Machine learning models using smartwatch data from a 54-participant test-track study detect alcohol-impaired driving with participant-averaged AUROC of 0.88 for any intoxication and 0.86 above 0.05 g/dL.
hub Canonical reference
2024.Global status report on alcohol and health and treatment of substance use disorders
Canonical reference. 100% of citing Pith papers cite this work as background.
30
Pith papers citing it
Background
100% of classified citations
hub tools
citation-role summary
background 7
citation-polarity summary
roles
background 7polarities
background 7representative citing papers
Biological ambiguity from temporally decoupled neurodegeneration and amyloid pathology creates one-to-many mappings that make MRI-to-amyloid PET synthesis intrinsically ill-posed, with performance restored by multimodal inputs.
CROWD is a new global dataset of 51,753 continuous urban dashcam segments spanning over 20,000 hours from 238 countries, with manual labels and automated object detections for routine driving analysis.
KG-TRACE fuses genomic features with RotatE KG embeddings via an epistemic trust gate for AMR prediction, reporting 0.976 AUROC on isoniazid resistance in the CRyPTIC cohort plus 92.5% symbolic coverage via a new Biological Grounding Ratio metric.
Dep-LLM is a training-free three-stage LLM framework that decomposes clinical interviews into clinical themes, modulates signals by token entropy, and outperforms zero-shot and supervised baselines on DAIC-WOZ and E-DAIC datasets.
InfoShield uses TimeAwareMINE to minimize mutual information between speech representations and sensitive attributes, cutting gender inference from 92.6% to 55.5% and age inference from 55.7% to 30.3% while dropping depression F1 by only 6%.
PIGMENT is a foundation model that recovers quantitative diffusion MRI parameter maps (tensor, kurtosis, NODDI) from sparse acquisitions by learning a universal generative prior of brain microstructure and adapting it zero-shot to new subjects.
A physiology and anatomy aware network infers myocardial infarct areas by jointly processing 3D heart geometry and multi-lead ECGs, trained on simulated data from realistic scar synthesis in digital twins.
AVCT theory grounds BP estimation in cardiac attractor geometry from PPG, validated by LightGBM on 46 subjects achieving SBP/DBP MAE of 2.05/1.67 mmHg under LOSO-CV and AAMI compliance.
The authors built and expert-evaluated an agentic AI system integrating DEA regulatory data with dynamic scientific literature via RAG to provide accurate, context-sensitive substance use education, with mean Likert ratings of 4.18-4.35 and substantial rater agreement.
Introduces the MMH dataset collected via psychology-inspired multimodal stimuli and a paradigm-aware framework that uses inter-disorder prior knowledge as prompts, outperforming baselines on differential detection of depression, anxiety and schizophrenia.
Benchmark shows that combining data rebalancing with feature disentanglement mitigates shortcut learning more effectively than rebalancing alone in medical imaging models.
U.S. data centers could cause more than $20 billion per year in public health costs by 2028, with low-income counties bearing a disproportionate share.
Survey of Jordanian nurses finds green transformational leadership and ethical climate boost sustainable behaviors via green psychological climate, weakened by perceived organizational hypocrisy, explaining 35.7% variance.
PRISM-Coach introduces four-view data separation, vault-based identity control, and a privacy-constrained contextual bandit for adaptive peer grouping, reporting higher adherence and weight loss in a 2,800-user commercial deployment.
Machine learning methods including denoising autoencoders, unsupervised interference mitigation, blind source separation, and certifiable classification are developed and experimentally validated to improve multi-species laser spectroscopy under complex conditions.
Knowledge distillation trains a 3.9x smaller YOLO student to retain 14.5% higher precision than direct training under INT8 quantization on BDD100K, exceeding the large teacher's FP32 precision while cutting false alarms.
Physical activity's protective association with lower mental distress strengthens monotonically with age and has eroded to null for young adults over the past decade.
Survey of 100 Bulgarian users finds half use LLMs for emotional support against interpersonal and academic stress, with ChatGPT dominant and 71% rating it effective despite privacy and reliability worries.
Proposes importance-weighted and target-weighted cross-validation to align validation distributions with deployment conditions in spatial prediction tasks.
Copewell proposes a multi-agent AI architecture using multi-source assessment, valence-arousal emotion mapping via Russell's Circumplex Model, and dual-mode interventions for equitable mental wellness support.
A PRISMA-ScR scoping review of 97 studies classifies AI models in dentistry into language, vision, and domain-specific types and concludes integrated pipelines outperform single models while noting data and benchmark gaps.
