Risk Stratification of Early-Stage Cervical Cancer with Intermediate-Risk Factors: Model Development and Validation Based on Machine Learning Algorithm

Abstract

Background. Adjuvant therapy for cervical cancer (CC) patients with intermediate-risk factors remains controversial. The objectives of the present study are to assess the prognoses of early-stage CC patients with pathological intermediate-risk factors and to provide a reference for adjuvant therapy choice. Materials and Methods. This retrospective study included 481 patients with stage IB-IIA CC. Cox proportional hazards regression analysis, machine learning (ML) algorithms, Kaplan-Meier analysis and the area under the receiver operating characteristic curve (AUC) were used to develop and validate prediction models for disease-free survival (DFS) and overall survival (OS). Results. A total of 35 (7.3%) patients experienced recurrence, and 20 (4.2%) patients died. Two prediction models were built for DFS and OS using clinical information, including age, lymphovascular space invasion, stromal invasion, tumor size, and adjuvant treatment. Patients were divided into high-risk or low-risk groups according to the risk score cutoff value. Kaplan-Meier analysis showed significant differences in DFS (p=0.001) and OS (p=0.011) between the two risk groups. In the traditional Sedlis criteria groups, there were no significant differences in DFS or OS (p >0.05). In the ML-based validation, the best AUCs of DFS at 2 and 5 years were 0.69/0.69, and the best AUCs of OS at 2 and 5 years were 0.88/0.63. Conclusion.Two prognostic assessment models were successfully established, and risk grouping stratified the prognostic risk of CC patients with pathological intermediaterisk factors. Evaluation of long-term survival will be needed to corroborate these findings. The Oncologist 2021;9999:• • Implications for Practice: The Sedlis criteria are intermediate-risk factors used to guide postoperative adjuvant treatment in patients with cervical cancer. However, for patients meeting the Sedlis criteria, the choice of adjuvant therapy remains controversial. Our study developed two prognostic models based on pathological intermediate-risk factors. According to the risk score obtained by the prediction model, patients can be further divided into groups with high or low risk of recurrence and death. The prognostic models developed in this study can be used in clinical practice to stratify prognostic risk and provide more individualized adjuvant therapy choices to early-stage cervical cancer patients.

A 5‐year survival status prognosis of nonmetastatic cervical cancer patients through machine learning algorithms

“…On the contrary, based on the traditional Sedlis criteria 38 as the risk classification system, no significant difference in OS was observed within the cohort. 39 Promising results incorporating ML algorithms with gene expression, molecular subtyping, and pharmacogenomics in CC patients were also reported recently. 40 , 41 , 42 …”

Retrospective analysis of prognosis using the Gynecology Oncology Group score of stage IB‑IIA node negative uterine cervical cancer after radical hysterectomy and trachelectomy

“…They emphasized that LVSI was the only independent prognostic factor. On the contrary, when the criteria were examined in more detail, Chu et al ( 15 ) reported on the validation of risk stratification using a machine learning algorithm in addition to the Sedlis criteria. This risk stratification consisted of age, LVSI, stromal invasion, size and type of adjuvant therapy, and was able to indicate expected OS and disease-free survival (DFS) 2 and 5 years after surgery ( 15 ).…”

“…On the contrary, when the criteria were examined in more detail, Chu et al ( 15 ) reported on the validation of risk stratification using a machine learning algorithm in addition to the Sedlis criteria. This risk stratification consisted of age, LVSI, stromal invasion, size and type of adjuvant therapy, and was able to indicate expected OS and disease-free survival (DFS) 2 and 5 years after surgery ( 15 ). These expected OS and DFS rates were derived based on the time-dependent receiver operating characteristic (ROC) curves and the area under the ROC curve.…”

Prediction of Postoperative Pathologic Risk Factors in Cervical Cancer Patients Treated with Radical Hysterectomy by Machine Learning

“…Another study [ 50 ] in 2020 found that pretreatment albumin to fibrinogen ratio was significantly related to lymph node metastasis, depth of stromal infiltration, etc. Many studies focused on prediction for survival outcomes or a single PRF of cervical cancer based on clinical factors [ 51 , 52 , 53 ] and/or radiomic parameters [ 54 , 55 ]. However, no studies have made an attempt to predict three PRFs based on a series of clinically readily available blood markers.…”