As machine learning (ML) continuously develops in cancer diagnosis and treatment, some researchers have attempted to predict the expression of programmed death ligand-1 (PD-L1) in non-small cell lung cancer (NSCLC) by ML. However, there is a lack of systematic evidence on the effectiveness of ML. We conducted a thorough search across Embase, PubMed, the Cochrane Library, and Web of Science from inception to December 14th, 2023.A systematic review and meta-analysis was conducted to assess the value of ML for predicting PD-L1 expression in NSCLC. Totally 30 studies with 12,898 NSCLC patients were included. The thresholds of PD-L1 expression level were < 1%, 1-49%, and ≥ 50%. In the validation set, in the binary classification for PD-L1 ≥ 1%, the pooled C-index was 0.646 (95%CI: 0.587-0.705), 0.799 (95%CI: 0.782-0.817), 0.806 (95%CI: 0.753-0.858), and 0.800 (95%CI: 0.717-0.883), respectively, for the clinical feature-, radiomics-, radiomics + clinical feature-, and pathomics-based ML models; in the binary classification for PD-L1 ≥ 50%, the pooled C-index was 0.649 (95%CI: 0.553-0.744), 0.771 (95%CI: 0.728-0.814), and 0.826 (95%CI: 0.783-0.869), respectively, for the clinical feature-, radiomics-, and radiomics + clinical feature-based ML models. At present, radiomics- or pathomics-based ML methods are applied for the prediction of PD-L1 expression in NSCLC, which both achieve satisfactory accuracy. In particular, the radiomics-based ML method seems to have wider clinical applicability as a non-invasive diagnostic tool. Both radiomics and pathomics serve as processing methods for medical images. In the future, we expect to develop medical image-based DL methods for intelligently predicting PD-L1 expression.

The epiphyses of the hand and wrist serve as crucial indicators for assessing skeletal maturity in adolescents. This study aimed to develop a deep learning (DL) model for bone age (BA) assessment using hand and wrist X-ray images, addressing the challenge of classifying BA in adolescents. The results of this DL-based classification were then compared and analyzed with those obtained from manual assessment. A retrospective analysis was conducted on 688 hand and wrist X-ray images of adolescents aged 11.00-23.99 years from western China, which were randomly divided into training set, validation set and test set. The BA assessment results were initially analyzed and compared using four DL network models: InceptionV3, InceptionV3 + SE + Sex, InceptionV3 + Bilinear and InceptionV3 + Bilinear. + SE + Sex, to identify the DL model with the best classification performance. Subsequently, the results of the top-performing model were compared with those of manual classification. The study findings revealed that the InceptionV3 + Bilinear + SE + Sex model exhibited the best performance, achieving classification accuracies of 96.15% and 90.48% for the training and test set, respectively. Furthermore, based on the InceptionV3 + Bilinear + SE + Sex model, classification accuracies were calculated for four age groups (< 14.0 years, 14.0 years ≤ age < 16.0 years, 16.0 years ≤ age < 18.0 years, ≥ 18.0 years), with notable accuracies of 100% for the age groups 16.0 years ≤ age < 18.0 years and ≥ 18.0 years. The BA classification, utilizing the feature fusion DL network model, holds significant reference value for determining the age of criminal responsibility of adolescents, particularly at the critical legal age boundaries of 14.0, 16.0, and 18.0 years.

To develop an integrative radiopathomic model based on deep learning to predict overall survival (OS) in locally advanced nasopharyngeal carcinoma (LANPC) patients. A cohort of 343 LANPC patients with pretreatment MRI and whole slide image (WSI) were randomly divided into training (n = 202), validation (n = 91), and external test (n = 50) sets. For WSIs, a self-attention mechanism was employed to assess the significance of different patches for the prognostic task, aggregating them into a WSI-level representation. For MRI, a multilayer perceptron was used to encode the extracted radiomic features, resulting in an MRI-level representation. These were combined in a multimodal fusion model to produce prognostic predictions. Model performances were evaluated using the concordance index (C-index), and Kaplan-Meier curves were employed for risk stratification. To enhance model interpretability, attention-based and Integrated Gradients techniques were applied to explain how WSIs and MRI features contribute to prognosis predictions. The radiopathomics model achieved high predictive accuracy in predicting the OS, with a C-index of 0.755 (95 % CI: 0.673-0.838) and 0.744 (95 % CI: 0.623-0.808) in the training and validation sets, respectively, outperforming single-modality models (radiomic signature: 0.636, 95 % CI: 0.584-0.688; deep pathomic signature: 0.736, 95 % CI: 0.684-0.810). In the external test, similar findings were observed for the predictive performance of the radiopathomics, radiomic signature, and deep pathomic signature, with their C-indices being 0.735, 0.626, and 0.660 respectively. The radiopathomics model effectively stratified patients into high- and low-risk groups (P < 0.001). Additionally, attention heatmaps revealed that high-attention regions corresponded with tumor areas in both risk groups. n: The radiopathomics model holds promise for predicting clinical outcomes in LANPC patients, offering a potential tool for improving clinical decision-making.

