AI News Archive: June 25, 2026 — Part 20
Sourced from 500+ daily AI sources, scored by relevance.
- Methamphetamine-induced disruption of neuropeptide expression in mice
Psychoactive and psychotoxic drugs are particularly harmful, if their use coincides with critical developmental windows of brain maturation. Methamphetamine is one such stimulant with developmental exposure increasing seizure susceptibility and long-term neuronal maladaptation in children. Nevertheless, the extent at which infant and adult vulnerability to methamphetamine could differ in time-course and severity remains incompletely understood. Here, we developed a method to monitor methamphetamine-induced hyperactivity in infant mice at high temporal resolution, differentiate it from a biphasic response in adults, and link it to activity changes in cortical areas executing goal-directed (escape) behaviors in infant subjects when using Fos expression as a molecular surrogate. Subsequently, we hypothesized that methamphetamine could alter the expression and cellular distribution of inhibitory neuropeptides, which, when co-released with fast neurotransmitters, could protect circuit plasticity by counteracting methamphetamine-induced hyperexcitability. Methamphetamine differentially altered somatostatin, cholecystokinin, and galanin expression in corticolimbic areas. These data suggest that methamphetamine can evoke age-specific neurocircuit modifications, at least in mice.
- Dysfunction of the colliculus-pulvinar pathway in children with developmental dyslexia
While evidence suggests magnocellular deficits in the geniculostriate pathway in adults with dyslexia, neural deficits in the subcortical pathways during childhood remain unclear. Here, we used high-resolution fMRI to investigate subcortical abnormalities in Chinese children with developmental dyslexia. Fast achromatic motion stimuli and slowly drifting chromatic gratings were used to assess magnocellular (M) and parvocellular (P) functions, respectively. Relative to controls, children with dyslexia showed a selective reduction in responses to the M stimulus in the ventromedial pulvinar (vmPul) and the superficial layers of the superior colliculus (SCs), along with significantly reduced SCs-vmPul connectivity. Importantly, while vmPul responses to the M stimulus were positively associated with reading skills in healthy controls, this correlation was absent in children with dyslexia. Unlike previous findings in adults, the lateral geniculate nucleus (LGN) exhibited a non-selective reduction in responses to both stimuli, no volume reduction, and no correlation with reading ability. These findings demonstrate a selective deficit to achromatic motion processing in the colliculus-pulvinar pathway in children with dyslexia, which contributes to their reading difficulties. This early subcortical disruption differs from, and precedes, the neural deficits previously reported in the adult LGN, offering new insight into the developmental trajectory of dyslexia.
- Exploring the functionality of market-available tools for neural recording
Low-cost and open-source neural recording systems are increasingly important for expanding access to electrophysiological research. However, many existing platforms still rely on specialized hardware or limited modularity, restricting flexibility for laboratories seeking customizable solutions. Here, we developed and evaluated a modular neural recording platform constructed entirely from commercially available components. Recordings were compared against the ground truth. The platform successfully recovered local field potential (LFP)-like waveforms in most conditions and detected spike-like activity during direct connection recordings. Principal component analysis and k-means clustering further demonstrated the ability to distinguish multiple simulated spike waveforms. Signal quality varied across configurations, with saline recordings and preamplifier integration introducing increased noise and reduced detectability. These findings demonstrate the feasibility of building affordable and modular electrophysiology systems using widely accessible hardware. Although the current implementation has limitations in sampling rate, noise performance, and in vivo validation, the presented framework provides a practical foundation for future customizable open-source neural recording.
- JNJ-42153605, a mGluR2 PAM, potentiates Levetiracetam treatments of TBI to mitigate subsequent tau aggregation in a larval zebrafish model
Traumatic brain injury (TBI) has long-term consequences that include chronic traumatic encephalopathy (CTE) and an elevated risk for Alzheimer Disease (AD). These dementias ultimately manifest as tauopathies but may begin with acute neuronal dysfunction including post-traumatic seizures. Provocative evidence suggests that these prodromal seizures are a viable target to mitigate the later onset of dementias, and anti-epileptic drugs (AED) that increase the threshold of action potentials have indeed been shown to mitigate later tauopathies[1, 2]. Here, we test whether AEDs and other compounds that modulate synaptic transmission, applied immediately after TBI, can also act as prophylactics that block subsequent CTE-like tau aggregation and neurodegeneration in a larval zebrafish model. Levetiracetam (LEV) is an AED that modulates synaptic vesicle release. Application of LEV immediately following TBI abrogated TBI-induced tau tau aggregation (IC50 = 3.168 x10-3 mM) and cell death in the larval zebrafish TBI model. We next considered a polypharmacy approach involving mGluR2, because mGluR2 positively allosteric modulators (PAMs) such as JNJ-42153605 have previously been able to improve LEV's action in reducing some recalcitrant forms of seizure in a mouse model. We found that JNJ-42153605 was itself effective at blocking TBI-induced tau aggregation (IC50 = 8.691 x10-5 mM). Moreover, a subeffective dose of JNJ-42153605 (10-5 mM) was able to substantially improve the efficacy of LEV (~16-fold) in its prophylactic actions. Thus, LEV and JNJ-42153605 applied briefly after TBI offer a potent polypharmacy approach, at least in our preclinical animal model, to tackle the later tau aggregation and neurodegeneration that follows from TBI neurotrauma. These results warrant further investigation, including testing into mammalian TBI models (with longer disease course).
