Ultrasound-based radiomics XGBoost model to assess the risk of central cervical lymph node metastasis in patients with papillary thyroid carcinoma: Individual application of SHAP

Prediction of preoperative tumor-related epilepsy using XGBoost radiomics models with 4 MRI sequences

Introduction. Tumor-related epilepsy is a prevalent condition in patients with gliomas. Accurate prediction of epilepsy is crucial for early treatment. This study aimed to evaluate the novel application of the eXtreme Gradient Boost (XGBoost) machine learning (ML) algorithm into a radiomics model predicting preoperative tumor-related epilepsy (PTRE). Its performance was compared with 4 conventional ML algorithms, including the least absolute shrinkage and selection operator (LASSO), elastic net, random forest, and support vector machine.Methods.This study used four magnetic resonance imaging (MRI) images consisting of four sequences (T1-weighted [T1W], T1-weighted contrast [T1WC], T2-weighted [T2W], and T2-weighted fluid-attenuated inversion recovery [T2W FLAIR]) acquired from 74 glioma patients, 30 with PTRE and 44 without PTRE. 394 radiomics features were extracted from the MRI scans usingPyradiomics, alongside 12 clinical features from the medical records. The ML algorithms were mixed and matched to create 20 radiomics models with two stages for: (1) feature selection and (2) prediction of PTRE. Nested cross-validation was used to tune the algorithms and select the stable features.Results.The XGBoost radiomics model demonstrated the second-highest balanced accuracy and F1-score of 0.81 ± 0.01 and 0.80 ± 0.01 respectively. It also achieved the highest recall of 0.81 ± 0.02. It used mostly textural radiomics features from the T1W, T2W and T2W FLAIR sequences to make the predictions.Conclusion.This study demonstrates that XGBoost is a viable alternative to conventional ML algorithms for developing a radiomics model to predict PTRE, as the model produced from XGBoost had among the highest metrics. XGBoost selected features with a higher predictive value than other models. The features selected by XGBoost were more stable, which is a useful property for radiomics analysis. Features selected from multiple MRI sequences were important in the model's decision.

Prediction of peripheral lymph node metastasis (LNM) in thyroid cancer using delta radiomics derived from enhanced CT combined with multiple machine learning algorithms

OBJECTIVES

This study aimed to develop a model for predicting peripheral lymph node metastasis (LNM) in thyroid cancer patients by combining enhanced CT radiomic features with machine learning algorithms. It increased the clinical utility and interpretability of the predictions through SHAP (SHapley Additive exPlanation) values and nomograms for model explanation and visualization.

METHODS

Clinical and enhanced CT image data from 375 patients with thyroid cancer confirmed by postoperative pathology at Xiangyang No. 1 People's Hospital were collected from January 2015 to July 2023. Among them, there were 88 patients in the LNM group and 287 patients in the non-LNM group. The delta radiomic features of the tumours were extracted. Various machine learning algorithms (such as SVM, GBM, RF, XGBoost, KNN, and LightGBM) were trained on the clinical and radiomic feature data sets and used to construct a reliable prediction model. During model training, cross-validation was used to evaluate model performance, and the optimal model was selected. In addition, SHAP values were used to interpret the prediction results of the optimal model, analyse the contribution of each feature to the prediction results, and further develop a nomogram to visually display the prediction results.

RESULTS

Univariate analysis confirmed that sex, Hashimoto's disease, tumour adjacency to the thyroid capsule, pathological subtype, Delta Radscore, and Radscore 1 are risk factors for peripheral lymph node metastasis in thyroid cancer patients. The machine learning model based on enhanced CT radiomics performed well in predicting peripheral lymph node metastasis in thyroid cancer patients. In the test set, the optimal model, SVM, achieved high AUC (0.879), sensitivity (0.849), and specificity (0.769) values. Through SHAP value analysis, the importance and contribution of tumour adjacency to the thyroid capsule, pathological subtype, Delta Radscore, and Radscore 1 in the prediction were clarified, providing a more detailed and intuitive basis for clinical decision-making. The nomogram illustrated the model prediction process, facilitating understanding and application by clinicians.