We propose a novel framework for integrating fragmented multi-modal data in Alzheimer's disease (AD) research using large language models (LLMs) and knowledge graphs. While traditional multimodal analysis requires matched patient IDs across datasets, our approach demonstrates population-level integration of MRI, gene expression, biomarkers, EEG, and clinical indicators from independent cohorts. Statistical analysis identified significant features in each modality, which were connected as nodes in a knowledge graph. LLMs then analyzed the graph to extract potential correlations and generate hypotheses in natural language. This approach revealed several novel relationships, including a potential pathway linking metabolic risk factors to tau protein abnormalities via neuroinflammation (r>0.6, p<0.001), and unexpected correlations between frontal EEG channels and specific gene expression profiles (r=0.42-0.58, p<0.01). Cross-validation with independent datasets confirmed the robustness of major findings, with consistent effect sizes across cohorts (variance <15%). The reproducibility of these findings was further supported by expert review (Cohen's k=0.82) and computational validation. Our framework enables cross modal integration at a conceptual level without requiring patient ID matching, offering new possibilities for understanding AD pathology through fragmented data reuse and generating testable hypotheses for future research.

We propose a novel framework for integrating fragmented multi-modal data in Alzheimer's disease (AD) research using large language models (LLMs) and knowledge graphs. While traditional multimodal analysis requires matched patient IDs across datasets, our approach demonstrates population-level integration of MRI, gene expression, biomarkers, EEG, and clinical indicators from independent cohorts. Statistical analysis identified significant features in each modality, which were connected as nodes in a knowledge graph. LLMs then analyzed the graph to extract potential correlations and generate hypotheses in natural language. This approach revealed several novel relationships, including a potential pathway linking metabolic risk factors to tau protein abnormalities via neuroinflammation (r>0.6, p<0.001), and unexpected correlations between frontal EEG channels and specific gene expression profiles (r=0.42-0.58, p<0.01). Cross-validation with independent datasets confirmed the robustness of major findings, with consistent effect sizes across cohorts (variance <15%). The reproducibility of these findings was further supported by expert review (Cohen's k=0.82) and computational validation. Our framework enables cross modal integration at a conceptual level without requiring patient ID matching, offering new possibilities for understanding AD pathology through fragmented data reuse and generating testable hypotheses for future research.

Exploring the trustworthiness of deep learning models is crucial, especially in critical domains such as medical imaging decision support systems. Conformal prediction has emerged as a rigorous means of providing deep learning models with reliable uncertainty estimates and safety guarantees. However, conformal prediction results face challenges due to the backbone model's struggles in domain-shifted scenarios, such as variations in different sources. To aim this challenge, this paper proposes a novel framework termed Conformal Ensemble of Vision Transformers (CE-ViTs) designed to enhance image classification performance by prioritizing domain adaptation and model robustness, while accounting for uncertainty. The proposed method leverages an ensemble of vision transformer models in the backbone, trained on diverse datasets including HAM10000, Dermofit, and Skin Cancer ISIC datasets. This ensemble learning approach, calibrated through the combined mentioned datasets, aims to enhance domain adaptation through conformal learning. Experimental results underscore that the framework achieves a high coverage rate of 90.38\%, representing an improvement of 9.95\% compared to the HAM10000 model. This indicates a strong likelihood that the prediction set includes the true label compared to singular models. Ensemble learning in CE-ViTs significantly improves conformal prediction performance, increasing the average prediction set size for challenging misclassified samples from 1.86 to 3.075.

Foundation models leveraging vision-language pretraining have shown promise in chest X-ray (CXR) interpretation, yet their real-world performance across diverse populations and diagnostic tasks remains insufficiently evaluated. This study benchmarks the diagnostic performance and generalizability of foundation models versus traditional convolutional neural networks (CNNs) on multinational CXR datasets. We evaluated eight CXR diagnostic models - five vision-language foundation models and three CNN-based architectures - across 37 standardized classification tasks using six public datasets from the USA, Spain, India, and Vietnam, and three private datasets from hospitals in China. Performance was assessed using AUROC, AUPRC, and other metrics across both shared and dataset-specific tasks. Foundation models outperformed CNNs in both accuracy and task coverage. MAVL, a model incorporating knowledge-enhanced prompts and structured supervision, achieved the highest performance on public (mean AUROC: 0.82; AUPRC: 0.32) and private (mean AUROC: 0.95; AUPRC: 0.89) datasets, ranking first in 14 of 37 public and 3 of 4 private tasks. All models showed reduced performance on pediatric cases, with average AUROC dropping from 0.88 +/- 0.18 in adults to 0.57 +/- 0.29 in children (p = 0.0202). These findings highlight the value of structured supervision and prompt design in radiologic AI and suggest future directions including geographic expansion and ensemble modeling for clinical deployment. Code for all evaluated models is available at https://drive.google.com/drive/folders/1B99yMQm7bB4h1sVMIBja0RfUu8gLktCE

