Preoperative Prediction Model Research Articles

Prediction of Ki-67 expression and malignant potential in gastrointestinal stromal tumors: novel models based on CE-CT and serological indicators.

To identify more reliable imaging and serological indicators for predicting Ki-67 expression and malignant potential in gastrointestinal stromal tumors, as well as to develop a preoperative prediction model with clinical utility. This study retrospectively analyzed patients with gastrointestinal stromal tumors (GIST) diagnosed at the First Affiliated Hospital of Jinzhou Medical University between May 2018 and May 2024. Univariate logistic analyses, two-way stepwise regression, P-value stepwise regression, and LASSO regression were employed to screen for Ki-67 high expression and high malignant potential risk factors associated with GIST. Models were established using various regression methods; Nomograms, calibration curves, and clinical decision curves were generated for the two best prediction models. Two-way stepwise regression analysis revealed that diameter (P=0.037; OR=1.22; 95% CI: 1.01 - 1.46), growth pattern (extraluminal type: P=0.028; OR=3.54; 95% CI: 1.14 - 10.94), enhancement model (P=0.099; OR=0.39; 95% CI: 0.12 - 1.20), EVFDM (P=0.069; OR=0.43; 95% CI: 0.17 - 1.07), PLR (P=0.099; OR=3.06; 95% CI: 0.81 - 11.59), and OPNI (P=0.058; OR=2.38; 95% CI: 0.97 - 5.84) are identified as independent risk factors for Ki-67 expression. Utilizing the two-way stepwise regression model to predict Ki-67 expression, the area under the curve (AUC) for the training group was 0.865 (95% CI: 0.807-0.922), while for the validation group it was 0.784 (95% CI: 0.631-0.937). The Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC) for the training group were 153.360 and 174.619, respectively. Two-way stepwise regression analysis revealed that volume (P < .001, OR = 1.06; 95% CI: 1.03 - 1.09), contour (P = 0.066; OR = 0.17; 95% CI: 0.05 - 0.62), ulcer (P = 0.094; OR = 0.16; 95% CI: 0.03 - 0.98), IBSC (P = 0.008; OR = 5.27; 95% CI: 1.57 - 17.69), and OPNI (P = 0.045; OR = 0.22; 95% CI: 0.05 - 0.96) are independent risk factors for malignant potential. Utilizing the two-way stepwise regression model to predict malignant potential, the AUC for the training group was 0.950 (95% CI: 0.920 - 0.980), while for the validation group it was 0.936 (95% CI: 0.867 - 1.000). The AIC and BIC values for the training group were 96.330 and 114.552, respectively. Diameter, growth pattern, enhancement pattern, EVFDM, PLR, and OPNI are independent risk factors for GIST with high Ki-67 expression. Additionally, volume, contour, ulceration, IBSC, and OPNI serve as independent risk factors for GIST with high malignant potential. The preoperative models developed using CT images can predict the malignant potential and Ki-67 expression status of GIST to a certain extent. When combined with serological indicators, these models' predictive performance can be further enhanced.

Establishment a nomogram model for preoperative prediction of the risk of cholangiocarcinoma with microvascular invasion

Establishment a nomogram model for preoperative prediction of the risk of cholangiocarcinoma with microvascular invasion

Development and Validation of a Comprehensive Predictive Model for Surgical Planning in Patients with Renal Cell Carcinoma and Inferior Vena Cava Tumor Thrombus