CONCLUSIONS

This study successfully constructed a model for predicting peripheral lymph node metastasis in thyroid cancer patients on the basis of enhanced CT radiomics combined with machine learning and improved the interpretability and clinical utility of the model through SHAP values and nomograms. The model not only improves the accuracy of predictions but also provides a more scientific and intuitive basis for clinical decision-making, with potential clinical application value.

Explainable Artificial Intelligence in Neuroimaging of Alzheimer's Disease

Alzheimer's disease (AD) remains a significant global health challenge, affecting millions worldwide and imposing substantial burdens on healthcare systems. Advances in artificial intelligence (AI), particularly in deep learning and machine learning, have revolutionized neuroimaging-based AD diagnosis. However, the complexity and lack of interpretability of these models limit their clinical applicability. Explainable Artificial Intelligence (XAI) addresses this challenge by providing insights into model decision-making, enhancing transparency, and fostering trust in AI-driven diagnostics. This review explores the role of XAI in AD neuroimaging, highlighting key techniques such as SHAP, LIME, Grad-CAM, and Layer-wise Relevance Propagation (LRP). We examine their applications in identifying critical biomarkers, tracking disease progression, and distinguishing AD stages using various imaging modalities, including MRI and PET. Additionally, we discuss current challenges, including dataset limitations, regulatory concerns, and standardization issues, and propose future research directions to improve XAI's integration into clinical practice. By bridging the gap between AI and clinical interpretability, XAI holds the potential to refine AD diagnostics, personalize treatment strategies, and advance neuroimaging-based research.

The Effect of Ultrasound Image Pre-Processing on Radiomics Feature Quality: A Study on Shoulder Ultrasound

Radiomics, the extraction of quantitative features from medical images, has shown great promise in enhancing diagnostic and prognostic models, particularly in CT and MRI. However, its application in ultrasound (US) imaging, especially in musculoskeletal (MSK) imaging, remains underexplored. The inherent variability of ultrasound, influenced by operator dependency and various imaging settings, presents significant challenges to the reproducibility of radiomic features. This study aims to identify whether commonly used image pre-processing methods can increase the reproducibility of radiomics features, increasing the quality of analysis. This is performed with shoulder calcific tendinopathy as a case study. Ultrasound images from 84 patients with rotator cuff calcifications were retrospectively analysed. Three pre-processing techniques-Histogram Equalization, Standard CLAHE, and Advanced CLAHE-were applied to adjust image quality. Manual segmentation of calcifications was performed, followed by the extraction of 849 radiomic features. The reproducibility of these features was assessed using the intraclass correlation coefficient (ICC), comparing results across pre-processing methods within the dataset. The Advanced CLAHE pre-processing method consistently yielded the highest ICC values, indicating superior reproducibility of radiomic features compared to other methods. Wavelet-transformed features, particularly in the GLCM and GLRLM subgroups, demonstrated robust reproducibility across all pre-processing techniques. Shape features, however, continued to show lower reproducibility. Advanced CLAHE pre-processing significantly enhances the reproducibility of radiomic features in ultrasound imaging of calcifications. This study underscores the importance of pre-processing in achieving reliable radiomic analyses, particularly in operator-dependent imaging modalities like ultrasound.

Machine learning based prediction models for the prognosis of COVID-19 patients with DKA

Patients with Diabetic ketoacidosis (DKA) have increased critical illness and mortality during coronavirus diseases 2019 (COVID-19). The aim of our study was to develop a predictive model for the occurrence of critical illness and mortality in COVID-19 patients with DKA utilizing machine learning. Blood samples and clinical data from 242 COVID-19 patients with DKA collected from December 2022 to January 2023 at Second Xiangya Hospital. Patients were categorized into non-death (n = 202) and death (n = 38) groups, and non-severe (n = 146) and severe (n = 96) groups. We developed five machine learning-based prediction models-Extreme Gradient Boosting (XGB), Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), and Multilayer Perceptron (MLP)-to evaluate the prognosis of COVID-19 patients with DKA. We employed 5-fold cross-validation for model evaluation and used the Shapley Additive Explanations (SHAP) algorithm for result interpretation to ensure reliability. The LR model demonstrated the highest accuracy (AUC = 0.933) in predicting mortality. Additionally, the LR model excelled (AUC = 0.898) in predicting progression to severe disease. This study developed a machine learning-based predictive model for the progression to severe disease or death in COVID-19 patients with DKA, which can serve as a valuable tool to guide clinical treatment decisions.

