scholarly journals 430 Machine learning models to predict survival outcomes after radical hysterectomy according to surgical approach in patients with FIGO stage IB cervical cancer

2020 ◽  
Author(s):  
S Kim ◽  
C Choi ◽  
M Lee ◽  
DH Suh ◽  
J Kim ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cervical Cancer ◽  
Surgical Approach ◽  
Radical Hysterectomy ◽  
Figo Stage ◽  
Survival Outcomes ◽  
Learning Models ◽  
Stage Ib ◽  
Machine Learning Models

scholarly journals Machine Learning Models to Predict Survival Outcomes According to the Surgical Approach of Primary Radical Hysterectomy in Patients with Early Cervical Cancer

Cancers ◽  
2021 ◽  
Vol 13 (15) ◽  
pp. 3709
Author(s):  
Se Ik Kim ◽  
Sungyoung Lee ◽  
Chel Hun Choi ◽  
Maria Lee ◽  
Dong Hoon Suh ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cervical Cancer ◽  
Logistic Regression ◽  
Surgical Approach ◽  
Radical Hysterectomy ◽  
Predictive Performance ◽  
Survival Outcomes ◽  
Learning Models ◽  
Early Cervical Cancer ◽  
Machine Learning Models

We purposed to develop machine learning models predicting survival outcomes according to the surgical approach for radical hysterectomy (RH) in early cervical cancer. In total, 1056 patients with 2009 FIGO stage IB cervical cancer who underwent primary type C RH by either open or laparoscopic surgery were included in this multicenter retrospective study. The whole dataset consisting of patients’ clinicopathologic data was split into training and test sets with a 4:1 ratio. Using the training set, we developed models predicting the probability of 5-year progression-free survival (PFS) and overall survival (OS) with tenfold cross validation. The developed models were validated in the test set. In terms of predictive performance, we measured the area under the receiver operating characteristic curve (AUC) values. The logistic regression models comprised of preoperative variables yielded AUCs of 0.679 and 0.715 for predicting 5-year PFS and OS rates, respectively. Combining both logistic regression and multiple machine learning models, we constructed hybrid ensemble models, and these models showed much improved predictive performance, with 0.741 and 0.759 AUCs for predicting 5-year PFS and OS rates, respectively. We successfully developed models predicting disease recurrence and mortality after primary RH in patients with early cervical cancer. As the predicted value is calculated based on the preoperative factors, such as the surgical approach, these ensemble models would be useful for making decisions when choosing between open or laparoscopic RH.

scholarly journals Survival impact of additional chemotherapy after adjuvant concurrent chemoradiation in patients with early cervical cancer who underwent radical hysterectomy

BMC Cancer ◽  
2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Se Ik Kim ◽  
Jeong Yun Kim ◽  
Chan Woo Wee ◽  
Maria Lee ◽  
Hee Seung Kim ◽  
...  
Keyword(s):  
Cervical Cancer ◽  
Radical Hysterectomy ◽  
Figo Stage ◽  
Concurrent Chemoradiation ◽  
Survival Outcomes ◽  
Control Group ◽  
Study Group ◽  
Additional Chemotherapy ◽  
Risk Patients ◽  
Early Cervical Cancer

Abstract Background To determine whether additional chemotherapy after concurrent chemoradiation (CCRT) improves survival outcomes in patients with early cervical cancer who undergo radical hysterectomy (RH). Methods We included high- or intermediate-risk patients from two institutions, with 2009 FIGO stage IB–IIA, who underwent primary RH and pelvic lymphadenectomy between January 2007 and June 2020, and had completed adjuvant CCRT. Survival outcomes were compared between patients who received additional chemotherapy (study group) and those who did not (control group). Results A total of 198 patients were included in this analysis. The study (n = 61) and control groups (n = 137) had similar patient age, histologic cancer type, 2009 FIGO stage, and tumor size. However, minimally invasive surgery was performed less frequently in the study group than in the control group (19.7% vs. 46.0%, P < 0.001). The presence of pathologic risk factors was similar, except for lymph node metastasis, which was more frequent in the study group (72.1% vs. 46.0%; P = 0.001). In survival analyses, no differences in the disease-free survival (DFS; P = 0.539) and overall survival (OS; P = 0.121) were observed between the groups. Multivariate analyses adjusting for surgical approach and other factors revealed that additional chemotherapy was not associated with DFS (adjusted HR, 1.149; 95% CI, 0.552–2.391; P = 0.710) and OS (adjusted HR, 1.877; 95% CI, 0.621–5.673; P = 0.264). The recurrence patterns did not differ with additional chemotherapy. Consistent results were observed in a subset of high-risk patients (n = 139). Conclusions Additional chemotherapy after CCRT might not improve survival outcomes in patients with early cervical cancer who undergo RH.

