External Validation Set Research Articles

Functional evaluation of TMEM176B and its predictive role for severe respiratory viral infection through integrated analysis of single-cell and bulk RNA-sequencing.

Transmembrane protein 176B (TMEM176B), localized mainly on the endosomal membrane, has been reported as an immune regulatory factor in malignant diseases. However, the biological function of this molecule remains undetermined during respiratory viral infections. To investigate the functions and prognostic value of this gene, six gene sets were selected from the Gene Expression Omnibus database for research. First, the function of TMEM176B and its co-expressed genes were evaluated at different levels (cell, peripheral blood, lung tissue). Afterwards, a machine learning algorithm was utilized to analyze the relationship between TMEM176B and its interacting genes with prognosis. After importance evaluation and variable screening, a prognostic model was established. Finally, the reliability of the model was further verified through external data sets. In vitro experiments were conducted to validate the function of TMEM176B. TMEM176B and its co-expressed genes are involved in multiple processes such as inflammasome activation, myeloid immune cell development, and immune cell infiltration. Machine learning further screened 27 interacting gene modules including TMEM176B as prognostic models for severe respiratory viral infections, with the area under the ROC curve (AUCs) of 0.986 and 0.905 in derivation and external validation sets, respectively. We further confirmed that viral load as well as NLRP3 activation and cell death were significantly enhanced in TMEM176B-/- THP-1-differentiated macrophages via in vitro experiments. Our study revealed that TMEM176B is involved in a wide range of biological functions in respiratory viral infections and has potential prognostic value, which is expected to bring new insights into the clinical management of severe respiratory viral infection hosts.

NADPHnet: a novel strategy to predict compounds for regulation of NADPH metabolism via network-based methods.

Identification of compounds to modulate NADPH metabolism is crucial for understanding complex diseases and developing effective therapies. However, the complex nature of NADPH metabolism poses challenges in achieving this goal. In this study, we proposed a novel strategy named NADPHnet to predict key proteins and drug-target interactions related to NADPH metabolism via network-based methods. Different from traditional approaches only focusing on one single protein, NADPHnet could screen compounds to modulate NADPH metabolism from a comprehensive view. Specifically, NADPHnet identified key proteins involved in regulation of NADPH metabolism using network-based methods, and characterized the impact of natural products on NADPH metabolism using a combined score, NADPH-Score. NADPHnet demonstrated a broader applicability domain and improved accuracy in the external validation set. This approach was further employed along with molecular docking to identify 27 compounds from a natural product library, 6 of which exhibited concentration-dependent changes of cellular NADPH level within 100 μM, with Oxyberberine showing promising effects even at 10 μM. Mechanistic and pathological analyses of Oxyberberine suggest potential novel mechanisms to affect diabetes and cancer. Overall, NADPHnet offers a promising method for prediction of NADPH metabolism modulation and advances drug discovery for complex diseases.

Pairwise analysis of gene expression for oral squamous cell carcinoma via a large-scale transcriptome integration.

Among all cancers occurring in the head and neck region, oral squamous cell carcinoma (OSCC) is the most common oral malignant tumours characterized by its aggressiveness and metastasis. The development of transcriptomics technology has greatly facilitated the diagnosis of various cancers. However, identifying genetic biomarkers is limited by data from a single batch of OSCC samples, and integrating analysis across different platforms remains a great challenge. In this study, we integrated five OSCC transcriptome datasets using an innovative strategy capable of mitigating batch effect, and extracting information from different datasets based on changes in the relative expression of gene pairs. By leveraging a machine learning method, we developed a prediction model including 27 differential gene pairs (DGPs) to discriminate OSCC from control samples, achieving an area under the receiver operating characteristic curve (AUC) of 0.8987 for the training set. Moreover, the model demonstrated commendable performance in four external validation sets, with AUCs of 0.9926, 0.9688, 0.8052 and 0.8565, respectively. Subsequently, a prognostic model was constructed based on six key gene pairs through univariate and multivariate Cox regression analysis. The AUCs of the model at 1-year and 3-year overall survival time prediction were 0.717 and 0.779 in an independent dataset. Our result demonstrates the effectiveness of this new method of integrating data and identifying DGPs. Using DGPs can significantly improve the performance of both diagnostic and prognostic models.

Radiomics model for predicting distant metastasis in soft tissue sarcoma of the extremities and trunk treated with surgery.

