Prediction model for rectal cancer treatment complications

Aim: to develop a model for predicting the risk of developing complications of rectal cancer treatment.

Material and Methods. A single-centre retrospective study included 302 patients diagnosed with rectal cancer, who were treated in 2017–2018 at the Yaroslavl Regional Clinical Oncology Hospital (YRCOH).

Inclusion criteria were: histologically verified rectal cancer and curative-intent radical surgery. The primary endpoint of the study was to identify factors influencing the development of complications. A binary logistic regression method was used to construct the model. The initial set of parameters for the model included the tumor differentiation grade (based on the primary biopsy), distance from the distal edge of the tumor to the dentate line, history of varicose veins of the lower extremities, diabetes mellitus, obesity, and the Charlson Comorbidity index. Seventy four rectal cancer patients treated in the YRCOH in 2019–2022 were studied as a test sample

Results. The resulting equation for the probability of developing complications of rectal cancer treatment was: р=1/(1 + e^-y), where р is the probability of developing complications of rectal cancer treatment, y=0.52-0.54x₁ - 0.1x₂ + 2.3x₃ + 3.4x₄ , where x₁ is the tumor differentiation grade (from primary biopsy), x₂ is the distance from the distal edge of the tumor to the dentate line, x₃ is a history of general obesity, x₄ is a history of diabetes mellitus. The quality of the model turned out to be acceptable (p (Hosmer-Lemeshev)=0.68; pseudo-R² Nagelkerke=0.53). At р>0.5, a conclusion was made about the high probability of developing cancer treatment complications. The prediction model was validated on a test sample of 74 patients. Thus, the sensitivity of the model was 82.35 % (95 % CI 73.2–94.9), the specificity was 97.50 % (95 % CI 82.2–99.9). The accuracy of the prognostic model was 89.33 % (95 % CI 80,0–99,5).

Conclusion. The model for predicting complicated follow-up in patients with rectal cancer will physicians to determine the likelihood of adverse events and take effective preventive measures.

1. Sung H., Ferlay J., Siegel R.L., Laversanne M., Soerjomataram I., Jemal A., Bray F. Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. CA Cancer J Clin. 2021; 71(3): 209–49. doi: 10.3322/caac.21660.

2. Kostin A.A., Krashenkov O.P., Konovalov O.E., Ivanikov I.O. Follow-up of patients from the third clinical group after treatment of colorectal neoplasia. Кremlin Medicine Journal. 2022; (3): 65–68. (in Russian). doi: 10.26269/9m4dbm84. EDN: FRAOGL.

3. Aliev I.I., Smirnov A.A., Pavlov R.V., Komyak K.N., Ivlev D.A., Domanskiy N.A., Sharygin G.A., Nazmiev A.I. Complications from the formation of preventive stomas in the surgical treatment of rectal cancer. Siberian Journal of Oncology. 2023; 22(2): 112–19. (in Russian). doi: 10.21294/1814-4861-2023-22-2-112-119. EDN: ACQJTV.

4. Kostin A.A., Ryabov M.M., Konovalov O.E., Shulaev A.V. Complications in surgical treatment of rectal cancer as a clinical-organizational and medical-social problem (literature review). The Bulletin of Contemporary Clinical Medicine. 2024; 17(3): 59–66. (in Russian). doi: 10.20969/VSKM.2024.17(3).59-66. EDN: JMWVQA.

5. Larichev A.B., Efremov K.N., Kuzmin V.S., Chetverov M.G., Izumov N.M. The quintessence of perineal wound healing after abdoperine-perinal extirpation of the rectum. Infections in surgery. 2023; 21(1): 47–53. (in Russian). EDN: DTGLBP.

6. Stukalova O.Yu., Ishchenko R.V., Polikarpov A.A., Farmonkulova A.I. Main aspects of personalized approach to the treatment of patients with chemotherapy resistant metastatic colorectal cancer. South Russian Journal of Cancer. 2024; 5(4): 29–37. (in Russian). doi: 10.37748/2686-9039-2024-5-4-4. EDN: CFOLDG.

7. Kochkina S.O., Gordeyev S.S., Petrov K.S., Mammedli Z.Z. Combined treatment of operable rectal cancer with negative prognosis factors: a prospective study. Siberian Journal of Oncology. 2021; 20(4): 49–56. (in Russian). doi: 10.21294/1814-4861-2021-20-4-49-56. EDN: ZZGVHZ.

8. Ryabov M.M. Complications of antitumor treatment of rectal cancer: structural features and prerequisites for development. Koloproktologia. 2025; 24(2): 112–20. (in Russian). doi: 10.33878/2073-7556-2025-24-2-112-120. EDN: RXEHZA.

9. Riley R.D., Archer L., Snell K.I.E., Ensor J., Dhiman P., Martin G.P., Bonnett L.J., Collins G.S. Evaluation of clinical prediction models (part 2): how to undertake an external validation study. BMJ. 2024; 384: e074820. doi: 10.1136/bmj-2023-074820.

10. Luchinin A.S. Prognostic Models in Medicine. Clinical Oncohematology. 2023; 16(1): 27–36. (in Russian). doi: 10.21320/2500-2139-2023-16-1-27-36. EDN: UZEQZU.

11. Suvorov V.A., Panin S.I., Kovalenko N.V., Zhavoronkova V.V., Postolov M.P., Tolstopyatov S.E., Panina A.A., Suleymanov Sh.R., Vezirov E.Sh., Peshkurova I.A. Comorbidity in predicting surgical outcomes for gastric cancer. Siberian Journal of Oncology. 2023; 22(4): 5–13. (in Russian). doi: 10.21294/1814-4861-2023-22-4-5-13. EDN: JRSYTS.

12. Reitter E.M., Kaider A., Ay C., Quehenberger P., Marosi C., Zielinski C., Pabinger I. Longitudinal analysis of hemostasis biomarkers in cancer patients during antitumor treatment. J Thromb Haemost. 2016; 14(2): 294–305. doi: 10.1111/jth.13218.

13. Penzin O.V., Shvyrev S.L., Zarubina T.V. Results of implementation in the clinical practice the prognostic model for assessing the risk development of mielotoxic complications of chemotherapy. Journal of New Medical Technologies. 2019; 26(1): 112–18. (in Russian). doi: 10.24411/1609-2163-2019-16061. EDN: ZALHUT.