ObjectiveTo investigate preoperative predictors for selecting different surgical approaches in patients with renal cell carcinoma with inferior vena cava (IVC) tumor thrombus (RCC-IVCTT), and to establish and validate corresponding predictive models. MethodsClinical data of 583 RCC-IVCTT patients were retrospectively analyzed. Of these, 465 cases were used to construct predictive models, and 118 cases were used for validation. Univariate and multivariate analyses identified independent predictors for surgical strategies. Two nomogram prediction models were established based on relevant independent factors to predict surgical approach. ResultsIn the development cohort, 342 patients underwent IVC thrombectomy (IVCT), 91 underwent IVC cavectomy (IVCC), and 32 underwent IVC reconstruction (IVCR). Multivariate logistic regression analysis identified the following predictors for inability to perform IVCT: higher Mayo classification of tumor thrombus (TT), IVC wall invasion, presence of bland thrombus, pan-immune-inflammation value (PIV) > 358×109, and maximum anteroposterior (AP) diameter of IVC at renal vein ostium (RVo) > 24mm. Platelet > 170×109/L and inadequate collateral circulation were predictors for IVCR. The developed model predicted capacity of the nomogram was evaluated in terms of its calibration, discrimination, and clinical utility. The validation set confirmed these findings. ConclusionThe comprehensive preoperative predictive model for RCC-IVCTT patients aids in preoperative determination of the required surgical approach and necessity for IVC angiography, facilitating perioperative preparation and reducing unnecessary invasive examinations.

Prediction of microvascular invasion in hepatocellular carcinoma with conventional ultrasound, Sonazoid-enhanced ultrasound, and biochemical indicator: a multicenter study

PurposeTo develop and validate a preoperative prediction model based on multimodal ultrasound and biochemical indicator for identifying microvascular invasion (MVI) in patients with a single hepatocellular carcinoma (HCC) ≤ 5 cm.MethodsFrom May 2022 to November 2023, a total of 318 patients with pathologically confirmed single HCC ≤ 5 cm from three institutions were enrolled. All of them underwent preoperative biochemical, conventional ultrasound (US), and contrast-enhanced ultrasound (CEUS) (Sonazoid, 0.6 mL, bolus injection) examinations. Univariate and multivariate logistic regression analyses on clinical information, biochemical indicator, and US imaging features were performed in the training set to seek independent predictors for MVI-positive. The models were constructed and evaluated using the area under the receiver operating characteristic curve (AUC), calibration curve, and decision curve analysis in both validation and test sets. Subgroup analyses in patients with different liver background and tumor sizes were conducted to further investigate the model’s performance.ResultsLogistic regression analyses showed that obscure tumor boundary in B-mode US, intra-tumoral artery in pulsed-wave Doppler US, complete Kupffer-phase agent clearance in Sonazoid-CEUS, and biomedical indicator PIVKA-II were independently correlated with MVI-positive. The combined model comprising all predictors showed the highest AUC, which were 0.937 and 0.893 in the validation and test sets. Good calibration and prominent net benefit were achieved in both sets. No significant difference was found in subgroup analyses.ConclusionsThe combination of biochemical indicator, conventional US, and Sonazoid-CEUS features could help preoperative MVI prediction in patients with a single HCC ≤ 5 cm.Critical relevance statementInvestigation of imaging features in conventional US, Sonazoid-CEUS, and biochemical indicators showed a significant relation with MVI-positivity in patients with a single HCC ≤ 5 cm, allowing the construction of a model for preoperative prediction of MVI status to help treatment decision making.Key PointsMVI status is important for patients with a single HCC ≤ 5 cm.The model based on conventional US, Sonazoid-CEUS and PIVKA-II performs best for MVI prediction.The combined model has potential for preoperative prediction of MVI status.Graphical

Predicting periprosthetic joint infection: external validation of preoperative prediction models.