The aim of this study was to develop a radiomics model based on magnetic resonance imaging (MRI) for predicting metastasis in soft tissue sarcomas (STSs) treated with surgery. MRI and clinical data of 73 patients with STSs of the extremities and trunk were obtained from TCIA database and Jiangsu Cancer Hospital as the training set, data of other 40 patients were retrospectively collected at our institution as the external validation set. Radiomics features were extracted from both intratumoral and peritumoral regions of fat-suppressed T2-weighted images (FS-T2WIs) of patients, and 3D ResNet10 was used to extract deep learning features. Recursive feature elimination (RFE) and least absolute shrinkage and selection operator (LASSO) algorithms were used for the selection of features. Based on 4 different sets of features, 5 machine learning algorithms were used to construct intratumor, peritumor, combined intratumor and peritumor radiomics models and deep learning radiomics (DLR) model. The area under the ROC curve (AUC) and Decision curve analysis (DCA) were used to evaluate the ability of models to predict metastasis. Based on 20 selected features from the deep-learning and radiomics features set, the DLR model was able to predict metastasis in the validation dataset, with an AUC of 0.9770. The DCA and Hosmer-Lemeshow test revealed that the DLR model had good clinical benefit and consistency. By getting richer information from MRI, The DLR model is a noninvasive, low-cost method for predicting the risk of metastasis in STSs, and can help develop appropriate treatment programs.

A machine learning model based on results of a comprehensive radiological evaluation can predict the prognosis of basal ganglia cerebral hemorrhage treated with neuroendoscopy.

Spontaneous intracerebral hemorrhage is the second most common subtype of stroke. Therefore, this study aimed to investigate the risk factors affecting the prognosis of patients with basal ganglia cerebral hemorrhage after neuroendoscopy. Between January 2020 and January 2024, 130 patients with basal ganglia cerebral hemorrhage who underwent neuroendoscopy were recruited from two independent centers. We split this dataset into training (n = 79), internal validation (n = 22), and external validation (n = 29) sets. The least absolute shrinkage and selection operator-regression algorithm was used to select the top 10 important radiomic features of different regions (perioperative hemorrhage area [PRH], perioperative surround area [PRS], postoperative hemorrhage area [PSH], and postoperative edema area [PSE]). The black hole, island, blend, and swirl signs were evaluated. The top 10 radiomic features and 4 radiological features were combined to construct the k-nearest neighbor classification (KNN), logistic regression (LR), and support vector machine (SVM) models. Finally, the performance of the perioperative hemorrhage and postoperative edema machine learning models was validated using another independent dataset (n = 29). The primary outcome is mRS at 6 months after discharge. The mRS score greater than 3 defined as functional independence. A total of 12 models were built: PRH-KNN, PRH-LR, PRH-SVM, PRS-KNN, PRS-LR, PRS-SVM, PSH-KNN, PSH-LR, PSH-SVM, PSE-KNN, PSE-LR, and PSE-SVM, with corresponding areas under the curve (AUC) values in the internal validation set of 0.95, 0.91, 0.94, 0.52, 0.91, 0.54, 0.67, 0.9, 0.72, 0.92, 0.92, and 0.95, respectively. The AUC values of the PRH-KNN, PRH-LR, PRH-SVM, PSE-KNN, PSE-LR, and PSE-SVM in the external validation were 0.9, 0.92, 0.89, 0.91, 0.92, and 0.88, respectively. The model built based on computed tomography images of different regions accurately predicted the prognosis of patients with basal ganglia cerebral hemorrhage treated with neuroendoscopy. The models built based on the preoperative hematoma area and postoperative edema area showed excellent predictive efficacy in external verification, which has important clinical significance.

Multimodal radiomics and deep learning models for predicting early femoral head deformity in LCPD

PurposeTo develop a predictive model combining clinical, radiomic, and deep learning features based on X-ray and MRI to identify risk factors for early femoral head deformity in Legg-Calvé-Perthes disease (LCPD). MethodsThis study involved 152 patients diagnosed with early unilateral LCPD across two centers between January 2013 and December 2023, and included an independent external validation set to assess generalizability. Four machine learning methods, including logistic regression (LR), random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGBoost), were employed to develop radiomics deep learning signatures. The clinical-radiomics model (Clinic + Rad), clinical-deep learning model (Clinic + DL), and clinical-radiomics-deep learning model (Clinic + Rad + DL) were developed by integrating radiomics deep learning signatures with clinical variables. The best model, integrated into a nomogram for clinical application, was evaluated using the area under the receiver operating characteristic curve (AUC). ResultsAmong the four machine learning methods, XGBoost demonstrated superior performance in our patient dataset: radiomic (Rad) model (AUC, 0.786) and deep learning (DL) model (AUC, 0.803). Clinical variables such as age at onset and JIC classification were associated with early femoral head deformity (p < 0.05). The combined model incorporating clinical, radiomic, and deep learning signatures demonstrated better predictive ability (AUC, 0.853). The nomogram can assist clinicians in effectively assessing the risk of early femoral head deformity. ConclusionThe Clinic + Rad + DL integrated model may be beneficial for prognostic assessment of early LCPD femoral head deformity, which is crucial for tailoring personalized treatment strategies for individual patients.

