Core AI Concepts
Core AI Concepts
Artificial intelligence refers to computer systems that perform tasks that normally require human intelligence—such as recognizing patterns, interpreting language, predicting outcomes, and solving problems.
Nursing example: An AI tool alerts a nurse that a patient’s vitals are trending toward deterioration.
A subset of AI where algorithms learn from data, identify patterns, and improve over time without being explicitly programmed.
Nursing example: ML predicts which patients are at highest risk for readmission based on EHR data.
A type of machine learning that uses multi-layered neural networks to analyze complex data like images, audio, and free text.
Nursing example: A deep-learning model reviews chest X-rays to detect early signs of pneumonia.
A computational model inspired by the human brain, made up of interconnected “neurons” that process information and learn relationships from data.
Nursing example: A neural network analyzes wound images to classify the stage of a pressure injury.
A type of AI trained on massive amounts of text to understand, generate, translate, and summarize human language.
Nursing example: A nurse uses an LLM to rewrite patient education material at a 6th-grade reading level.
AI that creates new content—text, images, audio, videos, or simulations—based on patterns learned from training data.
Nursing example: Generative AI produces realistic patient scenarios for a virtual clinical simulation
AI that enables computers to understand, interpret, and generate human language.
Nursing example: NLP extracts key symptoms from a triage note to speed up provider review.
AI-powered tools that provide alerts, recommendations, or evidence-based guidance to support clinical decision-making.
Nursing example: CDS flags a potential medication interaction when a nurse updates a patient’s MAR.*
Uses historical and real-time data to forecast patient outcomes, risks, or resource needs.
Nursing example: Predictive analytics identifies which patients are at high risk for falls during hospitalization.*
AI conversational tools that answer questions, guide patients, or automate simple clinical tasks.
Nursing example: A virtual agent screens patients for symptoms before a telehealth visit.*
AI that generates clinical notes or summaries based on speech, actions, or structured data.
Nursing example: A nurse speaks assessment findings aloud, and the AI automatically charts them in the EHR.*
Categorizing patients by level of risk (e.g., high, moderate, low) based on AI or statistical models.
Nursing example: AI identifies which post-op patients require enhanced monitoring for complications.*
AI that analyzes images to detect patterns, abnormalities, or clinical findings.
Nursing example: AI analyzes a wound photo to determine the likely stage of a pressure injury.*
Protecting patient information used by or exposed to AI systems, ensuring compliance with legal and ethical standards such as HIPAA.
Nursing example: A nurse ensures patient identifiers are removed before clinical notes are used to train an AI model.*
The process of informing patients when AI tools are involved in their care and obtaining agreement when appropriate.
Nursing example: Patients sign a consent acknowledging an AI triage tool will analyze their symptom report.*
Instances where an AI system generates inaccurate, fabricated, or misleading information.
Nursing example: A nurse double-checks an AI-generated discharge summary after noticing diagnoses that are not in the chart.*
Policies, oversight, and structures that ensure AI systems are used safely, transparently, and ethically within an organization.
Nursing example: A hospital’s AI governance committee reviews a new predictive tool before it is deployed in the ED.*
The dataset used to teach an AI model how to recognize patterns or make predictions.
Nursing example: A nurse educator assesses whether training data included diverse skin tones before adopting an AI wound evaluation tool.*
Methods used to detect, reduce, or prevent unfair or inequitable outcomes in AI predictions.
Nursing example: A health system updates its AI sepsis model after reviewing evidence that it under-identified cases in certain populations.*
AI-powered educational systems that adjust difficulty, content, and learning pathways based on the learner’s performance and needs.
Nursing example: A student who struggles with dosage calculations receives more targeted practice questions automatically.*
Virtual or augmented simulations enhanced by AI that allow scenarios to adapt dynamically in real time based on learner actions.
Nursing example: An AI-driven virtual patient develops new symptoms because the student delayed administering medication.*
The use of AI tools to create, evaluate, or support assessments of student learning, competency, or clinical judgment.
Nursing example: An AI tool analyzes patterns in student documentation to identify gaps in clinical reasoning.*
Crafting precise, effective instructions or questions (“prompts”) to guide AI systems to generate accurate, relevant results.
Nursing example: A nurse educator writes a structured prompt to generate culturally sensitive patient education materials.*