Development and Validation of Nomogram for Predicting Survival of Primary Liver Cancers Using Machine Learning.
Ontology highlight
ABSTRACT: Background and aims
Primary liver cancer (PLC) is a common malignancy with poor survival and requires long-term follow-up. Hence, nomograms need to be established to predict overall survival (OS) and cancer-specific survival (CSS) from different databases for patients with PLC.Methods
Data of PLC patients were downloaded from Surveillance, Epidemiology, and End Results (SEER) and the Cancer Genome Atlas (TCGA) databases. The Kaplan Meier method and log-rank test were used to compare differences in OS and CSS. Independent prognostic factors for patients with PLC were determined by univariate and multivariate Cox regression analyses. Two nomograms were developed based on the result of the multivariable analysis and evaluated by calibration curves and receiver operating characteristic curves.Results
OS and CSS nomograms were based on age, race, TNM stage, primary diagnosis, and pathologic stage. The area under the curve (AUC) was 0.777, 0.769, and 0.772 for 1-, 3- and 5-year OS. The AUC was 0.739, 0.729 and 0.780 for 1-, 3- and 5-year CSS. The performance of the two new models was then evaluated using calibration curves.Conclusions
We systematically reviewed the prognosis of PLC and developed two nomograms. Both nomograms facilitate clinical application and may benefit clinical decision-making.
SUBMITTER: Chen R
PROVIDER: S-EPMC9258303 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundHLA-B27 positivity is normal in patients undergoing rheumatic diseases. The diagnosis of many diseases requires an HLA-B27 examination.MethodsThis study screened totally 1503 patients who underwent HLA-B27 examination, liver/kidney function tests, and complete blood routine examination in First Affiliated Hospital of Guangxi Medical University. The training cohort included 509 cases with HLA-B27 positivity whereas 611 with HLA-B27 negativity. In addition, validation cohort included 147 cases with HLA-B27 positivity whereas 236 with HLA-B27 negativity. In this study, 3 ML approaches, namely, LASSO, support vector machine (SVM) recursive feature elimination and random forest, were adopted for screening feature variables. Subsequently, to acquire the prediction model, the intersection was selected. Finally, differences among 148 cases with HLA-B27 positivity and negativity suffering from ankylosing spondylitis (AS) were investigated.ResultsSix factors, namely red blood cell count, human major compatibility complex, mean platelet volume, albumin/globulin ratio (ALB/GLB), prealbumin, and bicarbonate radical, were chosen with the aim of constructing the diagnostic nomogram using ML methods. For training queue, nomogram curve exhibited the value of area under the curve (AUC) of 0.8254496, and C-value of the model was 0.825. Moreover, nomogram C-value of the validation queue was 0.853, and the AUC value was 0.852675. Furthermore, a significant decrease in the ALB/GLB was noted among cases with HLA-B27 positivity and AS cases.ConclusionTo conclude, the proposed ML model can effectively predict HLA-B27 and help doctors in the diagnosis of various immune diseases.
| S-EPMC10521518 | biostudies-literature
Project description:Purpose This study aims to develop and validate a prediction model for non-operative, epidermal growth factor receptor (EGFR)-positive, locally advanced elderly esophageal cancer (LAEEC). Methods A total of 80 EGFR-positive LAEEC patients were included in the study. All patients underwent radiotherapy, while 41 cases received icotinib concurrent systemic therapy. A nomogram was established using univariable and multivariable Cox analyses. The model’s efficacy was assessed through area under curve (AUC) values, receiver operating characteristic (ROC) curves at different time points, time-dependent AUC (tAUC), calibration curves, and clinical decision curves. Bootstrap resampling and out-of-bag (OOB) cross-validation methods were employed to verify the model’s robustness. Subgroup survival analysis was also conducted. Results Univariable and multivariable Cox analyses revealed that icotinib, stage, and ECOG score were independent prognostic factors for LAEEC patients. The AUCs of model-based prediction scoring (PS) for 1-, 2-, and 3-year overall survival (OS) were 0.852, 0.827, and 0.792, respectively. Calibration curves demonstrated that the predicted mortality was consistent with the actual mortality. The time-dependent AUC of the model exceeded 0.75, and the internal cross-validation calibration curves showed good agreement between predicted and actual mortality. Clinical decision curves indicated that the model had a substantial net clinical benefit within a threshold probability range of 0.2 to 0.8. Model-based risk stratification analysis demonstrated the model’s excellent ability to distinguish survival risk. Further subgroup analyses showed that icotinib significantly improved survival in patients with stage III and ECOG score of 1 (HR 0.122, P<0.001). Conclusions Our nomogram model effectively predicts the overall survival of LAEEC patients, and the benefits of icotinib were found in the clinical stage III population with good ECOG scores.