Enhancing Performance of the National Field Triage Guidelines Using Machine Learning: Development of a Prehospital Triage Model to Predict Severe Trauma.

Prehospital trauma triage is essential to get the right patient to the right hospital. However, the national field triage guidelines proposed by the American College of Surgeons have proven to be relatively insensitive when identifying severe traumas. This study aimed to build a prehospital triage model to predict severe trauma and enhance the performance of the national field triage guidelines. This was a multisite prediction study, and the data were extracted from the National Trauma Data Bank between 2017 and 2019. All patients with injury, aged 16 years of age or older, and transported by ambulance from the injury scene to any trauma center were potentially eligible. The data were divided into training, internal, and external validation sets of 672,309; 288,134; and 508,703 patients, respectively. As the national field triage guidelines recommended, age, 7 vital signs, and 8 injury patterns at the prehospital stage were included as candidate variables for model development. Outcomes were severe trauma with an Injured Severity Score ≥16 (primary) and critical resource use within 24 hours of emergency department arrival (secondary). The triage model was developed using an extreme gradient boosting model and Shapley additive explanation analysis. The model's accuracy regarding discrimination, calibration, and clinical benefit was assessed. At a fixed specificity of 0.5, the model showed a sensitivity of 0.799 (95% CI 0.797-0.801), an undertriage rate of 0.080 (95% CI 0.079-0.081), and an overtriage rate of 0.743 (95% CI 0.742-0.743) for predicting severe trauma. The model showed a sensitivity of 0.774 (95% CI 0.772-0.776), an undertriage rate of 0.158 (95% CI 0.157-0.159), and an overtriage rate of 0.609 (95% CI 0.608-0.609) when predicting critical resource use, fixed at 0.5 specificity. The triage model's areas under the curve were 0.755 (95% CI 0.753-0.757) for severe trauma prediction and 0.736 (95% CI 0.734-0.737) for critical resource use prediction. The triage model's performance was better than those of the Glasgow Coma Score, Prehospital Index, revised trauma score, and the 2011 national field triage guidelines RED criteria. The model's performance was consistent in the 2 validation sets. The prehospital triage model is promising for predicting severe trauma and achieving an undertriage rate of <10%. Moreover, machine learning enhances the performance of field triage guidelines.

Development and external validation of clinical predictive model for stress urinary incontinence in Chinese women : a multicenter retrospective study

BackgroundStress urinary incontinence (SUI), the prevalent form of urinary incontinence, significantly impairs women’s quality of life. This study aims to create a visual nomogram to estimate the risk of SUI within one year postpartum for early intervention in high-risk Chinese women.MethodsWe recruited 1,531 postpartum women who gave birth at two hospitals in Kunshan City from 2021 to 2022. Delivery details were meticulously extracted from the hospitals’ medical records system, while one-year postpartum follow-ups were conducted via phone surveys specifically designed to ascertain SUI status. Utilizing data from one hospital as the training set, logistic regression analysis was performed to pinpoint significant factors and subsequently construct the nomogram. To ensure robustness, an independent dataset sourced from the second hospital served as the external validation cohort. The model’s performance was rigorously evaluated using calibration plots, ROC curves, AUC values, and DCA curves.ResultsThe study population was 1,125 women. The SUI incidence within one year postpartum was 26% (293/1125). According to the regression analysis, height, pre-pregnancy BMI, method of induction, mode of delivery, perineal condition, neonatal weight, SUI during pregnancy, and SUI during the first pregnancy were incorporated into the nomogram. The AUC of the nomogram was 0.829 (95% CI 0.790–0.867), and the external validation set was 0.746 (95% CI 0.689–0.804). Subgroup analysis based on parity showed good discrimination. The calibration curve indicated concordance. The DCA curve showed a significant net benefit.ConclusionDrawing from real-world data, we have successfully developed an SUI predictive model tailored for postpartum Chinese women. Upon successful external validation, this model holds immense potential as an effective screening tool for SUI, enabling timely interventions and ultimately may improve women’s quality of life.

