Prediction Model For Recurrence Research Articles

Deep learning-based segmentation of acute ischemic stroke MRI lesions and recurrence prediction within 1 year after discharge: A multicenter study

ObjectiveTo explore the performance of deep learning-based segmentation of infarcted lesions in the brain MRI of patients with AIS and the recurrence prediction value of radiomics within 1 year after discharge as well as to develop a model incorporating radiomics features and clinical factors to accurately predict AIS recurrence. Materials and MethodsTo generate a segmentation model of MRI lesions in AIS, the deep learning algorithm multiscale residual attention UNet (MRA-UNet) was employed. Furthermore, the risk factors for AIS recurrence within 1 year were explored using logistic regression analysis. In addition, to develop the prediction model for AIS recurrence within 1 year after discharge, four machine learning algorithms, namely, LR, RandomForest, CatBoost, and XGBoost, were employed based on radiomics data, clinical data, and their combined data. ResultsIn the validation set, the MDice and MIou of the MRA-UNet segmentation model were 0.816 and 0.801, respectively. In multivariate logistic regression analysis, age, renal insufficiency, C-reactive protein, triglyceride glucose index, prognostic nutritional index, and infarct volume were identified as the independent risk factors for stroke recurrence. Furthermore, in the validation set, combining radiomics data and clinical data, the AUC was 0.835 (95%CI:0.738, 0.932), 0.834 (95%CI:0.740, 0.928), 0.858 (95%CI:0.770, 0.946), and 0.842 (95%CI:0.752, 0.932) for the LR, RandomForest, CatBoost, and XGBoost models, respectively. ConclusionThe MRA-UNet model can effectively improve the segmentation accuracy of diffusion-weighted images. The model, which was established by combining radiomics features and clinical factors, held some value for predicting ischemic stroke recurrence within 1 year.

Risk factors and nomogram predictive models for postsurgical progression/hyperprogression recurrence in hepatocellular carcinoma with macroscopic vascular invasion

PurposeThis study aimed to develop postsurgical progression/hyperprogression recurrence (type III-IV recurrence) prediction models for hepatocellular carcinoma (HCC) patients with macroscopic vascular invasion (MaVI) and to guide treatment strategies in the accurate healthcare era.Patients and methods393 HCC patients with MaVI from two central hospitals made up the entire study population. In developmental (290 patients) and validation (103 patients) cohorts, all patients were randomized into one or the other. Two prediction models for type III-IV recurrence were developed, based on the findings of univariate and multivariate analysis in the development cohort, and multidimensional verification was carried out in both cohorts.ResultsThe postoperative recurrence rate of type III-IV in 393 HCC patients with MaVI was 70.9%. Young age, large tumor size (≥ 10 cm), node number, incomplete tumor capsule, postoperative complications, and high Ki67 index were the independent risk factors for relapse of type III-IV. In the development cohort, two nomograms (pre- and postoperative) had the Area Under the ROC curve (AUC) of 0.827 and 0.891, respectively. The two nomograms performed well, according to multidimensional verification methods such as clinical impact curves, decision curve analysis (DCA), and calibration curves. The validation cohort saw similar encouraging results. Both nomograms could separate patients into two distinct prognosis subgroups with ideal cutoff values of 170.3 presurgery and 175.0 postsurgery (both P < 0.05).ConclusionWe constructed two novel and potentially clinically valuable models for predicting type III-IV recurrence. These two models can develop strategies for treating those suffering from HCC with MaVI owing to their strong prediction performance and availability.

Construction and validation of a nomogram prediction model for postoperative recurrence of lumbar disc herniation treated with percutaneous laminectomy.