| S-EPMC10213387 | biostudies-literature
Project description:BackgroundTuberculosis (TB) is a pandemic, being one of the top 10 causes of death and the main cause of death from a single source of infection. Drug-induced liver injury (DILI) is the most common and serious side effect during the treatment of TB.ObjectiveWe aim to predict the status of liver injury in patients with TB at the clinical treatment stage.MethodsWe designed an interpretable prediction model based on the XGBoost algorithm and identified the most robust and meaningful predictors of the risk of TB-DILI on the basis of clinical data extracted from the Hospital Information System of Shenzhen Nanshan Center for Chronic Disease Control from 2014 to 2019.ResultsIn total, 757 patients were included, and 287 (38%) had developed TB-DILI. Based on values of relative importance and area under the receiver operating characteristic curve, machine learning tools selected patients' most recent alanine transaminase levels, average rate of change of patients' last 2 measures of alanine transaminase levels, cumulative dose of pyrazinamide, and cumulative dose of ethambutol as the best predictors for assessing the risk of TB-DILI. In the validation data set, the model had a precision of 90%, recall of 74%, classification accuracy of 76%, and balanced error rate of 77% in predicting cases of TB-DILI. The area under the receiver operating characteristic curve score upon 10-fold cross-validation was 0.912 (95% CI 0.890-0.935). In addition, the model provided warnings of high risk for patients in advance of DILI onset for a median of 15 (IQR 7.3-27.5) days.ConclusionsOur model shows high accuracy and interpretability in predicting cases of TB-DILI, which can provide useful information to clinicians to adjust the medication regimen and avoid more serious liver injury in patients.
| S-EPMC8335604 | biostudies-literature
Project description:Background: Notch receptors (Notch 1/2/3/4), the critical effectors of the Notch pathway, participate in the tumorigenesis and progression of many malignancies. However, the clinical roles of Notch receptors in primary glioblastoma (GBM) have not been fully elucidated. Methods: The genetic alteration-related prognostic values of Notch receptors were determined in the GBM dataset from The Cancer Genome Atlas (TCGA). Two GBM datasets from TCGA and Chinese Glioma Genome Atlas (CGGA) were used to explore the differential expression between Notch receptors and IDH mutation status, and GBM subtypes. The biological functions of Notch Receptors were explored by Gene Ontology and KEGG analysis. The expression and prognostic significance of Notch receptors were determined in the TCGA and CGGA datasets and further validated in a clinical GBM cohort by immunostaining. A Notch3-based nomogram/predictive risk model was constructed in the TCGA dataset and validated in the CGGA dataset. The model performance was evaluated by receiver operating curves, calibration curves, and decision curve analyses. The Notch3-related phenotypes were analyzed via CancerSEA and TIMER. The proliferative role of Notch3 in GBM was validated in U251/U87 glioma cells by Western blot and immunostaining. Results: Notch receptors with genetic alterations were associated with poor survival of GBM patients. Notch receptors were all upregulated in GBM of TCGA and CGGA databases and closely related to the regulation of transcription, protein-lysine N-methyltransferase activity, lysine N-methyltransferase activity, and focal adhesion. Notch receptors were associated with Classical, Mesenchymal, and Proneural subtypes. Notch1 and Notch3 were closely correlated with IDH mutation status and G-CIMP subtype. Notch receptors displayed the differential expression at the protein level and Notch3 showed a prognostic significance in a clinical GBM cohort. Notch3 presented an independent prognostic role for primary GBM (IDH1 mutant/wildtype). A Notch3-based predictive risk model presented favorable accuracy, reliability, and net benefits for predicting the survival of GBM patients (IDH1 mutant/wildtype and IDH1 wildtype). Notch3 was closely related to immune infiltration (macrophages, CD4+ T cells, and dendritic cells) and tumor proliferation. Conclusion: Notch3-based nomogram served as a practical tool for anticipating the survival of GBM patients, which was related to immune-cell infiltration and tumor proliferation.
