BBlogFlow

ARES-SI: adaptive reinforcement-enhanced sampling for suicidal ideation - Nature

·3h ago

We’re sharing this article early to provide faster access to peer-reviewed, accepted research. It is citable and carries a permanent DOI. This version is subject to further edits and will be replaced automatically by the final Version of Record. All legal disclaimers apply.

AbstractSuicidal ideation (SI) fluctuates rapidly within individuals, but standard ecological momentary assessment (EMA) uses fixed schedules that miss critical risk windows. We present ARES-SI (Adaptive Reinforcement-Enhanced Sampling for Suicidal Ideation), a reinforcement learning system that personalizes EMA timing to individual risk patterns. ARES-SI combines random forest models to predict active SI probability and non-response likelihood with a Q-learning algorithm to determine optimal assessment intervals (30 min for high-risk states, 3 h for low-risk states, and next day to reduce burden). We trained the system using EMA data from 98 participants across three studies with varied sampling frequencies (4–15 assessments per day; 2359 positive active SI responses) over 28-day protocols.

This article is an excerpt. To read the full content, visit the original source. Nature

Reactions

Share Facebook Twitter Email

0 comments

No comments yet. Be the first to share your thoughts!

Related articles

HPV Self-Sampling May Improve Cervical Screening Access - EMJ

HUMAN papillomavirus (HPV) self-sampling could offer a promising approach to improving cervical cancer screening access among socially vulnerable migrant women, according to a mixed-methods study conducted in Portugal. Researchers found high levels of acceptability among women participating in a community-based HPV self-sampling intervention, with significant improvements in perceived comfort, confidence, and trust following the experience. The findings suggest that culturally adapted screening approaches delivered through trusted community organisations could help address persistent inequalities in cervical cancer prevention.

EMJ·

Error Mitigation Cuts Sampling Overhead For Quantum Circuits - Quantum Zeitgeist

Researchers at Google Quantum AI and Cornell University have demonstrated a new error mitigation technique that surpasses existing methods by operating entirely in classical post-processing. Their work introduces virtual error cancellation, a method that reduces sampling overhead by using only syndrome records from quantum circuits, bypassing the need for prior noise characterization and modified circuits. Numerical simulations using a distance-7 rotated surface code show the full-stack dual-decoder algorithm achieves more than three orders of magnitude of suppression in error rate compared to standard decoding. This approach operates entirely through classical post-processing, offering a streamlined pathway to more reliable computation. The core of this advancement lies in the ability to avoid the typical requirements of noise learning and circuit alterations, both of which add complexity and overhead to quantum error mitigation.

Quantum Zeitgeist·

Experimental characterization and scaling of flexural rigidity in sewn multilayer structures - Nature

We’re sharing this article early to provide faster access to peer-reviewed, accepted research. It is citable and carries a permanent DOI. This version is subject to further edits and will be replaced automatically by the final Version of Record. All legal disclaimers apply. AbstractSewing is one of the established methods used to fabricate and assemble multilayer insulation (MLI) blankets for aerospace applications, yet the resulting effective flexural behavior remains insufficiently understood. This study investigates the room-temperature, quasi-static flexural behavior of MLI blankets composed of aluminized BoPET radiation shields and polyester net spacers across structural configurations of 2, 6, 12, and 24 layers. A full factorial design was employed to evaluate the influence of the number of layers, stitch density, needle thread tension, and needle foot force. Statistical analyses demonstrated that the number of layers is the dominant factor governing flexural response. Among the sewing parameters, needle thread tension was associated with modifications in bending length, while needle foot force primarily affected local compaction.

Nature·

Targeted pathway mining reveals novel modified hexapeptides from the demiguisin family - Nature

IntroductionBirds rely on a collection of behavioural, physiological, and chemical defences to mitigate the constant threat posed by pathogens and parasites in their environment1. Preen oil from the uropygial gland (UG) is a key component of avian integumentary immunity, supporting feather maintenance and waterproofing, while the UG is also known to harbour diverse microbes, including γ- and α-Pseudomonadota and Actinomycetota, that contribute to feather defense2,3. We recently exemplified a case of the bacterial isolate Amycolatopsis sp. PS_44_ISF1 derived from the UG of the toxic bird Pachycephala schlegelii that can directly contribute to the bird’s chemical defence system, by producing bioactive metabolites such as the antifungal macrolactam ciromicin A3,4, the co-secreted tensioactive lipopeptide family pachycephalamides, and a highly modified hexapeptide, named demiguisin A (1) (Fig. 1). The chemical structure of 1, caught our interest, as it contains non-proteinogenic piperazic acid (hexahydropyridazine-3-carboxylic acid, Piz) residues within the sequence Gly–β,γ-OH-Piz–Leu–Piz–DHPA–γ-c-Pro (Fig. 1)3,5.

Nature·