Quantitative ultrasound radiomics analysis to evaluate lymph nodes in patients with cancer: a systematic review

This systematic review aims to evaluate the role of ultrasound (US) radiomics in assessing lymphadenopathy in patients with cancer and the ability of radiomics to predict metastatic lymph node involvement. A systematic literature search was performed in the PubMed (MEDLINE), Cochrane Central Register of Controlled Trials (CENTRAL), and EMBASE (Ovid) databases up to June 13, 2023. 42 articles were included in which the lymph node mass was assessed with a US exam, and the analysis was performed using radiomics methods. From the survey of the selected articles, experimental evidence suggests that radiomics features extracted from US images can be a useful tool for predicting and characterizing lymphadenopathy in patients with breast, head and neck, and cervical cancer. This noninvasive and effective method allows the extraction of important information beyond mere morphological characteristics, extracting features that may be related to lymph node involvement. Future studies are needed to investigate the role of US-radiomics in other types of cancers, such as melanoma.

Identification of texture MRI brain abnormalities on Fibromyalgia syndrome using interpretable machine learning models

To provide objective diagnostic markers for fibromyalgia symptoms (FMS) diagnosis, we have created interpretable extreme gradient boosting (XGBoost) models using radiomics to aid in the diagnosis of chronic pain (CP) and to develop nomogram models for diagnosing subgroups of FMS. A group of 54 patients with CP and 71 healthy controls was randomly separated into training and validation groups, using a 7:3 ratio. Radiomics features were extracted from grey-matter and white-matter in the filtered mwp0* image. The Mann-Whitney U test, Spearman's rank correlation test, and least absolute shrinkage and selection operator (LASSO) were utilized to select features. An XGBoost model was created based on these features, and Shapley Additive exPlanations (SHAP) was used for personalization and visual interpretation. A nomogram was developed for the diagnosis of FMS subgroups, utilizing radiomics scores and clinical predictors. The efficacy of the nomogram was evaluated using the area under the receiver operating characteristic curve, while decision curve analysis was employed to evaluate its clinical efficacy. The XGBoost model displays stability in the training validation group, indicating lower overfitting of CP model. The nomogram model combined with the rad-score has a greater ability to distinguish between typical and sub-clinical than the clinical factor model alone. We developed and validated a CP diagnosis model by XGBoost and realized model visualization through SHAP. The rad-score obtained by machine learning was used to build a nomogram model that combines clinical scales to distinguish patients with typical and sub-clinical fibromyalgia.

Prediction of Post-Treatment Visual Acuity in Age-Related Macular Degeneration Patients With an Interpretable Machine Learning Method

Purpose

We evaluated the features predicting visual acuity (VA) after one year in neovascular age-related macular degeneration (nAMD) patients.

Methods

A total of 527 eyes of 506 patients were included. Machine learning (ML) models were trained to predict VA deterioration beyond a logarithm of the minimum angle of resolution of 1.0 after 1 year based on the sequential addition of multimodal data. BaseM models used clinical data (age, sex, treatment regimen, and VA), SegM models included fluid volumes from optical coherence tomography (OCT) images, and RawM models used probabilities of visual deterioration (hereafter probability) from deep learning classifiers trained on baseline OCT (OCT0) and OCT after three loading doses (OCT3), fluorescein angiography, and indocyanine green angiography. We applied SHapley Additive exPlanations (SHAP) for machine learning model interpretation.