A novel online calculator based on inflammation-related endotypes and clinical features to predict postoperative pulmonary infection in patients with cervical spinal cord injury

BackgroundPostoperative pulmonary infection (POI) of patients with cervical spinal cord injury (CSCI) is highly heterogeneous, while the potential endotypes and related risk factors remain unclear. MethodsA retrospective collection of 290 CSCI patients was conducted from January 2010 to July 2024 using 1:1 propensity score matching to compare POI (n = 145) and non-POI (n = 145) groups. We generated laboratory examination data from admission patients and identified endotypes using unsupervised consensus clustering and machine learning. CSCI patients were randomly assigned to the training set (n = 203) and internal validation set (n = 87). A separate cohort comprising 245 CSCI patients were used for external validation. Independent predictors for POI were identified using univariate and multivariate logistic regression. A nomogram and an online calculator were developed and validated, both internally and externally. ResultsTwo inflammation-related endotypes were identified: high inflammation endotype (endotype C1) and low inflammation endotype (endotype C2). Eight predictors for POI were identified (including age, operation duration, number of surgical segments, time between injury and surgery, preoperative steroid pulse, American Spinal Injury Association (ASIA) grade, smoking history, and inflammation-related endotype). A nomogram integrating the risk factors showed excellent discrimination in the training set (AUC, 0.976; 95% CI 0.956–0.996), internal validation set (AUC, 0.993; 95% CI 0.981–1.000), and external validation set (AUC, 0.799; 95%CI 0.744–0.854). Calibration curves demonstrated excellent fit, and decision curves highlighted its favorable clinical value. An online calculator (https://tjspine.shinyapps.io/dynnomapp/) was constructed to improve the convenience and efficiency of our prediction model. ConclusionsWe identified inflammation-related endotype and constructed a web-based calculator for predicting POI in patients with CSCI, exhibiting excellent clinical utility.

A nomogram for enhanced risk stratification for predicting cervical lymph node metastasis in papillary thyroid carcinoma patients

BackgroundCervical lymph node metastasis (CLNM) significantly impacts the prognosis of papillary thyroid carcinoma (PTC) patients. Accurate CLNM prediction is crucial for surgical planning and patient outcomes. This study aimed to develop and validate a nomogram-based risk stratification system to predict CLNM in PTC patients.MethodsThis retrospective study included 1069 patients from Zhongshan Hospital and 253 from the Qingpu Branch of Zhongshan Hospital. Preoperative ultrasound (US) data and various nodule characteristics were documented. Patients underwent lobectomy with central lymph node dissection and lateral dissection if suspicious. Multivariate logistic regression, least absolute shrinkage and selection operator (LASSO) regression, and the random forest algorithm were used to identify CLNM risk factors. A nomogram was constructed and validated internally and externally. Model performance was assessed via receiver operating characteristic (ROC) curves, calibration plots, DeLong’s test, decision curve analysis (DCA), and the clinical impact curve (CIC).ResultsSix independent CLNM risk factors were identified: age, sex, tumor size, calcification, internal vascularity, and US-reported CLNM status. The model's area under the curve (AUC) was 0.77 for both the training and the external validation sets. Calibration plots and Hosmer‒Lemeshow (HL) tests showed good calibration. The optimal cutoff value was 0.57, with a sensitivity of 58.02% and a specificity of 83.43%. Risk stratification on the basis of the nomogram categorized patients into low-, intermediate-, and high-risk groups, effectively differentiating the likelihood of CLNM, and an online calculator was created for clinical use.ConclusionThe nomogram accurately predicts CLNM risk in PTC patients, aiding personalized surgical decisions and improving patient management.

Multi-sequence MRI-based radiomics model to preoperatively predict the WHO/ISUP grade of clear Cell Renal Cell Carcinoma: a two-center study

ObjectivesTo develop radiomics models based on multi-sequence MRI from two centers for the preoperative prediction of the WHO/ISUP grade of Clear Cell Renal Cell Carcinoma (ccRCC).MethodsThis retrospective study included 334 ccRCC patients from two centers. Significant clinical factors were identified through univariate and multivariate analyses. MRI sequences included Dynamic contrast-enhanced MRI, axial fat-suppressed T2-weighted imaging, diffusion-weighted imaging, and in-phase/out-of-phase images. Feature selection methods and logistic regression (LR) were used to construct clinical and radiomics models, and a combined model was developed using the Rad-score and significant clinical factors. Additionally, seven classifiers were used to construct the combined model and different folds LR was used to construct the combined model to evaluate its performance. Models were evaluated using receiver operating characteristic (ROC) curves, area under the curve (AUC), and decision curve analysis (DCA). The Delong test compared ROC performance, with p < 0.050 considered significant.ResultsMultivariate analysis identified intra-tumoral vessels as an independent predictor of high-grade ccRCC. In the external validation set, the radiomics model (AUC = 0.834) outperformed the clinical model (AUC = 0.762), with the combined model achieving the highest AUC (0.855) and significantly outperforming the clinical model (p = 0.003). DCA showed that the combined model had a higher net benefit within the 0.04–0.54 risk threshold range than clinical model. Additionally, the combined model constructed using logistic regression has a higher priority compared to other classifiers. Additionally, 10-fold cross-validation with LR for the combined model showed consistent AUC values (0.849–0.856) across different folds.ConclusionThe radiomics models based on multi-sequence MRI might be a noninvasive and effective tool, demonstrating good efficacy in preoperatively predicting the WHO/ISUP grade of ccRCC.