The aim was to investigate the independent risk factors for postoperative recurrence of lumbar disc herniation treated by percutaneous intervertebral laminectomy, and to establish a nomogram prediction model accordingly. Data on patients with lumbar disc herniation were collected from January 2018 to December 2023 in our hospital, and single-factor and multifactorial logistic regression analyses were used to determine the independent risk factors for postoperative recurrence of lumbar disc herniation and establish the corresponding nomogram. The receiver operating characteristic curves were plotted the area under the curve was calculated, and the calibration curves and decision curves were plotted to evaluate the model performance. A total of 644 patients with lumbar disc herniation were included in the study, and 61 patients had a postoperative recurrence, with a recurrence rate of 9.5%. After univariate and multivariate logistic regression model analysis, a total of 7 variables were identified as independent risk factors for postoperative recurrence of lumbar disc herniation: age > 60 years (OR, 3.709; 95% CI, 1.284-10.714), type of nucleus pulposus protrusion as herniation (OR, 7.342; 95% CI, 1.500-35.929), nucleus pulposus degeneration grade III-V (OR, 4.068; 95% CI, 1.214-13.627), operative segment L4-L5 (OR, 5.060; 95% CI, 1.659-15.431), incomplete intraoperative medullary removal (OR, 5.355; 95% CI, 2.017-14.220), and broken fibrous ring (OR, 5.229; 95% CI, 1.235-22.142), and postoperative high-intensity activity (OR, 5.096; 95% CI, 1.420-17.669). The nomogram constructed in this study for postoperative recurrence of lumbar disc herniation treated by percutaneous intervertebral foramenoscopy has good predictive accuracy, which helps orthopedic surgeons to intervene in advance in patients at high risk of postoperative recurrence of lumbar disc herniation treated by percutaneous intervertebral foramenoscopy.

Research on prediction and evaluation algorithm of sports athletes performance based on neural network.

The Ultimate Fighting Championship (UFC) stands as a prominent global platform for professional mixed martial arts, captivating audiences worldwide. With its continuous growth and globalization efforts, UFC events have garnered significant attention and achieved commendable results. However, as the scale of development expands, the operational demands on UFC events intensify. At its core, UFC thrives on the exceptional performances of its athletes, which serve as the primary allure for audiences. This study aims to enhance the allure of UFC matches and cultivate exceptional athletes by predicting athlete performance on the field. To achieve this, a recurrent neural network prediction model based on Bidirectional Long Short-Term Memory (BiLSTM) is proposed. The model seeks to leverage athlete portraits and characteristics for performance prediction. The proposed methodology involves constructing athlete portraits and analyzing athlete characteristics to develop the prediction model. The BiLSTM-based recurrent neural network is utilized for its ability to capture temporal dependencies in sequential data. The model's performance is assessed through experimental analysis. Experimental results demonstrate that the athlete performance prediction model achieved an overall accuracy of 0.7524. Comparative analysis reveals that the proposed BiLSTM model outperforms traditional methods such as Linear Regression and Multilayer Perceptron (MLP), showcasing superior prediction accuracy. This study introduces a novel approach to predicting athlete performance in UFC matches using a BiLSTM-based recurrent neural network. By leveraging athlete portraits and characteristics, the proposed model offers improved accuracy compared to classical methods. Enhancing the predictive capabilities in UFC not only enriches the viewing experience but also contributes to the development of exceptional athletes in the sport.

A preliminary study of developing an MRI-based model for postoperative recurrence prediction and treatment direction of intrahepatic cholangiocarcinoma.

To establish an MRI-based predictive model for postoperative recurrence in intrahepatic cholangiocarcinoma (iCCA) and further to evaluate the model utility in treatment direction for neoadjuvant and adjuvant therapies. Totally 114 iCCA patients with curative surgery were retrospectively included, including 38 patients in the neoadjuvant treatment, traditional surgery, and adjuvant treatment groups for each. Predictive variables associated with postoperative recurrence were identified using univariate and multivariate Cox regression analyses, and a prognostic model was formulated. Recurrence-free survival (RFS) curves were compared using log-rank test between MRI-predicted high-risk and low-risk iCCAs stratified by the optimal threshold. Tumor multiplicity (hazard ratio (HR) = 1.671 [95%CI 1.036, 2.695], P = 0.035), hemorrhage (HR = 2.391 [95%CI 1.189, 4.810], P = 0.015), peri-tumor diffusion-weighted hyperintensity (HR = 1.723 [95%CI 1.085, 2.734], P = 0.021), and positive regional lymph node (HR = 2.175 [95%CI 1.295, 3.653], P = 0.003) were independently associated with postoperative recurrence; treatment group was not significantly related to recurrence (P > 0.05). Independent variables above were incorporated for the recurrence prediction model, the 1-year and 2-year time-dependent area under the curve values were 0.723 (95%CI 0.631, 0.815) and 0.725 (95%CI 0.634, 0.816), respectively. After risk stratification, the MRI-predicted high-risk iCCA patients had higher cumulative incidences of recurrence and worse RFS than the low-risk patients (P < 0.001 for both). In the MRI-predicted high-risk patients, neoadjuvant therapy was associated with improved all-stage RFS (P = 0.034), and adjuvant therapy was associated with improved RFS after 4months (P = 0.014). The MRI-based iCCA recurrence predictive model may serve as a decision-making tool for both personalized prognostication and therapy selection.

