IEEE Pulse最新文献

The field of neuroscience and neuroimaging has been revolutionized with the use of artificial intelligence (AI), as it helps in enhancing the detection of brain activities and accurately diagnosing neurological disorders using various modalities. There are different modalities that help in measuring brain activities, but the most common and widely used are functional magnetic resonance imaging (fMRI) and electroencephalography (EEG). The advanced AI approaches, like deep learning (DL) models, give a new opportunity to various fields, including brain research. This research investigates various AI-driven techniques used for the detection and exploration of the human brain using fMRI and EEG. The AI methods include different machine learning (ML) and DL techniques used to interpret neural activities. Basically, the AI-based models, which also include ML and DL, identify the patterns and detect the abnormalities with higher accuracy, which is helpful in many applications, including brain decoding, monitoring cognitive states, brain-computer interface (BCI), and diagnosis of various diseases. This research provides a comprehensive overview of AI applications in neuroimaging, highlights key applications in cognitive neuroscience and medical imaging, along with a discussion of challenges and future directions. The AI impact of the transformation of neuroimaging research is comprehensively discussed with examples to enhance comprehension.

Wearable devices are rapidly becoming indispensable for at-home care and rehabilitation programs as their data-gathering capability informs better clinical decision-making, but as the technology advances, are we now looking at more than just smart watches? Jim Banks looks at how wearables, ranging from fitness trackers to robotic exoskeletons, are helping patients rebuild their lives.

When applied to physiological and behavioral data collected from wearable devices, artificial intelligence (AI) can identify patterns associated with a variety of conditions, including mental health events. Researchers are exploring applications such as the early detection of mental health disorders and personalized, real-time interventions. However, these technologies also come with technical challenges and ethical considerations.

Digital twins (DTs) are emerging as a transformative paradigm in health care, combining continuous data from sensors, real-world insights from wearables, and predictive power from artificial intelligence (AI). These virtual patient replicas evolve in real time, enabling early disease detection, personalized simulation of treatment responses, and preventive interventions before symptoms appear. Recent advances in cardiology, oncology, and metabolic health illustrate how digital twins integrate multimodal data streams to generate actionable foresight. Coupled with blockchain for secure data exchange and patient consent, digital twins stand at the intersection of precision medicine and ethical innovation. This article explores the evolving role of digital twins in health care detection and preventive care, highlighting how sensors, wearables, and AI converge to reshape the future of clinical practice. This article also discusses privacy, interoperability, and regulatory guardrails.

Traditional procedures for diagnosing COVID-19 have mostly depended on invasive or resource-intensive technologies such as X-ray imaging, computed tomography (CT) scans, magnetic resonance imaging (MRI), and reverse transcription polymerase chain reaction (RT-PCR). Although these methods have therapeutic value, they are sometimes impractical for widespread screening, especially in settings with low resources or remote areas where access to highly skilled specialists and advanced technology is scarce. This work investigates noninvasive, AI-driven pipelines for COVID-19 detection that use cough and breath sounds as the primary inputs to address these issues. The proposed approach starts with sound acquisition and moves on to comprehensive feature extraction, focusing on image-based audio representations. The ability of various techniques, including scalograms, spectrograms, mel-spectrograms, chromagrams, wavelet spectrograms, cepstral analysis, gammatonegrams, power spectrograms, and short-time Fourier transform (STFT), to produce discriminative features that can either parallel or even enhance radiological modalities in AI-assisted systems is assessed.

Postage-stamp-sized arrays of infinitesimal needles are being developed that may one day provide the foundation for at-home cancer detection kits and wearable biosensors that can alert diabetes patients in real time as their blood sugar fluctuates. Microneedle arrays-medical patches embedded with micro-scale projections-are an emerging class of devices that are creating pain-free access to the interstitial fluid that surrounds cells just under the surface of the skin. Packed with the same enzymes and metabolites as blood, interstitial fluid also contains many unique biomarkers not found in blood. Researchers have demonstrated that the arrays can be used for inexpensive, biopsy-free melanoma detection, reported using a test strip similar to at-home COVID-19 detectors, and in a diabetes management wristband that combines continuous glucose monitoring with other chemical and cardiovascular signals to alert patients to dangerous trends that today's glucose monitors would miss.

The technology of clinical air cuff plethysmography is explored, from the very first pneumo-mechanical devices to the development of fully computer-automated and calibrated blood pressure and pulse waveform display and analysis.

This article examines how AI could expand health care access but also risks deepening inequities, especially in low- and middle-income countries.

Dr. Ida Sim discusses why health wearables have yet to deliver on their promise-and how JupyterHealth, an open-source platform, aims to change that. By enabling seamless integration of wearable data into clinical care, JupyterHealth offers a path to both better patient outcomes and sustainable innovation in digital health.

In this IEEE Pulse Industry Corner Live interview, Editor-in-Chief Chad Andresen speaks with Jared Tangney, Ph.D., co-founder and Chief Technology Officer of Biolinq, about the decade-long journey from university research to FDA-bound product. Biolinq has developed a next-generation continuous glucose monitoring (CGM) platform that leverages silicon-based micro-needle arrays to measure biomarkers painlessly within the upper layers of the skin. Tangney discusses the company's translation from NIH-funded feasibility studies to large-scale semiconductor manufacturing, the role of non-invasive, multi-analyte sensing for metabolic health, and the challenges of balancing innovation speed with regulatory rigor. He also outlines Biolinq's expansion beyond glucose toward lactate, cortisol, and phenylalanine monitoring, enabling broader applications in wellness, sports performance, and cognitive resilience. This conversation highlights the perseverance required to commercialize disruptive biosensing technology and underscores the growing convergence of wearable electronics, biotechnology, and AI-driven health data in reshaping personalized medicine.