- NeuroEnergetics-on-Chip: a novel 3-compartment microfluidic platform to study metabolic interactions between brain parenchyma and cerebral vasculature
Neurological disorders are a major cause of death and disability worldwide. The brain's energy metabolism is essential to its proper function, yet the mechanisms driving neuroenergetic dysfunction remain poorly understood. A key challenge is the limited availability of human-relevant models that can reproduce the complexity of brain physiology. An Organ-on-Chip (OoC) system was developed to mimic the neurovascular unit metabolic coupling by incorporating human isogenic iPSC-derived endothelial-like cells, pericyte-like cells, astrocytes, and a cerebral organoid, representing the main cellular components of the NVU. The novel, customized microfluidic platform enables research on neurovascular coupling by interconnecting a blood-brain barrier-on-a-chip model with a 3D brain parenchymal compartment to mimic physiological conditions.
- A next-generation electronic frailty index leveraging deep learning on unstructured health records extends risk prediction across the full frailty spectrum
Background: Existing electronic frailty indices (eFI) are typically based on structured data and designed for older adults. We developed an eFI that integrates structured and unstructured electronic health records (EHRs) across adulthood and assessed its longitudinal trajectories and associations with adverse outcomes. Methods: We used longitudinal EHR data from 193629 individuals aged 35-103 in the Wellbeing Services County of Central Finland (2010-2023) and constructed a 53-item eFI including diagnosis codes, laboratory tests and items extracted from free-text clinical notes using deep-learning-based natural language processing. Associations with all-cause mortality, severe infections, fractures, and healthcare utilization were assessed using Cox and count models. Predictive performance was compared with Hospital Frailty Risk Score (HFRS) and Charlson Comorbidity Index (CCI). Findings: eFI trajectories accelerated notably from age 65 onwards. Using the eFI as a categorical variable, severe frailty was associated with higher risks of mortality (hazard ratio [HR] 7.31, 95% confidence interval [CI] 6.83-7.83), severe infections (HR 9.22, 95%CI 8.52-9.98), fractures (HR 2.75, 95%CI 2.52-3.01) and increased healthcare utilization (odds ratio [OR] 3.15, 95%CI 2.96-3.35) compared with non-frail. The risks were relatively greater in younger age groups and persisted when using the continuous eFI restricted to non-frail individuals. Across all outcomes, the eFI showed greater model discrimination than HFRS and CCI. Interpretation: An eFI using structured and unstructured EHR data improves risk stratification even in younger adults and at very low levels of frailty. Funding: Research Council of Finland, Instrumentarium Science Foundation, Sigrid Juselius Foundation and Samfundet Folkhalsan.
- Neurodevelopment Trajectory of Electrophysiological Functional Connectivity Following Alcohol Use Initiation
Background: Adolescence is characterized by profound neurodevelopmental changes that shape large-scale brain network organization and may confer vulnerability to risk-taking behaviors, including alcohol use. While cross-sectional and prospective studies have examined functional connectivity (FC) alterations before and after consumption, there is little evidence of how networks evolve during adolescence. Methods: The present longitudinal study investigated electrophysiological FC trajectories during alcohol initiation using resting-state magnetoencephalography (MEG). 61 alcohol-naive adolescents (mean age at baseline = 14.4) were assessed and re-evaluated two years later (mean age = 16.4). Results: At baseline, stronger FC in theta (4-8 Hz), alpha (8-12 Hz), and high-beta (20-30 Hz) bands predicted greater alcohol consumption at follow-up, replicating previous findings. Longitudinal analyses with linear mixed-effects models revealed significant stage-SAUs interactions across all three frequency bands. Adolescents with low-to-moderate alcohol use showed normative increases in FC over time, consistent with typical neurodevelopmental maturation. In contrast, heavier drinkers exhibited stabilization or reduction of FC, suggesting a divergence from normative trajectories. Notably, theta-band hyperconnectivity persisted after alcohol initiation and remained positively associated with current alcohol consumption, particularly across anteroposterior connections. Conclusion: These findings indicate heterogeneous neurodevelopmental trajectories associated with alcohol use severity. Elevated pre-consumption connectivity, especially in the theta band, may reflect a vulnerability marker rather than solely a consequence of alcohol exposure. Overall, results highlight the importance of considering individual variability in brain maturation when examining adolescent substance use and suggest that early hyperconnectivity may signal increased risk for heavier alcohol involvement.
