AI Transparency on FHIR
1.0.0-current - STU1 Ballot International flag

AI Transparency on FHIR, published by HL7 International / Electronic Health Records. This guide is not an authorized publication; it is the continuous build for version 1.0.0-current built by the FHIR (HL7® FHIR® Standard) CI Build. This version is based on the current content of https://github.com/HL7/aitransparency-ig/ and changes regularly. See the Directory of published versions

ValueSet: Recommended Device type codes for Artificial Intelligence

Official URL: http://hl7.org/fhir/uv/aitransparency/ValueSet/AIdeviceTypeVS Version: 1.0.0-current
Standards status: Trial-use Maturity Level: 2 Computable Name: AIdeviceTypeVS
Other Identifiers: OID:2.16.840.1.113883.4.642.40.79.48.1

Subset from HL7, plus those defined here

References

Logical Definition (CLD)

This value set includes codes based on the following rules:

This value set excludes codes based on the following rules:

 

Expansion

Expansion performed internally based on codesystem Device type for Artificial Intelligence v1.0.0-current (CodeSystem)

This value set contains 31 concepts

SystemCodeDisplay (en)DefinitionJSONXML
http://hl7.org/fhir/uv/aitransparency/CodeSystem/AIdeviceTypeCS  AI-By-ModelClassification by Technical ModelThis category classifies AI systems based on the underlying technical models they employ.
http://hl7.org/fhir/uv/aitransparency/CodeSystem/AIdeviceTypeCS  Rule-Based-SystemsRule-Based SystemsSystems that apply explicitly authored rules, logic, knowledge representations, or inference procedures to input data.
http://hl7.org/fhir/uv/aitransparency/CodeSystem/AIdeviceTypeCS  Machine-Learning-ModelsMachine Learning ModelsThey include supervised learning models (e.g., Support Vector Machines (SVM), Random Forests (RF)), which can be used for disease classification and risk prediction; unsupervised learning models (e.g., K-means clustering), which can discover hidden characteristics of patient subgroups; and reinforcement learning models, which can be applied in dynamic treatment plan management.
http://hl7.org/fhir/uv/aitransparency/CodeSystem/AIdeviceTypeCS  Deep-Learning-ModelsDeep Learning ModelsExamples include Convolutional Neural Networks (CNNs), which perform excellently in medical image analysis; Recurrent Neural Networks (RNNs) and their variant LSTMs, which are suitable for processing time-series physiological signal data; Generative Adversarial Networks (GANs), which can be used to synthesize training data and alleviate the scarcity of medical data; and Transformer models, which are widely used in multiple tasks such as medical imaging, text analysis, and physiological signal prediction.
http://hl7.org/fhir/uv/aitransparency/CodeSystem/AIdeviceTypeCS  Foundation-ModelsFoundation ModelsDeep learning models trained on broad data at scale that can be adapted to a range of downstream tasks.
http://hl7.org/fhir/uv/aitransparency/CodeSystem/AIdeviceTypeCS  Large-Language-ModelsLarge Language ModelsThese models, such as GPT-4 and PaLM, are trained on massive text datasets and can perform various natural language processing tasks, including medical text understanding, generation, and question answering.
http://hl7.org/fhir/uv/aitransparency/CodeSystem/AIdeviceTypeCS  Vision-Foundation-ModelsVision Foundation ModelsFoundation models trained primarily to process and represent visual data for adaptation to vision tasks.
http://hl7.org/fhir/uv/aitransparency/CodeSystem/AIdeviceTypeCS  Vision-Language-ModelsVision-Language ModelsFoundation models that jointly process visual and language data.
http://hl7.org/fhir/uv/aitransparency/CodeSystem/AIdeviceTypeCS  Hybrid-ModelsHybrid ModelsThese models combine multiple AI techniques to leverage their respective strengths. For instance, combining CNNs and RNNs can effectively process medical image sequences; integrating machine learning and deep learning models can enhance disease prediction accuracy; and combining rule-based systems with machine learning can improve interpretability and reliability in clinical decision support.
http://hl7.org/fhir/uv/aitransparency/CodeSystem/AIdeviceTypeCS  AI-By-BehaviorClassification by Output BehaviorGroups AI systems by whether identical inputs and execution conditions are expected to produce identical outputs.
http://hl7.org/fhir/uv/aitransparency/CodeSystem/AIdeviceTypeCS  Deterministic-AIDeterministic AIAn AI system that produces the same output for the same input when its model, configuration, state, and execution environment are unchanged.
