Machine learning radiomics can predict early liver recurrence after resection of intrahepatic cholangiocarcinoma.
Ontology highlight
ABSTRACT: Background
Most patients recur after resection of intrahepatic cholangiocarcinoma (IHC). We studied whether machine-learning incorporating radiomics and tumor size could predict intrahepatic recurrence within 1-year.Methods
This was a retrospective analysis of patients with IHC resected between 2000 and 2017 who had evaluable computed tomography imaging. Texture features (TFs) were extracted from the liver, tumor, and future liver remnant (FLR). Random forest classification using training (70.3%) and validation cohorts (29.7%) was used to design a predictive model.Results
138 patients were included for analysis. Patients with early recurrence had a larger tumor size (7.25 cm [IQR 5.2-8.9] vs. 5.3 cm [IQR 4.0-7.2], P = 0.011) and a higher rate of lymph node metastasis (28.6% vs. 11.6%, P = 0.041), but were not more likely to have multifocal disease (21.4% vs. 17.4%, P = 0.643). Three TFs from the tumor, FD1, FD30, and IH4 and one from the FLR, ACM15, were identified by feature selection. Incorporation of TFs and tumor size achieved the highest AUC of 0.84 (95% CI 0.73-0.95) in predicting recurrence in the validation cohort.Conclusion
This study demonstrates that radiomics and machine-learning can reliably predict patients at risk for early intrahepatic recurrence with good discrimination accuracy.
SUBMITTER: Jolissaint JS
PROVIDER: S-EPMC9355916 | biostudies-literature | 2022 Aug
REPOSITORIES: biostudies-literature
Publications
Machine learning radiomics can predict early liver recurrence after resection of intrahepatic cholangiocarcinoma.
Jolissaint Joshua S JS Wang Tiegong T Soares Kevin C KC Chou Joanne F JF Gönen Mithat M Pak Linda M LM Boerner Thomas T Do Richard K G RKG Balachandran Vinod P VP D'Angelica Michael I MI Drebin Jeffrey A JA Kingham T P TP Wei Alice C AC Jarnagin William R WR Chakraborty Jayasree J
HPB : the official journal of the International Hepato Pancreato Biliary Association 20220217 8
<h4>Background</h4>Most patients recur after resection of intrahepatic cholangiocarcinoma (IHC). We studied whether machine-learning incorporating radiomics and tumor size could predict intrahepatic recurrence within 1-year.<h4>Methods</h4>This was a retrospective analysis of patients with IHC resected between 2000 and 2017 who had evaluable computed tomography imaging. Texture features (TFs) were extracted from the liver, tumor, and future liver remnant (FLR). Random forest classification using ...[more]
Similar Datasets
Project description:The prediction of early recurrent of intrahepatic cholangiocarcinoma (ICC) has been widely investigated; however, the predictive value is currently insufficient. To determine the effectiveness of machine learning (ML) for the diagnosis of early recurrent intrahepatic cholangiocarcinoma (ICC), particularly in comparison with clinical models, the present study aimed to determine which ML model had the best diagnostic performance for inpatients with recurrent ICC. In order to search for studies which could be included, three electronic databases were screened from inception to November 2023. A pairwise meta-analysis was performed to evaluate the diagnostic accuracy of the random effects model. A network meta-analysis was performed to identify the most effective ML-based diagnostic model based on the surface under the cumulative ranking curve score. A total of 5 studies of acceptable quality containing 1,247 patients with ICC were included in the present study. Following pairwise meta-analysis, it was found that the ML-based diagnostic accuracy was greater than that of clinical models (surface under the cumulative ranking curve score closer to 1, with significant differences), which initially proved that the ML-based diagnostic power was more optimal than that of clinical models. According to the network meta-analysis, the nomogram performed the best, indicating that this ML model achieved the best diagnostic accuracy for patients with recurrent ICC. In conclusion, the application of ML-based diagnostic models for patients with recurrent ICC was more optimal than the application of the clinical model. The nomogram model ranked first among the models and is therefore recommended for patients with recurrent ICC.