- Stimulus and circuit contributions to the information geometry of neural manifolds
Understanding how network connectivity shapes neural representations is central to systems neuroscience. While dimensionality reduction methods uncover low-dimensional manifold structure in population recordings, a rigorous framework connecting manifold geometry to network mechanisms and information encoding remains lacking. We develop a differential geometric approach for analyzing neural manifolds in rate-based recurrent networks receiving tuned feedforward inputs. We derive expressions for the pullback metric of neural manifolds, showing how input tuning curves, feedforward and recurrent synaptic connectivity shape manifold geometry. Critically, we establish that the Fisher information matrix at steady states also has the structure of a pullback metric, directly linking intrinsic manifold geometry to stimulus discriminability and information encoding. For noise with slow temporal correlations propagated through the network, we show that recurrent effects on information geometry cancel: Fisher information depends only on the feedforward connectivity. Thus, feedforward connectivity critically determines representational geometry. As an example, we demonstrate that the representation of space by a module of hexagonal grid cells is approximately isometric for random distribution of grid phases. Moreover, a linear feedforward transformation can map spatially random input tuning curves into a population of hexagonal grid cells, forming a toroidal manifold. Thus, feedforward connectivity alone can generate structured spatial representations without requiring carefully tuned recurrent connectivity or continuous attractor dynamics. Recurrent connectivity, however, is shown to improve stimulus encoding under fast noise, thereby implementing a selective noise reduction.
- ST3GAL3 loss-of-function disrupts synaptic integrity and excitatory/inhibitory cortical dynamics
This study examined the role of ST3GAL3 as a regulator of excitatory/inhibitory (E/I) synaptic homeostasis using a human iPSC-based model. Neurodevelopmental disorders (NDDs) are increasingly linked to disruptions in the E/I balance, yet the molecular determinants remain poorly defined. ST3GAL3, a sialyltransferase associated with both rare monogenic disorders, including intellectual disability and infantile epilepsy, and complex polygenic conditions, such as ADHD, represents a strong candidate gene for involvement in synaptic regulation. To investigate this, isogenic ST3GAL3 knockout (ST3GAL3 KO) and wildtype (WT) iPSC lines were generated through CRISPR/Cas9 editing and diRerentiated into cortical neurons using both directed and induced protocols. This dual strategy enabled robust comparisons across cellular contexts and minimised methodological bias. To this end, we conducted functional characterisation using microelectrode array (MEA) technology alongside transcriptomic profiling through RNA sequencing (RNAseq), directly comparing ST3GAL3 KO-derived neurons with their isogenic controls. Functional assays using MEA revealed aberrant bursting patterns, particularly prolonged burst durations and heightened variability in S3GAL3KO neurons. Complementary transcriptomic profiling performed via RNAseq demonstrated downregulation in ST3GAL3 KO lines of genes involved in cognition, memory, as well as glutamatergic and GABAergic synaptic plasticity and functionality, providing molecular evidence for widespread synaptic dysregulation. Together, these findings establish ST3GAL3 as a key regulator of E/I balance in the cortices, advancing current knowledge on the pathophysiological involvement of ST3GAL3 deficiencies in the development of NDDs.