| S-EPMC10240236 | biostudies-literature
Project description:BackgroundPrimary retroperitoneal sarcoma (RPS) comprises over 70 histologic subtypes, yet there are limited studies that have developed prognostic nomograms for RPS patients to predict overall survival (OS) and cancer-specific survival (CSS). The objective of this study was to construct prognostic nomograms for predicting OS and CSS in RPS patients.MethodsWe identified a total of 1166 RPS patients from the Surveillance, Epidemiology and End Results (SEER) database, and an additional 261 cases were collected from a tertiary cancer center. The study incorporated various clinicopathological and epidemiologic features as variables, and prediction windows for overall survival (OS) and cancer-specific survival (CSS) were set at 3, 5, and 7 years. Multivariable Cox models were utilized to develop the nomograms, and variable selection was performed using a backward procedure based on the Akaike Information Criterion. To evaluate the performance of the nomograms in terms of calibration and discrimination, we used calibration plots, coherence index, and area under the curve.FindingsThe study included 818 patients in the development cohort, 348 patients in the internal validation cohort, and 261 patients in the external validation cohort. The backward procedure selected the following variables: age, French Federation of Cancer Centers Sarcoma Group (FNCLCC) grade, pre-/postoperative chemotherapy, tumor size, primary site surgery, and tumor multifocality. The validation results demonstrated that the nomograms had good calibration and discrimination, with C-indices of 0.76 for OS and 0.81 for CSS. Calibration plots also showed good consistency between the predicted and actual survival rates. Furthermore, the areas under the time-dependent receiver operating characteristic curves for the 3-, 5-, and 7-year OS (0.84, 0.82, and 0.78, respectively) and CSS (0.88, 0.88, and 0.85, respectively) confirmed the accuracy of the nomograms.InterpretationOur study developed accurate nomograms to predict OS and CSS in patients with RPS. These nomograms have important clinical implications and can assist healthcare providers in making informed decisions regarding patient care and treatment options. They may also aid in patient counseling and stratification in clinical trials.
| S-EPMC10620366 | biostudies-literature
Project description:Male breast cancer (MBC) is rare, and most patients are diagnosed at an advanced stage. We aimed to develop a reliable nomogram to predict breast cancer-specific survival (BCSS) for MBC patients, thus helping clinical diagnosis and treatment. Based on data from the Surveillance, Epidemiology, and End Results (SEER) database, 2,451 patients diagnosed with MBC from 2010 to 2015 were selected for this study. They were randomly assigned to either a training cohort (n = 1715) or a validation cohort (n = 736). The Multivariate Cox proportional hazards regression analysis was used to determine the independent prognostic factors, which were then utilized to build a nomogram for predicting 3- and 5-year BCSS. The discrimination and calibration of the new model was evaluated using the Concordance index (C-index) and calibration curves, while its accuracy and benefits were assessed by comparing it to the traditional AJCC staging system using the net reclassification improvement (NRI), the integrated discrimination improvement (IDI), and the decision curve analysis (DCA). Multivariate models revealed that age, AJCC stage, ER status, PR status, and surgery all showed a significant association with BCSS. A nomogram based on these variables was constructed to predict survival in MBC patients. Compared to the AJCC stage, the C-index (training group: 0.840 vs. 0.775, validation group: 0.818 vs. 0.768), the areas under the receiver operating characteristic curve of the training set (3-year AUC: 0.852 vs. 0.778, 5-year AUC: 0.841 vs. 0.774) and the validation set (3-year AUC: 0.778 vs. 0.752, 5-year AUC: 0.852 vs. 0.794), and the calibration plots of this model all exhibited better performance. Additionally, the NRI and IDI confirmed that the nomogram was a great prognosis tool. Finally, the 3- and 5-year DCA curves yielded larger net benefits than the traditional AJCC stage. In conclusion, we have successfully established an effective nomogram to predict BCSS in MBC patients, which can assist clinicians in determining the appropriate therapy strategies for individual male patients.
| S-EPMC6527749 | biostudies-literature
Project description:BackgroundCancer of unknown primary (CUP) has a variable prognosis and lacks any standard staging systems. We aim to improve the prediction of survival in patients with CUP by constructing a nomogram based on a real-world, population analysis.MethodsWe performed a population analysis of patients diagnosed with CUP between 2010 and 2016 in the Surveillance, Epidemiology, and End Results (SEER) database. Patients with complete study variables were respectively assigned to training and validation cohorts by diagnostic time. A prognostic nomogram was established based on the multivariate Cox proportional hazards model and was evaluated through calculating the Harrell's C-index and plotting calibration curves.ResultsIn total, 19,543 patients were identified under the selection criteria, and 3,347 cases with complete study variables were included for developing and validating the nomogram. Covariates incorporated in the final nomogram were sex, age, histological type, surgery, radiotherapy, chemotherapy, and the number of metastatic organs. The Harrell's C-index of nomogram was 0.705 (95% CI: 0.692-0.717) for the training cohort and 0.727 (95% CI: 0.703-0.752) for the validation cohort.ConclusionsWe developed and validated the first nomogram based on a large population, which showed good prediction ability for predicting overall survival of patients with CUP. The risk stratification based on this nomogram could also help clinicians in treatment planning. This nomogram requires further validation in external cohorts, since important clinical factors such as favorable/unfavorable subset, performance status, lactate dehydrogenase, blood cell counts, or metastatic patterns limited to multiple lymph nodes could not be considered due to the lack of availability of these data.
