Timely intervention for Alzheimers disease (AD) requires early detection. The development of immunotherapies targeting amyloid-beta and tau underscores the need for accessible, time-efficient biomarkers for early diagnosis. Here, we directly applied our previously developed MRI-based deep learning model for AD to the large Chinese SILCODE cohort (722 participants, 1,105 brain MRI scans). The model -- initially trained on North American data -- demonstrated robust cross-ethnic generalization, without any retraining or fine-tuning, achieving an AUC of 91.3% in AD classification with a sensitivity of 95.2%. It successfully identified 86.7% of individuals at risk of AD progression more than 5 years in advance. Individuals identified as high-risk exhibited significantly shorter median progression times. By integrating an interpretable deep learning brain risk map approach, we identified AD brain subtypes, including an MCI subtype associated with rapid cognitive decline. The models risk scores showed significant correlations with cognitive measures and plasma biomarkers, such as tau proteins and neurofilament light chain (NfL). These findings underscore the exceptional generalizability and clinical utility of MRI-based deep learning models, especially in large and diverse populations, offering valuable tools for early therapeutic intervention. The model has been made open-source and deployed to a free online website for AD risk prediction, to assist in early screening and intervention.

Artificial intelligence (AI) utilization is growing, but patient perceptions of AI are unclear. Our objective was to understand patient perceptions of AI through a multi-site survey of breast imaging patients. A 36-question survey was distributed to eight US practices (6 academic, 2 non-academic) from October 2023 through October 2024. This manuscript analyzes a subset of questions from the survey addressing digital health literacy and attitudes towards AI in medicine and breast imaging specifically. Multivariable analysis compared responses by respondent demographics. A total of 3,532 surveys were collected (response rate: 69.9%, 3,532/5053). Median respondent age was 55 years (IQR 20). Most respondents were White (73.0%, 2579/3532) and had completed college (77.3%, 2732/3532). Overall, respondents were undecided (range: 43.2%-50.8%) regarding questions about general perceptions of AI in healthcare. Respondents with higher electronic health literacy, more education, and younger age were significantly more likely to consider it useful to use utilize AI for aiding medical tasks (all p<0.001). In contrast, respondents with lower electronic health literacy and less education were significantly more likely to indicate it was a bad idea for AI to perform medical tasks (p<0.001). Non-White patients were more likely to express concerns that AI will not work as well for some groups compared to others (p<0.05). Overall, favorable opinions of AI use for medical tasks were associated with younger age, more education, and higher electronic health literacy. As AI is increasingly implemented into clinical workflows, it is important to educate patients and provide transparency to build patient understanding and trust.

Cerebral aneurysm is a silent yet prevalent condition that affects a substantial portion of the global population. Aneurysms can develop due to various factors and present differently, necessitating diverse treatment approaches. Choosing the appropriate treatment upon diagnosis is paramount, as the severity of the disease dictates the course of action. The vulnerability of an aneurysm, particularly in the circle of Willis, is a critical concern; rupture can lead to irreversible consequences, including death. The primary objective of this study is to predict the rupture status of cerebral aneurysms using a comprehensive dataset that includes clinical, morphological, and hemodynamic data extracted from blood flow simulations of patients with actual vessels. Our goal is to provide valuable insights that can aid in treatment decision-making and potentially save the lives of future patients. Diagnosing and predicting the rupture status of aneurysms based solely on brain scans poses a significant challenge, often with limited accuracy, even for experienced physicians. However, harnessing statistical and machine learning (ML) techniques can enhance rupture prediction and treatment strategy selection. We employed a diverse set of supervised and unsupervised algorithms, training them on a database comprising over 700 cerebral aneurysms, which included 55 different parameters: 3 clinical, 35 morphological, and 17 hemodynamic features. Two of our models including stochastic gradient descent (SGD) and multi-layer perceptron (MLP) achieved a maximum area under the curve (AUC) of 0.86, a precision rate of 0.86, and a recall rate of 0.90 for prediction of cerebral aneurysm rupture. Given the sensitivity of the data and the critical nature of the condition, recall is a more vital parameter than accuracy and precision; our study achieved an acceptable recall score. Key features for rupture prediction included ellipticity index, low shear area ratio, and irregularity. Additionally, a one-dimensional CNN model predicted rupture status along a continuous spectrum, achieving 0.78 accuracy on the testing dataset, providing nuanced insights into rupture propensity.