- A p53-ΔNp73 signaling axis drives selective motor neuron degeneration in spinal muscular atrophy
Selective neuronal vulnerability is a hallmark of many neurodegenerative diseases, yet how ubiquitous genetic insults cause highly selective neuronal loss remains poorly understood. In spinal muscular atrophy (SMA), reduced SMN levels trigger degeneration of specific motor neuron pools. Although non-apoptotic, p53-mediated death pathways have been implicated, p53 is expressed in both vulnerable and resistant neurons, leaving the downstream determinants of selective vulnerability unresolved. Here, we identify a p53-{Delta}Np73 signaling axis as a previously unrecognized execution pathway driving motor neuron degeneration. Using differential transcriptional profiling of SMA motor neurons following pharmacological modulation of p53 activity, we uncover p73 as a critical downstream mediator of neuronal death. Notably, SMN deficiency induces cell-autonomous, p53-dependent expression of the {Delta}Np73 isoform selectively in vulnerable, but not resistant, motor neurons. {Delta}Np73 induction precisely parallels the spatial and temporal pattern of degeneration in mouse models and is also detected in motor neurons from SMA patients. Strikingly, despite its established role as a pro-survival antagonist of p53, depletion of {Delta}Np73 improves motor neuron survival and partially preserves neuromuscular junction integrity in SMA mice. These findings reveal a context-dependent, isoform-specific functional switch in p53 family signaling that redirects a canonical survival factor into a driver of neurodegeneration, identifying a novel molecular mechanism underlying selective neuronal vulnerability in SMA and a potential therapeutic target for neuroprotection.
- Can Demographic Information Be Reduced in Retinal Fundus Images While Preserving Glaucoma-Relevant Features?
Purpose: To determine whether disease-aware adversarial perturbations can reduce demographic recoverability encoded in color fundus photographs (CFPs) while preserving glaucoma-related diagnostic features. Design: Retrospective analysis of a single-institution retinal imaging dataset using adversarial machine-learning experiments. Participants: A total of 4,271 patients contributing 13,959 CFPs from Massachusetts Eye and Ear. Methods: Vision Transformer (ViT) was trained for glaucoma detection and for prediction of race, sex, and ethnicity. Standard and disease-aware (DA) variants of four adversarial attacks--Fast Gradient Sign Method (FGSM), Projected Gradient Descent (PGD), Carlini & Wagner (C&W), and a diffusion-based attack--were applied to suppress demographic prediction; DA attacks augmented the adversarial objective with a disease-preservation term. Cross-architecture transferability was assessed by generating perturbations on ViT and applying them to ResNet50 and EfficientNetB0. Main Outcome Measures: Area under the receiver operating characteristic curve (AUC) and accuracy for glaucoma and demographic classification before and after perturbation, and disease-preservation and attack transferability across architectures. Results: At baseline, CFPs encoded both glaucoma-related and demographic information. Glaucoma detection AUCs were 0.958 (95% CI, 0.949-0.967), 0.960 (95% CI, 0.951-0.967), and 0.963 (95% CI, 0.955-0.971) in the race, sex, and ethnicity analysis cohorts, respectively. Demographic prediction performance was also high, with AUCs of 0.955 (95% CI, 0.945-0.963) for race, 0.983 (95% CI, 0.977-0.988) for sex, and 0.992 (95% CI, 0.987-0.996) for ethnicity. Standard attacks substantially reduced demographic AUC but often degraded glaucoma detection. Disease-aware optimization improved disease preservation while maintaining demographic suppression. Using a prespecified success criterion of at least 90% disease AUC preservation and demographic AUC reduction to 30% or less of baseline, DA-PGD and DA-Diffusion succeeded across race, sex, and ethnicity; DA-C&W succeeded for sex and ethnicity. Cross-architecture transferability experiments demonstrated that disease preservation transferred more robustly than demographic suppression. Conclusions: Disease-aware adversarial perturbations reduced the recoverability of demographic information in CFPs under white-box conditions while preserving glaucoma-relevant features, suggesting these representations are partially separable. Reduced demographic recoverability did not fully transfer across architectures, highlighting the need for architecture-agnostic methods.