Results

The RawM model based on the probability of OCT0 outperformed the SegM model (area under the receiver operating characteristic curve of 0.95 vs. 0.91). Adding probabilities from OCT3, fluorescein angiography, and indocyanine green angiography to RawM showed minimal performance improvement, highlighting the practicality of using raw OCT0 data for predicting visual outcomes. Applied SHapley Additive exPlanations analysis identified VA after 3 months and OCT3 probability values as the most influential features over quantified fluid segments.

Conclusions

Integrating multimodal data to create a visual predictive model yielded accurate, interpretable predictions. This approach allowed the identification of crucial factors for predicting VA in patients with nAMD.

Translational Relevance

Interpreting a predictive model for 1-year VA in patients with nAMD from multimodal data allowed us to identify crucial factors for predicting VA.

Interpretable machine learning model integrating clinical and elastosonographic features to detect renal fibrosis in Asian patients with chronic kidney disease

BACKGROUND

Non-invasive renal fibrosis assessment is critical for tailoring personalized decision-making and managing follow-up in patients with chronic kidney disease (CKD). We aimed to exploit machine learning algorithms using clinical and elastosonographic features to distinguish moderate-severe fibrosis from mild fibrosis among CKD patients.

METHODS

A total of 162 patients with CKD who underwent shear wave elastography examinations and renal biopsies at our institution were prospectively enrolled. Four classifiers using machine learning algorithms, including eXtreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), Light Gradient Boosting Machine (LightGBM), and K-Nearest Neighbor (KNN), which integrated elastosonographic features and clinical characteristics, were established to differentiate moderate-severe renal fibrosis from mild forms. The area under the receiver operating characteristic curve (AUC) and average precision were employed to compare the performance of constructed models, and the SHapley Additive exPlanations (SHAP) strategy was used to visualize and interpret the model output.

RESULTS

The XGBoost model outperformed the other developed machine learning models, demonstrating optimal diagnostic performance in both the primary (AUC = 0.97, 95% confidence level (CI) 0.94-0.99; average precision = 0.97, 95% CI 0.97-0.98) and five-fold cross-validation (AUC = 0.85, 95% CI 0.73-0.98; average precision = 0.90, 95% CI 0.86-0.93) datasets. The SHAP approach provided visual interpretation for XGBoost, highlighting the features' impact on the diagnostic process, wherein the estimated glomerular filtration rate provided the largest contribution to the model output, followed by the elastic modulus, then renal length, renal resistive index, and hypertension.

CONCLUSION

This study proposed an XGBoost model for distinguishing moderate-severe renal fibrosis from mild forms in CKD patients, which could be used to assist clinicians in decision-making and follow-up strategies. Moreover, the SHAP algorithm makes it feasible to visualize and interpret the feature processing and diagnostic processes of the model output.

Predicting central cervical lymph node metastasis in papillary thyroid microcarcinoma using deep learning

Background

The aim of this study is to design a deep learning (DL) model to preoperatively predict the occurrence of central lymph node metastasis (CLNM) in patients with papillary thyroid microcarcinoma (PTMC).

Methods

This research collected preoperative ultrasound (US) images and clinical factors of 611 PTMC patients. The clinical factors were analyzed using multivariate regression. Then, a DL model based on US images and clinical factors was developed to preoperatively predict CLNM. The model's efficacy was evaluated using the receiver operating characteristic (ROC) curve, along with accuracy, sensitivity, specificity, and the F1 score.

Results

The multivariate analysis indicated an independent correlation factors including age ≥55 (OR = 0.309, p < 0.001), tumor diameter (OR = 2.551, p = 0.010), macrocalcifications (OR = 1.832, p = 0.002), and capsular invasion (OR = 1.977, p = 0.005). The suggested DL model utilized US images achieved an average area under the curve (AUC) of 0.65, slightly outperforming the model that employed traditional clinical factors (AUC = 0.64). Nevertheless, the model that incorporated both of them did not enhance prediction accuracy (AUC = 0.63).

Conclusions

The suggested approach offers a reference for the treatment and supervision of PTMC. Among three models used in this study, the deep model relied generally more on image modalities than the data modality of clinic records when making the predictions.