Introduction: Prediction models for periprosthetic joint infections (PJIs) are gaining interest due to their potential to improve clinical decision-making. However, their external validity across various settings remains uncertain. This study aimed to externally validate promising preoperative PJI prediction models in a recent multinational European cohort. Methods: Three preoperative PJI prediction models - by Tan et al.(2018), Del Toro et al.(2019), and Bülow et al.(2022) - that have previously demonstrated high levels of accuracy were selected for validation. A retrospective observational analysis of patients undergoing total hip arthroplasty (THA) and total knee arthroplasty (TKA) at centers in the Netherlands, Portugal, and Spain between January2020 and December2021 was conducted. Patient characteristics were compared between our cohort and those used to develop the models. Performance was assessed through discrimination and calibration. Results: The study included 2684 patients, 60 of whom developed a PJI (2.2 %). Our cohort differed from the models' original cohorts with respect to demographic variables, procedural variables, and comorbidity prevalence. The overall accuracies of the models, measured with the statistic, were 0.72, 0.69, and 0.72 for the Tan, Del Toro, and Bülow models, respectively. Calibration was reasonable, but the PJI risk estimates were most accurate for predicted infection risks below 3 %-4 %. The Tan model overestimated PJI risk above 4 %, whereas the Del Toro model underestimated PJI risk above 3 %. Conclusions: The Tan, Del Toro, and Bülow PJI prediction models were externally validated in this multinational cohort, demonstrating potential for clinical application in identifying high-risk patients and enhancing preoperative counseling and prevention strategies.

Trajectory Analysis of Healthcare Use Before and After Gastrointestinal Cancer Surgery.

Frailty correlates with worse post-operative outcomes and higher surgical costs, but the long-term impact on healthcare utilization remains ill-defined. We sought to evaluate patterns of healthcare utilization pre- and post-surgery among patients with gastrointestinal cancer and characterize the association with frailty. Data on patients who underwent surgical resection for liver, biliary, pancreatic, colon and rectal cancer were obtained from the 2005-2020 SEER-Medicare database. Frailty was assessed using the claims-based frailty index. Group-based trajectory modelling identified clusters of patients with discrete patterns of healthcare utilization. Multivariable regression was performed to predict cluster membership based on preoperative factors, including frailty. Among 66,684 beneficiaries, four distinct utilization trajectories based on data from 12 months before and after surgery were identified. Following a surge in utilization during the month of surgery, most patients reverted to pre-surgery baseline utilization (low: n=6588, 9.9%; moderate: n=17,627, 26.4%; high: n=29,850, 44.8%). However, a notable trajectory involving 12,619 (18.9%) patients was identified, wherein surgery precipitated a transition from a "low" pre-surgery utilization state to a "high" utilization state post-surgery. Frail patients were more likely to be among those individuals who transitioned to high utilizers (low: 4.2% vs. vs. transition: 12.6% vs. high: 7.5%; p<0.001). On multivariable analysis incorporating preoperative variables, frailty was associated with high group trajectory membership (ref: least and moderate; highest: OR 4.90, 95%CI 4.49-5.35; p<0.001). Patients with gastrointestinal cancer demonstrated distinct clusters of healthcare utilization after surgical resection. Preoperative predictive models may help differentiate different health care utilization trajectories to help tailor care for patients in the postoperative period.

An immune signature of postoperative cognitive decline: A prospective cohort study.

Postoperative cognitive decline (POCD) is the predominant complication affecting patients over 60 years old following major surgery, yet its prediction and prevention remain challenging. Understanding the biological processes underlying the pathogenesis of POCD is essential for identifying mechanistic biomarkers to advance diagnostics and therapeutics. This study aimed to provide a comprehensive analysis of immune cell trajectories differentiating patients with and without POCD and to derive a predictive score enabling the identification of high-risk patients during the preoperative period. Twenty-six patients aged 60 years old and older undergoing elective major orthopedic surgery were enrolled in a prospective longitudinal study, and the occurrence of POCD was assessed seven days after surgery. Serial samples collected before surgery, and one, seven, and 90 days after surgery were analyzed using a combined single-cell mass cytometry and plasma proteomic approach. Unsupervised clustering of the high-dimensional mass cytometry data was employed to characterize time-dependent trajectories of all major innate and adaptive immune cell frequencies and signaling responses. Sparse machine learning coupled with data-driven feature selection was applied to the pre-surgery immunological dataset to classify patients at risk for POCD. The analysis identified cell-type and signaling-specific immune trajectories differentiating patients with and without POCD. The most prominent trajectory features revealed early exacerbation of JAK/STAT and dampening of inhibitory κB and nuclear factor-κB immune signaling responses in patients with POCD. Further analyses integrating immunological and clinical data collected before surgery identified a preoperative predictive model comprising one plasma protein and ten immune cell features that classified patients at risk for POCD with excellent accuracy (AUC=0.80, P=2.21e-02 U-test). Immune system-wide monitoring of patients over 60 years old undergoing surgery unveiled a peripheral immune signature of POCD. A predictive model built on immunological data collected before surgery demonstrated greater accuracy in predicting POCD compared to known clinical preoperative risk factors, offering a concise list of biomarker candidates to personalize perioperative management.

