Machine learning in point-of-care testing: innovations, challenges, and opportunities

Paper-Based Vertical Flow Assays for in Vitro Diagnostics and Environmental Monitoring

Microfluidic paper-based analytical devices (μPADs) are powerful tools for diagnostic and environmental monitoring. Being affordable and portable, μPADs enable rapid detection of small molecules, heavy metals, and biomolecules, thereby decentralizing diagnostics and expanding biosensor accessibility. However, the reliance on two-dimensional fluid flow restricts the utility of conventional μPADs, presenting challenges for applications that require simultaneous multibiomarker analysis from a single sample. Vertical flow paper-based analytical devices (VF-μPADs) overcome this challenge by allowing axial fluid movement through paper stacks, offering several advantages, including (1) enhanced multiplexing capabilities, (2) reduced hook effect for improved accuracy, and (3) shorter assay times. This review provides an overview of VF-μPADs technologies, exploring structural and functional performance trade-offs between VF-μPADs and conventional lateral flow systems. The sensing performance, fabrication methods, and applications in in vitro diagnostics and environmental monitoring are discussed. Furthermore, critical challenges─such as fabrication complexity, data analysis, and scalability─are addressed, along with proposed strategies for mitigating these barriers to facilitate broader adoption. By examining these strengths and challenges, this review presents the potential of VF-μPADs to advance point-of-care testing, particularly in resource-limited settings.

Mpox diagnosis at POC

The increasing number of Monkeypox (Mpox) cases in non-endemic countries resulted in the WHO declaring a public health emergency of international concern. Accurate and timely diagnosis of Mpox has a critical role in containing the spread of infection. Diagnosis currently relies on PCR, which requires trained personnel and complex laboratory infrastructure. Thus, the development of point-of-care (POC) tools are essential to facilitate rapid, accurate, and user-friendly diagnosis. Here, we review POC diagnostic tools available for Mpox. We also discuss bottlenecks preventing the widespread implementation of POC platforms for Mpox diagnosis and potential strategies to address these limitations. Furthermore, we describe future directions, including the role of machine learning (ML) and deep learning (DL)-based models and the integration of integrated field-deployable platforms for Mpox diagnosis.

Integrated Photonic Biosensors: Enabling Next-Generation Lab-on-a-Chip Platforms

Integrated photonic biosensors are revolutionizing lab-on-a-chip technologies by providing highly sensitive, miniaturized, and label-free detection solutions for a wide range of biological and chemical targets. This review explores the foundational principles behind their operation, including the use of resonant photonic structures such as microring and whispering gallery mode resonators, as well as interferometric and photonic crystal-based designs. Special focus is given to the design strategies that optimize light-matter interaction, enhance sensitivity, and enable multiplexed detection. We detail state-of-the-art fabrication approaches compatible with complementary metal-oxide-semiconductor processes, including the use of silicon, silicon nitride, and hybrid material platforms, which facilitate scalable production and seamless integration with microfluidic systems. Recent advancements are highlighted, including the implementation of optofluidic photonic crystal cavities, cascaded microring arrays with subwavelength gratings, and on-chip detector arrays capable of parallel biosensing. These innovations have achieved exceptional performance, with detection limits reaching the parts-per-billion level and real-time operation across various applications such as clinical diagnostics, environmental surveillance, and food quality assessment. Although challenges persist in handling complex biological samples and achieving consistent large-scale fabrication, the emergence of novel materials, advanced nanofabrication methods, and artificial intelligence-driven data analysis is accelerating the development of next-generation photonic biosensing platforms. These technologies are poised to deliver powerful, accessible, and cost-effective diagnostic tools for practical deployment across diverse settings.

Role of Artificial Intelligence and Personalized Medicine in Enhancing HIV Management and Treatment Outcomes

The integration of artificial intelligence and personalized medicine is transforming HIV management by enhancing diagnostics, treatment optimization, and disease monitoring. Advances in machine learning, deep neural networks, and multi-omics data analysis enable precise prognostication, tailored antiretroviral therapy, and early detection of drug resistance. AI-driven models analyze vast genomic, proteomic, and clinical datasets to refine treatment strategies, predict disease progression, and pre-empt therapy failures. Additionally, AI-powered diagnostic tools, including deep learning imaging and natural language processing, improve screening accuracy, particularly in resource-limited settings. Despite these innovations, challenges such as data privacy, algorithmic bias, and the need for clinical validation remain. Successful integration of AI into HIV care requires robust regulatory frameworks, interdisciplinary collaboration, and equitable technology access. This review explores both the potential and limitations of AI in HIV management, emphasizing the need for ethical implementation and expanded research to maximize its impact. AI-driven approaches hold great promise for a more personalized, efficient, and effective future in HIV treatment and care.