| S-EPMC7940932 | biostudies-literature
Project description:BackgroundPrimary bladder sarcoma (PBS) is a rare malignant tumor of the bladder with a poor prognosis, and its disease course is inadequately understood. Therefore, our study aimed to establish a prognostic model to determine individualized prognosis of patients with PBS.Patients and methodsData of 866 patients with PBS, registered from 1973 to 2015, were extracted from the surveillance, epidemiology, and end result (SEER) database. The patients included were randomly split into a training (n = 608) and a validation set (n = 258). Univariate and multivariate Cox regression analyses were employed to identify the important independent prognostic factors. A nomogram was then established to predict overall survival (OS). Using calibration curves, receiver operating characteristic curves, concordance index (C-index), decision curve analysis (DCA), net reclassification improvement (NRI) and integrated discrimination improvement (IDI), the performance of the nomogram was internally validated. We compared the nomogram with the TNM staging system. The application of the risk stratification system was tested using Kaplan-Meier survival analysis.ResultsAge at diagnosis, T-stage, N-stage, M-stage, and tumor size were identified as independent predictors of OS. C-index of the training cohort were 0.675, 0.670, 0.671 for 1-, 3- and 5-year OS, respectively. And that in the validation cohort were 0.701, 0.684, 0.679, respectively. Calibration curves also showed great prediction accuracy. In comparison with TNM staging system, improved net benefits in DCA, evaluated NRI and IDI were obtained. The risk stratification system can significantly distinguish the patients with different survival risk.ConclusionA prognostic nomogram was developed and validated in the present study to predict the prognosis of the PBS patients. It may assist clinicians in evaluating the risk factors of patients and formulating an optimal individualized treatment strategy.
| S-EPMC8614032 | biostudies-literature
Project description:This study aimed to develop a nomogram to predict the overall survival (OS) of stage IV breast cancer patients. We searched the National Cancer Database (NCDB) for stage IV breast cancer patients diagnosed between 2010 and 2013. Predictors of OS were identified and a nomogram was developed and validated using concordance index (C-index), calibration plots, and risk group stratifications. A total of 7199 patients from the NCDB were included in the study. With a median follow-up of 25.7 months, the 1-year and 3-year OS rates were 80.6% and 52.5%, respectively. Race, age, comorbidity status, T-stage, grade, ER/PR/Her2 status, the presence of lung/liver/brain metastasis, surgery, radiotherapy, and chemotherapy were significantly associated with OS. The developed nomogram had a C-index of 0.722 (95% CI 0.710-0.734) and 0.725 (95% CI 0.713-0.736) in the training and the validation cohorts, respectively. The predicted survival using the nomogram is well correlated with actual OS. The nomogram was able to stratify patients into different risk groups, among which the survival benefit of local therapy varied. We developed a nomogram to predict the overall survival of stage IV breast cancer patients. Prospectively designed studies with international collaborations are needed to further validate our nomogram.
| S-EPMC5673913 | biostudies-literature
Project description:This study aimed to develop and validate an effective prognostic nomogram for advanced PDAC patients. We conducted a prospective multicenter cohort study involving 1,526 advanced PDAC patients from three participating hospitals in China between January 1, 2004 and December 31, 2013. Two thirds of the patients were randomly assigned to the training set (n = 1,017), and one third were assigned to the validation set (n = 509). Multivariate cox regression analysis was performed to identify significant prognostic factors for overall survival to develop the nomogram. Internal and external validation using C-index and calibration curve were conducted in the training set and validation set respectively. As results, seven independent prognostic factors were identified: age, tumor stage, tumor size, ALT (alanine aminotransferase), ALB (albumin), CA 19-9, HBV infection status, and these factors were entered into the nomogram. The proposed nomogram showed favorable discrimination and calibration both in the training set and validation set. The C-indexes of the training set and validation set were 0.720 and 0.696 respectively, which were both significantly higher than that of the staging system (C-index = 0.613, P < 0.001). In conclusion, the proposed nomogram may be served as an effective tool for prognostic evaluation of advanced PDAC.
| S-EPMC5599641 | biostudies-literature