Predictive Value of Machine Learning Model Based on CT Values for Urinary Tract Infection Stones

Preoperative diagnosis of infection stones presents a significant clinical challenge. We developed a machine learning model to predict urinary infection stones using Computed Tomography (CT) values, enabling in vivo preoperative identification. In this study, we included 1209 patients who underwent urinary lithotripsy at our hospital. Seven machine learning algorithms along with eleven preoperative variables, were used to construct the prediction model. Subsequently, Model performance was evaluated by calculating AUC and AUPR for subjects in the validation set. On the validation set, all seven machine learning models demonstrated strong discrimination (AUC: 0.687-0.947). Additionally, the XGBoost model was identified as the optimal model significantly outperforming the traditional LR model. Taken together, the XGBoost model is the first machine learning model for preoperative prediction of infection stones based on CT values. It can rapidly and accurately identify infection stones in vitro, providing valuable guidance for urologists in managing these stones.

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.

Advanced diffusion-weighted MRI models for preoperative prediction of lymph node metastasis in resectable gastric cancer.

To investigate the potential of six advanced diffusion-weighted imaging (DWI) models for preoperative prediction of lymph node metastasis (LNM) in resectable gastric cancer (GC). Between Nov 2022 and Nov 2023, standard MRI scans were prospectively performed in consecutive patients with endoscopic pathology-confirmed gastric adenocarcinoma who were referred for direct radical gastrectomy. Six DWI models, including fractional order calculus (FROC), continuous-time random walk (CTRW), diffusion kurtosis imaging (DKI), intravoxel incoherent motion (IVIM), the mono-exponential model (MEM) and the stretched exponential model (SEM) were computed. Surgical pathologic diagnosis of LNM was the reference standard, and patients were classified into LNM-positive or LNM-negative groups accordingly. The morphological features and quantitative parameters of the DWI models in different LNM categories were analyzed and compared. Multivariable logistic regression was used to screen significant predictors. Receiver-operating characteristic curves and the area under the curve (AUC) were plotted to evaluate the performances, the Delong test was performed to compare the AUCs. In the LNM-positive group, tumor thickness and kurtosis (DKI_K) were significantly higher, while anomalous diffusion coefficient (CTRW_D), diffusivity (DKI_D), diffusion coefficient (FROC_D), pseudodiffusion coefficient (IVIM_D*), perfusion fraction (IVIM_f), and ADC were lower compared to the LNM-negative group. Clinical tumor staging (cT) and CTRW_D were independent predictors. Their combination demonstrated a superior AUC of 0.930, significantly higher than that of individual parameters. Tumor thickness, DKI_K, CTRW_D, DKI_D, FROC_D, IVIM_D*, IVIM_f and ADC were associated with LNM status. The combination of independent predictors of cT and CTRW_D further enhanced the performance.

Preoperative prediction model of lymph node metastasis in the inguinal and femoral region based on radiomics and artificial intelligence

ObjectiveTo predict preoperative inguinal lymph node metastasis in vulvar cancer patients using a machine learning model based on imaging features and clinical data from pelvic magnetic resonance imaging (MRI).Methods52 vulvar...

Clinical Nomogram Model for Pre-Operative Prediction of Microvascular Invasion of Hepatocellular Carcinoma before Hepatectomy.