Three-dimensional deep learning model complements existing models for preoperative disease-free survival prediction in localized clear cell renal cell carcinoma: a multicenter retrospective cohort study.

Current prognostic models have limited predictive abilities for the growing number of localized (stage I-III) ccRCCs. It is, therefore, crucial to explore novel preoperative recurrence prediction models to accurately stratify patients and optimize clinical decisions. The purpose of this study was to develop and externally validate a computed tomography (CT)-based deep learning (DL) model for presurgical disease-free survival (DFS) prediction. Patients with localized ccRCC were retrospectively enrolled from six independent medical centers. Three-dimensional (3D) tumor regions from CT images were utilized as input to architect a ResNet 50 model, which outputted DL computed risk score (DLCR) of each patient for DFS prediction later. The predictive performance of DLCR was assessed and compared to the radiomics model (Rad-Score), the clinical model the authors built and two existing prognostic models (UISS and Leibovich). The complementary value of DLCR to the UISS, Leibovich, as well as Rad-Score were evaluated by stratified analysis. Seven hundred seven patients with localized ccRCC were finally enrolled for models' training and validating. The DLCR the authors established can perfectly stratify patients into low-risks, intermediate-risks, and high-risks, and outperformed the Rad-Score, clinical model, UISS and Leibovich score in DFS prediction, with a C-index of 0.754 (0.689-0.821) in the external testing set. Furthermore, the DLCR presented excellent risk stratification capacity in subgroups defined by almost all clinic-pathological features. Moreover, patients classified as low-risk by the UISS/Leibovich score/Rad-Score but as intermediate - or high-risk by DLCR were significantly more likely to experience ccRCC recurrence than those stratified as intermediate- or high-risk by UISS/Leibovich score/Rad-Score but as low-risk by DLCR (all Log-rank P- values<0.05). Our DL model, derived from preoperative CT, is superior to radiomics and current models in precisely DFS predicting of localized ccRCC, and can provide complementary values to them, which may assist more informed clinical decisions and adjuvant therapies adoptions.

Application of preoperative NLR-based prognostic model in predicting prognosis of intrahepatic cholangiocarcinoma following radical surgery.

To investigate the application value of the neutrophil to lymphocyte count ratio (NLR) in the prognostic analysis of intrahepatic cholangiocarcinoma (ICC) after radical resection, and to offer guidance for the individualized perioperative diagnosis and treatment of ICC. The clinical data of 360 patients diagnosed with ICC following radical surgery were retrospectively analyzed. The cut-off value of NLR was calculated using the minimum p-value method, and then divided into High-NLR (H-NLR) group and Low-NLR (L-NLR) group according to the NLR cut-off value. The prognostic value of NLR in ICC was analyzed. Subsequently, the patients were divided into the hepatolithiasis-related intrahepatic cholangiocarcinoma (HICC) group and the non-hepatolithiasis-related intrahepatic cholangiocarcinoma (NHICC) group based on whether they combined with hepatolithiasis. Multiple regression models were constructed based on NLR and clinicopathological indicators to verify the application value of prognostic models in the survival and recurrence of ICC patients after radical surgery. The cut-off value of NLR was 2.36, and the survival analysis disclosed that overall ICC patients with NLR ≥ 2.36 manifested a poor 5-year survival rate and a higher tumor recurrence rate (p < 0.001). In the HICC group, patients with H-NLR presented a poor 5-year survival rate and a higher tumor recurrence rate compared with L-NLR (p < 0.001). The NLR-based survival/recurrence prediction models in the HICC group demonstrated excellent predictive capacity (H-L test: 0.359/0.680, AUC: 0.764/0.791). In the NHICC group, patients with H-NLR exhibited a poor 5-year survival rate compared with L-NLR (p < 0.001), yet there was no significant difference in tumor recurrence between the two groups (p = 0.071). The NLR-based survival prediction model in the NHICC group demonstrated acceptable predictive ability (H-L test: 0.268, AUC: 0.729), while the NLR-based recurrence prediction model did not show an effective predictive ability (H-L test: 0.01, AUC: 0.649). NLR is an independent risk factor influencing postoperative survival and recurrence in ICC patients, particularly in HICC patients. Preoperative NLR ≥ 2.36 suggests that patients might have a poor prognosis. The survival and recurrence prediction model constructed based on NLR and other clinical indicators demonstrates good prediction accuracy and can effectively predict the risk of postoperative adverse prognosis in patients with HICC. This study offers a novel idea for the clinical treatment of HICC patients.

