---
id: ai-in-healthcare
title: "AI in Healthcare: Diagnostics, Drug Discovery, and Robotics"
schema_type: Article
category: ai
language: en
confidence: high
last_verified: "2026-05-28"
created_date: "2026-05-24"
generation_method: ai_structured
ai_models:
  - claude-opus
derived_from_human_seed: true
conflict_of_interest: none_declared
is_live_document: false
data_period: static
atomic_facts:
  - id: f1
    statement: "CheXNet used a 121-layer convolutional neural network to detect pneumonia on chest X-rays in the ChestX-ray14 dataset."
    source_title: CheXNet Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning
    source_url: https://arxiv.org/abs/1711.05225
    confidence: high
  - id: f2
    statement: "McKinney et al. reported an international evaluation of an AI system for breast cancer screening in Nature in 2020."
    source_title: International evaluation of an AI system for breast cancer screening
    source_url: https://www.nature.com/articles/s41586-019-1799-6
    confidence: high
  - id: f3
    statement: "The FDA maintains a public list of AI-enabled medical devices authorized for marketing in the United States."
    source_title: Artificial Intelligence-Enabled Medical Devices
    source_url: https://www.fda.gov/medical-devices/software-medical-device-samd/artificial-intelligence-enabled-medical-devices
    confidence: high
completeness: 0.85
known_gaps:
  - Regulatory approval pathways outside the United States
  - Health equity and algorithmic bias in clinical AI
disputed_statements: []
primary_sources:
  - title: CheXNet Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning
    type: academic_paper
    year: 2017
    url: https://arxiv.org/abs/1711.05225
    institution: Stanford / arXiv
  - title: International evaluation of an AI system for breast cancer screening
    type: academic_paper
    year: 2020
    url: https://www.nature.com/articles/s41586-019-1799-6
    doi: 10.1038/s41586-019-1799-6
    institution: Nature
  - title: Artificial Intelligence-Enabled Medical Devices
    type: government_report
    year: 2026
    url: https://www.fda.gov/medical-devices/software-medical-device-samd/artificial-intelligence-enabled-medical-devices
    institution: U.S. Food and Drug Administration
secondary_sources:
  - title: Ethics and governance of artificial intelligence for health
    type: government_report
    year: 2021
    url: https://www.who.int/publications/i/item/9789240029200
    institution: World Health Organization
updated: "2026-05-28"
---

## TL;DR

AI in healthcare includes medical imaging, screening support, device software, clinical workflow tools, and research systems. Public claims should separate research results from regulatory authorization.

## Core Explanation

This repaired entry keeps claims tied to CheXNet, a Nature breast-screening evaluation, and the FDA's official AI-enabled medical-device list.

## Detailed Analysis

The previous version mixed research, drug discovery, robotics, and changing device counts under broad claims. Exact device totals and product-category shares should be refreshed from the FDA list when needed rather than hard-coded here.

## Further Reading

- [CheXNet](https://arxiv.org/abs/1711.05225)
- [Nature: AI system for breast cancer screening](https://www.nature.com/articles/s41586-019-1799-6)
- [FDA: Artificial Intelligence-Enabled Medical Devices](https://www.fda.gov/medical-devices/software-medical-device-samd/artificial-intelligence-enabled-medical-devices)

## Related Articles

- [AI for Drug Discovery: Molecular Docking, Virtual Screening, and De Novo Design](../ai-for-drug-discovery-molecular-docking-virtual-screening-and-de-novo-design.md)
- [AI for Drug Discovery: AlphaFold, Molecular Generation, and Generative Chemistry](../ai-for-drug-discovery.md)
- [AI Digital Twins for Healthcare: Patient-Specific Simulation, Treatment Planning, and Virtual Organs](../ai-digital-twins-healthcare.md)