Hanan Saeed Murayshid

Background: Knee osteoarthritis (KOA) is characterized by cartilage degradation and joint-space narrowing, resulting in increased friction and observable structural damage. Methods: This study introduces a composite hybrid framework for the automatic classification of KOA severity using anteroposterior knee X-ray images. The methodology applies joint-centered cropping and data augmentation to standardize inputs and uses class weighting to mitigate class imbalance. Deep features extracted from fine-tuned ResNet-101 and EfficientNetB7 models are integrated with handcrafted Gray Level Co-occurrence Matrix (GLCM) texture descriptors, and the final predictions are obtained using a soft-voting ensemble. Results: the proposed ensemble achieves 73% test accuracy (macro-F1 ≈ 0.70; weighted-F1 ≈ 0.73) in a four-class setting (KL-0, KL-2, KL-3, and KL-4). Additional experiments across different classification setups demonstrate consistent performance trends, while Grad-CAM indicates that the model primarily focuses on the joint region. Overall, Conclusions: combining ensemble deep learning with complementary handcrafted texture features provides a reliable and interpretable approach for grading radiographic KOA severity.

Early and reliable detection of cardiac disease is crucial for preventing complications and enhancing patient outcomes. Phonocardiogram (PCG) signals, which encode rich information about cardiac function, offer a non-invasive and cost-effective way to identify abnormalities such as valvular disorders, arrhythmias, and other heart pathologies. This study investigates advanced diagnostic methods for heart sound analysis to improve the detection and classification of cardiac abnormalities. In the proposed framework, recurrence plots (RPs) are used for feature extraction, while machine learning algorithms are applied for classification, creating a diagnostic model that can recognize cardiac conditions from composite acoustic signals. This method serves as an efficient alternative to more computationally intensive deep learning methods and other high-dimensional ML-based solutions. Experimental results demonstrate that the multiclass classification task achieves up to 98.4% accuracy, and the binary classification reaches 99.5% accuracy using 2 s signal segments. The techniques assessed in this research demonstrate the potential of automated heart sound analysis as a screening tool in both clinical and remote healthcare settings. Overall, the findings highlight the significance of machine learning in heart sound classification and its potential to facilitate timely, accessible, and cost-effective cardiovascular care.

We report an automated evaluation agent that can reliably assign classification labels to different Q&A pairs of both single-hop and multi-hop types, as well as to synthesis conditions datasets. Our agent is built around a suite of large language models (LLMs) and is designed to eliminate human involvement in the evaluation process. Through extensive testing of various approaches such as DSPy and finetuning, among others, we found that the performance of a given LLM on these Q&A and synthesis conditions classification tasks is determined primarily by the architecture of the agent where it makes a significant difference how the different inputs are parsed and processed, and how the LLMs are called. We also found that the quality of the prompt provided remains paramount, irrespective of the sophistication of the underlying model. Even models considered state-of-the-art, such as GPT-o1, exhibit poor performance when the prompt lacks sufficient detail and structure. To overcome these challenges, we performed systematic prompt optimization, iteratively refining the prompt to significantly improve classification accuracy and achieve human-level evaluation benchmarks. We show that while LLMs have made remarkable progress, they still fall short of human reasoning without substantial prompt engineering. The agent presented here provides a robust and reproducible tool for evaluating Q&A pairs and synthesis conditions in a scalable manner and can serve as a foundation for future developments in automated evaluation of LLM inputs and outputs.