VMD-HPCA-GRU ultra-short-term wind power forecasting based on COOT algorithm

In order to improve the prediction accuracy of ultra-short-term wind power, a combined prediction model of variational mode decomposition (VMD), hierarchical principal component analysis (HPCA) and gated recurrent unit neural network (GRU) based on COOT algorithm optimization is proposed. Firstly, the energy difference method is used to determine the number of sub-modes of variational mode decomposition, so that the original power sequence with strong nonlinearity is decomposed into a group of relatively stable sub-modes. Secondly, the correlation value between high-dimensional meteorological characteristics and power sequence is calculated by grey correlation analysis and sorted and layered. The first principal component of each layered characteristic variable is extracted by principal component analysis to achieve dimensionality reduction of high-dimensional meteorological characteristics. Finally, the COOT algorithm is introduced to optimize the hyperparameters of the gated recurrent unit prediction model, accelerate the model convergence speed, and improve the prediction accuracy of the model. The measured data of a wind farm in Guizhou are simulated and analyzed. The results show that compared with the prediction results of the traditional GRU model, the root mean square error, mean absolute error, and mean absolute percentage error of the proposed method are reduced 67.41%、72.25%、45.69%, and the prediction accuracy is higher than that of the other four combined prediction models, which effectively improves the prediction accuracy of ultra-short-term wind power.

Multiparametric MRI based deep learning model for prediction of early recurrence of hepatocellular carcinoma after SR following TACE

BackgroundSurgical resection (SR) following transarterial chemoembolization (TACE) is a promising treatment for unresectable hepatocellular carcinoma (uHCC). However, biomarkers for the prediction of postoperative recurrence are needed.PurposeTo develop and validate a model combining deep learning (DL) and clinical data for early recurrence (ER) in uHCC patients after TACE.MethodsA total of 511 patients who received SR following TACE were assigned to derivation (n = 413) and validation (n = 98) cohorts. Deep learning features were taken from the largest tumor area in liver MRI. A nomogram using DL signatures and clinical data was made to forecast early recurrence risk in uHCC patients. Model performance was evaluated using area under the curve (AUC).ResultsA total of 2278 subsequences and 31,346 slices multiparametric MRI including contrast-enhanced T1WI, T2WI and DWI were input in the DL model simultaneously. Multivariable analysis identified three independent predictors for the development of the nomogram: tumor number (hazard ratio [HR]:3.42, 95% confidence interval [CI]: 2.75–4.31, P = 0.003), microvascular invasion (HR: 9.21, 6.24–32.14; P < 0.001), and DL scores (HR: 17.46, 95% CI: 12.94–23.57, P < 0.001). The AUC of the nomogram was 0.872 and 0.862 in two cohorts, significantly outperforming single-subsequence-based DL mode and clinical model (all, P < 0.001). The nomogram provided two risk strata for cumulative overall survival in two cohorts, showing significant statistical results (P < 0.001).ConclusionsThe DL-based nomogram is essential to identify patients with uHCC suitable for treatment with SR following TACE and may potentially benefit personalized decision-making.

Creation of a Prediction Model of Local Tumor Recurrence After a Successful Conventional Transcatheter Arterial Chemoembolization Using Cone-Beam Computed Tomography Based-Radiomics.

