A team from Tarbiat Modares University introduces a multi-task CNN that analyzes STFT and CWT time-frequency EEG images to diagnose partial sleep deprivation. They optimize combined task outputs via genetic and Q-learning algorithms, using only three EEG channels, to achieve rapid, cost-effective, and accurate sleep disorder assessment for clinical support.

Key points

• A partially shared multi-task CNN processes STFT and CWT EEG images to extract task-specific and shared features.
• Genetic algorithm and Q-learning optimize linear weight combination of three task predictions to minimize loss and maximize accuracy.
• Model uses only three EEG channels (F3, F4, C4) and achieves 98% accuracy on partial sleep deprivation classification.

Why it matters: Multi-task learning with genetic and Q-learning optimization greatly speeds and improves automated EEG sleep disorder detection.

The Longevity Doctor clinic, led by anti-ageing specialist Dr Philip Borg, conducts over 150 biomarker assays, a Trudiagnostic Biological Age test, DEXA scans and VO₂ max evaluation. Integrating metabolic monitoring, body composition and fitness profiling, the clinic formulates personalized preventive and training protocols to optimize healthspan and mitigate age-related risks.

Key points

• Over 150 blood biomarkers and a Trudiagnostic Biological Age assay quantify cellular ageing relative to chronological age.
• Continuous glucose monitoring and VO₂ max testing evaluate metabolic and cardiovascular fitness for personalized health profiling.
• Full-body DEXA scans and ultrasound screenings assess organ health and bone density, guiding targeted resistance training to improve muscle mass and longevity.

Why it matters: Data-driven longevity assessments create a paradigm shift toward preventive, personalized health interventions that slow biological ageing and reduce disease burden.

Researchers demonstrate that p62 protein depletion drives skin cell senescence through USP7 pathway dysregulation and show that replenishing p62 delays senescence markers in fibroblasts and keratinocytes, offering a novel target for anti-aging skin therapies.

Key points

• p62 directly binds USP7, preserving autophagic degradation and preventing p53/p21/p16-mediated senescence in dermal fibroblasts and keratinocytes.
• p62 knockout in keratinocytes accelerates skin thinning and increases inflammatory SASP markers (interleukins, TNF-α) in a mouse model.
• p62 overexpression halves UV-induced senescence rates in skin cells and reduces expression of USP7 and senescence biomarkers.

Why it matters: Targeting p62 replenishment offers a novel senomorphic strategy to maintain skin health and delay visible signs of aging.

Analysts at Longevity.Technology publish the 2024 Annual Longevity Investment Report, detailing USD 8.49 billion invested across 331 transactions. They segment funding by technology domain, investment stage, and geography to uncover trends in senotherapeutics, discovery platforms, and consumer applications driving healthspan extension.

Key points

• Report quantifies USD 8.49 billion funding across 331 deals, marking a 220% increase from 2023.
• Segmentation across 25 domains highlights over USD 2 billion for discovery platforms and significant investment in senotherapeutics.
• U.S. firms represent 57% of companies and 84% of deal volume, with later-stage VC comprising 31% of total funding.

Why it matters: This financial rebound underscores maturing longevity biotech, catalyzing resource allocation toward foundational discovery platforms and accelerating translational therapies.

Researchers at Thomas Jefferson National Accelerator Facility leverage high-frequency data and unsupervised machine learning to detect and predict SRF cavity anomalies in real time, enhancing beamtime reliability and efficiency in CEBAF operations.

Key points

• High-frequency (5 kHz) data acquisition enables real-time capture of transient SRF cavity behaviors.
• Unsupervised PCA models detect anomalous cavity instabilities before beam trips.
• Deep learning predicts 80 % of slow-developing cavity faults with 99.99 % normal-operation accuracy.
• Gradient-based optimization of cavity voltages cuts field emission radiation by up to 45 %.

Why it matters: AI-driven anomaly detection and optimization extend accelerator uptime and enhance experimental throughput, accelerating discoveries in nuclear physics.