A mixed-methods survey of 275 Australians finds moderate optimism toward healthcare AI alongside concerns about accuracy and data use, with strong preference for AI-generated consultation summaries over clinician-written ones when the source is unknown.
Satellite embeddings improve malaria and respiratory infection predictions with R^2 gains but add no value for stunting due to collinearity with fixed effects.
citing papers explorer
-
Detecting Drunk Driving Using Off-the-Shelf Smartwatches
Machine learning models using smartwatch data from a 54-participant test-track study detect alcohol-impaired driving with participant-averaged AUROC of 0.88 for any intoxication and 0.86 above 0.05 g/dL.
-
When Brains Disagree: Biological Ambiguity Underlies the Challenge of Amyloid PET Synthesis from Structural MRI
Biological ambiguity from temporally decoupled neurodegeneration and amyloid pathology creates one-to-many mappings that make MRI-to-amyloid PET synthesis intrinsically ill-posed, with performance restored by multimodal inputs.
-
A global dataset of continuous urban dashcam driving
CROWD is a new global dataset of 51,753 continuous urban dashcam segments spanning over 20,000 hours from 238 countries, with manual labels and automated object detections for routine driving analysis.
-
KG-TRACE: A Neuro-Symbolic Framework for Mechanistic Grounding in Antimicrobial Resistance Prediction
KG-TRACE fuses genomic features with RotatE KG embeddings via an epistemic trust gate for AMR prediction, reporting 0.976 AUROC on isoniazid resistance in the CRyPTIC cohort plus 92.5% symbolic coverage via a new Biological Grounding Ratio metric.
-
Dep-LLM: Training-Free Depression Diagnosis via Evidence-Guided Structured Multi-factor with Reliable LLM Reasoning
Dep-LLM is a training-free three-stage LLM framework that decomposes clinical interviews into clinical themes, modulates signals by token entropy, and outperforms zero-shot and supervised baselines on DAIC-WOZ and E-DAIC datasets.
-
InfoShield: Privacy-Preserving Speech Representations for Mental Health Screening via Information-Theoretic Optimization
InfoShield uses TimeAwareMINE to minimize mutual information between speech representations and sensitive attributes, cutting gender inference from 92.6% to 55.5% and age inference from 55.7% to 30.3% while dropping depression F1 by only 6%.
-
A physics-informed foundation model for quantitative diffusion MRI
PIGMENT is a foundation model that recovers quantitative diffusion MRI parameter maps (tensor, kurtosis, NODDI) from sparse acquisitions by learning a universal generative prior of brain microstructure and adapting it zero-shot to new subjects.
-
Physiology and Anatomy Aware Inverse Inference of Myocardial Infarction for Cardiac Digital Twin
A physiology and anatomy aware network infers myocardial infarct areas by jointly processing 3D heart geometry and multi-lead ECGs, trained on simulated data from realistic scar synthesis in digital twins.
-
Attractor-Vascular Coupling Theory: Formal Grounding and Empirical Validation for AAMI-Standard Cuffless Blood Pressure Estimation from Smartphone Photoplethysmography
AVCT theory grounds BP estimation in cardiac attractor geometry from PPG, validated by LightGBM on 46 subjects achieving SBP/DBP MAE of 2.05/1.67 mmHg under LOSO-CV and AAMI compliance.
-
Agentic AI for Substance Use Education: Integrating Regulatory and Scientific Knowledge Sources
The authors built and expert-evaluated an agentic AI system integrating DEA regulatory data with dynamic scientific literature via RAG to provide accurate, context-sensitive substance use education, with mean Likert ratings of 4.18-4.35 and substantial rater agreement.
-
Differential Mental Disorder Detection with Psychology-Inspired Multimodal Stimuli
Introduces the MMH dataset collected via psychology-inspired multimodal stimuli and a paradigm-aware framework that uses inter-disorder prior knowledge as prompts, outperforming baselines on differential detection of depression, anxiety and schizophrenia.
-
Mitigating Shortcut Learning via Feature Disentanglement in Medical Imaging: A Benchmark Study
Benchmark shows that combining data rebalancing with feature disentanglement mitigates shortcut learning more effectively than rebalancing alone in medical imaging models.
-
Health-Informed Computing: Estimating and Addressing the Public Health Impact of Data Centers
U.S. data centers could cause more than $20 billion per year in public health costs by 2028, with low-income counties bearing a disproportionate share.
-
Green Transformational Leadership and Sustainable Nursing Practices: Evidence from the Healthcare Sector
Survey of Jordanian nurses finds green transformational leadership and ethical climate boost sustainable behaviors via green psychological climate, weakened by perceived organizational hypocrisy, explaining 35.7% variance.