- Multi-task artificial intelligence annotation of echocardiographic images: a retrospective multi-cohort study
Summary Background A comprehensive transthoracic echocardiogram involves the assessment of over 70 parameters, placing a substantial burden on sonographers and physicians for manual annotation with considerable inter-observer variability. Prior open-source segmentation models have largely addressed 2D B-mode ventricular function, leaving a gap in the spectral Doppler and atrial measurements required for valvular and diastolic assessment such as velocity-time integral (VTI) and atrial chamber size. Methods In this retrospective multi-cohort study, we developed EchoNet-Segmentation, comprehensive task-specific deep learning segmentation models for left and right atrial area and VTI Doppler measurements. Training used 186,712 sonographer-annotated images from 93,978 studies (56,855 patients) at Cedars-Sinai Medical Center (CSMC). Performance was evaluated on a held-out CSMC test set, a CSMC temporal split, an external Kaiser Permanente Northern California cohort, and the public MIMIC-Echo dataset. Findings On the CSMC held-out test set, our AI models showed strong agreement with sonographer measurements, with R2 of 0.817-0.882 and mean absolute error (MAE) of 1.13-3.80 cm for automated VTI measurements, and R2 of 0.675-0.747 and MAE of 2.48-2.52 cm2 for left and right atrial area segmentation. Performance was consistently confirmed on the CSMC temporal split (VTI: R2 0.606-0.866, atrial area: R2 0.694-0.705) and on the KPNC external cohort (VTI: R2 0.575-0.859, atrial area: R2 0.803-0.876), on the MIMIC-Echo dataset. Robustness was demonstrated on a different vendor's machines and across subgroups. EchoNet-Segmentation outperformed an open-source medical image foundation model with bounding-box, point prompt configurations on R2, MAE, and Dice score on both held-out test dataset and MIMIC apical four-chamber data. Interpretation EchoNet-Segmentation is the first open-source framework that delivers accurate, generalizable automated measurement across several key routine echocardiographic parameters, supporting end-to-end automation of clinically important echocardiographic assessments. Public release of model weights, code, and demonstration tools can facilitate reproducibility, research use and clinical deployment.
- Associations Between TMS-Induced Electric Fields and Craving and Consumption Outcomes in Substance Use Disorders: A Multimodal Dose-Response Meta-Analysis
Background: Transcranial magnetic stimulation (TMS) is a promising treatment for substance use disorders (SUDs), although heterogeneous stimulation parameters hinder the identification of optimal strategies. Using meta modeling, we linked treatment effect sizes (Hedges' g) to simulated electric field (E field) distributions to identify brain regions associated with efficacy variability. Methods: TMS trials in individuals with SUDs published through the end of 2025 were identified through a systematic PubMed search. Studies reporting craving or consumption outcomes with quantifiable effect sizes were included. Objectives were to (i) examine associations between study-level effect sizes and simulated local E field strength in MNI space for craving and consumption outcomes; (ii) generate a combined E field effect size association map; and (iii) assess spatial overlap with fMRI drug cue reactivity patterns in 60 individuals with SUDs. Results: The analysis included 81 randomized controlled TMS studies, yielding 107 effect size estimates for craving and consumption (n = 75 and n = 32, respectively). Compared with sham stimulation, TMS produced small-to-moderate improvements in both outcomes. E-field modeling identified the pre-supplementary motor area (preSMA) and inferior frontal gyrus (IFG) as regions associated with variability in craving-related effect sizes, and the frontopolar cortex with variability in consumption-related effect sizes. Correlation maps were highly robust (mean leave one out similarity r = 0.996), and the frontopolar cluster showed significant spatial overlap with fMRI drug cue reactivity patterns (Dice coefficient = 0.37). Conclusion: These findings identify frontopolar, preSMA, and IFG regions where local E-field strength is associated with SUD treatment effects, supporting more precise neuromodulation strategies.
- A Reproducible Clinical Decision-Support Suite on MIMIC-IV
Most published clinical-AI results are single models on a single dataset, difficult to reproduce, and rarely validated outside their training hospital. We built a broad, methodologically rigorous, reproducible clinical decision-support (CDS) suite spanning four families - intensive-care deterioration and outcomes, emergency- department triage, electrocardiographic interpretation, and clini- cal natural-language processing - comprising 26 models. Tabular models are gradient-boosted trees over point-in-time, leakage- safe first-24-hour features; deep models include one-dimensional convolutional networks on raw 12-lead ECG, fine-tuned clinical transformers, and an instruction-tuned large language model for discharge-summary drafting. Every model uses patient-level data splits, probability calibration, a shuffled-label leakage gate, and SHAP explanations, and is characterised by its full confusion matrix with sensitivity, specificity and predictive values. Dis- crimination matched or approached published benchmarks: ICU mortality AUROC 0.884, acute kidney injury 0.830, prolonged stay 0.813; emergency-department-to-ICU 0.875; cardiologist- labelled ECG diagnosis 0.909; full-note diagnostic coding 0.892. Raw-signal ECG deep learning improved myocardial-infarction detection by +0.142 AUROC over interval features. The MIMIC- trained mortality model generalised to a different multi-centre US cohort (199,133 stays) with only a 0.044 AUROC drop. We describe how each model family is incorporated into the latest version of the zMed Critical Care application and its CDS tools
- Time-Aware Contrastive Transformer for Longitudinal Patient Representation Learning
Learning high-quality longitudinal patient representations from irregular electronic health records (EHRs) is essential for understanding heterogeneity in time-evolving diseases such as cancer. Longitudinal patient representation learning methods often rely on external labels for downstream tasks or do not model the temporal dynamics between medical events explicitly, reducing the clinical applicability of learned disease trajectories. In this work, we propose the Time-Aware-Contrastive-Transformer (TACT), a transformer-based model that integrates explicit temporal modeling with a fully self-supervised contrastive learning framework. We introduce a sampling-based data augmentation workflow that leverages hierarchical taxonomies of diagnoses and medications to enrich representation learning. Evaluated on a large real-world dataset, TACT demonstrates robust performance across patient representation and event embedding metrics and outperforms two time-aware transformer comparison models. Unlike the comparison models, TACT successfully bridges contrastive learning with medical hierarchies, allowing it to track precise disease trajectories and discover clinically actionable patient phenotypes. Consequently, this approach establishes a comprehensive framework for characterizing patient heterogeneity through the identification of potentially clinically meaningful subgroups with distinct progression profiles.
