Background/Objectives: Accurate and reproducible grading of lumbar spinal stenosis (LSS) is clinically critical for guiding treatment decisions and patient management, yet manual assessment remains challenging due to imaging variability and inter-observer subjectivity. To address these limitations, this study aimed to evaluate the generalizability of deep learning–based feature extraction methods—VGG19, ConvNeXt-Tiny, and DINOv2—combined with classical machine learning classifiers for automated multi-grade LSS assessment. Automated grading enables objective, reproducible, and scalable assessment of lumbar spinal stenosis severity, addressing key limitations of manual interpretation. Methods: Axial MRI images were processed using pretrained VGG19, ConvNeXt-Tiny, and DINOv2 models to extract deep features. Logistic Regression, Support Vector Machine (SVM), and LightGBM were trained on internal datasets and externally validated using MRI data from the University of Phayao Hospital. Performance was assessed using accuracy, precision, recall, F1-score, confusion matrices, and multi-class ROC curves. Results: VGG19-based features yielded the strongest external performance, with Logistic Regression achieving the highest accuracy (0.9556) and F1-score (0.9558). External validation further demonstrated excellent discrimination, with AUC values ranging from 0.994 to 1.000 across all severity grades. SVM (0.9333 accuracy) and LightGBM (0.9222 accuracy) also performed well. ConvNeXt-Tiny showed stable cross-model performance, while DINOv2 features exhibited reduced generalizability, especially with LightGBM (accuracy 0.6222). Most classification errors occurred between adjacent grades. Conclusions: Deep convolutional features—particularly VGG19—combined with classical machine learning classifiers provide robust and generalizable LSS grading across external MRI data. Despite advances in modern architectures, CNN-based feature extraction remains highly effective for spinal imaging and represents a practical pathway for clinical decision support.

Background: Urinary tract infections (UTIs) remain among the most common bacterial infections, yet reliable risk stratification remains challenging. Serum vitamin D has been linked to immune regulation, but its predictive role in UTI subtypes is unclear. Methods: We analyzed 332 de-identified clinical records using six machine learning algorithms: Extra Trees, Gradient Boosting, XGBoost, Logistic Regression, Random Forest, and LightGBM. Two preprocessing strategies were applied: (i) removing rows with missing fasting blood sugar (FBs) and HbA1c, and (ii) dropping columns with Null FBs and HbA1c values. Model performance was evaluated using 10-fold cross-validation. Results: Serum vitamin D showed weak correlations with UTI subtypes but modest importance in tree-based models. The highest predictive accuracy was obtained with Extra Trees (0.9510) under the row-removal strategy and Random Forest (0.9525) under the column-dropping strategy. Models excluding vitamin D maintained comparable accuracy, suggesting minimal impact on overall predictive performance. Conclusions: Machine learning models demonstrated high accuracy and robustness in predicting UTI subtypes across preprocessing strategies. While vitamin D contributes as a supportive feature, it is not essential for reliable prediction. These findings highlight the adaptability and clinical utility of both vitamin D-inclusive and vitamin D-exclusive models, supporting deployment in diverse healthcare settings.

The rising deployment of artificial intelligence in public services is constrained by computational costs and limited domain-specific data, particularly in multilingual contexts. This study proposes a generalizable Agentic AI pipeline for developing question–answer chatbot systems using small language models (SLMs), demonstrated through a case study on the Thai Student Loan Fund (TSLF). The pipeline integrates four stages: OCR-based document digitization using Typhoon2-3B, agentic question–answer dataset construction via a clean–check–plan–generate (CCPG) workflow, parameter-efficient fine-tuning with QLoRA on Typhoon2-1B and Typhoon2-3B models, and retrieval-augmented generation (RAG) for source-grounded responses. Evaluation using BERTScore and CondBERT confirmed high semantic consistency (F_BERT = 0.9807) and stylistic reliability (F_BERT = 0.9839) of the generated QA corpus. Fine-tuning improved the 1B model’s domain alignment (F_BERT: 0.8593 → 0.8641), while RAG integration further enhanced factual grounding (F_BERT = 0.8707) and citation transparency. Cross-validation with GPT-5 and Gemini 2.5 Pro demonstrated dataset transferability and reliability. The results establish that Agentic AI combined with SLMs offers a cost-effective, interpretable, and scalable framework for automating bilingual advisory services in resource-constrained government and educational institutions.