| S-EPMC11222917 | biostudies-literature
Project description:ImportanceAlthough surgery offers the best chance of a potential cure for patients with localized, resectable intrahepatic cholangiocarcinoma (ICC), prognosis of patients remains dismal largely because of a high incidence of recurrence.ObjectiveTo predict very early recurrence (VER) (ie, recurrence within 6 months after surgery) following resection for ICC in the pre- and postoperative setting.Design, setting, and participantsPatients who underwent curative-intent resection for ICC between May 1990 and July 2016 were identified from an international multi-institutional database. The study was conducted at The Ohio State University in collaboration with all other participating institutions. The data were analyzed in December 2019.Main outcomes and measuresTwo logistic regression models were constructed to predict VER based on pre- and postoperative variables. The final models were used to develop an online calculator to predict VER and the tool was internally and externally validated.ResultsAmong 880 patients (median age, 59 years [interquartile range, 51-68 years]; 388 women [44.1%]; 428 [50.2%] white; 377 [44.3%] Asian; 27 [3.2%] black]), 196 (22.3%) developed VER. The 5-year overall survival among patients with and without VER was 8.9% vs 49.8%, respectively (P < .001). A preoperative model was able to stratify patients relative to the risk for VER: low risk (6-month recurrence-free survival [RFS], 87.7%), intermediate risk (6-month RFS, 72.3%), and high risk (6-month RFS, 49.5%) (log-rank P < .001). The postoperative model similarly identified discrete cohorts of patients based on probability for VER: low risk (6-month RFS, 90.0%), intermediate risk (6-month RFS, 73.1%), and high risk (6-month RFS, 48.5%) (log-rank, P < .001). The calibration and predictive accuracy of the pre- and postoperative models were good in the training (C index: preoperative, 0.710; postoperative, 0.722) as well as the internal (C index: preoperative, 0.715; postoperative, 0.728; bootstrapping resamples, n = 5000) and external (C index: postoperative, 0.672) validation data sets.Conclusion and relevanceAn easy-to-use online calculator was developed to help clinicians predict the chance of VER after curative-intent resection for ICC. The tool performed well on internal and external validation. This tool may help clinicians in the preoperative selection of patients for neoadjuvant therapy as well as during the postoperative period to inform surveillance strategies.
| S-EPMC7344787 | biostudies-literature
Project description:To investigate the ability of CT-based radiomics signature for pre-and postoperatively predicting the early recurrence of intrahepatic mass-forming cholangiocarcinoma (IMCC) and develop radiomics-based prediction models. Institutional review board approved this study. Clinicopathological characteristics, contrast-enhanced CT images, and radiomics features of 125 IMCC patients (35 with early recurrence and 90 with non-early recurrence) were retrospectively reviewed. In the training set of 92 patients, preoperative model, pathological model, and combined model were developed by multivariate logistic regression analysis to predict the early recurrence (≤ 6 months) of IMCC, and the prediction performance of different models were compared using the Delong test. The developed models were validated by assessing their prediction performance in test set of 33 patients. Multivariate logistic regression analysis identified solitary, differentiation, energy- arterial phase (AP), inertia-AP, and percentile50th-portal venous phase (PV) to construct combined model for predicting early recurrence of IMCC [the area under the curve (AUC) = 0.917; 95% CI 0.840-0.965]. While the AUC of pathological model and preoperative model were 0.741 (95% CI 0.637-0.828) and 0.844 (95% CI 0.751-0.912), respectively. The AUC of the combined model was significantly higher than that of the preoperative model (p = 0.049) or pathological model (p = 0.002) in training set. In test set, the combined model also showed higher prediction performance. CT-based radiomics signature is a powerful predictor for early recurrence of IMCC. Preoperative model (constructed with homogeneity-AP and standard deviation-AP) and combined model (constructed with solitary, differentiation, energy-AP, inertia-AP, and percentile50th-PV) can improve the accuracy for pre-and postoperatively predicting the early recurrence of IMCC.