- A Natural Experiment Reveals Clinically Essential and Compliance-Driven Nursing Documentation
Despite contributing substantially to clinician burnout, nursing documentation lacks empirical evidence distinguishing clinically essential from administratively driven documentation. Exploiting a COVID-19 documentation relaxation policy as a natural experiment, we analyzed 520,357 patient shifts from 36,321 patients in 54 inpatient units (2019 - 2022) using large language model-assisted flowsheet classification and structural equation modeling. When permitted, front-line nurses reliably distinguished two types of documentation: in acute care units, primary nurses reduced compliance-driven Cares & Safety documentation by 19% (106.4 to 86.2 entries, r = -0.19), while maintaining or increasing documentation directly relevant to respiratory management, with no impact on patient respiratory outcomes. Documentation intensity also co-varied with real-time patient deterioration, consistently across unit types (|{beta}| = 0.13 - 0.14). Together, these findings provide the first large-scale quantitative evidence distinguishing clinically essential documentation from compliance-driven documentation and demonstrate that targeted reduction of the latter is a viable strategy for alleviating documentation burden without compromising care quality for respiratory care management.
- Predicting Depression and Anxiety Progression in Multiple Sclerosis from Longitudinal Clinical Data Using Machine Learning
Depression and anxiety are highly prevalent in multiple sclerosis (MS), yet tools for predicting mental health trajectories from clinical data remain limited. We investigated what structured electronic health record data can predict about depression and anxiety progression in MS, and where its limits lie. We developed gradient boosting models to predict PHQ-9 (depression) and GAD-7 (anxiety) score change using EHR data from 2,163 MS patients (7,327 observations) and 1,465 patients (3,319 observations), respectively. Models achieved R^2 of 0.22 (PHQ-9) and 0.28 (GAD-7). Baseline score was the dominant predictor, but this largely reflects regression to the mean: patients with high baseline scores tend to improve, while those with low scores tend to worsen. Age emerged as a consistent secondary predictor across both models: younger patients showed smaller improvements independent of baseline severity. Feature importance differed between models---PHQ-9 prediction relied on symptom subscales while GAD-7 incorporated pain and disease duration. These results suggest that structured clinical data alone capture only a fraction of what drives mental health trajectories, and that richer data sources---clinical notes, patient-reported outcomes, digital phenotyping---will be needed to enable meaningful individual-level prediction.
- Heron
Wireshark for AI Agents: passive eBPF observability
- Milestones
Native project planning app, now on Mac & with an MCP server
- Nashra
Turn followers into clients.
- Paybond CLI
Safe agent spend from the terminal
- Grass 2.0
The always-on computer for your coding agents
- Signspell
Real-time ASL alphabet recognition in py ,pip install and go
- Silica
Your private local AI workspace for Mac
- Seavid AI | Image to Video Generator
Turn ideas into stunning AI videos instantly.
- TopAITools4U
Find the best AI tools for every workflow
- Vobbin
Health & Fitness Coach
- Evaluating Generative Video AI for Standardized Psychiatric Patient Simulation With Graded Hygiene Deterioration.