Automated segmentation and source prediction of bone tumors using ConvNeXtv2 Fusion based Mask R-CNN to identify lung cancer metastasis

Lung cancer, which is a leading cause of cancer-related deaths worldwide, frequently metastasizes to the bones, significantly diminishing patients’ quality of life and complicating treatment strategies. This study aims to develop an advanced 3D Mask R-CNN model, enhanced with the ConvNeXt-V2 backbone, for the automatic segmentation of bone tumors and identification of lung cancer metastasis to support personalized treatment planning. Data were collected from two hospitals: Center A (106 patients) and Center B (265 patients). The data from Center B were used for training, while Center A’s dataset served as an independent external validation set. High-resolution CT scans with 1 mm slice thickness and no inter-slice gaps were utilized, and the regions of interest (ROIs) were manually segmented and validated by two experienced radiologists. The 3D Mask R-CNN model achieved a Dice Similarity Coefficient (DSC) of 0.856, a sensitivity of 0.921, and a specificity of 0.961 on the training set. On the test set, it achieved a DSC of 0.849, a sensitivity of 0.911, and a specificity of 0.931. For the classification task, the model attained an AUC of 0.865, an accuracy of 0.866, a sensitivity of 0.875, and a specificity of 0.835 on the training set, while achieving an AUC of 0.842, an accuracy of 0.836, a sensitivity of 0.847, and a specificity of 0.819 on the test set. These results highlight the model’s potential in improving the accuracy of bone tumor segmentation and lung cancer metastasis detection, paving the way for enhanced diagnostic workflows and personalized treatment strategies in clinical oncology.

Peripheral blood cell count composite score as a prognostic factor in patients with colorectal cancer

Objective: To develop a prognostic prediction model for patients with colorectal cancer based on a peripheral blood cell composite score (PBCS) system. Methods: This retrospective observational study included patients who had primary colorectal cancer without distant metastasis, who did not undergo radiotherapy or chemotherapy before surgery, who did not receive leukocyte or platelet-raising therapy within 1 month before surgery, and whose postoperative pathology confirmed colorectal adenocarcinoma with complete tumor resection. Patients with severe anemia, infection, or hematologic diseases before surgery, as well as those with severe heart, lung, or other important organ diseases or concurrent malignant tumors, were excluded. In total, 1021 patients with colorectal cancer who underwent surgical treatment in the Department of Gastrointestinal Surgery of the Fourth Hospital of Hebei Medical University from April 2018 to April 2020 were retrospectively included as the training set (766 patients) and the internal validation set (255 patients). Additionally, using the same criteria, 215 patients with colorectal cancer who underwent surgical treatment in another treatment group from March 2015 to December 2020 were selected as the external validation set. The "surv_cutpoint" function in R software was used to analyze the optimal cut-off values of neutrophils, lymphocytes, and platelets, and a PBCS system was established based on the optimal cut-off values. The scoring rules of the PBCS system were as follows: Neutrophils and platelets below the optimal cut-off value = 1 point, otherwise 0 points; Lymphocytes above the optimal cut-off value = 1 point, otherwise 0 points. The scores of the three cell types were added together to obtain the PBCS. Univariate and multivariate Cox regression analyses were performed to explore the correlation between patients' clinicopathological features and prognosis, and a nomogram was constructed based on the Cox regression analysis to predict patients' prognosis. The accuracy of the nomogram prediction model was validated using the C-index, calibration curve, and decision curve analysis. Results: The optimal cut-off values for neutrophils, lymphocytes, and platelets were 4.40×109/L, 1.41×109/L, and 355×109/L, respectively. The patients were divided into high and low groups according to the optimal cut-off values of these cells. Survival curve analysis showed that a high lymphocyte count (training set: P=0.042, internal validation: P=0.010, external validation: P=0.029), low neutrophil count (training set: P=0.035, internal validation: P=0.001, external validation: P=0.024), and low platelet count (training set: P=0.041, internal validation: P=0.030, external validation: P=0.024) were associated with prolonged overall survival (OS), with statistically significant differences in all cases. Survival analysis of different PBCS groups showed that patients with a high PBCS had longer OS than those with a low PBCS (P<0.05). Univariate and multivariate Cox regression analysis results showed that aspirin use history, vascular thrombus, neural invasion, CA19-9, N stage, operation time, M stage, and PBCS were independent factors affecting OS (all P<0.05). The PBCS was also an independent factor affecting disease-specific survival (P<0.05), but not progression-free survival (P>0.05). The above independent risk or protective factors were included in R software to construct a nomogram for predicting OS. The C-index (0.873), calibration curve, and decision curve analysis (threshold probability: 0.0%-75.2%) all indicated that the nomogram prediction model had good predictive performance for OS. Conclusion: This study demonstrates that the PBCS constructed based on preoperative peripheral blood levels of neutrophils, lymphocytes, and platelets is an independent factor associated with the prognosis of patients with colorectal cancer. The nomogram model constructed based on this score system exhibits good predictive efficacy for the prognosis of these patients.