-
Privacy-by-Design Adaptive Group Assignment for Digital Lifestyle Coaching at Scale
PRISM-Coach introduces four-view data separation, vault-based identity control, and a privacy-constrained contextual bandit for adaptive peer grouping, reporting higher adherence and weight loss in a 2,800-user commercial deployment.
-
Machine Learning Enhanced Laser Spectroscopy for Multi-Species Gas Detection in Complex and Harsh Environments
Machine learning methods including denoising autoencoders, unsupervised interference mitigation, blind source separation, and certifiable classification are developed and experimentally validated to improve multi-species laser spectroscopy under complex conditions.
-
Edge AI for Automotive Vulnerable Road User Safety: Deployable Detection via Knowledge Distillation
Knowledge distillation trains a 3.9x smaller YOLO student to retain 14.5% higher precision than direct training under INT8 quantization on BDD100K, exceeding the large teacher's FP32 precision while cutting false alarms.
-
Age-Dependent Heterogeneity in the Association Between Physical Activity and Mental Distress: A Causal Machine Learning Analysis of 3.2 Million U.S. Adults
Physical activity's protective association with lower mental distress strengthens monotonically with age and has eroded to null for young adults over the past decade.
-
Using Large Language Models for Emotional Support of Bulgarian Users: A Survey
Survey of 100 Bulgarian users finds half use LLMs for emotional support against interpersonal and academic stress, with ChatGPT dominant and 71% rating it effective despite privacy and reliability worries.
-
Aligning Validation with Deployment in Spatial Prediction: Target-Weighted Cross-Validation
Proposes importance-weighted and target-weighted cross-validation to align validation distributions with deployment conditions in spatial prediction tasks.
-
Copewell: A Multi-Agent Swarm Architecture for Equitable Mental Wellness Support
Copewell proposes a multi-agent AI architecture using multi-source assessment, valence-arousal emotion mapping via Russell's Circumplex Model, and dual-mode interventions for equitable mental wellness support.
-
Large AI Models in Dental Healthcare: From General-Purpose Systems to Domain-Specific Foundation Models
A PRISMA-ScR scoping review of 97 studies classifies AI models in dentistry into language, vision, and domain-specific types and concludes integrated pipelines outperform single models while noting data and benchmark gaps.
-
Consumer Attitudes Towards AI in Digital Health: A Mixed-Methods Survey in Australia
A mixed-methods survey of 275 Australians finds moderate optimism toward healthcare AI alongside concerns about accuracy and data use, with strong preference for AI-generated consultation summaries over clinician-written ones when the source is unknown.
-
AlphaEarth Satellite Embeddings for Modelling Climate Sensitive Diseases Towards Global Health Resilience
Satellite embeddings improve malaria and respiratory infection predictions with R^2 gains but add no value for stunting due to collinearity with fixed effects.
-
No Pedestrian Left Behind: Real-Time Detection and Tracking of Vulnerable Road Users for Adaptive Traffic Signal Control
NPLB combines YOLOv12 detection and ByteTrack tracking with an adaptive controller to extend pedestrian phases, cutting simulated stranding rates from 9.1% to 2.6% while extending signals in only 12.1% of cycles.
-
Toward Zero-Egress Psychiatric AI: On-Device LLM Deployment for Privacy-Preserving Mental Health Decision Support
A cross-platform mobile application deploys an ensemble of quantized open-source LLMs for fully local, DSM-5-aligned psychiatric decision support with claimed accuracy comparable to prior cloud versions.
-
Community Driving-Safety Deterioration as a Push Factor for Public Endorsement of AI Driving Capability
Perceived community driving-safety concern creates an inconsistent mediation on AI driving evaluations: a small positive direct effect offset by suppression of general AI orientation, yielding near-zero total effect moderated by driving frequency.
-
PsyBridge: A Hybrid Intelligent Framework for Multi-Dimensional Mental Health Assessment and Decision Support
PsyBridge integrates PHQ-9, GAD-7, cognitive and personality indicators via modular weighted aggregation on a 500-profile semi-synthetic dataset to reach 0.84 accuracy in multi-dimensional mental health risk classification.
-
TA-RAG: Tone-Aware Retrieval-Augmented Generation for Peer-Support Health Communication
TA-RAG is a prompt-based framework that operationalizes four tone components (stigma-free rewriting, readability, recipient adaptation, empathy) to improve RAG suitability for peer-support health communication.
-
Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security
A survey that maps risks along the agent workflow and consolidates metrics and benchmarks for safety, robustness, privacy, and security in agentic AI.