datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
rsna-2023-abdominal-trauma-detectionThis dataset is the preprocessed version of the dataset from RSNA 2023 Abdominal Trauma Detection Kaggle Competition.
It is tailored for segmentation and classification tasks. It contains 3 different configs as described below:
- segmentation: 206 instances where each instance includes a CT scan in NIfTI format, a segmentation mask in NIfTI format, and its relevant metadata (e.g., patient_id, series_id, incomplete_organ, aortic_hu, pixel_representation, bits_allocated, bits_stored)
- classification: 4711 instances where each instance includes a CT scan in NIfTI format, target labels (e.g., extravasation, bowel, kidney, liver, spleen, any_injury), and its relevant metadata (e.g., patient_id, series_id, incomplete_organ, aortic_hu, pixel_representation, bits_allocated, bits_stored)
- classification-with-mask: 206 instances where each instance includes a CT scan in NIfTI format, a segmentation mask in NIfTI format, target labels (e.g., extravasation, bowel, kidney, liver, spleen, any_injury), and its relevant metadata (e.g., patient_id, series_id, incomplete_organ, aortic_hu, pixel_representation, bits_allocated, bits_stored)
All CT scans and segmentation masks had already been resampled with voxel spacing (2.0, 2.0, 3.0) and thus its reduced file size.africa-synth-flooding-extreme-weather-trauma-all
Extreme Weather & Trauma (SSA) | Africa (Electric Sheep Africa metadata inventory)
Size category: 10K<n<100K - Formats: csv - Sector: climate_environment - Engineered by Electric Sheep Africa
TL;DR
This dataset is part of the Electric Sheep Africa catalog on Hugging Face. It is indexed for African data discovery with standardized metadata, loading guidance, provenance notes, and analyst-oriented context.
What This Dataset Covers
Public datasets… See the full description on the dataset page: https://huggingface.co/datasets/electricsheepafrica/africa-synth-flooding-extreme-weather-trauma-all.road-traffic-injury-trauma
Road Traffic Injury & Trauma (GCS, ISS, Prehospital, Emergency Care) | Africa (Electric Sheep Africa metadata inventory)
Size category: 10K<n<100K - Formats: csv - Sector: infrastructure_transport - Engineered by Electric Sheep Africa
TL;DR
This dataset is part of the Electric Sheep Africa catalog on Hugging Face. It is indexed for African data discovery with standardized metadata, loading guidance, provenance notes, and analyst-oriented context.… See the full description on the dataset page: https://huggingface.co/datasets/electricsheepafrica/road-traffic-injury-trauma.africa-synth-prehospital-trauma-care-all
Prehospital Trauma Care | Africa (World Health Organization)
Size category: 10K<n<100K - Formats: csv - Sector: health - Engineered by Electric Sheep Africa
TL;DR
This dataset is part of the Electric Sheep Africa catalog on Hugging Face. It is indexed for African data discovery with standardized metadata, loading guidance, provenance notes, and analyst-oriented context.
What This Dataset Covers
Health datasets help researchers examine disease… See the full description on the dataset page: https://huggingface.co/datasets/electricsheepafrica/africa-synth-prehospital-trauma-care-all.clinical-quad-perfusion-buffer-lag-coupling-trauma-deterioration-v0.1
What this repo does
This dataset models the transition from compensated trauma physiology to systemic deterioration using a four-variable coupling structure.
The goal is to detect when trauma patients are drifting toward hemodynamic collapse before overt shock or organ failure occurs.
Trauma deterioration often unfolds as a cascade: perfusion declines, physiological reserves are consumed, treatment delays amplify instability, and organ systems begin to couple into systemic failure.… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-quad-perfusion-buffer-lag-coupling-trauma-deterioration-v0.1.clinical-quad-perfusion-buffer-lag-coupling-trauma-deterioration-v0.5
What this repo does
This repository provides a Clarus v0.5 cascade recovery geometry dataset for trauma deterioration.
Earlier Clarus datasets focused on detecting cascade states and identifying instability boundaries.Version v0.5 introduces a recovery geometry layer that asks a deeper question:
Can the system still return to stability?