Multimodal Ultrasound Radiomic Technology for Diagnosing Benign and Malignant Thyroid Nodules of Ti-Rads 4-5: A Multicenter Study

This study included 468 patients and aimed to use multimodal ultrasound radiomic technology to predict the malignancy of TI-RADS 4-5 thyroid nodules. First, radiomic features are extracted from conventional two-dimensional ultrasound (transverse ultrasound and longitudinal ultrasound), strain elastography (SE), and shear-wave-imaging (SWE) images. Next, the least absolute shrinkage and selection operator (LASSO) is used to screen out features related to malignant tumors. Finally, a support vector machine (SVM) is used to predict the malignancy of thyroid nodules. The Shapley additive explanation (SHAP) method was used to intuitively analyze the specific contributions of radiomic features to the model’s prediction. Our proposed model has AUCs of 0.971 and 0.856 in the training and testing sets, respectively. Our proposed model has a higher prediction accuracy compared to those of models with other modal combinations. In the external validation set, the AUC of the model is 0.779, which proves that the model has good generalization ability. Moreover, SHAP analysis was used to examine the overall impacts of various radiomic features on model predictions and local explanations for individual patient evaluations. Our proposed multimodal ultrasound radiomic model can effectively integrate different data collected using multiple ultrasound sensors and has good diagnostic performance for TI-RADS 4-5 thyroid nodules.

Prognostic Significance and Immune Landscape of an Efferocytosis-Related Gene Signature in Bladder Cancer.

Bladder cancer poses a significant global health challenge, underscoring the imperative for precise prognostic instruments to advance patient care. Against the backdrop of efferocytosis's increasingly recognized role in cancer, this research endeavors to develop and authenticate a prognostic signature intricately linked to efferocytosis in bladder cancer. LASSO-COX regression analysis crafted an efferocytosis-related genes risk prognostic model, followed by the construction of a column chart. External validation sets confirmed the predictive accuracy of both the model and chart. Clinical, tumor microenvironment, drug sensitivity, and immunotherapy analyses were employed to comprehensively assess efferocytosis-related scores. The expression of TGFB3 key genes was validated via RT-PCR and western blotting. Further validation included Transwell, Wound healing, Colony formation, and EDU assays. We formulated and validated an efferocytosis-related genes risk model in bladder cancer, comprising 13 core genes. The risk model demonstrated autonomous prognostic significance in both univariate and multivariate Cox analyses. Following the multivariate analysis, we devised a nomogram. Moreover, by utilizing individual risk scores derived from this risk model, we successfully stratified patients into two discernible risk cohorts, unveiling noteworthy variances in immune infiltration profiles and responsiveness to immunotherapy. Notably, the model's key gene TGFB3 was validated through comprehensive experimental investigations, including Transwell assays for migration and invasion and Wound healing assays for motility on the T24 and BIU cell lines. This study has furnished innovative perspectives on an efferocytosis-related prognostic signature, elucidating the prognosis and immune milieu intricacies in patients with bladder cancer.

A Machine Learning Approach for Predicting Biochemical Outcome After PSMA-PET-Guided Salvage Radiotherapy in Recurrent Prostate Cancer After Radical Prostatectomy: Retrospective Study.

Salvage radiation therapy (sRT) is often the sole curative option in patients with biochemical recurrence after radical prostatectomy. After sRT, we developed and validated a nomogram to predict freedom from biochemical failure. This study aims to evaluate prostate-specific membrane antigen-positron emission tomography (PSMA-PET)-based sRT efficacy for postprostatectomy prostate-specific antigen (PSA) persistence or recurrence. Objectives include developing a random survival forest (RSF) model for predicting biochemical failure, comparing it with a Cox model, and assessing predictive accuracy over time. Multinational cohort data will validate the model's performance, aiming to improve clinical management of recurrent prostate cancer. This multicenter retrospective study collected data from 13 medical facilities across 5 countries: Germany, Cyprus, Australia, Italy, and Switzerland. A total of 1029 patients who underwent sRT following PSMA-PET-based assessment for PSA persistence or recurrence were included. Patients were treated between July 2013 and June 2020, with clinical decisions guided by PSMA-PET results and contemporary standards. The primary end point was freedom from biochemical failure, defined as 2 consecutive PSA rises >0.2 ng/mL after treatment. Data were divided into training (708 patients), testing (271 patients), and external validation (50 patients) sets for machine learning algorithm development and validation. RSF models were used, with 1000 trees per model, optimizing predictive performance using the Harrell concordance index and Brier score. Statistical analysis used R Statistical Software (R Foundation for Statistical Computing), and ethical approval was obtained from participating institutions. Baseline characteristics of 1029 patients undergoing sRT PSMA-PET-based assessment were analyzed. The median age at sRT was 70 (IQR 64-74) years. PSMA-PET scans revealed local recurrences in 43.9% (430/979) and nodal recurrences in 27.2% (266/979) of patients. Treatment included dose-escalated sRT to pelvic lymphatics in 35.6% (349/979) of cases. The external outlier validation set showed distinct features, including higher rates of positive lymph nodes (47/50, 94% vs 266/979, 27.2% in the learning cohort) and lower delivered sRT doses (<66 Gy in 57/979, 5.8% vs 46/50, 92% of patients; P<.001). The RSF model, validated internally and externally, demonstrated robust predictive performance (Harrell C-index range: 0.54-0.91) across training and validation datasets, outperforming a previously published nomogram. The developed RSF model demonstrates enhanced predictive accuracy, potentially improving patient outcomes and assisting clinicians in making treatment decisions.

