Search for: All records

Algorithmic bias in COVID-19 detection systems poses aserious threat to equitable pandemic response, asdemographicdisparities in model performance risk worsening healthoutcomes across vulnerable populations. We present anadoptedCausal Concept Bottleneck Model (C2BM) framework thatsystematically addresses fairness in multimodal COVID-19detection by learning interpretable concepts from chest CTscans and patient metadata. Our approach targets theCountry → Institution → COVID causal pathway throughprincipledinterventions, achieving substantial bias reduction: age andgender demographic parity differences decrease from 51.15%to 18.50% (64% reduction), gender disparate impact improvesfrom 0.6475 to 0.9812 (51% improvement), whilepreserving 98.45% diagnostic F1-score. Throughcomprehensive evaluation across four model variants, wedemonstrate that causal interventions enable stable andreproduciblefairness improvements without compromising clinicalutility. Our work establishes that principled causalreasoning canachieve practical fairness-accuracy trade-offs in COVID-19detection systems, providing actionable guidance forequitable healthcare AI deployment. 

Designing and manufacturing devices at the micro- and nanoscales offers significant advantages, including high precision, quick response times, high energy density ratios, and low production costs. These benefits have driven extensive research in micro-electromechanical systems (MEMS) and nano-electromechanical systems (NEMS), resulting in various classifications of materials and manufacturing techniques, which are ultimately used to produce different classifications of MEMS devices. The current work aims to systematically organize the literature on MEMS in biomedical devices, encompassing past achievements, present developments, and future prospects. This paper reviews the current research trends, highlighting significant material advancements and emerging technologies in biomedical MEMS in order to meet the current challenges facing the field, such as ensuring biocompatibility, achieving miniaturization, and maintaining precise control in biological environments. It also explores projected applications, including use in advanced diagnostic tools, targeted drug delivery systems, and innovative therapeutic devices. By mapping out these trends and prospects, this review will help identify current research gaps in the biomedical MEMS field. By pinpointing these gaps, researchers can focus on addressing unmet needs and advancing state-of-the-art biomedical MEMS technology. Ultimately, this can lead to the development of more effective and innovative biomedical devices, improving patient care and outcomes.