Three Kinds of Clinical AI
Module 1 · The Clinical AI Landscape

Three Kinds of Clinical AI

Distinguish predictive models, regulated device AI, and generative AI in healthcare, and see how the 4D fluency framework applies to each.

“AI” Means Several Different Things in Healthcare

When a colleague says “we’re rolling out AI,” they could mean a deterioration score in the EHR, an FDA-cleared algorithm that flags intracranial hemorrhage on CT, or a chatbot that drafts replies to patient portal messages. These tools fail in different ways, carry different regulatory status, and demand different kinds of oversight. Fluency starts with telling them apart.

Predictive modelsDevice AI (SaMD)Generative AI
ExamplesSepsis and deterioration scores, readmission risk, no-show predictionImaging triage and detection, ECG interpretation, diabetic retinopathy screeningAmbient scribes, inbox reply drafts, chart summarization, general chat assistants
OutputA score or alertA finding, flag, or measurementFree text (notes, letters, answers)
Built fromHistorical EHR data, often at one institutionCurated, labeled datasets for a narrow taskVery large general text corpora, sometimes tuned on clinical text
Typical oversightLocal governance committeeFDA clearance or approval (US), CE marking (EU)Varies widely; often none specific to the use case
Classic failurePerforms worse at a new site or over timeNarrow: misses what it wasn’t trained onFluent, plausible, and wrong

Predictive models

These estimate the probability of an outcome from structured data: vitals, labs, demographics, utilization. They’ve been in EHRs for years. Their key weakness is dataset shift: a model trained on one hospital’s patients, documentation habits, and coding practices may perform very differently at another hospital, or at the same hospital after a workflow change.

Device AI

Software intended to diagnose, treat, or prevent disease can be regulated as a medical device: Software as a Medical Device (SaMD). The US FDA’s public list of AI-enabled devices passed one thousand entries in 2025, with radiology accounting for roughly three quarters. Clearance means the device met a regulatory bar for a specific intended use and population. It doesn’t mean it will work equally well for every patient in your clinic.

Generative AI

Large language models (LLMs) produce text by predicting likely next words. They power ambient documentation, inbox drafting, chart summarization, and general-purpose assistants clinicians use on their own. They’re remarkably capable with language and can perform well on licensing-exam questions, but they have no built-in mechanism to know when they’re wrong. Most of this course focuses here, because generative AI is where individual clinicians make the most day-to-day judgment calls.

⚠️ Common Pitfall: Treating All 'AI' as Equally Validated

Common mistake: assuming a general chatbot carries the same evidence base as an FDA-cleared imaging algorithm, or that either is validated for your patients.

Ask of any tool: What exactly is it intended to do? On whom was it tested? Who monitors it here? A general-purpose assistant answering a dosing question has no clinical validation for that use at all.


A Framework for Using Any of Them: The 4Ds

This course applies the 4D AI Fluency Framework to clinical work. Each competency answers a question you face whenever AI touches patient care:

  1. 1 Delegation

    Should AI do this task, and which part?

  2. 2 Description

    How do I specify the task precisely?

  3. 3 Discernment

    Is the output accurate, complete, and safe?

  4. 4 Diligence

    Is my use ethical, compliant, and accountable?

CompetencyIn the clinic, it sounds like…
Delegation”An AI draft of this patient education handout is fine. An AI deciding whether this chest pain needs a troponin is not.”
Description”I gave the model the patient’s age, renal function, and current medications, and asked it to flag uncertainty.”
Discernment”The scribe note documented a normal abdominal exam I never performed. I removed it.”
Diligence”I used our BAA-covered tool, not a consumer app, and I signed the note knowing I own every word.”

The modules follow this structure: the landscape and failure modes first, then one or more modules per competency.

🧪 Try It: Inventory the AI in Your Workflow
  1. List every AI-powered tool you encounter in a typical week: EHR alerts and scores, imaging flags, scribe or dictation tools, inbox drafts, and anything you use on your own (including a phone app).
  2. Classify each as predictive, device, or generative.
  3. For each, write whether you know (a) who approved it for use in your organization and (b) whether it’s been validated on a population like yours.
  4. Circle any tool where you can’t answer either question. You’ll revisit this list in Module 6.
🧠 Knowledge Check

1. An EHR model that predicts which inpatients will deteriorate in the next 12 hours is best described as:

2. What does FDA clearance of an AI imaging device tell you?

3. Which characteristic of generative AI matters most for clinical safety?

About the Framework

The 4D AI Fluency Framework was created by Rick Dakan and Joseph Feller with Anthropic and is released under CC BY-NC-SA 4.0. This course’s clinical applications, examples, and exercises are original. Learn more at aifluencyframework.org.

Up Next

Before deciding what to delegate, you need a clear picture of how these tools fail. Next: the failure modes every clinician should recognize.