A Radiomics Approach to Identify Immunologically Active Tumor in Patients with Head and Neck Squamous Cell Carcinomas

BACKGROUND

We recently developed a gene-expression-based HOT score to identify the hot/cold phenotype of head and neck squamous cell carcinomas (HNSCCs), which is associated with the response to immunotherapy. Our goal was to determine whether radiomic profiling from computed tomography (CT) scans can distinguish hot and cold HNSCC.

METHOD

We included 113 patients from The Cancer Genome Atlas (TCGA) and 20 patients from the Groupe Hospitalier Pitié-Salpêtrière (GHPS) with HNSCC, all with available pre-treatment CT scans. The hot/cold phenotype was computed for all patients using the HOT score. The IBEX software (version 4.11.9, accessed on 30 march 2020) was used to extract radiomic features from the delineated tumor region in both datasets, and the intraclass correlation coefficient (ICC) was computed to select robust features. Machine learning classifier models were trained and tested in the TCGA dataset and validated using the area under the receiver operator characteristic curve (AUC) in the GHPS cohort.

RESULTS

A total of 144 radiomic features with an ICC >0.9 was selected. An XGBoost model including these selected features showed the best performance prediction of the hot/cold phenotype with AUC = 0.86 in the GHPS validation dataset.

CONCLUSIONS AND RELEVANCE

We identified a relevant radiomic model to capture the overall hot/cold phenotype of HNSCC. This non-invasive approach could help with the identification of patients with HNSCC who may benefit from immunotherapy.

Ultrasound radiomics models based on multimodal imaging feature fusion of papillary thyroid carcinoma for predicting central lymph node metastasis

OBJECTIVE

This retrospective study aimed to establish ultrasound radiomics models to predict central lymph node metastasis (CLNM) based on preoperative multimodal ultrasound imaging features fusion of primary papillary thyroid carcinoma (PTC).

METHODS

In total, 498 cases of unifocal PTC were randomly divided into two sets which comprised 348 cases (training set) and 150 cases (validition set). In addition, the testing set contained 120 cases of PTC at different times. Post-operative histopathology was the gold standard for CLNM. The following steps were used to build models: the regions of interest were segmented in PTC ultrasound images, multimodal ultrasound image features were then extracted by the deep learning residual neural network with 50-layer network, followed by feature selection and fusion; subsequently, classification was performed using three classical classifiers-adaptive boosting (AB), linear discriminant analysis (LDA), and support vector machine (SVM). The performances of the unimodal models (Unimodal-AB, Unimodal-LDA, and Unimodal-SVM) and the multimodal models (Multimodal-AB, Multimodal-LDA, and Multimodal-SVM) were evaluated and compared.

RESULTS

The Multimodal-SVM model achieved the best predictive performance than the other models (P < 0.05). For the Multimodal-SVM model validation and testing sets, the areas under the receiver operating characteristic curves (AUCs) were 0.910 (95% CI, 0.894-0.926) and 0.851 (95% CI, 0.833-0.869), respectively. The AUCs of the Multimodal-SVM model were 0.920 (95% CI, 0.881-0.959) in the cN0 subgroup-1 cases and 0.828 (95% CI, 0.769-0.887) in the cN0 subgroup-2 cases.

CONCLUSION

The ultrasound radiomics model only based on the PTC multimodal ultrasound image have high clinical value in predicting CLNM and can provide a reference for treatment decisions.

Increasing transparency in machine learning through bootstrap simulation and shapely additive explanations

