The development of a prediction model based on random survival forest for the prognosis of non- Hodgkin lymphoma: A prospective cohort study in China.

Background and objective: The pathological staging of non-Hodgkin lymphoma (NHL) is complex, the clinical manifestations are varied, and the prognosis differ considerably. To provide a useful reference for early detection and effective treatment of NHL, we developed a random survival forest (RSF) prognostic model based on machine learning (ML) algorithms using prospective cohort data collected from Chongqing Cancer Hospital from Jan 1, 2017 to Dec 31, 2019 (n = 1449) to compare with the traditional cornerstone method Cox proportional hazards (CPH) model and evaluate the predictability of the model. Methods: Patients were randomly split into a training cohort (TC) and validation cohort (VC) based on 65/35 ratio. The least absolute shrinkage and selection operator (LASSO) regression analysis was used to extracted the important features. And the RSF was modeled to explore the prognostic factors impacting the overall survival (OS) of patients with NHLs in the TC and validated in the VC. The C-index, the Integrated Brier Score (IBS), Kaplan-Meir method, the receiver operating characteristic (ROC) curve, and the area under the ROC curve (AUC) were selected to measure performances and discriminations of the models. In addition, individual survival probability predicted for NHL patients. Results: According to the features extracted by LASSO model and univariable Cox model, 16 variables were selected to develop the RSF model with log-rank splitting rule, which were age, ethnicity, medical insurance, Ann Arbor stage, pathology, targeted-therapy, chemo-therapy, peripheral blood neutrophil count to lymphocyte count ratio (NLR), peripheral blood platelet count to lymphocyte count ratio (PLR), serum lactate dehydrogenase (LDH), CD4/CD8, platelet (PLT), absolute neutrophil count (ANC), lymphocyte (LYM), B-symptoms, and (CPR) were important prognostic factors. Compared to the CPH model (C-index = 0.748, IBS = 0.166), the RSF model (C-index = 0.786, IBS = 0.165) is outperformed in predictability and accuracy. The AUC of the RSF model to estimate the 1-, 3-, and 5-year OS in TC were 0.847, 0.847, and 0.809, respectively; while those in the CPH were 0.816, 0.803, and 0.750, respectively. Conclusions: To provide practical implications for the implementation of individualized therapy, the study constructed a high-performed RSF model and reveal that it outperformed the traditional model CPH. And the RSF model ranked the risk variables. In addition, we stratified the risk of NHL patients and estimated individual survival probability based on the RSF model.

Development and validation of nomogram prognostic model for predicting OS in patients with diffuse large B-cell lymphoma: a cohort study in China.

This study comprehensively incorporates pathological parameters and novel clinical prognostic factors from the international prognostic index (IPI) to develop a nomogram prognostic model for overall survival in patients with diffuse large B-cell lymphoma (DLBCL). The aim is to facilitate personalized treatment and management strategies. This study enrolled a total of 783 cases for analysis. LASSO regression and stepwise multivariate COX regression were employed to identify significant variables and build a nomogram model. The calibration curve, receiver operating characteristic (ROC) curve, and decision curve analysis (DCA) curve were utilized to assess the model's performance and effectiveness. Additionally, the time-dependent concordance index (C-index) and time-dependent area under the ROC curve (AUC) were computed to validate the model's stability across different time points. The study utilized 8 selected clinical features as predictors to develop a nomogram model for predicting the overall survival of DLBCL patients. The model exhibited robust generalization ability with an AUC exceeding 0.7 at 1, 3, and 5 years. The calibration curve displayed evenly distributed points on both sides of the diagonal, and the slopes of the three calibration curves were close to 1 and statistically significant, indicating high prediction accuracy of the model. Furthermore, the model demonstrated valuable clinical significance and holds the potential for widespread adoption in clinical practice. The novel prognostic model developed for DLBCL patients incorporates readily accessible clinical parameters, resulting in significantly enhanced prediction accuracy and performance. Moreover, the study's use of a continuous general cohort, as opposed to clinical trials, makes it more representative of the broader lymphoma patient population, thus increasing its applicability in routine clinical care.

Development and validation of prediction model for overall survival in patients with lymphoma: a prospective cohort study in China.

