Background: Lumbar degenerative disc disease (LDDD) is a leading cause of chronic lower back pain; however, a lack of clear diagnostic criteria and solid LDDD interventional therapies have made predicting the benefits of therapeutic strategies challenging. Our goal is to develop machine learning (ML)–based radiomic models based on pre-treatment imaging for predicting the outcomes of lumbar nucleoplasty (LNP), which is one of the interventional therapies for LDDD. Methods: The input data included general patient characteristics, perioperative medical and surgical details, and pre-operative magnetic resonance imaging (MRI) results from 181 LDDD patients receiving lumbar nucleoplasty. Post-treatment pain improvements were categorized as clinically significant (defined as a ≥80% decrease in the visual analog scale) or non-significant. To develop the ML models, T2-weighted MRI images were subjected to radiomic feature extraction, which was combined with physiological clinical parameters. After data processing, we developed five ML models: support vector machine, light gradient boosting machine, extreme gradient boosting, extreme gradient boosting random forest, and improved random forest. Model performance was measured by evaluating indicators, such as the confusion matrix, accuracy, sensitivity, specificity, F1 score, and area under the receiver operating characteristic curve (AUC), which were acquired using an 8:2 allocation of training to testing sequences. Results: Among the five ML models, the improved random forest algorithm had the best performance, with an accuracy of 0.76, a sensitivity of 0.69, a specificity of 0.83, an F1 score of 0.73, and an AUC of 0.77. The most influential clinical features included in the ML models were pre-operative VAS and age. In contrast, the most influential radiomic features had the correlation coefficient and gray-scale co-occurrence matrix. Conclusions: We developed an ML-based model for predicting pain improvement after LNP for patients with LDDD. We hope this tool will provide both doctors and patients with better information for therapeutic planning and decision-making.

Objectives: Neoadjuvant chemoradiotherapy (NCRT) followed by surgery is the mainstay of treatment for patients with locally advanced rectal cancer. Based on baseline 18F-fluorodeoxyglucose ([18F]-FDG)-positron emission tomography (PET)/computed tomography (CT), a new artificial intelligence model using metric learning (ML) was introduced to predict responses to NCRT. Patients and Methods: This study used the data of 236 patients with newly diagnosed rectal cancer; the data of 202 and 34 patients were for training and validation, respectively. All patients received pretreatment [18F]FDG-PET/CT, NCRT, and surgery. The treatment response was scored by Dworak tumor regression grade (TRG); TRG3 and TRG4 indicated favorable responses. The model employed ML combined with the Uniform Manifold Approximation and Projection for dimensionality reduction. A receiver operating characteristic (ROC) curve analysis was performed to assess the model’s predictive performance. Results: In the training cohort, 115 patients (57%) achieved TRG3 or TRG4 responses. The area under the ROC curve was 0.96 for the prediction of a favorable response. The sensitivity, specificity, and accuracy were 98.3%, 96.5%, and 97.5%, respectively. The sensitivity, specificity, and accuracy for the validation cohort were 95.0%, 100%, and 98.8%, respectively. Conclusions: The new ML model presented herein was used to determined that baseline 18F[FDG]-PET/CT images could predict a favorable response to NCRT in patients with rectal cancer. External validation is required to verify the model’s predictive value.

This study aimed to develop and evaluate an AI-driven platform, the Adaptive RAG Assistant MRI Platform (ARAMP), for assisting in the diagnosis and reporting of brain metastases using post-contrast axial T1-weighted (AX_T1+C) MRI. In this retrospective study, 2447 cancer patients who underwent MRI between 2010 and 2022 were screened. A subset of 100 randomized patients with confirmed brain metastases and 100 matched non-cancer controls were selected for evaluation. ARAMP integrates quantitative radiomic feature extraction with an adaptive Retrieval-Augmented Generation (RAG) framework based on a large language model (LLM, GPT-4o), incorporating five authoritative medical references. Three board-certified neuroradiologists and an independent LLM (Gemini 2.0 Pro) assessed ARAMP performance. Metrics of the assessment included Pre-/Post-Trained Inference Difference, Inter-Inference Agreement, and Sensitivity. Post-training, ARAMP achieved a mean Inference Similarity score of 67.45%. Inter-Inference Agreement among radiologists averaged 30.20% (p = 0.01). Sensitivity for brain metastasis detection improved from 0.84 (pre-training) to 0.98 (post-training). ARAMP also showed improved reliability in identifying brain metastases as the primary diagnosis post-RAG integration. This adaptive RAG-based framework may improve diagnostic efficiency and standardization in radiological workflows.