Abstract Introduction: A clinician's initial assessment during the mental status examination (MSE) places substantial weight on a patient's general appearance, grooming, and hygiene. However, the logistical difficulty of producing simulated or standardized patient (SP) videos that systematically manipulate these characteristics limits the development of clinical AI tools and training curricula. This pilot study investigates the technical feasibility of using a video-generation diffusion model to re-animate modified reference images onto driving videos, enabling the creation of diverse patient presentations without the need for repeated filming. Methods: Utilizing an established publicly available dataset, we extracted reference images of three SPs and applied a text-to-image AI model to generate five appearance conditions: the unmodified baseline and four escalating hygiene-deterioration levels: mild, moderate, marked, and severe. We then used the Wan2.2-Animate-14B animate video generation AI model to re-animate these modified portraits onto the original driving footage. This factorial design varied several model parameters including; pose retargeting, classifier-free guidance scales, and generation modes, resulting in 180 unique videos. Quality was measured through Frechet Video Distance (FVD) for distributional fidelity and a physics-aware assessment performed by a multimodal large language model to evaluate physical plausibility. Results: Our analysis yielded two primary observations. First, compositing through replacement-mode achieved significantly higher temporal fidelity than animation-mode (mean FVD 8.6 vs. 19.4; Cohen's d = 1.84). Second, while distributional fidelity showed a monotonic decline as hygiene perturbation increased (Spearman rho = 0.48, p < 0.001), physics-aware scores did not follow a similar trend. This pattern is consistent with fine-motor artifacts arising from model-level generative constraints rather than from the severity of the appearance modification alone. Conclusions: These findings demonstrate that generating appearance-modulated clinical video libraries is technically achievable. Nevertheless, the persistence of fine-motor artifacts underscores the necessity of expert human oversight before these materials can be safely deployed in educational and translational settings. Keywords: Generative artificial intelligence; Standardized patients; Video diffusion models; Psychiatric simulation; Mental status examination; AI-generated video; Medical education; Digital psychiatry
- Automated EEG Classification to Track Levels of Consciousness
Precise prognostication in acute brain injury is limited by a lack of reliable biomarkers of consciousness available to clinicians at the bedside. The ABCD framework is a method of classifying resting-state clinical EEG into categories that reflect levels of thalamocortical network function. ABCD classifications in the intensive care unit (ICU) have been shown to provide diagnostic and prognostic utility for patients with severe brain injuries, but the current gold standard for ABCD classification is visual inspection of power spectra, which is labor-intensive and requires expertise in spectral analysis. Using 4,611 manually classified EEG power spectra, we developed an automated, highly accurate, and well-calibrated convolutional neural net-based classifier of EEG into ABCD categories. The classifier has performance comparable to that of the current gold standard and that outperforms an alternative method of automated spectral analysis. As proof-of-principle for clinical implementation, we apply the classifier to a continuous EEG record from a patient with acute severe traumatic brain injury in the ICU, demonstrating its ability to yield continuous ABCD classifications that capture state fluctuations with high temporal and spatial resolution. The automated ABCD classifier allows for efficient analysis of continuous EEG records, facilitating the translation of the ABCD framework to the bedside for patients with acute severe brain injuries. The ABCD classifier also creates new opportunities to efficiently analyze large EEG datasets and generate new insights into the electrophysiological properties of human consciousness.
- remio: Your Personal ChatGPT
Get Tailored Answer with Your Personal ChatGPT
- Autoregressive Boltzmann Generators
Efficient sampling of molecular systems at thermodynamic equilibrium is a hallmark challenge in statistical physics. This challenge has driven the development of Boltzmann Generators (BGs), which allow rapid generation of uncorrelated equilibrium samples by combining a generative model with exact li...
- Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning
Multimodal web agents can assist humans in operating repetitive GUI tasks, where effective task planning is essential for decomposing complex tasks into executable actions. While small open source MLLMs are cost efficient and privacy preserving compared with commercial large models, they suffer from...
- When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models
Multi-model LLM systems such as routing, voting, cascades, fusion, and mixture-of-agents are used to beat single-model accuracy. We show that their gain is capped by a quantity the field rarely reports. For any policy whose output is one member model answer, accuracy cannot exceed one minus beta, wh...
- Dub Ninja
Live autonomous AI DJ that digs, mixes & explains 24/7
- Prompt Injection in Automated Résumé Screening with Large Language Models: Single and Multi-Injection Settings
Large language models (LLMs) are increasingly used to screen and rank job applicants, creating incentives for candidates to strategically manipulate algorithmic hiring systems. We study prompt injection in automated résumé screening, defined as subtle self-promotional text that introduces no new qua...
