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.

Early identification of unresectable hepatocellular carcinoma (HCC) patients who may benefit from immune checkpoint inhibitors (ICIs) is crucial for optimizing outcomes. Here, we developed a multimodal fusion (MMF) system integrating CT-derived deep learning features and clinical data to predict overall survival (OS) and progression-free survival (PFS). Using retrospective multicenter data (n = 859), the MMF combining an ensemble deep learning (Ensemble-DL) model with clinical variables achieved strong external validation performance (C-index: OS = 0.74, PFS = 0.69), outperforming radiomics (29.8% OS improvement), mRECIST (27.6% OS improvement), clinical benchmarks (C-index: OS = 0.67, p = 0.0011; PFS = 0.65, p = 0.033), and Ensemble-DL (C-index: OS = 0.69, p = 0.0028; PFS = 0.66, p = 0.044). The MMF system effectively stratified patients across clinical subgroups and demonstrated interpretability through activation maps and radiomic correlations. Differential gene expression analysis revealed enrichment of the PI3K/Akt pathway in patients identified by the MMF system. The MMF system provides an interpretable, clinically applicable approach to guide personalized ICI treatment in unresectable HCC.

The prevalence of Alzheimer's disease (AD) is rising annually, imposing a severe burden on patients and society. Therefore, assisted AD assessment is crucial. The decline in language function and the cognitive impairment it reflects are key external manifestations of AD. Many studies have utilized speech analysis to achieve convenient, non-invasive, and low-cost AD detection. Although state-of-the-art researches achieve high-precision AD detection using multimodal information, these studies often ignore interactions between different modalities and lack explanations for complex models. To address this, we propose a multi-task learning (MTL) AD assessment model that combines hybrid attention with multimodal representations. The model fuses audio, text, and expert knowledge to fully capture intra- and inter-modal interactions, achieving simultaneous AD detection and cognitive state prediction, along with comprehensive explainability analyses of the model and various modalities. Results show that the proposed method is sufficiently sensitive in assessing AD, achieving 89.58% accuracy and 91.67% recall for the classification task and a root mean square error of 4.31 for the regression task with good generalization performance. Multimodal representations with expert knowledge and MTL contribute to AD assessment performance. Explainability analyses indicate that, compared to healthy controls, AD patients exhibit slower speech rates, reduced syntactic complexity, and a greater tendency to use pause fillers and pronouns. Therefore, Our study validates the effectiveness of the proposed method, addressing trust issues in clinical practice for assisted decision-making and further advancing the development of speech as a promising biomarker for early AD screening and cognitive decline monitoring.

Modulating the temporoparietal junction (TPJ), especially the right counterpart, shows promises in enhancing social cognitive ability. However, it is ambiguous whether the functional lateralization of TPJ determines people's responsiveness to brain stimulation. Here, this issue is investigated with an individual difference approach. Forty‐five participants attended three sessions of transcranial direct current stimulation (tDCS) experiments and one neuroimaging session. The results support the symmetric mechanism of left and right TPJ stimulation. First, the left and right TPJ stimulation effect are comparable in the group‐level analysis. Second, the individual‐level analysis reveals that a less right‐lateralized TPJ is associated with a higher level of responsiveness. Participants could be classified into positive responders showing cognitive enhancement and negative responders showing cognitive impairment due to stimulation. The positive responders show weaker connectivity between bilateral TPJ and the medial prefrontal cortex, which mediates the prediction of offline responsiveness by the lateralization and the social‐related trait. These findings call for a better characterization and predictive models for whom tDCS should be used for, and highlight the necessity and feasibility of prestimulation screening.

Identifying effective predictive strategies to assess the response of immune checkpoint inhibitors (ICIs)-based combination therapy in advanced hepatocellular carcinoma (HCC) is crucial. This study presents a new longitudinal CT-based radiomics model to predict treatment response and prognosis in advanced HCC patients undergoing ICIs-based combination therapy. Longitudinal CT images were collected before and during the treatment for HCC patients across three institutions from January 2019 to April 2022. A total of 1316 radiomic features were extracted from arterial and portal venous phase abdominal CT images for each patient. A model called Longitudinal Whole-liver CT-based Radiomics (LWCTR) was developed to categorize patients into responders or non-responders using radiomic features and clinical information through support vector machine (SVM) classifiers. The area under the curve (AUC) was used as the performance metric and subsequently applied for risk stratification and prognostic assessment. The Shapley Additive explanations (SHAP) method was used to calculate the Shapley value, which explains the contribution of each feature in the SVM model to the prediction. This study included 395 eligible participants, with a median age of 57 years (IQR 51–66), comprising 344 males and 51 females. The LWCTR model performed well in predicting treatment response, achieving an AUC of 0.883 (95% confidence interval [CI] 0.881–0.888) in the training cohort, 0.876 (0.858–0.895) in the internal validation cohort, and 0.875 (0.860–0.887) in the external test cohort. The Rad-Nomo model, integrating the LWCTR model's prediction score (Rad-score) with the modified Response Evaluation Criteria in Solid Tumors (mRECIST), demonstrated strong prognostic performance. It achieved time-dependent AUC values of 0.902, 0.823, and 0.850 at 1, 2, and 3 years in the internal validation cohort and 0.893, 0.848, and 0.762 at the same intervals in the external test cohort. The proposed LWCTR model performs well in predicting treatment response and prognosis in patients with HCC receiving ICIs-based combination therapy, potentially contributing to personalized and timely treatment decisions.