Background and Objectives: Microvascular invasion (MVI) significantly impacts recurrence and survival rates after liver resection in hepatocellular carcinoma (HCC). Pre-operative prediction of MVI is crucial in determining the treatment strategy. This study aims to develop a nomogram model to predict the probability of MVI based on clinical features in HCC patients. Materials and Methods: A total of 489 patients with a pathological diagnosis of HCC were enrolled from our hospital. Those registered from 2012-2015 formed the derivation cohort, and those from 2016-2019 formed the validation cohort for pre-operative prediction of MVI. A nomogram model for prediction was created using a regression model, with risk factors derived from clinical and tumor-related features before surgery. Results: Using the nomogram model to predict the odds ratio of MVI before hepatectomy, the AFP, platelet count, GOT/GPT ratio, albumin-alkaline phosphatase ratio, ALBI score, and GNRI were identified as significant variables for predicting MVI. The Youden index scores for each risk variable were 0.287, 0.276, 0.196, 0.185, 0.115, and 0.112, respectively, for the AFP, platelet count, GOT/GPT ratio, AAR, ALBI, and GNRI. The maximum value of the total nomogram scores was 220. An increase in the number of nomogram points indicated a higher probability of MVI occurrence. The accuracy rates ranged from 55.9% to 64.4%, and precision rates ranged from 54.3% to 68.2%. Overall survival rates were 97.6%, 83.4%, and 73.9% for MVI(-) and 80.0%, 71.8%, and 41.2% for MVI(+) (p < 0.001). The prognostic effects of MVI(+) on tumor-free survival and overall survival were poor in both the derivation and validation cohorts. Conclusions: Our nomogram model, which integrates clinical factors, showed reliable calibration for predicting MVI and provides a useful tool enabling surgeons to estimate the probability of MVI before resection. Consequently, surgical strategies and post-operative care programs can be adapted to improve the prognosis of HCC patients where possible.

Using Machine Learning to Predict Outcomes Following Transfemoral Carotid Artery Stenting.

Transfemoral carotid artery stenting (TFCAS) carries important perioperative risks. Outcome prediction tools may help guide clinical decision-making but remain limited. We developed machine learning algorithms that predict 1-year stroke or death following TFCAS. The VQI (Vascular Quality Initiative) database was used to identify patients who underwent TFCAS for carotid artery stenosis between 2005 and 2024. We identified 112 features from the index hospitalization (82 preoperative [demographic/clinical], 13 intraoperative [procedural], and 17 postoperative [in-hospital course/complications]). The primary outcome was 1-year postprocedural stroke or death. The data were divided into training (70%) and test (30%) sets. Six machine learning models were trained using preoperative features with 10-fold cross-validation. The primary model evaluation metric was area under the receiver operating characteristic curve. The algorithm with the best performance was further trained using intra- and postoperative features. Model robustness was assessed using calibration plots and Brier scores. Overall, 35 214 patients underwent TFCAS during the study period and 3257 (9.2%) developed 1-year stroke or death. The best preoperative prediction model was extreme gradient boosting, achieving an area under the receiver operating characteristic curve of 0.94 (95% CI, 0.93-0.95). In comparison, logistic regression had an AUROC of 0.65 (95% CI, 0.63-0.67). The extreme gradient boosting model maintained excellent performance at the intra- and postoperative stages, with area under the receiver operating characteristic curve values of 0.94 (95% CI, 0.93-0.95) and 0.98 (95% CI, 0.97-0.99), respectively. Calibration plots showed good agreement between predicted/observed event probabilities with Brier scores of 0.11 (preoperative), 0.11 (intraoperative), and 0.09 (postoperative). Machine learning can accurately predict 1-year stroke or death following TFCAS, performing better than logistic regression.

Prediction of Length of Stay After Colorectal Surgery Using Intraoperative Risk Factors.