To create and evaluate prediction models of local tumor recurrence after successful conventional transcatheter arterial chemoembolization (c-TACE) via radiomics analysis of lipiodol deposition using cone-beam computed tomography (CBCT) images obtained at the completion of TACE. A total of 103 hepatocellular carcinoma nodules in 71 patients, who achieved a complete response (CR) based on the modified Response Evaluation Criteria in Solid Tumors 1month after TACE, were categorized into two groups: prolonged CR and recurrence groups. Three types of areas were segmented on CBCT: whole segment (WS), tumor segment (TS), and peritumor segment (PS). From each segment, 105 radiomic features were extracted. The nodules were randomly divided into training and test datasets at a ratio of 7:3. Following feature reduction for each segment, three models (clinical, radiomics, and clinical-radiomics models) were developed to predict recurrence based on logistic regression. The clinical-radiomics model of WS showed the best performance, with the area under the curve values of 0.853 (95% confidence interval: 0.765-0.941) in training and 0.752 (0.580-0.924) in test dataset. In the analysis of radiomic feature importance of all models, among all radiomic features, glcm_MaximumProbability, shape_MeshVolume and shape_MajorAxisLength had negative coefficients. In contrast, shape_SurfaceVolumeRatio, shape_Elongation, glszm_SizeZoneNonUniformityNormalized, and gldm_GrayLevelNonUniformity had positive coefficients. In this study, a machine-learning model based on cone-beam CT images obtained at the completion of c-TACE was able to predict local tumor recurrence after successful c-TACE. Nonuniform lipiodol deposition and irregular shapes may increase the likelihood of recurrence.

Predictors of Durable Remission After Successful Surgery for Cushing Disease: Results From the Multicenter RAPID Registry.

Cushing disease (CD) affects mortality and quality of life along with limited long-term remission, underscoring the need to better identify recurrence risk. The identification of surgical or imaging predictors for CD remission after transsphenoidal surgery has yielded some inconsistent results and has been limited by single-center, single-surgeon, or meta-analyses studies. We sought to evaluate the multicenter Registry of Adenomas of the Pituitary and Related Disorders (RAPID) database of academic US pituitary centers to assess whether robust nonhormonal recurrence predictors could be elucidated. Patients with treated CD from 2011 to 2023 were included. The perioperative and long-term characteristics of CD patients with and without recurrence were assessed using univariable and multivariable analyses. Of 383 patients with CD from 26 surgeons achieving postoperative remission, 288 (75.2%) maintained remission at last follow-up while 95 (24.8%) showed recurrence (median time to recurrence 9.99 ± 1.34 years). Patients with recurrence required longer postoperative hospital stays (5 ± 3 vs 4 ± 2 days, P = .002), had larger average tumor volumes (1.76 ± 2.53 cm 3 vs 0.49 ± 1.17 cm 3 , P = .0001), and more often previously failed prior treatment (31.1% vs 14.9%, P = .001) mostly being prior surgery. Multivariable hazard prediction models for tumor recurrence found younger age (odds ratio [OR] = 0.95, P = .002) and Knosp grade of 0 (OR = 0.09, reference Knosp grade 4, P = .03) to be protective against recurrence. Comparison of Knosp grade 0 to 2 vs 3 to 4 showed that lower grades had reduced risk of recurrence (OR = 0.27, P = .04). Other factors such as length of stay, surgeon experience, prior tumor treatment, and Knosp grades 1, 2, or 3 failed to reach levels of statistical significance in multivariable analysis. This multicenter study centers suggests that the strongest predictors of recurrence include tumor size/invasion and age. This insight can help with patient counseling and prognostication. Long-term follow-up is necessary for patients, and early treatment of small tumors may improve outcomes.

Machine learning model to predict early recurrence in patients with perihilar cholangiocarcinoma planned treatment with curative resection: a multicenter study

BackgroundEarly recurrence is the leading cause of death for patients with perihilar cholangiocarcinoma (pCCA) after surgery. Identifying high-risk patients preoperatively is important. This study aimed to construct a preoperative prediction model for the early recurrence of patients with pCCA to facilitate planned treatment with curative resection. MethodsThis study ultimately enrolled 400 patients with pCCA after curative resection in 5 hospitals between 2013 and 2019. They were randomly divided into training (n = 300) and testing groups (n = 100) at a ratio of 3:1. Associated variables were identified via least absolute shrinkage and selection operator (LASSO) regression. Four machine learning models were constructed: support vector machine, random forest (RF), logistic regression, and K-nearest neighbors. The predictive ability of the models was evaluated via receiving operating characteristic (ROC) curves, precision-recall curve (PRC) curves, and decision curve analysis. Kaplan-Meier (K-M) survival curves were drawn for the high-/low-risk population. ResultsFive factors: carbohydrate antigen 19–9, tumor size, total bilirubin, hepatic artery invasion, and portal vein invasion, were selected by LASSO regression. In both the training and testing groups, the ROC curve (area under the curve: 0.983 vs 0.952) and the PRC (0.981 vs 0.939) showed that RF was the best. The cutoff value for distinguishing high- and low-risk patients was 0.51. K-M survival curves revealed that in both groups, there was a significant difference in RFS between high- and low-risk patients (P < .001). ConclusionThis study used preoperative variables from a large, multicenter database to construct a machine learning model that could effectively predict the early recurrence of pCCA in patients to facilitate planned treatment with curative resection and help clinicians make better treatment decisions.

