Mycosis fungoides is characterized by widespread skin patches that may progress to plaques and tumors, necessitating precise tumor burden assessment for staging and treatment guidance. However, existing methods, including the widely accepted modified Severity Weighted Assessment Tool (mSWAT), present significant challenges in routine practice owing to their time-consuming nature and interobserver variability. This study developed an artificial intelligence model, mSWAT-Net, to estimate mSWAT scores using clinical images of patients with mycosis fungoides. Notably, the overlap area segmentation submodule of mSWAT-Net addressed double-counting errors in multiangle photos through training on 3904 annotated images generated from 61 three-dimensional human images. Across 2463 standardized full-body photographs from 134 imaging series, mSWAT-Net demonstrated performance comparable with that of experienced cutaneous lymphoma specialists, achieving intraclass correlation coefficients of 0.917 (internal validation) and 0.846 (temporal validation) for mSWAT score. Moreover, mSWAT-Net outperformed 3 junior dermatologists in image-based scoring (intraclass correlation coefficient = 0.917 vs 0.777) and demonstrated robust performance when compared with ground truth derived from 3-dimensional patient imaging (intraclass correlation coefficient = 0.812). Finally, mSWAT-Net was deployed as a free web application to support mycosis fungoides management in clinical settings. These findings highlight the potential of mSWAT-Net as an accurate, automated clinical tool for facilitating patient follow-up, treatment monitoring, and remote consultations.
Volatile elements are essential for life development and planetary evolution. However, the timing of their delivery to terrestrial planets remains unclear. Sulfur, selenium, and tellurium are volatiles, but also siderophile elements. Their abundances in Earth’s mantle can be used to determine whether volatile elements were delivered to Earth during or after the segregation of the core. Here, we experimentally measured their partition coefficients between core-forming metal and mantle silicate under pressure, temperature, and oxygen fugacity conditions relevant to a deep magma ocean. Our results show that these elements exhibit similar partitioning behaviors, indicating that core-mantle equilibrium preserves their chondritic relative abundances. If a volatile-rich late veneer has been delivered to Earth after core segregation, it must have been limited in mass, making up a maximum of 0.1% Earth’s mass. This suggests that volatile elements, including water, were accreted continuously during Earth’s growth rather than being delivered predominantly by a late veneer of volatile-rich material such as carbonaceous chondrites.
This longitudinal study investigates the structure, developmental trends, and well-being implications of values among Chinese adolescents – a large, culturally distinctive population undergoing rapid social change. We conducted a large-scale, two-wave longitudinal study (Wave 1: N = 69,115; M = 12.74 ± 2.25 years; 49.84% girls; Wave 2: N = 45,762; M = 12.98 ± 2.22 years; 50.53% girls; with 45,762 students participating in both waves) across a 6-month interval. A three-factor structure of adolescent values emerged: Collective Altruism, Individual Initiative, and Individual Hedonism. Results revealed distinct developmental trajectories: Collective Altruism declined slightly, while Individual Hedonism increased, both stabilizing around mid-adolescence (age~15)—a developmental inflection point in value orientation. Cross-lagged models demonstrated small but significant reciprocal positive associations between Collective Altruism, Individual Initiative, and well-being, while Individual Hedonism showed a small but significant negative association with subsequent well-being. These findings support the theoretical framework of contextually healthy values—value orientations that are culturally normative and developmentally adaptive. This study also provides valuable insights for promoting adolescent mental health and positive development in rapidly modernizing contexts.
Digital technologies such as telepsychology, mobile health applications, artificial intelligence (AI), and immersive virtual environments are rapidly transforming the delivery of psychological care. Despite these advances, music therapy remains weakly integrated into most digital mental health systems. In many current interventions, including virtual reality therapies and mental health applications, music is typically used as background ambience rather than as an active therapeutic mechanism. This disconnect limits the potential of music-based interventions for emotional regulation and psychological support. Advances in artificial intelligence create new opportunities to address this gap. Through emotion recognition, behavioral data analysis, and generative music algorithms, AI systems can anticipate emotional states and deliver adaptive musical interventions before psychological distress escalates. Such AI-driven proactive music therapy enables music to function as an embedded regulatory component within digital mental health ecosystems rather than as a passive environmental feature. A conceptual framework for integrating proactive music therapy into digital mental health platforms is proposed, highlighting key technological components including emotion sensing, adaptive music intelligence, and digital therapeutic delivery. Ethical considerations and research priorities for AI-enabled music interventions are also outlined. AI-driven proactive music therapy may represent an important direction for scalable and personalized psychological care in the era of digital mental health.
Alumni relationships are essential social capital that are significant in companies’ resource acquisition and information sharing. Using 2018 data from Chinese listed companies, this study examines the impact of the chairperson–alumni network on corporate artificial intelligence (AI) adoption. The results show that chairperson–alumni relations are positively associated with AI adoption. Moreover, the impact of chairperson–alumni networks on AI adoption may span industrial, administrative, and geographical boundaries. This study shows that chairperson–alumni networks can indirectly influence AI adoption by influencing board size. Finally, this study demonstrates the heterogeneity of the impact of the chairperson–alumni network on AI adoption.