Enhancing diabetic foot ulcer prediction with machine learning: A focus on Localized examinations

Backgrounddiabetices foot ulcer (DFU) are serious complications. It is crucial to detect and diagnose DFU early in order to provide timely treatment, improve patient quality of life, and avoid the social and economic consequences. Machine learning techniques can help identify risk factors associated with DFU development. ObjectiveThe aim of this study was to establish correlations between clinical and biochemical risk factors of DFU through local foot examinations based on the construction of predictive models using automated machine learning techniques. MethodsThe input dataset consisted of 566 diabetes cases and 50 DFU risk factors, including 9 local foot examinations. 340 patients with Class 0 labeling (low-risk DFU), 226 patients with Class 1 labeling (high-risk DFU). To divide the training group (consisting of 453 cases) and the validation group (consisting of 113 cases), as well as preprocess the data and develop a prediction model, a Monte Carlo cross-validation approach was employed. Furthermore, potential high-risk factors were analyzed using various algorithms, including Bayesian BYS, Multi-Gaussian Weighted Classifier (MGWC), Support Vector Machine (SVM), and Random Forest Classifier (RF). A three-layer machine learning training was constructed, and model performance was estimated using a Confusion Matrix. The top 30 ranking feature variables were ultimately determined. To reinforce the robustness and generalizability of the predictive model, an independent dataset comprising 248 cases was employed for external validation. This validation process evaluated the model's applicability and reliability across diverse populations and clinical settings. Importantly, the external dataset required no additional tuning or adjustment of parameters, enabling an unbiased assessment of the model's generalizability and its capacity to predict the risk of DFU. ResultsThe ensemble learning method outperformed individual classifiers in various performance evaluation metrics. Based on the ROC analysis, the AUC of the AutoML model for assessing diabetic foot risk was 88.48 % (74.44–97.83 %). Other results were found to be as follows: 87.23 % (63.33 %–100.00 %) for sensitivity, 87.43 % (70.00 %–100.00 %) for specificity, 87.33 % (76.66 %–95.00 %) for accuracy, 87.69 % (75.00 %–100.00 %) for positive predictive value, and 87.70 % (71.79 %–100.00 %) for negative predictive value. In addition to traditional DFU risk factors such as cardiovascular disorders, peripheral artery disease, and neurological damage, we identified new risk factors such as lower limb varicose veins, history of cerebral infarction, blood urea nitrogen, GFR (Glomerular Filtration Rate), and type of diabetes that may be related to the development of DFU. In the external validation set of 158 samples, originating from an initial 248 with exclusions due to missing labels or features, the model still exhibited strong predictive accuracy. The AUC score of 0.762 indicated a strong discriminatory capability of the model. Furthermore, the Sensitivity and Specificity values provided insights into the model's ability to correctly identify both DFU cases and non-cases, respectively. ConclusionThe predictive model, developed through AutoML and grounded in local foot examinations, has proven to be a robust and practical instrument for the screening, prediction, and diagnosis of DFU risk. This model not only aids medical practitioners in the identification of potential DFU cases but also plays a pivotal role in mitigating the progression towards adverse outcomes. And the recent successful external validation of our DFU risk prediction model marks a crucial advancement, indicating its readiness for clinical application. This validation reinforces the model's efficacy as an accessible and reliable tool for early DFU risk assessment, thereby facilitating prompt intervention strategies and enhancing overall patient outcomes.