The primary objective of this study was to develop a length of stay (LOS) prediction model. Predicting the LOS is crucial for patient care, planning, managing expectations, and optimizing hospital resources. Prolonged LOS after colorectal surgery is largely influenced by complications, and an accurate prediction model could significantly benefit patient outcomes and healthcare efficiency. This study included patients who underwent colorectal surgery in 14 different hospitals between January 2016 and December 2020. Two distinct random forest models were developed: one solely based on preoperative variables (preoperative prediction model [PP model]) and the other incorporating both preoperative and intraoperative variables (intraoperative prediction model [IP model]). Both models underwent validation using 10-fold cross-validation. The discriminative power of the model was assessed using the area under the curve (AUC), and calibration was evaluated using a calibration curve. The 2 developed models were compared using DeLong test. A total of 2140 patients were included in the analysis. After internal validation, the PP model achieved an AUC of 0.75 (95% confidence interval [CI]: 0.73-0.77), and the IP model achieved an AUC of 0.84 (95% CI: 0.82-0.85). The difference in discrimination between the 2 models was statistically significant (DeLong test, P < 0.001). Both models exhibited good calibration. Incorporating intraoperative parameters enhances the accuracy of the predictive model for LOS after colorectal surgery. Improving LOS prediction can assist in managing the increasing number of patients and optimizing the allocation of healthcare resources.

Preoperative prediction of microvascular invasion risk in hepatocellular carcinoma with MRI: peritumoral versus tumor region

ObjectivesTo explore the predictive performance of tumor and multiple peritumoral regions on dynamic contrast-enhanced magnetic resonance imaging (MRI), to identify optimal regions of interest for developing a preoperative predictive model for the grade of microvascular invasion (MVI).MethodsA total of 147 patients who were surgically diagnosed with hepatocellular carcinoma, and had a maximum tumor diameter ≤ 5 cm were recruited and subsequently divided into a training set (n = 117) and a testing set (n = 30) based on the date of surgery. We utilized a pre-trained AlexNet to extract deep learning features from seven different regions of the maximum transverse cross-section of tumors in various MRI sequence images. Subsequently, an extreme gradient boosting (XGBoost) classifier was employed to construct the MVI grade prediction model, with evaluation based on the area under the curve (AUC).ResultsThe XGBoost classifier trained with data from the 20-mm peritumoral region showed superior AUC compared to the tumor region alone. AUC values consistently increased when utilizing data from 5-mm, 10-mm, and 20-mm peritumoral regions. Combining arterial and delayed-phase data yielded the highest predictive performance, with micro- and macro-average AUCs of 0.78 and 0.74, respectively. Integration of clinical data further improved AUCs values to 0.83 and 0.80.ConclusionCompared with those of the tumor region, the deep learning features of the peritumoral region provide more important information for predicting the grade of MVI. Combining the tumor region and the 20-mm peritumoral region resulted in a relatively ideal and accurate region within which the grade of MVI can be predicted.Clinical relevance statementThe 20-mm peritumoral region holds more significance than the tumor region in predicting MVI grade. Deep learning features can indirectly predict MVI by extracting information from the tumor region and directly capturing MVI information from the peritumoral region.Key PointsWe investigated tumor and different peritumoral regions, as well as their fusion.MVI predominantly occurs in the peritumoral region, a superior predictor compared to the tumor region.The peritumoral 20 mm region is reasonable for accurately predicting the three-grade MVI.Graphical

Radiogenomic analysis for predicting lymph node metastasis and molecular annotation of radiomic features in pancreatic cancer