Advanced diagnostic instruments are crucial for the accurate detection and treatment of lung diseases, which affect millions of individuals globally. This study examines the effectiveness of deep learning and transfer learning models using a hybrid dataset, created by merging four individual datasets from Bangladesh and global sources. The hybrid dataset significantly enhances model accuracy and generalizability, particularly in detecting COVID-19, pneumonia, lung opacity, and normal lung conditions from chest X-ray images. A range of models, including CNN, VGG16, VGG19, InceptionV3, Xception, ResNet50V2, InceptionResNetV2, MobileNetV2, and DenseNet121, were applied to both individual and hybrid datasets. The results showed superior performance on the hybrid dataset, with VGG16, Xception, ResNet50V2, and DenseNet121 each achieving an accuracy of 99%. This consistent performance across the hybrid dataset highlights the robustness of these models in handling diverse data while maintaining high accuracy. To understand the models implicit behavior, explainable AI techniques were employed to illuminate their black-box nature. Specifically, LIME was used to enhance the interpretability of model predictions, especially in cases of misclassification, contributing to the development of reliable and interpretable AI-driven solutions for medical imaging.

To develop an interpretable machine learning (ML) model based on cardiac magnetic resonance (CMR) multimodal parameters and clinical data to discriminate Takotsubo syndrome (TTS), acute myocardial infarction (AMI), and acute myocarditis (AM), and to further assess the diagnostic value of right ventricular (RV) strain in TTS. This study analyzed CMR and clinical data of 130 patients from three centers. Key features were selected using least absolute shrinkage and selection operator regression and random forest. Data were split into a training cohort and an internal testing cohort (ITC) in the ratio 7:3, with overfitting avoided using leave-one-out cross-validation and bootstrap methods. Nine ML models were evaluated using standard performance metrics, with Shapley additive explanations (SHAP) analysis used for model interpretation. A total of 11 key features were identified. The extreme gradient boosting model showed the best performance, with an area under the curve (AUC) value of 0.94 (95% CI: 0.85-0.97) in the ITC. Right ventricular basal circumferential strain (RVCS-basal) was the most important feature for identifying TTS. Its absolute value was significantly higher in TTS patients than in AMI and AM patients (-9.93%, -5.21%, and -6.18%, respectively, p < 0.001), with values above -6.55% contributing to a diagnosis of TTS. This study developed an interpretable ternary classification ML model for identifying TTS and used SHAP analysis to elucidate the significant value of RVCS-basal in TTS diagnosis. An online calculator (https://lsszxyy.shinyapps.io/XGboost/) based on this model was developed to provide immediate decision support for clinical use.

We aimed to develop and validate multimodal models integrating computed tomography (CT) images, text and tabular clinical data to predict poor functional outcomes and in-hospital mortality in patients with intracerebral hemorrhage (ICH). These models were designed to assist non-specialists in emergency settings with limited access to stroke specialists. A retrospective analysis of 527 patients with ICH admitted to a Japanese tertiary hospital between April 2019 and February 2022 was conducted. Deep learning techniques were used to extract features from three-dimensional CT images and unstructured data, which were then combined with tabular data to develop an L1-regularized logistic regression model to predict poor functional outcomes (modified Rankin scale score 3-6) and in-hospital mortality. The model's performance was evaluated by assessing discrimination metrics, calibration plots, and decision curve analysis (DCA) using temporal validation data. The multimodal model utilizing both imaging and text data, such as medical interviews, exhibited the highest performance in predicting poor functional outcomes. In contrast, the model that combined imaging with tabular data, including physiological and laboratory results, demonstrated the best predictive performance for in-hospital mortality. These models exhibited high discriminative performance, with areas under the receiver operating curve (AUROCs) of 0.86 (95% CI: 0.79-0.92) and 0.91 (95% CI: 0.84-0.96) for poor functional outcomes and in-hospital mortality, respectively. Calibration was satisfactory for predicting poor functional outcomes, but requires refinement for mortality prediction. The models performed similar to or better than conventional risk scores, and DCA curves supported their clinical utility. Multimodal prediction models have the potential to aid non-specialists in making informed decisions regarding ICH cases in emergency departments as part of clinical decision support systems. Enhancing real-world data infrastructure and improving model calibration are essential for successful implementation in clinical practice.