| S-EPMC8443588 | biostudies-literature
Project description:BackgroundAccurate prognosis assessment is essential for surgically resected intrahepatic cholangiocarcinoma (ICC) while published prognostic tools are limited by modest performance. We therefore aimed to establish a novel model to predict survival in resected ICC based on readily-available clinical parameters using machine learning technique.MethodsA gradient boosting machine (GBM) was trained and validated to predict the likelihood of cancer-specific survival (CSS) on data from a Chinese hospital-based database using nested cross-validation, and then tested on the Surveillance, Epidemiology, and End Results (SEER) database. The performance of GBM model was compared with that of proposed prognostic score and staging system.ResultsA total of 1050 ICC patients (401 from China and 649 from SEER) treated with resection were included. Seven covariates were identified and entered into the GBM model: age, tumor size, tumor number, vascular invasion, number of regional lymph node metastasis, histological grade, and type of surgery. The GBM model predicted CSS with C-Statistics ≥ 0.72 and outperformed proposed prognostic score or system across study cohorts, even in sub-cohort with missing data. Calibration plots of predicted probabilities against observed survival rates indicated excellent concordance. Decision curve analysis demonstrated that the model had high clinical utility. The GBM model was able to stratify 5-year CSS ranging from over 54% in low-risk subset to 0% in high-risk subset.ConclusionsWe trained and validated a GBM model that allows a more accurate estimation of patient survival after resection compared with other prognostic indices. Such a model is readily integrated into a decision-support electronic health record system, and may improve therapeutic strategies for patients with resected ICC.
| S-EPMC8915487 | biostudies-literature
Project description:IntroductionBenchmarking in surgery has been proposed as a means to compare results across institutions to establish best practices. We sought to define benchmark values for hepatectomy for intrahepatic cholangiocarcinoma (ICC) across an international population.MethodsPatients who underwent liver resection for ICC between 1990 and 2020 were identified from an international database, including 14 Eastern and Western institutions. Patients operated on at high-volume centers who had no preoperative jaundice, ASA class <3, body mass index <35 km/m2, without need for bile duct or vascular resection were chosen as the benchmark group.ResultsAmong 1193 patients who underwent curative-intent hepatectomy for ICC, 600 (50.3%) were included in the benchmark group. Among benchmark patients, median age was 58.0 years (interquartile range [IQR] 49.0-67.0), only 28 (4.7%) patients received neoadjuvant therapy, and most patients had a minor resection (n = 499, 83.2%). Benchmark values included ≥3 lymph nodes retrieved when lymphadenectomy was performed, blood loss ≤600 mL, perioperative blood transfusion rate ≤42.9%, and operative time ≤339 min. The postoperative benchmark values included TOO achievement ≥59.3%, positive resection margin ≤27.5%, 30-day readmission ≤3.6%, Clavien-Dindo III or more complications ≤14.3%, and 90-day mortality ≤4.8%, as well as hospital stay ≤14 days.ConclusionsBenchmark cutoffs targeting short-term perioperative outcomes can help to facilitate comparisons across hospitals performing liver resection for ICC, assess inter-institutional variation, and identify the highest-performing centers to improve surgical and oncologic outcomes.
| S-EPMC10997542 | biostudies-literature
Project description:PurposeTo predict the tertiary lymphoid structures (TLSs) status and recurrence-free survival (RFS) of intrahepatic cholangiocarcinoma (ICC) patients using preoperative CT radiomics.Patients and methodsA total of 116 ICC patients were included (training: 86; external validation: 30). The enhanced CT images were performed for the radiomics model. The logistic regression analysis was applied for the clinical model. The combined model was based on the clinical and radiomics models.ResultsA total of 107 radiomics features were extracted, and after being eliminated and selected, six features were combined to establish a radiomics model for TLSs prediction. Arterial phase diffuse hyperenhancement and AJCC 8th stage were combined to construct a clinical model. The combined (radiomics nomogram) model outperformed both the independent radiomics model and clinical model in the training cohort (AUC, 0.85 vs. 0.82 and 0.75, respectively) and was validated in the external validation cohort (AUC, 0.88 vs. 0.86 and 0.71, respectively). Patients in the rad-score no less than -0.76 (low-risk) group showed significantly better RFS than those in the less than -0.76 (high-risk) group (p < 0.001, C-index = 0.678). Patients in the nomogram score no less than -1.16 (low-risk) group showed significantly better RFS than those of the less than -1.16 (high-risk) group (p < 0.001, C-index = 0.723).ConclusionsCT radiomics nomogram could serve as a preoperative biomarker of intra-tumoral TLSs status, better than independent radiomics or clinical models; preoperative CT radiomics nomogram achieved accurate stratification for RFS of ICC patients, better than the postoperative pathologic TLSs status.Critical relevance statementThe radiomics nomogram showed better performance in predicting TLSs than independent radiomics or clinical models and better prognosis stratification than postoperative pathologic TLSs status in ICC patients, which may facilitate identifying patients benefiting most from surgery and subsequent immunotherapy.Key points• The combined (radiomics nomogram) model consisted of the radiomics model and clinical model (arterial phase diffuse hyperenhancement and AJCC 8th stage). • The radiomics nomogram showed better performance in predicting TLSs than independent radiomics or clinical models in ICC patients. • Preoperative CT radiomics nomogram achieved more accurate stratification for RFS of ICC patients than the postoperative pathologic TLSs status.