http://hl7.org/fhir/uv/aitransparency/CodeSystem/AIdeviceTypeCS  Non-Deterministic-AINon-deterministic AIAn AI system whose output may vary for the same input and execution conditions, for example because it uses probabilistic sampling or stochastic processing.
http://hl7.org/fhir/uv/aitransparency/CodeSystem/AIdeviceTypeCS  AI-By-ScenarioClassification by Application ScenarioThis category classifies AI systems based on their application scenarios in the medical field.
http://hl7.org/fhir/uv/aitransparency/CodeSystem/AIdeviceTypeCS  Intelligent-Diagnosis-and-TreatmentIntelligent Diagnosis and TreatmentBy analyzing massive volumes of medical data, these AI systems assist doctors in making more accurate diagnostic and treatment decisions.
http://hl7.org/fhir/uv/aitransparency/CodeSystem/AIdeviceTypeCS  Medical-Image-AnalysisMedical Image AnalysisLeveraging deep learning technologies, these AI tools automatically identify lesion areas in medical images.
http://hl7.org/fhir/uv/aitransparency/CodeSystem/AIdeviceTypeCS  Personalized-TreatmentPersonalized TreatmentThese AI systems create precise patient profiles to formulate personalized treatment plans.
http://hl7.org/fhir/uv/aitransparency/CodeSystem/AIdeviceTypeCS  Clinical-Monitoring-and-Early-WarningClinical Monitoring and Early WarningMonitors longitudinal or real-time patient data to identify deterioration, adverse events, or other conditions requiring attention.
http://hl7.org/fhir/uv/aitransparency/CodeSystem/AIdeviceTypeCS  Clinical-Documentation-and-WorkflowClinical Documentation and WorkflowCreates, summarizes, extracts, codes, routes, or quality-checks clinical and administrative information to support healthcare workflows.
http://hl7.org/fhir/uv/aitransparency/CodeSystem/AIdeviceTypeCS  Drug-Discovery-and-DevelopmentDrug Discovery and DevelopmentAI in this category accelerates the screening of candidate drugs and optimizes the design of clinical trials.
http://hl7.org/fhir/uv/aitransparency/CodeSystem/AIdeviceTypeCS  Medical-Quality-ControlMedical Quality ControlThese AI tools are used to generate standardized medical document templates and detect defects in medical documents and images.
http://hl7.org/fhir/uv/aitransparency/CodeSystem/AIdeviceTypeCS  Patient-ServicesPatient ServicesAI systems here provide patients with services such as intelligent medical guidance, symptom self-assessment, and medical consultation.
http://hl7.org/fhir/uv/aitransparency/CodeSystem/AIdeviceTypeCS  Population-Health-and-OperationsPopulation Health and Healthcare OperationsSupports population stratification, public health, resource planning, scheduling, logistics, or other healthcare operational activities.
http://hl7.org/fhir/uv/aitransparency/CodeSystem/AIdeviceTypeCS  AI-By-DataTypeClassification by Processed Data TypeThis category classifies AI systems based on the types of medical data they primarily process.
http://hl7.org/fhir/uv/aitransparency/CodeSystem/AIdeviceTypeCS  AI-for-Medical-Imaging-DataAI for Medical Imaging DataIt mainly processes medical imaging data such as X-rays, MRIs, and CT scans.
http://hl7.org/fhir/uv/aitransparency/CodeSystem/AIdeviceTypeCS  AI-for-Physiological-Signal-DataAI for Physiological Signal DataThis type of AI deals with physiological signal data like electrocardiograms (ECG) and electroencephalograms (EEG).
http://hl7.org/fhir/uv/aitransparency/CodeSystem/AIdeviceTypeCS  AI-for-Medical-Text-DataAI for Medical Text DataIt processes text data such as electronic health records (EHRs) and medical abstracts.
http://hl7.org/fhir/uv/aitransparency/CodeSystem/AIdeviceTypeCS  AI-for-Structured-Clinical-DataStructured Clinical DataProcesses coded, tabular, or relational health data such as diagnoses, medications, laboratory results, observations, claims, or FHIR resources.
http://hl7.org/fhir/uv/aitransparency/CodeSystem/AIdeviceTypeCS  AI-for-Genomic-and-Omics-DataGenomic and Omics DataProcesses genomic, transcriptomic, proteomic, metabolomic, or related molecular data.
http://hl7.org/fhir/uv/aitransparency/CodeSystem/AIdeviceTypeCS  AI-for-Audio-DataAudio DataProcesses speech, heart sounds, respiratory sounds, or other clinically relevant audio.
http://hl7.org/fhir/uv/aitransparency/CodeSystem/AIdeviceTypeCS  AI-for-Video-DataVideo DataProcesses temporal image sequences such as endoscopy, ultrasound cine loops, gait recordings, or procedure video.
http://hl7.org/fhir/uv/aitransparency/CodeSystem/AIdeviceTypeCS  AI-for-Multimodal-DataMultimodal DataJointly processes two or more data modalities, such as images and text or physiological signals and structured clinical data.

Description of the above table(s).