ABSTRACT
Objective:To construct machine learning models based on CT imaging and clinical parameters for predicting progression-free survival (PFS) of locally advanced cervical cancer (LACC) patients after concurrent chemoradiotherapy (CCRT).Methods:Clinical data of 167 LACC patients treated with CCRT at Shandong Cancer Hospital from September 2015 to October 2021 were retrospectively analyzed. All patients were randomly divided into the training and validation cohorts according to the ratio of 7 vs. 3. Clinical features were selected by univariate and multivariate Cox proportional hazards model ( P<0.1). Radiomics models and nomograms were constructed by radiomics features which were selected by least absolute shrinkage and selection operator (LASSO) Cox regression model to predict the 1-, 3- and 5-year PFS. Combined models and nomogram models were developed by selected clinical and radiomics features. The Kaplan Meier-curve, receiver operating characteristic (ROC) curve, C-index and calibration curve were used to evaluate the model performance. Results:A total of 1 409 radiomics features were extracted based on the region of interest (ROI) in CT images. CT radiomics models showed better performance for predicting 1-, 3-and 5-year PFS than the clinical model in the training and validation cohorts. The combined model displayed the optimal performance in predicting 1-, 3-and 5-year PFS in the training cohort [area under the curve (AUC): 0.760, 0.648, 0.661, C-index: 0.740, 0.667, 0.709] and verification cohort (AUC: 0.763, 0.677, 0.648, C-index: 0.748, 0.668, 0.678).Conclusions:Combined model constructed based on CT radiomics and clinical features yield better prediction performance than that based on radiomics or clinical features alone. As an objective image analysis approach, it possesses high prediction efficiency for PFS of LACC patients after CCRT, which can provide reference for clinical decision-making.
ABSTRACT
Objective:To investigate the predictive value of clinical radiomics model based on nnU-Net for the prognosis of gallbladder carcinoma (GBC).Methods:The retrospective cohort study was conducted. The clinicopathological data of 168 patients who underwent curative-intent radical resection of GBC in the First Affiliated Hospital of Xi'an Jiaotong University from January 2012 to December 2020 were collected. There were 61 males and 107 females, aged (64±11)years. All the 168 patients who underwent preoperative enhanced computed tomography (CT) examina-tion were randomly divided into 126 cases in training set and 42 cases in test set according to the ratio of 3:1 based on random number table. For the portal venous phase images, 2 radiologists manually delineated the region of interest (ROI), and constructed a nnU-net model to automatically segment the images. The 5-fold cross-validation and Dice similarity coefficient were used to evaluate the generalization ability and predictive performance of the nnU-net model. The Python software (version 3.7.10) and Pyradiomics toolkit (version 3.0.1) were used to extract the radiomics features, the R software (version 4.1.1) was used to screen the radiomics features, and the variance method, Pearson correlation analysis, one-way COX analysis and random survival forest model were used to screen important radiomics features and calculate the Radiomics score (Radscore). X-tile software (version 3.6.1) was used to determine the best cut-off value of Radscore, and COX proportional hazard regression model was used to analyze the independent factors affecting the prognosis of patients. The training set data were imported into R software (version 4.1.1) to construct a clinical radiomics nomogram model of survival prediction for GBC. Based on the Radscore and the independent clinical factors affecting the prognosis of patients, the Radscore risk model and the clinical model for predicting the survival of GBC were constructed respectively. The C-index, calibration plot and decision curve analysis were used to evaluate the predictive ability of different survival prediction models for GBC. Observation indicators: (1) segmentation results of portal venous phase images in CT examination of GBC; (2) radiomic feature screening and Radscore calculation; (3) prognostic factors analysis of patients after curative-intent radical resection of GBC; (4) construction and evaluation of different survival prediction models for GBC. Measurement data with normal distribution were represented by Mean± SD. Count data were expressed as absolute numbers or percentages, and comparison between groups was analyzed using the chi-square test. Univariate and multivariate analyses were performed using the COX proportional hazard regression model. The postoperative overall survival rate was calculated by the life table method. Results:(1) Segmentation results of portal venous phase images in CT examination of GBC: the Dice similarity coefficient of the ROI based on the manual segmentation and nnU-Net segmentation models was 