BackgroundTo provide a preoperative prediction model for lymph node metastasis in pancreatic cancer patients and provide molecular information of key radiomic features.MethodsTwo cohorts comprising 151 and 54 pancreatic cancer patients were included in the analysis. Radiomic features from the tumor region of interests were extracted by using PyRadiomics software. We used a framework that incorporated 10 machine learning algorithms and generated 77 combinations to construct radiomics-based models for lymph node metastasis prediction. Weighted gene coexpression network analysis (WGCNA) was subsequently performed to determine the relationships between gene expression levels and radiomic features. Molecular pathways enrichment analysis was performed to uncover the underlying molecular features.ResultsPatients in the in-house cohort (mean age, 61.3 years ± 9.6 [SD]; 91 men [60%]) were separated into training (n = 105, 70%) and validation (n = 46, 30%) cohorts. A total of 1,239 features were extracted and subjected to machine learning algorithms. The 77 radiomic models showed moderate performance for predicting lymph node metastasis, and the combination of the StepGBM and Enet algorithms had the best performance in the training (AUC = 0.84, 95% CI = 0.77–0.91) and validation (AUC = 0.85, 95% CI = 0.73–0.98) cohorts. We determined that 15 features were core variables for lymph node metastasis. Proliferation-related processes may respond to the main molecular alterations underlying these features.ConclusionsMachine learning-based radiomics could predict the status of lymph node metastasis in pancreatic cancer, which is associated with proliferation-related alterations.

Prediction of Early Adverse Events After THA: A Comparison of Different Machine-Learning Strategies Based on 262,356 Observations From the Nordic Arthroplasty Register Association (NARA) Dataset.

Preoperative risk prediction models can support shared decision-making before total hip arthroplasties (THAs). Here, we compare different machine-learning (ML) approaches to predict the six-month risk of adverse events following primary THA to obtain accurate yet simple-to-use risk prediction models. We extracted data on primary THAs (N = 262,356) between 2010 and 2018 from the Nordic Arthroplasty Register Association dataset. We benchmarked a variety of ML algorithms in terms of the area under the receiver operating characteristic curve (AUROC) for predicting the risk of revision caused by periprosthetic joint infection (PJI), dislocation or periprosthetic fracture (PPF), and death. All models were internally validated against a randomly selected test cohort (one-third of the data) that was not used for training the models. The incidences of revisions because of PJI, dislocation, and PPF were 0.8%, 0.4%, and 0.3%, respectively, and the incidence of death was 1.2%. Overall, Lasso regression with stable iterative variable selection (SIVS) produced models using only four to five input variables but with AUROC comparable to more complex models using all 32 variables available. The SIVS-based Lasso models based on age, sex, preoperative diagnosis, bearing couple, fixation, and surgical approach predicted the risk of revisions caused by PJI, dislocations, and PPF, as well as death, with AUROCs of 0.61, 0.67, 0.76, and 0.86, respectively. Our study demonstrates that satisfactory predictive potential for adverse events following THA can be reached with parsimonious modeling strategies. The SIVS-based Lasso models may serve as simple-to-use tools for clinical risk assessment in the future.

A Preoperative Prediction Model for Lymph Node Metastasis in Patients with Gastric Cancer Using a Machine Learning-based Ultrasomics Approach.

This study aimed to develop an ultrasomics model for predicting lymph node metastasis preoperative in patients with gastric cancer (GC). This study enrolled GC patients who underwent preoperative ultrasound examination. Manual segmentation of the region of interest (ROI) was performed by an experienced radiologist to extract radiomics features using the Pyradiomics software. The Z-score algorithm was used for feature normalization, followed by the Wilcoxon test to identify the most informative features. Linear prediction models were constructed using the least absolute shrinkage and selection operator (LASSO). The performance of the ultrasomics model was evaluated using the area under curve (AUC), sensitivity, specificity, and the corresponding 95% confidence intervals (CIs). A total of 464 GC patients (mean age: 60.4 years ±11.3 [SD]; 328 men [70.7%]) were analyzed, of whom 291 had lymph node metastasis. The patients were randomly assigned to either the training (n=324) or test (n=140) sets, using a 7:3 ratio. An ultrasomics model that consisted of 19 radiomics features was developed using Wilcoxon and LASSO algorithms in the training set. Our ultrasomics model showed moderate performance for lymph node metastasis prediction in both the training (AUC: 0.802, 95%CI: 0.752-0.851, P<0.001) and test sets (AUC: 0.802, 95%CI: 0.724-0.879, P<0.001). The calibration curve analysis indicated good agreement between the predicted probabilities of ultrasomics and actual lymph node metastasis status. Our study highlights the potential of a machine learning-based ultrasomics model in predicting lymph node metastasis in GC patients, offering implications for personalized therapy approaches.