OBJECTIVE: The survival of patients with lymphoma varies greatly among individuals and were affected by various factors. The aim of this study was to develop and validate a prognostic model for predicting overall survival (OS) in patients with lymphoma. METHODS: We conducted a prospective longitudinal cohort study in China between January 2014 and December 2018 (n = 1,594). After obtaining the follow-up data, we randomly split the cohort into the training cohort (n = 1,116) and the validation cohort (n = 478). The least absolute shrinkage and selection operator (LASSO) regression analysis was used to select the predictors of the model. Cox stepwise regression analysis was used to identify independent prognostic factors, which were finally displayed as static nomogram and web-based dynamic nomogram. We calculated the concordance index(C-index) to describe how the predicted survival of objectively confirmed prognosis. The calibration plot is used to evaluate the prediction accuracy and discrimination ability of the model. Net reclassification index (NRI) and decision curve analysis (DCA) curves were also used to evaluate the prediction ability and net benefit of the model. RESULTS: Nine variables in the training cohort were considered to be independent risk factors for patients with lymphoma in the final model: age, Ann Arbor Stage, pathologic type, B symptoms, chemotherapy, targeted therapy, lactate dehydrogenase (LDH), ß2-microglobulin and C-reactive protein (CRP). The C-indices of OS were 0.749 (95% CI, 0.729-0.769) in the training cohort and 0.731 (95% CI, 0.762-0.700) in the validation cohort. A good agreement between prediction by nomogram and actual observation was shown in the calibration curve for the probability of survival in both the training cohort and validation cohorts. The areas under curve (AUC) of the area under the receiver operating characteristic (ROC) curves for 1-year, 3-year, and 5-year OS were 0.813, 0.800, and 0.762, respectively, in the training cohort, and 0.802, 0.768, and 0.721, respectively, in the validation cohort. Compared with the Ann Arbor Stage system, NRI and DCA showed that the model had a higher predictive capacity and net benefit. CONCLUSION: The prediction models reliably estimate the outcome of patients with lymphoma. The model had high discrimination and calibration, which provided a simple and reliable tool for the survival prediction of the patients, and it might help patients benefit from personalized intervention.

Machine learning predicts cancer-associated venous thromboembolism using clinically available variables in gastric cancer patients.

Stomach cancer (GC) has one of the highest rates of thrombosis among cancers and can lead to considerable morbidity, mortality, and additional costs. However, to date, there is no suitable venous thromboembolism (VTE) prediction model for gastric cancer patients to predict risk. Therefore, there is an urgent need to establish a clinical prediction model for VTE in gastric cancer patients. We collected data on 3092 patients between January 1, 2018 and December 31, 2021. And after feature selection, 11 variables are reserved as predictors to build the model. Five machine learning (ML) algorithms are used to build different VTE predictive models. The accuracy, sensitivity, specificity, and AUC of these five models were compared with traditional logistic regression (LR) to recommend the best VTE prediction model. RF and XGB models have selected the essential characters in the model: Clinical stage, Blood Transfusion History, D-Dimer, AGE, and FDP. The model has an AUC of 0.825, an accuracy of 0.799, a sensitivity of 0.710, and a specificity of 0.802 in the validation set. The model has good performance and high application value in clinical practice, and can identify high-risk groups of gastric cancer patients and prevent venous thromboembolism.

Development and validation of a risk prediction model for overall survival in patients with nasopharyngeal carcinoma: a prospective cohort study in China.

OBJECTIVE: Nasopharyngeal carcinoma (NPC) is prevailing in Southern China, characterized by distinct geographical distribution. Aimed to predict the overall survival (OS) of patients with nasopharyngeal carcinoma, this study developed and validated nomograms considering demographic variables, hematological biomarkers, and oncogenic pathogens in China. METHODS: The clinicopathological and follow-up data of the nasopharyngeal carcinoma patients obtained from a prospective longitudinal cohort study in the Chongqing University Cancer Hospital between Jan 1, 2017 and Dec 31, 2019 ([Formula: see text]). Cox regression model was used to tested the significance of all available variables as prognostic factors of OS. And independent prognostic factors were identified based on multivariable analysis to model nomogram. Concordance index (C-index), area under the receiver operating characteristic (AUC), calibration curve, and decision curve analysis (DCA) were measured to assess the model performance of nomogram. RESULTS: Data was randomly divided into a training cohort (1227 observers, about 70% of data) and a validation group (408 observers, about 30% of data). At multivariable analysis, the following were independent predictors of OS in NPC patients and entered into the nomogram: age (hazard ratio [HR]: 1.03), stage (stage IV vs. stage I-II, HR: 4.54), radiotherapy (Yes vs. No, HR: 0.43), EBV ([Formula: see text] vs.[Formula: see text], HR: 1.92), LAR ([Formula: see text] vs.[Formula: see text], HR: 2.05), NLR ([Formula: see text] vs. [Formula: see text] HR: 1.54), and PLR ([Formula: see text] vs.[Formula: see text], HR: 1.79). The C-indexes for training cohort at 1-, 3- and 5-year were 0.73, 0.83, 0.80, respectively, in the validation cohort, the C-indexes were 0.74 (95% CI 0.63-0.86), 0.80 (95% CI 0.73-0.87), and 0.77 (95% CI 0.67-0.86), respectively. The calibration curve demonstrated that favorable agreement between the predictions of the nomograms and the actual observations in the training and validation cohorts. In addition, the decision curve analysis proved that the nomogram model had the highest overall net benefit. CONCLUSION: A new prognostic model to predict OS of patients with NPC was developed. This can offer clinicians treatment making and patient counseling. Furthermore, the nomogram was deployed into a website server for use.