0.92±0.08 in the training set and 0.74±0.15 in the test set, respectively. (2) Radiomic feature screening and Radscore calculation: 1 502 radiomics features were finally extracted from 168 patients. A total of 13 radiomic features (3 shape features and 10 high-order features) were screened by the variance method, Pearson correlation analysis, one-way COX analysis and random survival forest model. Results of random survival forest model analysis and X-tile software analysis showed that the best cut-off values of the Radscore were 6.68 and 25.01. A total of 126 patients in the training set were divided into 41 cases of low-risk (≤6.68), 72 cases of intermediate-risk (>6.68 and <25.01), and 13 cases of high-risk (≥25.01). (3) Prognostic factors analysis of patients after curative-intent radical resection of GBC: the 1-, 2-, and 3-year overall survival rates of 168 patients were 75.8%, 54.9% and 45.7%, respectively. The results of univariate analysis showed that preopera-tive jaundice, serum CA19-9 level, Radscore risk (medium risk and high risk), extent of surgical resection, pathological T staging, pathological N staging, tumor differentiation degree (moderate differentiation and low differentiation) were related factors affecting prognosis of patients in the training set ( hazard ratio=3.28, 3.00, 3.78, 6.34, 4.48, 6.43, 3.35, 7.44, 15.11, 95% confidence interval as 1.91?5.63, 1.76?5.13, 1.76?8.09, 2.49?16.17, 2.30?8.70, 1.57?26.36, 1.96?5.73, 1.02?54.55, 2.04?112.05, P<0.05). Results of multivariate analysis showed that preoperative jaundice, serum CA19-9 level, Radscore risk as high risk and pathological N staging were independent influencing factors for prognosis of patients in the training set ( hazard ratio=2.22, 2.02, 2.89, 2.07, 95% confidence interval as 1.20?4.11, 1.11?3.68, 1.04?8.01, 1.15?3.73, P<0.05). (4) Construction and evaluation of different survival prediction models for GBC. Clinical radiomics model, Radscore risk model and clinical model were established based on the independent influencing factors for prognosis, the C-index of which was 0.775, 0.651 and 0.747 in the training set, and 0.759, 0.633, 0.739 in the test set, respectively. The calibration plots showed that the Radscore risk model, clinical model and clinical radiomics model had good predictive ability for prognosis of patients. The decision curve analysis showed that the prognostic predictive ability of the clinical radiomics model was better than that of the Radscore risk and clinical models. Conclusion:The clinical radiomics model based on the nnU-Net has a good predictive performance for prognosis of GBC.
ABSTRACT
Objective To explore the prognostic factors of patients with intrahepatic cholangiocarcinoma (ICC) after surgical resection and establish a nomogram for survival prediction.Methods A total of 160 patients with ICC who underwent surgical resection in the First Affiliated Hospital of Xi'an Jiaotong University from January 2010 to December 2018 were retrospectively analyzed.Among them,89 patients were males and 71 were females,aged from 29 to 81 years with a age of (57.41 ± 10.35) years.Observation indicators included:(1) The result of follow-up:postoperative survival.(2) The univariate analysis and multivariate analysis affecting postoperative patients' prognosis.(3) The establishment and validation of nomogram model.The follow-up using outpatient and telephone was performed once every 3 months within 1 year postoperatively and once every 3-6 months after 1 year postoperatively up to August 1,2019.The follow-up included liver function,CA19-9,upper abdominal ultrasound,CT or MRI.The overall postoperative survival time,end point of observation,was the date from the operation date to the follow-up date,or the date of death due to tumor recurrence and metastasis.The patients' clinicopathological data was included in the prognostic factor analysis,the Kaplan-meier method and Log-rank test were conducted for the univariate analysis,the Cox proportional risk regression model was used for the multivariate analysis.The independent risk factors based on Cox regression model were screened to establish a nomogram for postoperative survival prediction.The patients were divided into the model group (n =112) for the establishment of survival nomogram and the validation group (n =48) for the assessment of predictive ability at a ratio of 7∶ 3,and the accuracy of nomogram in postoperative survival prediction was assessed by c-index.Measurement data with normal distribution were expressed with (Mean ± SD).Measurement data with skewed distribution were described as M (range).Count data were expressed as cases and percentage.Results During the follow-up period,all patients with ICC after surgical resection were followed up for a survival time of 20 months (2-111 months).100 patients died of multiple organ failure caused by tumor recurrence and metastasis and 60 patients survived.The 1-,3-and 5-year overall survival rates of patients were 63.3％,30.0％ and 