuvant therapy or upfront surgery for gastric cancer //Journal of Surgical Oncology. – 2020. – Т. 122. – №. 2. – С. 293-305.Incidence, time course and independent risk factors for metachronous peritoneal carcinomatosis of gastric origin – a longitudinal experience from a prospectively collected database of 1108 patients / F. Seyfried [et al.] // BMC Cancer. – 2015. – Vol. 15. – Р. 1–10.Seyfried F. et al. Incidence, time course and independent risk factors for metachronous peritoneal carcinomatosis of gastric origin–a longitudinal experience from a prospectively collected database of 1108 patients //BMC cancer. – 2015. – Т. 15. – С. 1-10.Lauren histologic type is the most important factor associated with pattern of recurrence following resection of gastric adenocarcinoma / J. H. Lee [et al.] // Annals of Surgery. – 2018. – Vol. 267, no. 1. – Р. 105.Lee J. H. et al. Lauren histologic type is the most important factor associated with pattern of recurrence following resection of gastric adenocarcinoma //Annals of surgery. – 2018. – Т. 267. – №. 1. – С. 105.Reutovich, M. Y. Hyperthermic intraperitoneal chemotherapy in prevention of gastric cancer metachronous peritoneal metastases: a systematic review / M. Y. Reutovich, O. V. Krasko, O. G. Sukonko // J. of Gastrointestinal Oncology. – 2021. – Vol. 12, suppl. 1. – Р. S5–S17. https://doi.org/10.21037/jgo-20-129Reutovich M.Y, Krasko O.V, Sukonko O.G. Hyperthermic intraperitoneal chemotherapy in prevention of gastric cancer metachronous peritoneal metastases: a systematic review. J Gastrointest Oncol 2021;12(Suppl 1):S5-S17. doi: 10.21037/jgo-20-129.Analysis and external validation of a nomogram to predict peritoneal dissemination in gastric cancer / X. Chen [et al.] // Chinese J. of Cancer Research. – 2020. – Vol. 32, no. 2. – Р. 197–207.Chen X. et al. Analysis and external validation of a nomogram to predict peritoneal dissemination in gastric cancer //Chinese Journal of Cancer Research. – 2020. – Т. 32. – №. 2. – С. 197-207.Staging of peritoneal carcinomatosis: enhanced CT vs. PET/CT / C. Dromain [et al.] // Abdominal Imaging. – 2008. – Vol. 33. – Р. 87–93.Dromain C. et al. Staging of peritoneal carcinomatosis: enhanced CT vs. PET/CT //Abdominal imaging. – 2008. – Т. 33. – С. 87-93.Added value of pretreatment 18F-FDG PET/CT for staging of advanced gastric cancer: comparison with contrast-enhanced MDCT / Y. Kawanaka [et al.] // European J. of Radiology. – 2016. – Vol. 85, no. 5. – Р. 989–995.Kawanaka Y. et al. Added value of pretreatment 18F-FDG PET/CT for staging of advanced gastric cancer: comparison with contrast-enhanced MDCT //European journal of radiology. – 2016. – Т. 85. – №. 5. – С. 989-995.Peritoneal recurrence in gastric cancer following curative resection can be predicted by postoperative but not preoperative biomarkers: a single-institution study of 320 cases / F. Wu [et al.] // Oncotarget. – 2017. – Vol. 8, no. 44. – Р. 78120.Wu F. et al. Peritoneal recurrence in gastric cancer following curative resection can be predicted by postoperative but not preoperative biomarkers: a single-institution study of 320 cases //Oncotarget. – 2017. – Т. 8. – №. 44. – С. 78120.Ревтович, М. Ю. Местнораспространенный рак желудка: современные направления радикального лечения и прогнозирование отдаленных результатов : монография / М. Ю. Ревтович, О. В. Красько. – Минск : БелМАПО, 2022. – 217 с.Locally advanced gastric cancer: modern directions of radical treatment and prediction of long-term results: monograph / Reutovich M.Yu., Krasko O.V.. – Minsk: Belarusian Medical Academy of Postgraduate Education, 2022. – 217 p.Результаты радикального лечения инфильтративных форм рака желудка с применением перфузионной термохимиотерапии / М. Ю. Ревтович [и др.] // Евразийский онкологический журнал. – 2022. – Т. 10, № 2. – С. 107–117.Results of radical treatment of infiltrative gastric cancer using perfusion thermochemotherapy / Reutovich M.Yu., Krasko O.V., Malkevich V.T., Patseika A.I. // Eurasian Journal of Oncology. – 2022, – Vol. 10, №2, – P. 107-117.