- Ask, Don't Judge: Binary Questions for Interpretable LLM Evaluation and Self-Improvement
Evaluating LLM outputs remains a major bottleneck in NLP: human evaluation is expensive and slow, lexical metrics correlate poorly with human judgments on open-ended generation, and holistic LLM judges often produce opaque scores that are hard to debug. We propose BINEVAL, a framework that decompose...
- Vulnerability of Natural Language Classifiers to Evolutionary Generated Adversarial Text
Deep learning models have achieved impressive performance across various fields but remain vulnerable to adversarial inputs, particularly in NLP, where such attacks can have significant real-world consequences. Adversarial attacks often involve small, semantically similar token replacements to fool ...
- Automating Potential-based Reward Shaping with Vision Language Model Guidance
Sparse rewards are inherently challenging for reinforcement learning agents as they lack intermediate feedback to guide exploration and to correctly attribute the sparse success rewards to relevant parts of the trajectory. Naive reward shaping can induce reward hacking, yielding policies that exploi...
- TOPS: First-Principles Visual Token Pruning via Constructing Token Optimal Preservation Sets for Efficient MLLM Inference
Multimodal large language models (MLLMs) have achieved strong multimodal reasoning capabilities, but their efficiency is limited by the large number of visual tokens, which introduces substantial computational overhead. Visual token pruning offers a natural solution, yet existing methods are imperfe...
- OpenRCA 2.0: From Outcome Labels to Causal Process Supervision
Root cause analysis (RCA) poses a holistic test of LLM agentic capabilities, such as long-context understanding, multi-step reasoning, and tool use. However, existing datasets suffer from a fundamental gap: they label only the root cause, not the propagation path connecting it to the observed sympto...
- Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks
Unlike diffusion-based models that operate in continuous latent spaces, autoregressive unified multimodal models produce images by sequentially predicting discretized visual tokens. These tokens are derived from a codebook that maps embeddings to quantized visual patterns. The language-like architec...
- Joint Learning of Experiential Rules and Policies for Large Language Model Agents
For LLM agents in multi-step interactive environments, a key challenge is to make effective use of accumulated interaction experience. Existing work has typically separated two uses of such experience: keeping it outside the model as natural-language rules for later prompting, or using trajectories ...
- Heavy-Ball Q-Learning with Residual Weighting Correction
This paper proposes a corrected heavy-ball Q-learning method for reinforcement learning (RL) and establishes its convergence. It also identifies conditions under which the method is theoretically guaranteed to converge faster than standard Q-learning. The same construction is then extended to Q-lear...
- Application of LLMs to Threat Assessment of Foreign Peacekeeping Missions
We present a novel approach for applying Large Language Models (LLMs) to threat assessment in the context of foreign peacekeeping missions. Building on the PINPOINT project and its use case, the EU Monitoring Mission in Georgia, we combine an interdisciplinary risk-model with OSINT-based media colle...
- Data-Free Reservoir Features for Efficient Long-Horizon Cold-Start Continual Learning
Cold-start exemplar-free class-incremental learning requires learning a growing set of classes without replay, external pretraining, or a large initial task. Existing cold-start methods typically either train the backbone throughout the stream and compensate for semantic drift, or freeze a backbone ...
- Inherited Circuits, Learned Semantics: How Fine-Tuning Creates Evasion Vulnerabilities Invisible to Standard Evaluation
LLMs fine-tuned for security classification are usually evaluated on held-out examples from the same distribution as their training data. We show that this can miss vulnerabilities introduced by fine-tuning itself: models can learn token-level indicator semantics that preserve canonical accuracy whi...
- NuclearQAv2: A Structured Benchmark for Evaluating Domain-Science Competence in Large Language Models
Large language models (LLMs) have demonstrated strong performance across a wide range of tasks, but ensuring their reliability in highly technical domains remains a significant challenge. In nuclear engineering, problem solving often requires not only factual knowledge but also quantitative reasonin...
- State Representation Matters in Deep Reinforcement Learning: Application to Energy Trading
Energy trading decisions depend not only on current market prices, but also on expected future market conditions, and operational constraints. This makes the state representation given to a reinforcement learning agent an important design choice. We study this in HydroDam, a pumped-storage arbitrage...
- ShareLock: A Stealthy Multi-Tool Threshold Poisoning Attack Against MCP
With the rapid evolution of LLM-driven agents, Model Context Protocol (MCP), an open protocol bridging LLMs with external tools, has quickly become foundational to modern agent ecosystems. However, the expanding adoption of MCP has also introduced novel security concerns such as Tool Poisoning Attac...
- SendTidings
Turn your analytics into beautiful monthly email reports