19.6％,respectively.Univariate analysis showed that CA19-9,hepatolithiasis,number of tumor,range of liver resection,tumor differentiation,pathology type,tumor diameter,vascular invasion,TNM stage,lymphatic metastasis,satellite foci and surgical margin were the prognostic factors of ICC patients after surgical resection (HR =1.78,1.97,2.91,1.89,3.06,2.86,2.07,1.94,2.24,1.95,2.68,2.00,95 ％ CI:1.12-2.85,1.22-3.16,1.85-4.56,1.26-2.85,1.38-6.82,1.31-6.25,1.37-3.14,1.07-3.51,1.24-4.06,1.26-3.01,1.28-5.60,1.11-3.59,P ＜ 0.05).Multivariate analysis showed that hepatolithiasis,number of tumor,range of liver resection,tumor differentiation (low differentiation) and pathology type were independent risk factors of ICC patients after surgical resection (HR =2.47,2.37,2.06,5.52,5.72,95％ CI:1.39-4.38,1.44-3.91,1.25-3.40,1.24-24.49,2.31-14.17,P ＜ 0.05).The nomogram was established based on above five independent risk factors,the c-index value for postoperative survival of the model group and validation group were 0.71 (95％ CI:0.64-0.79) and 0.71 (95％ CI:0.61-0.81),respectively.Conclusion A nomogram based on hepatolithiasis,number of tumor,range of liver resection,tumor differentiation and pathology type has better accuracy in postoperative survival prediction for patients with ICC.
ABSTRACT
Objective@#To explore the prognostic factors of patients with intrahepatic cholangiocarcinoma (ICC) after surgical resection and establish a nomogram for survival prediction.@*Methods@#A total of 160 patients with ICC who underwent surgical resection in the First Affiliated Hospital of Xi′an Jiaotong University from January 2010 to December 2018 were retrospectively analyzed. Among them, 89 patients were males and 71 were females, aged from 29 to 81 years with a age of (57.41±10.35) years. Observation indicators included: (1) The result of follow-up: postoperative survival. (2) The univariate analysis and multivariate analysis affecting postoperative patients′ prognosis. (3) The establishment and validation of nomogram model. The follow-up using outpatient and telephone was performed once every 3 months within 1 year postoperatively and once every 3-6 months after 1 year postoperatively up to August 1, 2019. The follow-up included liver function, CA19-9, upper abdominal ultrasound, CT or MRI. The overall postoperative survival time, end point of observation, was the date from the operation date to the follow-up date, or the date of death due to tumor recurrence and metastasis. The patients′ clinicopathological data was included in the prognostic factor analysis, the Kaplan-meier method and Log-rank test were conducted for the univariate analysis, the Cox proportional risk regression model was used for the multivariate analysis. The independent risk factors based on Cox regression model were screened to establish a nomogram for postoperative survival prediction. The patients were divided into the model group (n=112) for the establishment of survival nomogram and the validation group (n=48) for the assessment of predictive ability at a ratio of 7∶3, and the accuracy of nomogram in postoperative survival prediction was assessed by c-index. Measurement data with normal distribution were expressed with (Mean±SD). Measurement data with skewed distribution were described as M (range). Count data were expressed as cases and percentage.@*Results@#During the follow-up period, all patients with ICC after surgical resection were followed up for a survival time of 20 months (2-111 months). 100 patients died of multiple organ failure caused by tumor recurrence and metastasis and 60 patients survived. The 1-, 3- and 5-year overall survival rates of patients were 63.3%, 30.0% and 19.6%, respectively. Univariate analysis showed that CA19-9, hepatolithiasis, number of tumor, range of liver resection, tumor differentiation, pathology type, tumor diameter, vascular invasion, TNM stage, lymphatic metastasis, satellite foci and surgical margin were the prognostic factors of ICC patients after surgical resection (HR=1.78, 1.97, 2.91, 1.89, 3.06, 2.86, 2.07, 1.94, 2.24, 1.95, 2.68, 2.00, 95%CI: 1.12-2.85, 1.22-3.16, 1.85-4.56, 1.26-2.85, 1.38-6.82, 1.31-6.25, 1.37-3.14, 1.07-3.51, 1.24-4.06, 1.26-3.01, 1.28-5.60, 1.11-3.59, P<0.05). Multivariate analysis showed that hepatolithiasis, number of tumor, range of liver resection, tumor differentiation (low differentiation) and pathology type were independent risk factors of ICC patients after surgical resection (HR=2.47, 2.37, 2.06, 5.52, 5.72, 95%CI: 1.39-4.38, 1.44-3.91, 1.25-3.40, 1.24-24.49, 2.31-14.17, P<0.05). The nomogram was established based on above five independent risk factors, the c-index value for postoperative survival of the model group and validation group were 0.71 (95%CI: 0.64-0.79) and 0.71(95%CI: 0.61-0.81), respectively.@*Conclusion@#A nomogram based on hepatolithiasis, number of tumor, range of liver resection, tumor differentiation and pathology type has better accuracy in postoperative survival prediction for patients with ICC.
