Trustworthy & Auditable AI
Systems whose evidence, limitations, decisions, and human oversight can be examined throughout the AI lifecycle.
Auditability · Explainability · Trustworthiness
Research
We develop biomedical and healthcare AI that can be inspected, explained, evaluated, and responsibly integrated into scientific and clinical workflows.
Research identity
Core Research Pillars
Our portfolio connects foundational AI methods with biomedical data, clinical systems, knowledge engineering, and rigorous evaluation.
Explainable Clinical AI
Models and interfaces designed to help clinicians and other stakeholders understand how recommendations are produced.
Biomedical Knowledge Engineering
Ontologies, linked data, semantic technologies, knowledge graphs, and structured scientific metadata.
Benchmarking & Evaluation
Frameworks that make biomedical AI and data infrastructure measurable, comparable, and reproducible.
Research portfolio
Projects, Platforms & Initiatives
Explore research projects, software platforms, standards, and initiatives spanning trustworthy AI, biomedical informatics, and healthcare data science.
Published Software
CEDAR OnDemand
A browser extension that enables ontology-based scientific metadata entry through existing web repository submission forms.
View sourceResearch Platform
MediLoom
Automated biomedical knowledge graph generation and enrichment using biomedical ontologies and embedding-based inference.
View sourceResearch Project
Burnout Surveillance AI
A narrative-based natural language processing and machine learning framework for clinician burnout surveillance.
View sourceResearch Platform
Semantically
A platform supporting trustworthy medical-code recommendation and biomedical semantic content authoring.
View sourceResearch Initiative
Care Escalators
Research on early prediction of respiratory, hemodynamic, renal, and neurological care-escalation triggers using electronic health records.
View sourceResearch Platform
KG-4Bio
Knowledge graph-based recommendation infrastructure for biomedical semantic content authoring.
View sourceResearch Project
Deep-FLAIM
Deep neural network research for early mortality prediction in trauma patients admitted to intensive care.
View sourceStandards Resource
AIRR Standards
MiAIRR standards resources supporting reproducible reporting, curation, and sharing of adaptive immune receptor repertoire data.
View sourceLab Project
Linked IM
Open repositoryLab Project
Disease Prediction Model
Open repositoryLab Project
Lyme Detector
Open repositoryResearch Initiative
Ghost Semanticly
Research Initiative
Anaplasia
A defining research pillar
Benchmarking & Evaluation
The lab’s benchmark-oriented portfolio includes two completed works spanning clinical AI readiness and RDF data infrastructure.
Benchmark preprint · 2026
FHIRTrustBench
FHIR-based clinical AI readiness, interoperability, and trustworthiness.
Peer-reviewed benchmark study · 2019
SPARQL Benchmark Analysis
Representativeness and performance characteristics of RDF triplestore benchmarks.
Benchmarking research in progress
The lab continues to expand its benchmarking portfolio across trustworthy clinical AI and biomedical data infrastructure.
Foundational portfolio
Project Archive
Browse the lab's existing archive of publications, models, semantic technologies, and biomedical informatics projects.
semantic web
Our Socio-technical Approach for Biomedical Content Authoring and Structured Web Publishing
Balancing the speed and accuracy in structured biomedical content authoring
View projectsemantic web
Ontology-based Scientific Metadata Generation
Public biomedical data repositories often provide web-based interfaces to collect experimental metadata. …
View projectsemantic web
Reporting and connecting cell type names and gating definitions through ontologies
Human immunology studies often rely on the isolation and quantification of cell populations from an input sample based on flow cytometry and related techniques. …
View projectsemantic web
How Representative Is a SPARQL Benchmark? An Analysis of RDF Triplestore Benchmarks
Triplestores are data management systems for storing and querying RDF data. …
View projectdata integration
Formal representation of immunology related data with ontologies
The Human Immunology Project Consortium (HIPC) is a multicenter collaboration between research centers performing large-scale human immunology studies that focus on profili...
View projectdata integration
A linked data graph approach to integration of immunological data
Systems biology involves the integration of multiple data types (across different data sources) to offer a more complete picture of the biological system being studied. …
View projectdata integration
The ADC API: a web API for the programmatic query of the AIRR Data Commons
The Adaptive Immune Receptor Repertoire (AIRR) Community is a research-driven group that is establishing a clear set of community-accepted data and metadata standards. …
View projectclinical prediction
Predicting 30-days All-cause Hospital Readmissions Considering Discharge-to-alternate-care-facilities
Hospital discharge is a decision based on several data points including diagnostic, physiological, demographic and caretaker information. …
View projectclinical prediction
LDA–GA–SVM: improved hepatocellular carcinoma prediction through dimensionality reduction and genetically optimized support vector machine
Hepatocellular carcinoma (HCC) is a common type of liver cancer worldwide. …
View projectmedical imaging
Multimodal Brain Tumor Classification Using Deep Learning and Robust Feature Selection: A Machine Learning Application for Radiologists
Manual identification of brain tumors is an error-prone and tedious process for radiologists; therefore, it is crucial to adopt an automated system. …
View projectclinical prediction
Statistically rigorous deep neural network approach to predict mortality in trauma patients admitted to the intensive care unit
Trauma patients admitted to critical care are at high risk of mortality because of their injuries. …
View projectmedical imaging
Classification of positive COVID-19 CT scans using deep learning
In medical imaging, computer vision researchers are faced with a variety of features for verifying the authenticity of classifiers for an accurate diagnosis. …
View projectmedical imaging
A Deep Learning Approach for COVID-19 8 Viral Pneumonia Screening with X-ray Images
Beginning in December 2019, the spread of the novel Coronavirus (COVID-19) has exposed weaknesses in healthcare systems across the world. …
View project