Understanding users is a key for many business applications. In this paper, we propose to pursue user preference understanding by their Wi-Fi logs collected from their mobile devices. As shown, Wi-Fi data are essentially of various information types and with noises. The challenges lie in how to refine relevant information from noisy Wi-Fi data. Aiming at the challenges, this paper proposes a data cleaning and information enrichment framework for enabling user preference understanding through Wi-Fi logs, and introduces a series of filters for cleaning, correcting, and refining Wi-Fi logs. A comprehensive experiment with real data collected from users is made to verify the effectiveness of the proposed techniques for cleaning noisy Wi-Fi data for user preference profiling. To the best of our knowledge, this work is the first attempt to study user behavior understanding by mining Wi-Fi logs.

Background/Objectives: The implementation of adaptive radiation therapy (ART) is increasingly becoming widely available in the clinical practice of radiotherapy (RT). For patients with pharyngeal cancer receiving RT, this study aimed to develop a deep learning (DL) model by merging baseline and ART simulation computed tomography (CT) images to predict treatment outcomes. Methods: Clinical and imaging data from 162 patients of newly diagnosed oropharyngeal or hypopharyngeal cancer were analyzed. All completed definitive treatment and their baseline and ART non-contrast simulation CTs were utilized for training. After augmentation of the CT images, a deep contrastive learning model was employed to predict the occurrence of local recurrence (LR), neck lymph node relapse (NR), and distant metastases (DM). Receiver operating characteristic curve analysis was conducted to evaluate the model’s performance. Results: Over a median follow-up period of 34 months, 53 (32.7%), 36 (22.2%), and 23 (14.0%) patients developed LR, NR, and DM, respectively. Following the integration of prediction results from baseline and ART simulation CTs, the area under the curve for predicting the occurrence of LR, NR, and DM reached 0.773, 0.747, and 0.793. At the same time, the accuracy for the three endpoints was 72.4%, 74.7%, and 75.7%, respectively. Conclusions: For patients with pharyngeal cancer ready to receive RT-based treatment, our proposed models can predict the development of LR, NR, or DM through baseline and ART simulation CTs. External validation needs to be conducted to confirm the model’s performance.

Background/Objectives: For many schoolchildren—particularly those in low-resource areas—the school lunch is the most reliable balanced meal of the day, so its composition is a direct determinant of dietary equity. The aim of this study was to quantify urban–rural disparities in school lunch food composition at national scale and to test whether they persist once county socioeconomic structure is controlled. Methods: Using 12,688,008 dish records from 3894 schools across all 22 Taiwanese counties over 24 months (May 2024–April 2026), retrieved from the Ministry of Education’s School Food Registry Platform, we constructed four dish-level dietary composition indicators—plant-forward, organic, processed, and whole-grain shares—and analyzed county-month panels (N = 418) using hierarchical regression with weighted least squares and heteroskedasticity-consistent standard errors. Results: The four dimensions followed distinct urban–rural patterns. Plant-forward provision exhibited a stable urban-to-rural decline. Organic and whole-grain provision displayed a suppressor structure: rural disadvantage disappeared—and reversed—once county income was controlled, revealing latent local supply capacity masked by income disparities. Processed-dish use, once income and population density were accounted for, was concentrated in lower-income, more densely populated counties rather than rural ones, indicating an urban concentration pattern rather than a rural deficit. A 2017 traceable-food pilot policy still exhibited a legacy effect on organic procurement seven years after its nationwide rollout. Conclusions: School meal programs thus deliver systematically different dietary environments to children in different places. Narrowing these gaps, rather than raising national averages, should be the core criterion for evaluating school lunch reform, with interventions differentiated across dietary dimensions.