ABSTRACT
Objective To predict the 5-year survival of patients with non-small cell lung cancer (NSCLC) by machine learning, and to improve the prediction efficiency and prediction accuracy. Methods The experiments were performed using NSCLC data from the SEER database. According to the imbalance of patient data, the Borderline-SMOTE method was used for data sampling. The perturbation-based feature selection (PFS) method and decision tree ( DT ) algorithm were used to screen the features and construct the postoperative survival prediction model . Results The patient data was balanced, and seven prognostic variables were screened, including primary site, stage group, surgical primary site, international classification of diseases, race and grade. Compared with LASSO, Tree-based, PFS-SVM and PFS-kNN models, the model constructed using PFS-DT has the best predictive effect. Conclusions The patient survival prediction model based on PFS-DT can effectively improve the accuracy of postoperative survival prediction in patients with NSCLC, and can provide a reference for doctors to provide treatment and improve prognosis.
ABSTRACT
Objective@#To investigate the clinical value of Bayesian network in predicting survival of patients with advanced gallbladder cancer(GBC)who underwent curative intent surgery.@*Methods@#The clinical data of patients with advanced GBC who underwent curative intent surgery in 9 institutions from January 2010 to December 2015 were analyzed retrospectively.A median survival time model based on a tree augmented naïve Bayes algorithm was established by Bayesia Lab software.The survival time, number of metastatic lymph nodes(NMLN), T stage, pathological grade, margin, jaundice, liver invasion, age, sex and tumor morphology were included in this model.Confusion matrix, the receiver operating characteristic curve and area under the curve were used to evaluate the accuracy of the model.A priori statistical analysis of these 10 variables and a posterior analysis(survival time as the target variable, the remaining factors as the attribute variables)was performed.The importance rankings of each variable was calculated with the polymorphic Birnbaum importance calculation based on the posterior analysis results.The survival probability forecast table was constructed based on the top 4 prognosis factors. The survival curve was drawn by the Kaplan-Meier method, and differences in survival curves were compared using the Log-rank test.@*Results@#A total of 316 patients were enrolled, including 109 males and 207 females.The ratio of male to female was 1.0∶1.9, the age was (62.0±10.8)years.There was 298 cases(94.3%) R0 resection and 18 cases(5.7%) R1 resection.T staging: 287 cases(90.8%) T3 and 29 cases(9.2%) T4.The median survival time(MST) was 23.77 months, and the 1, 3, 5-year survival rates were 67.4%, 40.8%, 32.0%, respectively.For the Bayesian model, the number of correctly predicted cases was 121(≤23.77 months) and 115(>23.77 months) respectively, leading to a 74.86% accuracy of this model.The prior probability of survival time was 0.503 2(≤23.77 months) and 0.496 8(>23.77 months), the importance ranking showed that NMLN(0.366 6), margin(0.350 1), T stage(0.319 2) and pathological grade(0.258 9) were the top 4 prognosis factors influencing the postoperative MST.These four factors were taken as observation variables to get the probability of patients in different survival periods.Basing on these results, a survival prediction score system including NMLN, margin, T stage and pathological grade was designed, the median survival time(month) of 4-9 points were 66.8, 42.4, 26.0, 9.0, 7.5 and 2.3, respectively, there was a statistically significant difference in the different points(P<0.01).@*Conclusions@#The survival prediction model of GBC based on Bayesian network has high accuracy.NMLN, margin, T staging and pathological grade are the top 4 risk factors affecting the survival of patients with advanced GBC who underwent curative resection.The survival prediction score system based on these four factors could be used to predict the survival and to guide the decision making of patients with advanced GBC.