Preoperative prediction of nodal status using clinical data and artificial intelligence derived mammogram features enabling abstention of sentinel lymph node biopsy in breast cancer.

Patients with clinically node-negative breast cancer have a negative sentinel lymph node status (pN0) in approximately 75% of cases and the necessity of routine surgical nodal staging by sentinel lymph node biopsy (SLNB) has been questioned. Previous prediction models for pN0 have included postoperative variables, thus defeating their purpose to spare patients non-beneficial axillary surgery. We aimed to develop a preoperative prediction model for pN0 and to evaluate the contribution of mammographic breast density and mammogram features derived by artificial intelligence for de-escalation of SLNB. This retrospective cohort study included 755 women with primary breast cancer. Mammograms were analyzed by commercially available artificial intelligence and automated systems. The additional predictive value of features was evaluated using logistic regression models including preoperative clinical variables and radiological tumor size. The final model was internally validated using bootstrap and externally validated in a separate cohort. A nomogram for prediction of pN0 was developed. The correlation between pathological tumor size and the preoperative radiological tumor size was calculated. Radiological tumor size was the strongest predictor of pN0 and included in a preoperative prediction model displaying an area under the curve of 0.68 (95% confidence interval: 0.63-0.72) in internal validation and 0.64 (95% confidence interval: 0.59-0.69) in external validation. Although the addition of mammographic features did not improve discrimination, the prediction model provided a 21% SLNB reduction rate when a false negative rate of 10% was accepted, reflecting the accepted false negative rate of SLNB. This study shows that the preoperatively available radiological tumor size might replace pathological tumor size as a key predictor in a preoperative prediction model for pN0. While the overall performance was not improved by mammographic features, one in five patients could be omitted from axillary surgery by applying the preoperative prediction model for nodal status. The nomogram visualizing the model could support preoperative patient-centered decision-making on the management of the axilla.

Construction of a nomogram model for predicting the outcome of debulking surgery for ovarian cancer on the basis of clinical indicators.

This study aimed to investigate the risk factors affecting satisfaction with debulking surgery for ovarian cancer and establish a preoperative clinical predictive model. Clinical data from 131 patients who underwent ovarian cancer debulking surgery at Jiangnan University Affiliated Hospital between 2016 and 2022 were collected. Patients were randomly separated into an experimental group and a control group in a 7:3 ratio. On the basis of intraoperative outcomes, patients were grouped as either surgery-satisfactory or surgery-unsatisfactory. Clinical indicators were compared through single-factor analysis between groups. Significantly different factors (p < 0.1) were further analyzed through multivariate logistic regression. A predictive nomogram model was developed and validated by receiver operating characteristic (ROC), calibration, and clinical decision curves. Single-factor analysis revealed the significance of factors such as albumin levels, alkaline phosphatase (ALP), ECOG scores, CA125, HE4, and lymph node metastasis. Multivariate regression analysis identified albumin levels, ALP, ECOG scores, HE4, and lymph node metastasis as independent risk factors for satisfactory surgical outcomes in patients with ovarian cancer undergoing debulking surgery as (p < 0.05). A clinical predictive model was successfully constructed. ROC curves showed AUC values of 0.818 and 0.796 for the experimental and validation groups, respectively. Internal validation through the bootstrap method confirmed the model's fit in both groups. Meanwhile, the clinical decision curve demonstrated the model's high utility. Independent risk factors associated with satisfactory tumor reduction in patients with ovarian cancer undergoing debulking surgery included decreased albumin levels, ALP > 137 U/L, ECOG = 1 score, HE4 > 140 pmol/L, and lymph node metastasis. Constructing a clinical predictive model through logistic regression analysis enables individualized testing and maximizes clinical benefits.