| S-EPMC10577112 | biostudies-literature
Project description:ObjectiveTo predict the very early recurrence (VER) of patients with intrahepatic cholangiocarcinoma (ICC) based on TLSs and MVI status, and further perform prognosis stratifications.MethodsA total of 160, 51 ICC patients from two institutions between May 2012 and July 2022 were retrospectively included as training, external validation cohort. Clinical, radiological and pathological variables were evaluated and collected. Univariate and multivariate analysis were applied to select the significant factors related to VER of ICC. The factors selected were combined to perform stratification of overall survival (OS) using the Kaplan-Meier method with the log-rank test.ResultsOverall, 39 patients (24.4%) had VER, whereas 121 (75.6%) did not (non-VER group). In the training cohort, the median OS was 40.5 months (95% CIs: 33.2-47.7 months). The VER group showed significantly worse OS than the non-VER group (median OS: 14.8, 95% CI:11.6-18.0 months vs. 53.4, 34.3-72.6 months; p<0.001), and it was confirmed in the validation cohort (median OS: 22.1, 95% CI: 8.8-35.4 months vs. 40.1, 21.2-59.0 months; p = 0.003). According to the univariate analysis, four variables were significantly different between the VER group and non-VER group (TLSs status, p = 0.028; differentiation, p = 0.023; MVI status, p = 0.012; diameter, p = 0.028). According to the multivariate analysis, MVI-positive status was independently associated with a higher probability of VER (odds ratio [OR], 2.5; 95% CIs,1.16-5.18; p = 0.018), whereas intra-tumoral TLSs-positive status was associated with lower odds of VER (OR, 0.43; 95% CIs, 0.19-0.97; p = 0.041). Based on the TLSs and MVI status, patients of ICC were categorized into four groups: TLSs-positive and MVI-negative (TP/MN); TLSs-negative and MVI-negative (TN/MN); TLSs-positive and MVI-positive (TP/MP), TLSs-negative and MVI-positive groups (TN/MP). In the training cohort, the four groups could be correlated with OS significantly (p<0.001), and it was confirmed in the validation cohort (p<0.001).ConclusionIntra-tumoral TLSs and MVI status are independent predictive factors of VER after surgery, based on which immunovascular stratifications are constructed and associated with OS significantly of resectable intrahepatic cholangiocarcinoma.
| S-EPMC10588260 | biostudies-literature
Project description:BackgroundThe incidence of stage pN3b gastric cancer (GC) is low, and the clinical prognosis is poor, with a high rate of postoperative recurrence. Machine learning (ML) methods can predict the recurrence of GC after surgery. However, the prognostic significance for pN3b remains unclear. Therefore, we aimed to predict the recurrence of pN3b through ML models.MethodsThis retrospective study included 336 patients with pN3b GC who underwent radical surgery. A 3-fold cross-validation was used to partition the participants into training and test cohorts. Linear combinations of new variable features were constructed using principal component analysis (PCA). Various ML algorithms, including random forest, support vector machine (SVM), logistic regression, multilayer perceptron (MLP), extreme gradient boosting (XGBoost), and Gaussian naive Bayes (GNB), were utilized to establish a recurrence prediction model. Model performance was evaluated using the receiver operating characteristic (ROC) curve and the area under the curve (AUC). Python was used for the analysis of ML algorithms.ResultsNine principal components with a cumulative variance interpretation rate of 90.71% were identified. The output results of the test set showed that random forests had the highest AUC (0.927) for predicting overall recurrence with an accuracy rate of 80.5%. Random forests had the highest AUC (0.940) for predicting regional recurrence with an accuracy of 89.7%. For predicting distant recurrence, random forests had the highest AUC (0.896) with an accuracy of 84.3%. For peritoneal recurrence, random forests had the highest AUC (0.923) with an accuracy of 83.3%.ConclusionsML can personalize the prediction of postoperative recurrence in patients with GC with stage pN3b.