Development and validation of a recurrence risk assessment model for high-grade bladder cancer based on TCGA and GEO.

Bladder cancer is one of the most commonly diagnosed urinary cancers worldwide. Although muscle-invasive bladder cancer (MIBC) accounts for only 25% of bladder cancer cases, it has a high recurrence rate and poor prognosis, especially among high-grade cases. Despite the existence of some molecular markers, there is a clear clinical need for a robust recurrence prediction model that can assist in patient management and therapeutic decision-making. Therefore, we aimed to use public databases to develop such an effective assessment model. We developed a recurrence risk assessment model for high-grade bladder cancer based on the clinical information of 217 cases from The Cancer Genome Atlas (TCGA) and profiles of 87 samples from GSE31684 in the Gene Expression Omnibus (GEO) database. Edge R was used to analyze differences between RNAs of bladder cancer in the TCGA database, with thresholds of P<0.05 and |log2(fold change)| >1; least absolute shrinkage and selection operator (LASSO) Cox regression models were used to screen the RNAs significantly related to recurrence with minimum λ. Survival receiver operating characteristic (ROC) and area under the curve (AUC) was used to assess the predictive accuracy of the model in the training and validation sets of GSE31684. There were 2,876 differential RNAs obtained from TCGA data. Among a total of 284 RNAs identified as significantly related to recurrence of bladder cancer, 49 were obtained by LASSO regression, and 30 were finally obtained by multifactor risk regression to construct a risk assessment model. The model was found to predict the prognosis of bladder cancer recurrence well, with an AUC of 0.911 in the TCGA training set and an adjusted AUC value of 0.839 in the GEO validation set. The recurrence assessment model is a relatively accurate recurrence prediction tool for high-grade bladder cancer and could provide a guidance for the treatment of bladder cancer.

Establishment and evaluation of prediction model of recurrence after laparoscopic choledocholithotomy.

Choledocholithiasis is a common clinical bile duct disease, laparoscopic choledocholithotomy is the main clinical treatment method for choledocholithiasis. However, the recurrence of postoperative stones is a big challenge for patients and doctors. To explore the related risk factors of gallstone recurrence after laparoscopic choledocholithotomy, establish and evaluate a clinical prediction model. A total of 254 patients who underwent laparoscopic choledocholithotomy in the First Affiliated Hospital of Ningbo University from December 2017 to December 2020 were selected as the research subjects. Clinical data of the patients were collected, and the recurrence of gallstones was recorded based on the postoperative follow-up. The results were analyzed and a clinical prediction model was established. Postoperative stone recurrence rate was 10.23% (26 patients). Multivariate Logistic regression analysis showed that cholangitis, the diameter of the common bile duct, the diameter of the stone, number of stones, lithotripsy, preoperative total bilirubin, and T tube were risk factors associated with postoperative recurrence (P < 0.05). The clinical prediction model was ln (p/1-p) = -6.853 + 1.347 × cholangitis + 1.535 × choledochal diameter + 2.176 × stone diameter + 1.784 × stone number + 2.242 × lithotripsy + 0.021 × preoperative total bilirubin + 2.185 × T tube. Cholangitis, the diameter of the common bile duct, the diameter of the stone, number of stones, lithotripsy, preoperative total bilirubin, and T tube are the associated risk factors for postoperative recurrence of gallstone. The prediction model in this study has a good prediction effect, which has a certain reference value for recurrence of gallstone after laparoscopic choledocholithotomy.

Validation of the R3-AFP model for risk prediction of HCC recurrence after liver transplantation in the SiLVER randomized clinical trial.