Utilizing machine learning algorithms for predicting risk factors for bone metastasis from right-sided colon carcinoma after complete mesocolic excision: a 10-year retrospective multicenter study

BackgroundBone metastasis (BM) occurs when colon cancer cells disseminate from the primary tumor site to the skeletal system via the bloodstream or lymphatic system. The emergence of such bone metastases typically heralds a significantly poor prognosis for the patient. This study's primary aim is to develop a machine learning model to identify patients at elevated risk of bone metastasis among those with right-sided colon cancer undergoing complete mesocolonectomy (CME).Patients and methodsThe study cohort comprised 1,151 individuals diagnosed with right-sided colon cancer, with a subset of 73 patients presenting with bone metastases originating from the colon. We used univariate and multivariate regression analyses as well as four machine learning algorithms to screen variables for 38 characteristic variables such as patient demographic characteristics and surgical information. The study employed four distinct machine learning algorithms, namely, extreme gradient boosting (XGBoost), random forest (RF), support vector machine (SVM), and k-nearest neighbor algorithm (KNN), to develop the predictive model. Additionally, the model was assessed using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA), while Shapley additive explanation (SHAP) was utilized to visualize and analyze the model.ResultsThe XGBoost algorithm performed the best performance among the four prediction models. In the training set, the XGBoost algorithm had an area under curve (AUC) value of 0.973 (0.953–0.994), an accuracy of 0.925 (0.913–0.936), a sensitivity of 0.921 (0.902–0.940), and a specificity of 0.908 (0.894–0.922). In the validation set, the XGBoost algorithm had an AUC value of 0.922 (0.833–0.995), an accuracy of 0.908 (0.889–0.926), a sensitivity of 0.924 (0.873–0.975), and a specificity of 0.883 (0.810–0.956). Furthermore, the AUC value of 0.83 for the external validation set suggests that the XGBoost prediction model possesses strong extrapolation capabilities. The results of SHAP analysis identified alkaline phosphatase (ALP) levels, tumor size, invasion depth, lymph node metastasis, lung metastasis, and postoperative neutrophil-to-lymphocyte ratio (NLR) levels as significant risk factors for BM from right-sided colon cancer subsequent to CME.ConclusionThe prediction model for BM from right-sided colon cancer developed using the XGBoost machine learning algorithm in this study is both highly precise and clinically valuable.

Rapid and accurate identification of Gastrodia elata Blume species based on FTIR and NIR spectroscopy combined with chemometric methods

Different varieties of Gastrodia elata Blume (G. elata Bl.) have different qualities and different contents of active ingredients, such as polysaccharide and gastrodin, and it is generally believed that the higher the active ingredients, the better the quality of G. elata Bl. and the stronger the medicinal effects. Therefore, effective identification of G. elata Bl. species is crucial and has important theoretical and practical significance. In this study, first unsupervised PCA and t-SNE are established for data visualisation, follow by traditional machine learning (PLS-DA, OPLS-DA and SVM) models and deep learning (ResNet) models were established based on the fourier transform infrared (FTIR) and near infrared (NIR) spectra data of three G. elata Bl. species. The results show that PLS-DA, OPLS-DA and SVM models require complex preprocessing of spectral data to build stable and reliable models. Compared with traditional machine learning models, ResNet models do not require complex spectral preprocessing, and the training and test sets of ResNet models built based on raw NIR and low-level data fusion (FTIR + NIR) spectra reach 100 % accuracy, the external validation set based on low-level data fusion reaches 100 % accuracy, and the external validation set based on NIR has only one sample classification error and no overfitting.

A drug mix and dose decision algorithm for individualized type 2 diabetes management

Pharmacotherapy guidelines for type 2 diabetes (T2D) emphasize patient-centered care, but applying this approach effectively in outpatient practice remains challenging. Data-driven treatment optimization approaches could enhance individualized T2D management, but current approaches cannot account for drug-specific and dose-dependent variations in safety and efficacy. We developed and evaluated an AI Drug mix and dose Advisor (AIDA) for glycemic management, using electronic medical records from 107,854 T2D patients in the SingHealth Diabetes Registry. Given a patient’s medical profile, AIDA leverages a predict-then-optimize approach to identify the minimal drug mix and dose changes required to optimize glycemic control, subject to clinical knowledge-based guidelines. On unseen data from large internal, external, and temporal validation sets, AIDA recommendations were estimated to improve post-visit glycated hemoglobin (HbA1c) by an average of 0.40–0.68% over standard of care (P < 0.0001). In qualitative evaluations on 60 diverse cases by a panel of three endocrinologists, AIDA recommendations were mostly rated as reasonable and precise. Finally, AIDA’s ability to account for drug-dose specifics offered several advantages over competing methods, including greater consistency with practice preferences and clinical guidelines for practical but effective options, indication-based treatments, and renal dosing. As AIDA provides drug-dose recommendations to improve outcomes for individual T2D patients, it could be used for clinical decision support at point-of-care, especially in resource-limited settings.