Alzheimer’s disease (AD) has traditionally been approached through a biomedical lens, focusing on neurodegenerative markers such as amyloid-β plaques and tau protein accumulation. However, clinical evidence increasingly demonstrates that social dysfunction, which includes identity confusion, emotional withdrawal, and breakdowns in social roles. This article reconceptualizes AD as a disorder in which the primary dimension of decline lies in social relationship management capacity (SRMC), while recognizing that neurobiological and cognitive deterioration remain integral to its manifestation and progression. SRMC refers to a person’s ability to identify, interpret, maintain, and regulate social ties embedded in complex networks. This article introduces a conceptual and technical framework for a socially embedded artificial intelligence (AI) framework designed to recognize and compensate for the deterioration of SRMC in AD. Drawing on social capital theory, affective computing, and neural social cognition research, this framework proposes a four-dimensional intervention model: relationship recognition, relationship learning, relationship establishment, and relationship management. By aligning cutting-edge AI techniques with the lived social reality of individuals with AD, this approach not only provides a new path for supportive care but also reorients ethical and technological discourse toward sustaining social personhood in the face of neurodegeneration.
Traditional polysomnography (PSG) systems are limited by cumbersome hardware, inefficient clinical workflows, and significant patient discomfort, hindering accurate characterization of natural sleep. Here, we present a wearable sleep-breathing monitoring system based on a printed electronic skin (E-skin) sensor that enables comfortable, high-fidelity, and home-viable respiratory assessment. The device employs a resistive eutectic gallium-indium-tin (EGaInSn) liquid-metal sensing layer screen-printed onto a flexible thermoplastic polyurethane (TPU) substrate, offering stable sensitivity over a broad dynamic range, mechanical robustness, and seamless skin conformability for long-term wear. A six-channel sensing network was implemented to capture thoracic and abdominal respiratory dynamics across diverse sleeping positions. Comprehensive clinical validation was conducted against gold-standard PSG, with respiratory events independently scored by Registered Polysomnographic Technologists (RPSGTs) under single-blind conditions. The system demonstrates high concordance with PSG in identifying obstructive and central sleep apnea, hypopnea, Cheyne–Stokes respiration, and respiratory rate abnormalities. By integrating flexible electronics and clinically aligned signal interpretation, this work advances wearable health technologies from conventional physiological monitoring toward credible diagnostic capability, providing a practical solution for continuous, accurate evaluation of sleep-related breathing disorders.
Physical activity guidelines commonly recommend that older adults engage in at least 150–300 min of moderate intensity aerobic activity each week, combined with muscle strengthening and balance training. Although this target is clear, measurable, and useful for public health monitoring, it may be insufficient when directly applied to community-dwelling older adults who are frail, multimorbid, socially isolated, digitally excluded, or constrained by unsafe environments and limited care resources. For these populations, the central challenge is not only whether they can meet a weekly exercise volume, but whether they can preserve the functional abilities needed for independent living, social participation, and active aging. This Perspective argues for moving exercise promotion for community-dwelling older adults beyond a narrow adherence-based view of the 150-min target and toward a function-oriented paradigm of active health. We propose an integrated framework that places functional preservation at the center, uses micro dose exercise as an accessible entry point, applies Behavior Change Techniques to translate recommendations into sustainable daily habits, embeds exercise within community life through social prescribing, and supports long-term participation through human and digital collaboration. This approach does not reject existing physical activity guidelines. Rather, it reframes them as flexible references that can be adapted to older adults’ heterogeneous bodily conditions, social contexts, and everyday routines. By shifting from exercise adherence to long-term functional integration, community-based exercise promotion can become more inclusive, equitable, and feasible for older adults who are most likely to be left behind by standard dose-based models.
Bioleaching offers a sustainable alternative to conventional metallurgy, but its application is limited by low leaching rates, inhibition by heavy metals, and prolonged adaptation. Here, we engineered Acidithiobacillus ferrooxidans, a model bioleaching microorganism ubiquitous in mining environments, by modulating intracellular bis(3′ −5′)-cyclic dimeric guanosine monophosphate (c-di-GMP) signaling to enhance biofilm formation, bioleaching efficiency, and arsenic tolerance. Overexpression of diguanylate cyclase genes AFE_1379, AFE_0053, and AFE_1373 produced engineered strains S-222, S-306, and S-651, respectively, with 1.7-, 2.5-, and 5-fold higher intracellular c-di-GMP levels than the control carrying the empty plasmid vector. Under arsenic-free condi tions, all engineered strains showed similar growth profiles, but S-306, at intermediate c-di-GMP (306.3 ± 28.1 μg mg−1), formed cytochrome-rich biofilms with low internal resistance and achieved the highest bioleaching efficiency. Under arsenic stress, S-651, at high c-di-GMP (651.4 ± 15.5 μg mg−1), developed polysaccharide-rich biofilms that enhanced arsenic tolerance, scorodite (FeAsO₄·2H₂O) precipitation, and bioleaching performance. Transcriptomic analysis confirmed these strain-specific gene expression patterns. These findings demonstrate that tuning intracellular c-di-GMP enables A. ferrooxidans to reprogram biofilm matrix composition for extracellular electron uptake and heavy-metal resistance, providing a synthetic biology strategy for environmentally friendly bioleaching and tailings recycling