Explant-based models for assessing HCC recurrence after liver transplantation serve as the gold standard, guiding post-liver transplantation screening and immunosuppression adjustment. Incorporating alpha-fetoprotein (AFP) levels into these models, such as the novel R3-AFP score, has notably enhanced risk stratification. However, validation of these models in high-evidence data is mandatory. Therefore, the aim of the present research was to validate the R3-AFP score in a randomized clinical trial. We analyzed the intention-to-treat population from the 2-arm SiLVER trial (NCT00355862), comparing calcineurin-based ([calcineurin inhibitors]-Group A) versus mammalian target of rapamycin inhibitors-based (sirolimus-Group B) immunosuppression for post-liver transplantation HCC recurrence. Competing risk analysis estimated sub-hazard ratios, with testing of discriminant function and calibration. Overall, 508 patients from the intention-to-treat analysis were included (Group A, n = 256; Group B, n = 252). The R3-AFP score distribution was as follows: 42.6% low-risk (n = 216), 35.7% intermediate-risk (n = 181), 19.5% high-risk (n = 99), and 2.2% very-high-risk (n = 11) groups. The R3-AFP score effectively stratified HCC recurrence risk, with increasing risk for each stratum. Calibration of the R3-AFP model significantly outperformed other explant-based models (Milan, Up-to-7, and RETREAT), whereas discrimination power (0.75 [95% CI: 0.69; 0.81]) surpassed these models, except for the RETREAT model ( p = 0.49). Subgroup analysis showed lower discrimination power in the mammalian target of rapamycin group versus the calcineurin inhibitors group ( p = 0.048). In conclusion, the R3-AFP score accurately predicted HCC recurrence using high-quality evidence-based data, exhibiting reduced performance under mammalian target of rapamycin immunosuppression. This highlights the need for further research to evaluate surveillance schedules and adjuvant regimens.

Multitask machine learning-based tumor-associated collagen signatures predict peritoneal recurrence and disease-free survival in gastric cancer.

Accurate prediction of peritoneal recurrence for gastric cancer (GC) is crucial in clinic. The collagen alterations in tumor microenvironment affect the migration and treatment response of cancer cells. Herein, we proposed multitask machine learning-based tumor-associated collagen signatures (TACS), which are composed of quantitative collagen features derived from multiphoton imaging, to simultaneously predict peritoneal recurrence (TACSPR) and disease-free survival (TACSDFS). Among 713 consecutive patients, with 275 in training cohort, 222 patients in internal validation cohort, and 216 patients in external validation cohort, we developed and validated a multitask machine learning model for simultaneously predicting peritoneal recurrence (TACSPR) and disease-free survival (TACSDFS). The accuracy of the model for prediction of peritoneal recurrence and prognosis as well as its association with adjuvant chemotherapy were evaluated. The TACSPR and TACSDFS were independently associated with peritoneal recurrence and disease-free survival in three cohorts, respectively (all P < 0.001). The TACSPR demonstrated a favorable performance for peritoneal recurrence in all three cohorts. In addition, the TACSDFS also showed a satisfactory accuracy for disease-free survival among included patients. For stage II and III diseases, adjuvant chemotherapy improved the survival of patients with low TACSPR and low TACSDFS, or high TACSPR and low TACSDFS, or low TACSPR and high TACSDFS, but had no impact on patients with high TACSPR and high TACSDFS. The multitask machine learning model allows accurate prediction of peritoneal recurrence and survival for GC and could distinguish patients who might benefit from adjuvant chemotherapy.

A nomogram model for early recurrence of HBV-related hepatocellular carcinomas after radical hepatectomy.

To identify the risk factors and construct a predictive model for early recurrence of hepatitis B virus(HBV-)- related hepatocellular carcinomas(HCCs) after radical resection. A total of 465 HBV-related HCC patients underwent radical resections between January 1, 2012 and August 31, 2018.Their data were collected through the inpatient information management system of the First Affiliated Hospital of University of Science and Technology of China. Survival and subgroup analyses of early recurrence among male and female patients were performed using Kaplan-Meier curves. The independent risk factors associated with early postoperative tumor recurrence were analyzed using multivariate Cox proportional hazards regression model. Based on these independent risk factors, a risk function model for early recurrence was fitted, and a column chart for the prediction model was drawn for internal and external validation. A total of 181 patients developed early recurrences, including 156 males and 25 females. There was no difference in the early recurrence rates between males and females. Tumor diameters>5cm, microvascular invasion and albumin level<35 g/L were independent risk factors for early recurrence. A nomogram for the early recurrence prediction model was drawn; the areas under the curve for the model and for external verification were 0.638 and 0.655, respectively. Tumor diameter>5 cm, microvascular invasion, and albumin level<35 g/L were independent risk factors for early recurrence. The prediction model based on three clinical indicators could predict early recurrence, with good discrimination, calibration, and extrapolation.