ABSTRACT
<p>There are few reports on the disclosure of survival prediction to patients themselves in Japan, and how concretely it is performed. We retrospectively studied the disclosure of survival prediction to patients who were referred for the first medical examination to the Palliative Care Department between April 2013 and March 2016. Two hundred forty-eight patients (and their families) met the study criteria. Forty-three percent of the patients and their families had received information on definite periods of life expectancy without probability or ranges. On the other hand, 19% of the patients and families had not been told about survival prediction by the previous physician. Our results suggest that patients and families often received information on definite periods of life expectancy. There will be a need for improvement of end-of-life discussion in Japan.</p>
ABSTRACT
Introduction: Among various predicting tools of survival developed for terminally ill cancer patients, Palliative Prognostic Score (PaP) is used very frequently. The target diseases of PaP are solid malignancies other than renal cancer; thus hematological malignancies are not included in them. Objective: To demonstrate that it is appropriate and useful to apply PaP to patients with terminally ill hematological malignancies. Methods: We used PaP to predict the survival of 18 patients with terminally ill hematological malignancies hospitalized in our hospice ward and compared the prediction accuracy with that of the previous studies. Results: The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of 21-day survival probability were 91.7%, 83.3%, 91.7%, 83.3%, and 88.9%, respectively. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of 30-day survival probability were 72.7%, 85.7%, 88.9%, 66.7%, and 77.8%, respectively. Conclusion: Our results suggest that it may be possible to apply PaP to patients with terminally ill hematological malignancies.
ABSTRACT
<b>Introduction</b>: The importance of estimating the prognosis of advanced cancer patients is well known, but clinicians do not estimate survival time accurately. Since there is a need for an objective index to estimate survival time, the utility of the Prognostic Nutritional Index (PNI), which depends only on objective factors, was evaluated. <b>Methods</b>: The PNI was calculated using the following formula, PNI=10×serum albumin value (g/dL)+0.005×lymphocyte count in peripheral blood, at 3 months, 2 months, 1 month, 3 weeks, 2 weeks, 1 week, and within 3 days before death in 278 cancer patients (166 men, 112 women; age range, 33-99 years; mean age, 69.8 years) who died in a hospital surgical unit. <b>Results</b>: Sites of primary diseases included lung, breast, esophagus, stomach, colorectum, liver, biliary tract, and pancreas. The PNI values showed a gradual decrease over time. Changes in the PNI values were lower in non-gastrointestinal cancer patients than in gastrointestinal cancer patients. The mean PNI value was significantly higher in patients who lived >3 weeks (38.8) than in those who died within 3 weeks (32.4). When the PNI cut-off point was set at 35, and it was assumed that the life expectancy was within 3 weeks in cases with PNI <35, the sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were 74.8%, 62.2%, 68.1%, and 69.6%, respectively. <b>Discussion</b>: The PNI appears to be a useful and simple parameter to predict clinical outcomes of patients with terminal stage cancer. Particularly, the PNI is considered feasible for gastrointestinal cancer patients.
ABSTRACT
OBJECTIVE: To assess whether there is an association between improvement of computed tomography imaging results prior to interval debulking with survival in patients treated by neoadjuvant chemotherapy. METHODS: The clinical and outcome data of all advanced ovarian, primary peritoneal and tubal carcinoma patients who after diagnosis had neoadjuvant chemotherapy and underwent interval debulking during the period 2000-2010, were abstracted. Results of computed tomography imaging at diagnosis and prior to interval debulking were compared. Two parameters were assessed: the change of the size and number of abnormal findings and the change in the amount of ascites. CA-125 level response was also calculated. An assessment of progression free survival and of survival by the Kaplan-Meier method was made according to the change in computed tomography imaging results and according to response of CA-125 levels. RESULTS: The median progression free survival and the median survival of the 37 study group patients were 7.9 and 49.2 months respectively. No significant difference in progression free survival and survival was observed between patients with marked improvement in the computed tomography results and those with less desirable results (7.93 vs. 7.23 months respectively, p=0.89; 45.8% vs. 52.5% months respectively, p=0.95). There were also no statistically significant difference according to CA-125 level response. CONCLUSION: It seems that neither improvement in imaging results nor CA-125 level response can predict the survival of ovarian carcinoma patients prior to interval debulking after neoadjuvant chemotherapy.