Loewe Score Dual-Guided Diffusion Model for Synergistic Drug Combination Generation
Ling Wang, Xiwei Wang, Zhengyang Zhang, and Tie Hua Zhou
Health emergencies need to face the potential challenges about the public psychological healthcare and heart disease concurrent occurrence probability, especially for the large-scale pandemic disease spread situation. The complex bidirectional relationship between cardiovascular and psychological diseases highlights the importance of appropriate combination drug strategies, because of psychological therapy medicines could affect the heart sympathetic and parasympathetic nerve responses, at the same time, there may also cause a counter-effect. However, existing drug interaction prediction models focus only on the twoby-two drug relationship, which is difficult to meet the actual clinical needs for synergistic combination drugs. To address this, this paper proposes a Loewe score dual-guided diffusion model for synergistic drug combination generation aimed at generating drug combinations with high synergistic potential. It introduces drug text description information and Loewe synergistic score information into the training process of diffusion models, uses Loewe scores for conditional bias and weighted loss, and double guided denoising network learning to generate drug combinations with high synergy potential. The experimental results show that our proposed model is able to generate reasonable and reliable drug combinations, which provides a new perspective and an effective tool for solving the problem of clinical combination drug selection.
Ensemble-Based Deep Learning Framework for Multi-Class Skin Lesion Diagnosis with Class Imbalance Mitigation
Ujjwal Jain, Santosh Prakash Chouhan, Roshni Chakarborty, and Mahua Bhattacharya
Accurate multi-class classification of skin lesions remains a challenging task due to the intrinsic complexity of dermoscopic images and the severe class imbalance present in medical datasets. This paper introduces an ensemble-based deep learning pipeline designed to achieve robust and generalizable multi-class skin lesion diagnosis. The proposed framework systematically addresses the primary challenges of class imbalance using an aggressive mix up augmentation. A five face structured pipeline encompassing data preparation, stratified cross validation, model training, ensemble inference, and performance evaluation is performed. The proposed ensemble integrates five heterogeneous deep architectures: Vision Transformer (ViT), Swin Transformer, ConvNeXt, EfficientNet, and DenseNet, each contributing complementary representational strengths. To enhance model robustness and fairness, the pipeline incorporates regularization and a hybrid loss combining focal Loss and label smoothing. Ensemble predictions are aggregated using a weighted soft voting strategy, ensuring stable and accurate classification outcomes across all lesion categories. Experimental evaluations demonstrate that the proposed system achieves state-of-the-art performance on the HAM10000 dataset, delivering high accuracy and balanced sensitivity across minority classes. The end-to-end design emphasizes reproducibility, scalability, and transparency, establishing a robust foundation for future research in automated dermatological diagnosis.
Uncovering the Impact of Productivity on Mental Health Among Older Adults: A Data-Driven Analysis
Rachel Zhang, Ziqing(Jack) Zhao, Elizaveta Tremsina, and Tingying Helen Zeng
Mental health challenges such as depression and anxiety continue to affect a significant portion of the global population. As the understanding of these challenges evolves, there is an increasing need for data-driven methods to identify the factors that contribute to mental health and to strengthen resources for at-risk individuals. This study utilizes a publicly available mental health dataset from Kaggle to investigate predictors of depression in older adults. An XGBoost machine learning model was employed to estimate depression scores based on multiple psychological and behavioral variables. The primary research discovered that productivity score was the most significant predictor of depression in older adults, exhibiting a feature importance score of 0.762, substantially higher than other contributing factors. Visual analyses further confirmed a strong negative correlation between productivity levels and depression severity. These new findings underscore the pivotal role of productivity in late-life mental health and highlight opportunities for healthcare practitioners to develop targeted interventions aimed at improving well-being and reducing depressive symptoms among older adults.