Preoperative nomogram for prediction of microscopic parametrial infiltration in patients with FIGO stage IB cervical cancer treated with radical hysterectomy

2016 ◽  
Vol 142 (1) ◽  
pp. 109-114 ◽  
Author(s):  
Tae-Wook Kong ◽  
Jayoun Kim ◽  
Joo-Hyuk Son ◽  
Seong Woo Kang ◽  
Jiheum Paek ◽  
...  
Keyword(s):  
Cervical Cancer ◽  
Radical Hysterectomy ◽  
Figo Stage ◽  
Stage Ib

Comparison of Laparoscopic Versus Abdominal Radical Hysterectomy for FIGO Stage IB and IIA Cervical Cancer With Tumor Diameter of 3 cm or Greater

2014 ◽  
Vol 24 (2) ◽  
pp. 280-288 ◽  
Author(s):  
Tae Wook Kong ◽  
Suk-Joon Chang ◽  
Jisun Lee ◽  
Jiheum Paek ◽  
Hee-Sug Ryu
Keyword(s):  
Cervical Cancer ◽  
Radical Hysterectomy ◽  
Operating Time ◽  
Figo Stage ◽  
Tumor Diameter ◽  
Pelvic Magnetic Resonance Imaging ◽  
Laparoscopic Radical Hysterectomy ◽  
Stage Ib ◽  
Estimated Blood Loss ◽  
The Mean

ObjectiveThere have been many comparative reports on laparoscopic radical hysterectomy (LRH) versus abdominal radical hysterectomy (ARH) for early-stage cervical cancer. However, most of these studies included patients with International Federation of Gynecology and Obstetrics (FIGO) stage IA2 and small (tumor diameter ≤2 or 3 cm) IB1 disease. The purpose of this study was to compare the feasibility, morbidity, and recurrence rate of LRH and ARH for FIGO stage IB and IIA cervical cancer with tumor diameter of 3 cm or greater.Materials and MethodsWe conducted a retrospective analysis of 88 patients with FIGO stage IB and IIA cervical cancer with tumor diameter of 3 cm or greater. All patients had no evidence of parametrial invasion and lymph node metastasis in preoperative gynecologic examination, pelvic magnetic resonance imaging, and positron emission tomography–computed tomography, and they all underwent LRH or ARH between February 2006 and March 2013.ResultsAmong 88 patients, 40 patients received LRH whereas 48 underwent ARH. The mean estimated blood loss was 588.0 mL for the ARH group compared with 449.1 mL for the LRH group (P< 0.001). The mean operating time was similar in both groups (246.0 minutes in the ARH vs 254.5 minutes in the LRH group,P= 0.589). Return of bowel motility was observed earlier after LRH (1.8 vs 2.2 days,P= 0.042). The mean hospital stay was significantly shorter for the LRH group (14.8 vs 18.0 days,P= 0.044). There were no differences in histopathologic characteristics between the 2 groups. The mean tumor diameter was 44.4 mm in the LRH and 45.3 mm in the ARH group. Disease-free survival rates were 97.9% in the ARH and 97.5% in the LRH group (P= 0.818).ConclusionsLaparoscopic radical hysterectomy might be a feasible therapeutic procedure for the management of FIGO stage IB and IIA cervical cancer with tumor diameter of 3 cm or greater. Further randomized studies that could support this approach are necessary to evaluate long-term clinical outcome.

scholarly journals Comparison of adenocarcinoma and adenosquamous carcinoma prognoses in Chinese patients with FIGO stage IB-IIA cervical cancer following radical surgery

2020 ◽  
Author(s):  
Xiaojing Zhang ◽  
Zunfu Lv ◽  
Xiaoxian Xu ◽  
Zhuomin Yin ◽  
hanmei Lou
Keyword(s):  
Cervical Cancer ◽  
Cox Regression ◽  
Adenosquamous Carcinoma ◽  
Risk Groups ◽  
Figo Stage ◽  
Chinese Patients ◽  
Survival Outcomes ◽  
Intermediate Risk ◽  
Stage Ib ◽  
Risk Patients

Abstract Background: To compare adenocarcinoma (AC) and adenosquamous carcinoma (ASC) prognoses in patients with FIGO stage IB–IIA cervical cancer who underwent radical hysterectomy. Methods. We performed a retrospective analysis of 240 patients with AC and 130 patients with ASC. Kaplan–Meier curves, Cox regression models, and log-rank tests were used for statistical analysis. Results: Patients with ASC had higher frequencies of lymphovascular space invasion (LVSI) and serum squamous cell carcinoma antigen (SCC-Ag) > 5 ng/ml (p=0.049 and p=0.013, respectively); moreover, they were much older (P=0.029) than patients with AC. There were no clinically significant differences in overall survival (OS) between the groups. When stratified into three risk groups based on clinicopathological features, survival outcomes did not differ between patients with AC and those with ASC in any risk group. Multivariate analysis showed that lymph node metastasis (LNM) was an independent risk factor for recurrence-free survival (RFS) and OS in patients with AC and in patients with ASC. Carcinoembryonic antigen (CEA) > 5 ng/ml and SCC-Ag > 5 ng/ml were independent predictors of RFS and OS in patients with AC. In addition, among those stratified as intermediate-risk, patients with ASC who received concurrent chemoradiotherapy (CCRT) had significantly better RFS and OS (P=0.036 and P=0.047, respectively). Conclusions: We did not find evidence to suggest that AC and ASC subtypes of cervical cancer were associated with different survival outcomes. CCRT is beneficial for survival in intermediate-risk patients with ASC, but not in those with AC. Serum tumour markers can assist in evaluating prognosis and in providing additional information for patient-tailored therapy for cervical AC.

Sign in / Sign up

Export Citation Format

Share Document