The task is binary classification over trauma-linked deterioration states using:
• a four-variable clinical quad• trajectory dynamics• boundary… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-quad-perfusion-buffer-lag-coupling-trauma-deterioration-v0.5.clinical-quad-perfusion-buffer-lag-coupling-trauma-deterioration-v0.7
What this repo does
This repository contains a Clarus v0.7 dataset modeling trauma deterioration using a quad-coupling system representation.
The dataset extends the v0.6 intervention layer by introducing uncertainty geometry.
The question addressed by earlier versions was:
Can the system be stabilized?
v0.7 adds a second critical question:
How confident are we in that conclusion?
This allows Clarus to distinguish three operational states:
• confident deterioration
• confident… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-quad-perfusion-buffer-lag-coupling-trauma-deterioration-v0.7.huberman_lab_Erasing_Fears__Traumas_Based_on_the_Modern_Neuroscience_of_Fearthousand-voices-trauma
Thousand Voices of Trauma: Synthetic PE Therapy Dataset
Thousand Voices of Trauma is a large-scale, privacy-preserving benchmark dataset designed to advance AI-driven research in trauma therapy, particularly Prolonged Exposure (PE) therapy for PTSD.
It comprises 3,000 structured therapy conversations generated using Claude Sonnet 3.5, spanning 500 unique simulated clients, each undergoing six core therapy phases.
Citation
If you use Thousand Voices of Trauma dataset in your… See the full description on the dataset page: https://huggingface.co/datasets/yenopoya/thousand-voices-trauma.clinical-quad-perfusion-buffer-lag-coupling-trauma-deterioration-v0.2
What this repo does
This dataset evaluates whether machine learning models can detect clinical deterioration trajectories using both system state and system motion.
Earlier Clarus datasets (v0.1) describe system position in state space.
Clarus v0.2 datasets introduce a trajectory signal that indicates where the system is moving next.
The dataset therefore tests whether models can detect approaching instability even when the current state appears stable.
Core quad… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-quad-perfusion-buffer-lag-coupling-trauma-deterioration-v0.2.clinical-quad-perfusion-buffer-lag-coupling-trauma-deterioration-v0.4
What this repo does
This repository contains a Clarus v0.4 cascade boundary discovery dataset modeling trauma deterioration.
Earlier Clarus datasets focused on detecting cascade states or forecasting collapse trajectories.
Version v0.4 extends the framework to a harder problem:
detecting whether a system lies on the instability boundary itself.
The dataset models trauma physiology as a coupled system in which deterioration occurs when perfusion strain, delayed intervention, reduced… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-quad-perfusion-buffer-lag-coupling-trauma-deterioration-v0.4.huberman_lab_Dr__Paul_Conti_Therapy_Treating_Trauma__Other_Life_Challengesclinical-quad-perfusion-buffer-lag-coupling-trauma-deterioration-v0.3
What this repo does
This dataset models trauma patient deterioration using the Clarus quad coupling framework combined with trajectory and system dynamics.
The goal is to predict whether a trauma patient is approaching a physiological deterioration cascade.
The dataset introduces a dynamic forecasting layer that allows models to reason about motion through the stability manifold rather than relying only on static physiological snapshots.
Core quad… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-quad-perfusion-buffer-lag-coupling-trauma-deterioration-v0.3.abd-traumaTraumatologia_Hiztegia
[!NOTE]
Dataset origin: https://www.ivap.euskadi.eus/webivap00-a5app3/fr/ac36aEuskaltermWar/publiko/erakutsiBankuEdukia
huberman_lab_Dr._Paul_Conti_Therapy_Treating_Trauma__Other_Life_ChallengesThe-Overclocked-Mind-Trauma-to-Flow-Datasetthe_crisis_counseling_and_traumatic_events_treatment_plannerclinical-quad-perfusion-buffer-lag-coupling-trauma-deterioration-v0.6What this repo does
This repository contains a Clarus v0.6 intervention pathway dataset focused on trauma deterioration dynamics.
The dataset evaluates whether a model can determine if a proposed intervention meaningfully stabilizes a deteriorating trauma system.
The task requires reasoning from:
system state
trajectory toward instability
boundary geometry
recovery geometry
intervention vector
projected trajectory consequence
The model cannot read the answer directly.
It must infer… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-quad-perfusion-buffer-lag-coupling-trauma-deterioration-v0.6.odia-critical-care-trauma-fluid-maths-reasoning-v3