Ревтович, М. Ю. Интраоперационная оценка риска развития канцероматоза после радикального хирургического лечения рака желудка / М. Ю. Ревтович, О. В. Красько // Онкология и радиология Казахстана. – 2020. – № 2(56). – С. 26–30. https://doi.org/10.52532/2521-6414-2020-2-56-26-30Reutovich M.Yu., Krasko O.V. Intraoperative risk assessment of carcinomatosis development after radical surgery for gastric cancer// Oncology and Radiology of Kazakhstan, N2 (56) 2020. DOI: 10.52532/2521-6414-2020-2-56-26-30.Reutovich, M. Prophylactic hyperthermic intraperitoneal chemotherapy in gastric cancer management: short- and long-term outcomes of a prospective randomized study / M. Reutovich, O. Krasko // Oncology in Clinical Practice. – 2021. – Vol. 17, no. 5. – Р. 187–193. https://doi.org/10.5603/OCP.2021.0028Reutovich M., Krasko O. Prophylactic hyperthermic intraperitoneal chemotherapy in gastric cancer management: short- and long-term outcomes of a prospective randomized study // Oncology in clinical practice . 2021, Vol. 17, № 5, – p. 187–193. DOI: 10.5603/OCP.2021.0028.Reutovich, M. Yu. Efficacy of adjuvant systemic chemotherapy combined with radical surgery and hyperthermic intraperitoneal chemotherapy in gastric cancer treatment / M. Yu. Reutovich, O. V. Krasko, O. G. Sukonko // Indian J. of Surgical Oncology. – 2020. – Vol. 11. – P. 337–343. https://doi.org/10.1007/s13193-020-01102-wM. Yu Reutovich, O.V.Krasko, O.G.Sukonko: Efficacy of Adjuvant Systemic Chemotherapy Combined with Radical Surgery and Hyperthermic Intraperitoneal Chemotherapy in Gastric Cancer Treatment // Indian Journal of Surgical Oncology. 2020. –Vol. 11. P. 337-343. https://doi.org/10.1007/s13193-020-01102-w.Schoenfeld, D. Partial residuals for the proportional hazards regression model / D. Schoenfeld // Biometrika. – 1982. – Vol. 69, no. 1. – Р. 239–241.Алгоритмы диагностики и лечения злокачественных новообразований: клинический протокол: утв. Постановлением М-ва здравоохранения Респ. Беларусь № 60 от 06.07.2018 г. / под ред. О. Г. Суконко, С. А. Красного. – Минск: Профессиональные издания, 2019. – С. 97–110.Алгоритмы диагностики и лечения злокачественных новообразований : клинический протокол : утв. Постановлением М-ва здравоохранения Респ. Беларусь № 60 от 06.07.2018 г. / под ред. О. Г. Суконко, С. А. Красного. – Минск : Профессиональные издания, 2019. – С. 97–110.Schoenfeld D. Partial residuals for the proportional hazards regression model //Biometrika. – 1982. – Т. 69. – №. 1. – С. 239-241.Heagerty, P. J. Time‐dependent ROC curves for censored survival data and a diagnostic marker / P. J. Heagerty, T. Lumley, M. S. Pepe // Biometrics. – 2000. – Vol. 56, no. 2. – Р. 337–344.Harrell F. E. et al. Regression modeling strategies: with applications to linear models, logistic regression, and survival analysis. – New York : Springer, 2001. – Т. 608.Harrell, F. E. Regression Modeling Strategies: With Applications to Linear Models, Logistic Regression, and Survival Analysis / F. E. Harrell. – N. Y. : Springer, 2001. – 600 р.Heagerty P. J., Lumley T., Pepe M. S. Time‐dependent ROC curves for censored survival data and a diagnostic marker //Biometrics. – 2000. – Т. 56. – №. 2. – С. 337-344.Steyerberg, E. W. Clinical Prediction Models: A Practical Approach to Development, Validation, and Updating / E. W. Steyerberg. – Springer, 2009. – 528 р.Steyerberg E. W. A practical approach to development, validation, and updating //Clinical Prediction Models. – 2009.Vickers, A. J. Decision curve analysis: a novel method for evaluating prediction models / A. J. Vickers, E. B. Elkin // Medical Decision Making. – 2006. – Vol. 26, no. 6. – Р. 565–574.Vickers A. J., Elkin E. B. Decision curve analysis: a novel method for evaluating prediction models //Medical Decision Making. – 2006. – Т. 26. – №. 6. – С. 565-574.Vickers, A. J. Net benefit approaches to the evaluation of prediction models, molecular markers, and diagnostic tests [Electronic resource] / A. J. Vickers, B. Van Calster, E. W. Steyerberg // BMJ. – 2016. – Vol. 352. – Mode of access: https://www.bmj.com/content/bmj/352/bmj.i6.full.pdf. – Date of access: 12.09.2023.Vickers A. J., Van Calster B., Steyerberg E. W. Net benefit approaches to the evaluation of prediction models, molecular markers, and diagnostic tests //bmj. – 2016. – Т. 352.Extensions to decision curve analysis, a novel method for evaluating diagnostic tests, prediction models and molecular markers / A. J. Vickers [et al.] // BMC Medical Informatics and Decision Making. – 2008. – Vol. 8. – Р. 1–17.Vickers A. J. et al. Extensions to decision curve analysis, a novel method for evaluating diagnostic tests, prediction models and molecular markers //BMC medical informatics and decision making. – 2008. – Т. 8. – С. 1-17.

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