1413P Multi-modal deep-learning model for real-time prediction of recurrence in early-stage esophageal cancer: A multi-modal approach

1413P Multi-modal deep-learning model for real-time prediction of recurrence in early-stage esophageal cancer: A multi-modal approach

Multimodal ischemic stroke recurrence prediction model based on the capsule neural network and support vector machine.

Ischemic stroke (IS) has a high recurrence rate. Machine learning (ML) models have been developed based on single-modal biochemical tests, and imaging data have been used to predict stroke recurrence. However, the prediction accuracy of these models is not sufficiently high. Therefore, this study aimed to collect biochemical detection and magnetic resonance imaging (MRI) data to establish a dataset and propose a high-performance heterogeneous multimodal IS recurrence prediction model based on deep learning. This is a retrospective cohort study. Data were retrospectively collected from 634 IS patients in Zhuhai, China, a 12-month follow-up was conducted to determine stroke recurrence. We propose the ischemic stroke multi-group learning (ISGL) model, an integrated model for predicting the recurrence risk of multimodal IS in patients, based on a capsule neural network and a linear support vector machine (SVM). Two capsule neural network prediction models based on T1 and T2 signals in the MRI data and a SVM prediction model based on biochemical test data were established. Finally, a vote was conducted on the final judgment of the integrated model. The ISGL model was compared with 6 classical ML and deep learning models: k-nearest neighbors, SVM, logistic regression, random forest, eXtreme Gradient Boosting, and visual geometry group. The results revealed that the accuracy, specificity, sensitivity and the area under the curve of the ISGL model were 95%, 96%, 94%, and 95%, respectively. Among the comparison models, the visual geometry group method exhibited the best performance, but it much lower than those of the ISGL model. Analysis of the importance of biochemical test data revealed that low-density lipoprotein, smoking, and heart disease history were the positively correlated factors, and total cholesterol, high-density lipoprotein, and diabetes were and the negatively correlated factors. This study proposes the ISGL model can be used simultaneously with MRI and biochemical data to predict IS recurrence. This combination resulted in higher rate of performance than that of the other ML models. Additionally, this study found related risk factors affected recurrence, which can be used to intervene in high-risk patients' recurrence as early as possible and promote the development of secondary prevention of stroke.

An inflammatory liquid fingerprint predicting tumor recurrence after liver transplantation for hepatocellular carcinoma.

Tumor recurrence is a life-threatening complication after liver transplantation (LT) for hepatocellular carcinoma (HCC). Precise recurrence risk stratification before transplantation is essential for the management of recipients. Here, we aimed to establish an inflammation-related prediction model for posttransplant HCC recurrence based on pretransplant peripheral cytokine profiling. Two hundred and ninety-three patients who underwent LT in two independent medical centers were enrolled, and their pretransplant plasma samples were sent for cytokine profiling. We identified four independent risk factors, including alpha-fetoprotein, systemic immune-inflammation index, interleukin 6, and osteocalcin in the training cohort (n=190) by COX regression analysis. A prediction model named inflammatory fingerprint (IFP) was established based on the above factors. The IFP effectively predicted posttransplant recurrence (area under the receiver operating characteristic curve [AUROC]: 0.792, C-index: 0.736). The high IFP group recipients had significantly worse 3-year recurrence-free survival rates (37.9vs. 86.9%, p<0.001). Simultaneous T-cell profiling revealed that recipients with high IFP were characterized by impaired T cell function. The IFP also performed well in the validation cohort (n=103, AUROC: 0.807, C-index: 0.681). In conclusion, the IFP efficiently predicted posttransplant HCC recurrence and helped to refine pretransplant risk stratification. Impaired T cell function might be the intrinsic mechanism for the high recurrence risk of recipients in the high IFP group.