Machine learning methods are widely used within the medical field. However, the reliability and efficacy of these models is difficult to assess, making it difficult for researchers to identify which machine-learning model to apply to their dataset. We assessed whether variance calculations of model metrics (e.g., AUROC, Sensitivity, Specificity) through bootstrap simulation and SHapely Additive exPlanations (SHAP) could increase model transparency and improve model selection. Data from the England National Health Services Heart Disease Prediction Cohort was used. After comparison of model metrics for XGBoost, Random Forest, Artificial Neural Network, and Adaptive Boosting, XGBoost was used as the machine-learning model of choice in this study. Boost-strap simulation (N = 10,000) was used to empirically derive the distribution of model metrics and covariate Gain statistics. SHapely Additive exPlanations (SHAP) to provide explanations to machine-learning output and simulation to evaluate the variance of model accuracy metrics. For the XGBoost modeling method, we observed (through 10,000 completed simulations) that the AUROC ranged from 0.771 to 0.947, a difference of 0.176, the balanced accuracy ranged from 0.688 to 0.894, a 0.205 difference, the sensitivity ranged from 0.632 to 0.939, a 0.307 difference, and the specificity ranged from 0.595 to 0.944, a 0.394 difference. Among 10,000 simulations completed, we observed that the gain for Angina ranged from 0.225 to 0.456, a difference of 0.231, for Cholesterol ranged from 0.148 to 0.326, a difference of 0.178, for maximum heart rate (MaxHR) ranged from 0.081 to 0.200, a range of 0.119, and for Age ranged from 0.059 to 0.157, difference of 0.098. Use of simulations to empirically evaluate the variability of model metrics and explanatory algorithms to observe if covariates match the literature are necessary for increased transparency, reliability, and utility of machine learning methods. These variance statistics, combined with model accuracy statistics can help researchers identify the best model for a given dataset.

Prediction of Surgical Approach in Mitral Valve Disease by XGBoost Algorithm Based on Echocardiographic Features

In this study, we aimed to develop a prediction model to assist surgeons in choosing an appropriate surgical approach for mitral valve disease patients. We retrospectively analyzed a total of 143 patients who underwent surgery for mitral valve disease. The XGBoost algorithm was used to establish a predictive model to decide a surgical approach (mitral valve repair or replacement) based on the echocardiographic features of the mitral valve apparatus, such as leaflets, the annulus, and sub-valvular structures. The results showed that the accuracy of the predictive model was 81.09% in predicting the appropriate surgical approach based on the patient's preoperative echocardiography. The result of the predictive model was superior to the traditional complexity score (81.09% vs. 75%). Additionally, the predictive model showed that the three main factors affecting the choice of surgical approach were leaflet restriction, calcification of the leaflet, and perforation or cleft of the leaflet. We developed a novel predictive model using the XGBoost algorithm based on echocardiographic features to assist surgeons in choosing an appropriate surgical approach for patients with mitral valve disease.

Development and validation of an interpretable radiomic nomogram for severe radiation proctitis prediction in postoperative cervical cancer patients

Background

Radiation proctitis is a common complication after radiotherapy for cervical cancer. Unlike simple radiation damage to other organs, radiation proctitis is a complex disease closely related to the microbiota. However, analysis of the gut microbiota is time-consuming and expensive. This study aims to mine rectal information using radiomics and incorporate it into a nomogram model for cheap and fast prediction of severe radiation proctitis prediction in postoperative cervical cancer patients.

Methods

The severity of the patient's radiation proctitis was graded according to the RTOG/EORTC criteria. The toxicity grade of radiation proctitis over or equal to grade 2 was set as the model's target. A total of 178 patients with cervical cancer were divided into a training set (n = 124) and a validation set (n = 54). Multivariate logistic regression was used to build the radiomic and non-raidomic models.

Results

The radiomics model [AUC=0.6855(0.5174-0.8535)] showed better performance and more net benefit in the validation set than the non-radiomic model [AUC=0.6641(0.4904-0.8378)]. In particular, we applied SHapley Additive exPlanation (SHAP) method for the first time to a radiomics-based logistic regression model to further interpret the radiomic features from case-based and feature-based perspectives. The integrated radiomic model enables the first accurate quantitative assessment of the probability of radiation proctitis in postoperative cervical cancer patients, addressing the limitations of the current qualitative assessment of the plan through dose-volume parameters only.

Conclusion

We successfully developed and validated an integrated radiomic model containing rectal information. SHAP analysis of the model suggests that radiomic features have a supporting role in the quantitative assessment of the probability of radiation proctitis in postoperative cervical cancer patients.