We propose a multimodal spatiotemporal graph neural network (STG) framework to predict colorectal cancer liver metastasis (CRLM) progression. Current clinical models do not effectively integrate the tumor's spatial heterogeneity, dynamic evolution, and complex multimodal data relationships, limiting their predictive accuracy. Our STG framework combines preoperative CT imaging and clinical data into a heterogeneous graph structure, enabling joint modeling of tumor distribution and temporal evolution through spatial topology and cross-modal edges. The framework uses GraphSAGE to aggregate spatiotemporal neighborhood information and leverages supervised and contrastive learning strategies to enhance the model's ability to capture temporal features and improve robustness. A lightweight version of the model reduces parameter count by 78.55%, maintaining near-state-of-the-art performance. The model jointly optimizes recurrence risk regression and survival analysis tasks, with contrastive loss improving feature representational discriminability and cross-modal consistency. Experimental results on the MSKCC CRLM dataset show a time-adjacent accuracy of 85% and a mean absolute error of 1.1005, significantly outperforming existing methods. The innovative heterogeneous graph construction and spatiotemporal decoupling mechanism effectively uncover the associations between dynamic tumor microenvironment changes and prognosis, providing reliable quantitative support for personalized treatment decisions.

Accurate classification of focal liver lesions is crucial for diagnosis and treatment in hepatology. However, traditional supervised deep learning models depend on large-scale annotated datasets, which are often limited in medical imaging. Recently, Vision-Language models (VLMs) such as Contrastive Language-Image Pre-training model (CLIP) has been applied to image classifications. Compared to the conventional convolutional neural network (CNN), which classifiers image based on visual information only, VLM leverages multimodal learning with text and images, allowing it to learn effectively even with a limited amount of labeled data. Inspired by CLIP, we pro-pose a Liver-VLM, a model specifically designed for focal liver lesions (FLLs) classification. First, Liver-VLM incorporates class information into the text encoder without introducing additional inference overhead. Second, by calculating the pairwise cosine similarities between image and text embeddings and optimizing the model with a cross-entropy loss, Liver-VLM ef-fectively aligns image features with class-level text features. Experimental results on MPCT-FLLs dataset demonstrate that the Liver-VLM model out-performs both the standard CLIP and MedCLIP models in terms of accuracy and Area Under the Curve (AUC). Further analysis shows that using a lightweight ResNet18 backbone enhances classification performance, particularly under data-constrained conditions.

Reliable methods for predicting pathological complete response (pCR) in non-small cell lung cancer (NSCLC) patients undergoing neoadjuvant chemoimmunotherapy are still under exploration. Although Fluorine-18 fluorodeoxyglucose-positron emission tomography/computed tomography (18F-FDG PET/CT) features reflect tumour response, their utility in predicting pCR remains controversial. This retrospective analysis included NSCLC patients who received neoadjuvant chemoimmunotherapy followed by 18F-FDG PET/CT imaging at Shanghai Pulmonary Hospital from October 2019 to August 2024. Eligible patients were randomly divided into training and validation cohort at a 7:3 ratio. Relevant 18F-FDG PET/CT features were evaluated as individual predictors and incorporated into 5 machine learning (ML) models. Model performance was assessed using the area under the receiver operating characteristic curve (AUC), and Shapley additive explanation was applied for model interpretation. A total of 205 patients were included, with 91 (44.4%) achieving pCR. Post-treatment tumour maximum standardized uptake value (SUVmax) demonstrated the highest predictive performance among individual predictors, achieving an AUC of 0.72 (95% CI 0.65-0.79), while ΔT SUVmax achieved an AUC of 0.65 (95% CI 0.53-0.77). The Light Gradient Boosting Machine algorithm outperformed other models and individual predictors, achieving an average AUC of 0.87 (95% CI 0.78-0.97) in training cohort and 0.83 (95% CI 0.72-0.94) in validation cohort. Shapley additive explanation analysis identified post-treatment tumour SUVmax and post-treatment nodal volume as key contributors. This ML models offer a non-invasive and effective approach for predicting pCR after neoadjuvant chemoimmunotherapy in NSCLC.

A cortical hierarchical architecture is vital for encoding and integrating sensorimotor-to-cognitive information. However, whether this gradient structure is disrupted in end-stage renal disease (ESRD) patients and how this disruption provides valuable information for potential clinical symptoms remain unknown. We prospectively enrolled 77 ESRD patients and 48 healthy controls. Using resting-state functional magnetic resonance imaging, we studied ESRD-related hierarchical alterations. The Neurosynth platform and machine-learning models with 10-fold cross-validation were applied. ESRD patients had abnormal gradient metrics in core regions of the default mode network, sensorimotor network, and frontoparietal network. These changes correlated with creatinine, depression, and cognitive functions. A logistic regression classifier achieved a maximum performance of 84.8% accuracy and 0.901 area under the ROC curve (AUC). Our results highlight hierarchical imbalances in ESRD patients that correlate with diverse cognitive deficits, which may be used as potential neuroimaging markers for clinical symptoms.