Lung Cancer-Specific Mortality Risk and Public Health Insurance: A Prospective Cohort Study in Chongqing, Southwest China.

Objective: The incidence and mortality of lung cancer rank first among malignant tumors, and its long treatment cycle will bring serious economic burdens to lung cancer patients and their families. There are few studies on the prognosis of lung cancer and insurance policies. This article explores the relationship between the lung cancer-specific death and public health insurance, self-paying rate, and the joint effect of public health insurance and self-paying rate. Materials and Methods: A prospective longitudinal cohort study was conducted in Chongqing, China from 2013 to 2019. The selected subjects were patients with C33-C34 coded according to the tenth edition of the International Classification of Diseases (ICD-10), aged 20 years or older. We conduct a subgroup analysis based on public health insurance types and self-paying rates. After following the inclusion and exclusion criteria, the chi-square test was used to describe the demographic and clinical characteristics of patients with different insurance types and different self-paying rates. Multivariate logistic regression was used to analyze the relationship between patients with different insurance types, self-paying rates, and lung cancer treatment methods. Finally, the Cox proportional hazard model and the competitive risk model are used to calculate the cumulative hazard ratio of all-cause death and lung cancer-specific death for different insurance types and different self-paying rate groups. Results: A total of 12,464 patients with lung cancer were included in this study. During the follow-up period (median 13 months, interquartile range 5.6-25.2 months), 5,803 deaths were observed, of which 3,781 died of lung cancer. Compared with patients who received urban resident-based basic medical insurance (URBMI), patients who received urban employee-based basic medical insurance (UEBMI) had a 38.1% higher risk of lung cancer-specific death (Hazard Ratios (HRs) = 1.381, 95% confidence interval (CI): 1.293-1.476, P < 0.005), Compared with patients with insufficient self-paying rate, patients with a higher self-paying rate had a 40.2% lower risk of lung cancer-specific death (HRs = 0.598, 95% CI: 0.557-0.643, P < 0.005). Every 10% increase in self-paying rate of URBMI reduces the risk of lung cancer-specific death by 17.6%, while every 10% increase in self-paying rate of UEBMI reduces the risk of lung cancer-specific death by 18.0%. Conclusions: The National Medical Security Administration should, under the condition of limited medical insurance funds, try to include the original self-paid anti-tumor drugs into the national medical insurance coverage. This can not only reduce the mortality rate of lung cancer patients, but also reduce the family burden of lung cancer patients. On the other hand, high-risk groups should increase their awareness of lung cancer screening and actively participate in the national cancer screening project led by the state.

[Study on burden of disease in Chongqing, 2010-2013].

OBJECTIVE: To analysis the burden of diseases (BOD) and economic burden of disease (EBOD) in Chongqing and provide scientific evidence for effective prevention and control of diseases. METHODS: The burden of diseases of Chongqing were estimated by use of disability-adjusted life year (DALY) from 2010 to 2013, two-step method was used in the calculation of direct economic burden of diseases. DALY combined with the human capital method were used to measure the indirect economic burden. RESULTS: From 2010 to 2013, DALY loss by all causes for the residents in Chongqing were 123.90, 127.01, 123.30 and 125.99 person year per thousand persons, respectively. The diseases mainly included non-communicable diseases, accounting for 83%-87%, followed by injure and infectious diseases. The five leading diseases of BOD in Chongqing were respiratory system disease, circulatory system disease, malignant tumor, accidental death, neuropsychiatric disease, respectively. The total economic burden of diseases was 1 621.34 million yuan RMB in 2013. The direct and indirect economic burden of diseases were 794.42 million yuan RMB and 826.92 million yuan RMB, which could be attributed to circulatory system disease, respiratory system diseases, injury, malignant tumor and muscle bones and connective tissue diseases. CONCLUSION: Respiratory system disease, circulatory system diseases, malignant tumor, and injury have caused heavy burden both in people's health and economic status in Chongqing. It is necessary to take effective measures to prevent and control these diseases.