| S-EPMC11009806 | biostudies-literature
Project description:Background:Liver resection is the only curative therapeutic option for intrahepatic cholangiocarcinoma (ICC), but the approach to recurrent ICC is controversial. This study analysed the outcome of liver resection in patients with recurrent ICC. Methods:Demographic, radiological, clinical, operative, surgical pathological and follow-up data for all patients with a final surgical pathological diagnosis of ICC treated in a tertiary referral centre between 2001 and 2015 were collected retrospectively and analysed. Results:A total of 190 patients had liver resection for primary ICC. The 1-, 3- and 5-year overall survival (OS) rates were 74·8, 56·6 and 37·9 per cent respectively. Independent determinants of OS were age 65 years or above (hazard ratio (HR) 2·18, 95 per cent c.i. 1·18 to 4·0; P = 0·012), median tumour diameter 5 cm or greater (HR 2·87, 1·37 to 6·00; P = 0·005), preoperative biliary drainage (HR 2·65, 1·13 to 6·20; P = 0·025) and local R1-2 status (HR 1·90, 1·02 to 3·53; P = 0·043). Recurrence was documented in 87 patients (45·8 per cent). The mean(s.d.) survival time after recurrence was 16(17) months. Independent determinants of recurrence were median tumour diameter 5 cm or more (HR 1·71, 1·09 to 2·68; P = 0·020), high-grade (G3-4) tumour (HR 1·63, 1·04 to 2·55; P = 0·034) and local R1 status (HR 1·70, 1·09 to 2·65; P = 0·020). Repeat resection with curative intent was performed in 25 patients for recurrent ICC, achieving a mean survival of 25 (95 per cent c.i. 16 to 34) months after the diagnosis of recurrence. Patients deemed to have unresectable disease after recurrence received chemotherapy or chemoradiotherapy alone, and had significantly poorer survival. Conclusion:Patients with recurrent ICC may benefit from repeat surgical resection.
| S-EPMC6887914 | biostudies-literature
Project description:BackgroundEarly cancer recurrence after oesophagectomy is a common problem, with an incidence of 20-30 per cent despite the widespread use of neoadjuvant treatment. Quantification of this risk is difficult and existing models perform poorly. This study aimed to develop a predictive model for early recurrence after surgery for oesophageal adenocarcinoma using a large multinational cohort and machine learning approaches.MethodsConsecutive patients who underwent oesophagectomy for adenocarcinoma and had neoadjuvant treatment in one Dutch and six UK oesophagogastric units were analysed. Using clinical characteristics and postoperative histopathology, models were generated using elastic net regression (ELR) and the machine learning methods random forest (RF) and extreme gradient boosting (XGB). Finally, a combined (ensemble) model of these was generated. The relative importance of factors to outcome was calculated as a percentage contribution to the model.ResultsA total of 812 patients were included. The recurrence rate at less than 1 year was 29·1 per cent. All of the models demonstrated good discrimination. Internally validated areas under the receiver operating characteristic (ROC) curve (AUCs) were similar, with the ensemble model performing best (AUC 0·791 for ELR, 0·801 for RF, 0·804 for XGB, 0·805 for ensemble). Performance was similar when internal-external validation was used (validation across sites, AUC 0·804 for ensemble). In the final model, the most important variables were number of positive lymph nodes (25·7 per cent) and lymphovascular invasion (16·9 per cent).ConclusionThe model derived using machine learning approaches and an international data set provided excellent performance in quantifying the risk of early recurrence after surgery, and will be useful in prognostication for clinicians and patients.
| S-EPMC7299663 | biostudies-literature