This study investigates the hypothesis that chronic insomnia disorder (CID) is characterized by sex-specific changes in resting-state functional connectivity (rsFC), with certain molecular mechanisms potentially influencing CID's pathophysiology by altering rsFC in relevant networks. Utilizing a resting-state functional magnetic resonance imaging (fMRI) dataset of 395 participants, including 199 CID patients and 196 healthy controls, we examined sex-specific rsFC effects, particularly in the default mode network (DMN) and five insomnia-genetically vulnerable regions of interest (ROIs). By integrating gene expression data from the Allen Human Brain Atlas, we identified genes linked to these sex-specific rsFC alterations and conducted enrichment analysis to uncover underlying molecular mechanisms. Additionally, we simulated the impact of sex differences in rsFC with different sex compositions in our dataset and employed machine learning classifiers to distinguish CID from healthy controls based on sex-specific rsFC data. We identified both shared and sex-specific rsFC changes in the DMN and the five genetically vulnerable ROIs, with gene expression variations associated with these sex-specific connectivity differences. Enrichment analysis highlighted genes involved in synaptic signaling, ion channels, and immune function as potential contributors to CID pathophysiology through their influence on connectivity. Furthermore, our findings demonstrate that different sex compositions significantly affect study outcomes and higher diagnostic performance in sex-specific rsFC data than combined sex. This study uncovered both shared and sex-specific connectivity alterations in CID, providing molecular insights into its pathophysiology and suggesting considering sex differences in future fMRI-based diagnostic and treatment strategies.

Early detection is clinically crucial for the strategic handling of sarcopenia, yet the screening process, which includes assessments of muscle mass, strength, and function, remains complex and difficult to access. This study aims to develop a convolutional neural network model based on ultrasound images to simplify the diagnostic process and promote its accessibility. This study prospectively evaluated 357 participants (101 with sarcopenia and 256 without sarcopenia) for training, encompassing three types of data: muscle ultrasound images, clinical information, and laboratory information. Three monomodal models based on each data type were developed in the training cohort. The data type with the best diagnostic performance was selected to develop the bimodal and multimodal model by adding another one or two data types. Subsequently, the diagnostic performance of the above models was compared. The contribution ratios of different data types were further analyzed for the multimodal model. A sensitivity analysis was performed by excluding 86 cases with missing values and retaining 271 complete cases for robustness validation. By comprehensive comparison, we finally identified the optimal model (SARCO model) as the convenient solution. Moreover, the SARCO model underwent an external validation with 145 participants (68 with sarcopenia and 77 without sarcopenia) and a proof-of-concept validation with 82 participants (19 with sarcopenia and 63 without sarcopenia) from two other hospitals. The monomodal model based on ultrasound images achieved the highest area under the receiver operator characteristic curve (AUC) of 0.827 and F1-score of 0.738 among the three monomodal models. Sensitivity analysis on complete data further confirmed the superiority of the ultrasound images model (AUC: 0.851; F1-score: 0.698). The performance of the multimodal model demonstrated statistical differences compared to the best monomodal model (AUC: 0.845 vs 0.827; P=.02) as well as the two bimodal models based on ultrasound images+clinical information (AUC: 0.845 vs 0.826; P=.03) and ultrasound images+laboratory information (AUC: 0.845 vs 0.832, P=0.035). On the other hand, ultrasound images contributed the most evidence for diagnosing sarcopenia (0.787) and nonsarcopenia (0.823) in the multimodal models. Sensitivity analysis showed consistent performance trends, with ultrasound images remaining the dominant contributor (Shapley additive explanation values: 0.810 for sarcopenia and 0.795 for nonsarcopenia). After comprehensive clinical analysis, the monomodal model based on ultrasound images was identified as the SARCO model. Subsequently, the SARCO model achieved satisfactory prediction performance in the external validation and proof-of-concept validation, with AUCs of 0.801 and 0.757 and F1-scores of 0.727 and 0.666, respectively. All three types of data contributed to sarcopenia diagnosis, while ultrasound images played a dominant role in model decision-making. The SARCO model based on ultrasound images is potentially the most convenient solution for diagnosing sarcopenia. Chinese Clinical Trial Registry ChiCTR2300073651; https://www.chictr.org.cn/showproj.html?proj=199199.

This review evaluates the role of artificial intelligence (AI) in diagnosing solitary pulmonary nodules (SPNs), focusing on clinical applications and limitations in pulmonary medicine. It explores AI's utility in imaging and blood/tissue-based diagnostics, emphasizing practical challenges over technical details of deep learning methods. AI enhances computed tomography (CT)-based computer-aided diagnosis (CAD) through steps like nodule detection, false positive reduction, segmentation, and classification, leveraging convolutional neural networks and machine learning. Segmentation achieves Dice similarity coefficients of 0.70-0.92, while malignancy classification yields areas under the curve of 0.86-0.97. AI-driven blood tests, incorporating RNA sequencing and clinical data, report AUCs up to 0.907 for distinguishing benign from malignant nodules. However, most models lack prospective, multiinstitutional validation, risking overfitting and limited generalizability. The "black box" nature of AI, coupled with overlapping inputs (e.g., nodule size, smoking history) with physician assessments, complicates integration into clinical workflows and precludes standard Bayesian analysis. AI shows promise for SPN diagnosis but requires rigorous validation in diverse populations and better clinician training for effective use. Rather than replacing judgment, AI should serve as a second opinion, with its reported performance metrics understood as study-specific, not directly applicable at the bedside due to double-counting issues.