Google Cloud

Healthcare API / Discovery Engine Complete Guide: FHIR, MedLM & HIPAA

2026-05-24
NicheeLab Editorial Team

Cloud Healthcare API is GCP's integrated platform for medical data, supporting the three major medical standards: FHIR / HL7v2 / DICOM.Discovery Engine is the umbrella brand for Gen AI Search (covering Vertex AI Search, Recommendations, and more). In the healthcare space, it pairs with MedLM and Healthcare NLP to power EHR Q&A and clinical summarization.

Healthcare API Components

ServiceStandardUse case
FHIR StoreHL7 FHIR R4EHRs, patient information, test results
HL7v2 StoreHL7v2Legacy medical messaging
DICOM StoreDICOMwebRadiology images / pathology images
Consent ManagementFHIR ConsentPatient consent management
Healthcare NLP APIStructured extraction from medical documents
Healthcare Data EngineLakehouse-integrated platform

FHIR Store Example

from google.cloud import healthcare_v1

client = healthcare_v1.FhirStoreServiceClient()
fhir_store = "projects/PROJECT/locations/us-central1/datasets/my-dataset/fhirStores/my-fhir"

# 患者リソース作成
patient = {
    "resourceType": "Patient",
    "name": [{"family": "山田", "given": ["太郎"]}],
    "gender": "male",
    "birthDate": "1985-04-01",
}

# Bulk Export → BigQuery
client.export_resources(
    request={
        "name": fhir_store,
        "bigquery_destination": {
            "dataset_uri": "bq://my-project.fhir_export",
            "schema_config": {"schema_type": "ANALYTICS_V2"},
        },
    }
)

Healthcare NLP Example

from google.cloud import healthcare_v1

client = healthcare_v1.NlpServiceClient()
parent = "projects/PROJECT/locations/us-central1/services/nlp"

response = client.analyze_entities(
    nlp_service=parent,
    document_content="患者は 65 歳男性、高血圧と 2 型糖尿病の既往あり。メトホルミン 500mg を内服中。"
)

for entity in response.entity_mentions:
    print(f"{entity.text.content} → {entity.type_} (ICD-10: {entity.linked_entities})")
# 出力例:
# 高血圧 → PROBLEM (ICD-10: I10)
# 2 型糖尿病 → PROBLEM (ICD-10: E11)
# メトホルミン → MEDICINE (RxNorm)

MedLM (Healthcare-Specialized LLM)

  • Enterprise-grade productization of Google Research's Med-PaLM family
  • Clinical summarization, Q&A, and clinical coding assistance
  • Accessed via Vertex AI; supports CMEK / VPC SC
  • Covered by HIPAA BAA
  • MedLM-Large / MedLM-Medium

Discovery Engine Components

  • Vertex AI Search (general purpose)
  • Vertex AI Search for Healthcare (specialized for medical documents)
  • Vertex AI Search for Retail (e-commerce)
  • Vertex AI Search for Media (video / audio)
  • Recommendations AI (recommendations)
  • Conversational Agents (formerly Dialogflow CX)

Pricing Examples

ItemPrice
FHIR storage$0.45/GB/month
FHIR operations (Read / Write)$0.40 per 1,000 operations
DICOM storage$0.10/GB/month
HL7v2 storage$0.50/GB/month
Healthcare NLP$1.50 per 1,000 characters
MedLMGemini-equivalent per-token pricing + a Healthcare premium

Regulatory Compliance

  • Covered by HIPAA BAA (United States)
  • GDPR Article 9 (special categories of personal data)
  • FedRAMP High
  • HITRUST CSF
  • ISO 27001 / 27017 / 27018 / 27701
  • Japan: Medical Information Guidelines (the 3-ministry, 2-guideline framework)

Typical Use Cases

  • Cloud integration of EHR (electronic health record) systems
  • Legacy HL7v2 → FHIR conversion
  • Centralized management of radiology images (DICOM) plus AI-assisted diagnosis
  • Clinical summarization (MedLM)
  • Clinical research: FHIR Bulk Export → BigQuery for large-scale analysis
  • Automated medical coding (Healthcare NLP)
  • Patient-facing self-service Q&A (Vertex AI Search Healthcare)

What is Healthcare API?

GCP's healthcare data platform. It provides managed stores for the three major medical standards (FHIR / HL7v2 / DICOM), is HIPAA BAA compliant, and is used for EHRs, diagnostic imaging, and clinical research.

What is Discovery Engine?

The umbrella brand for Gen AI Search. It covers Vertex AI Search, Recommendations AI, Healthcare-specific Search, and more. It has been positioned as the unified product name since 2023.

What can Healthcare NLP API do?

It automatically extracts diseases, medications, symptoms, anatomical sites, and test findings from medical charts and diagnostic documents, and auto-maps them to SNOMED CT / ICD-10 / RxNorm codes.

What is MedLM?

A healthcare-specialized LLM fine-tuned for the medical industry (based on Google's Med-PaLM family). It supports clinical summarization, Q&A, and coding assistance.

What is the pricing model?

Healthcare API: FHIR storage $0.45/GB/month + per-operation charges. NLP $1.50 per 1,000 characters. MedLM is charged per token. DICOM Image: $0.10/GB storage.

Is a HIPAA BAA available?

Google Cloud offers a HIPAA BAA, and Healthcare API is a core BAA-covered service. Combine it with CMEK / VPC SC / Audit Logs for full regulatory compliance.

What is Cloud Healthcare Consent Management?

A patient consent management service. It controls the scope and duration of data usage, enabling regulation-compliant handling of PHI.

What is FHIR Bulk Export?

A feature that exports large volumes of FHIR data to Cloud Storage / BigQuery. Essential for clinical research and for building ML training datasets.

Related Articles: Healthcare / Search AI

Vertex AI Agent Builder 完全ガイド|Conversational Agents・Vertex AI Search・Tool Use (GCP)

Google Cloud Vertex AI Agent Builder の全機能解説。Conversational Agents (Dialogflow CX 後継)、Vertex AI Search、Tool Use、Grounding、Playbook、料金、ChatGPT GPTs / Copilot Studio 比較を網羅。

Generative AI Leader (GAIL) 完全ガイド|Google Cloud 生成 AI 認定 (2025 年 5 月リリース新試験)

Google Cloud Generative AI Leader (GAIL、2025-05-14 リリース) の完全ガイド。4 ドメイン (生成 AI 基礎 30% / GCP 提供サービス 35% / モデル出力改善 20% / ビジネス戦略 15%)、Gemini ファミリー、Vertex AI Agent Builder、RAG、ビジネス導入観点を日本語で網羅。

Vertex AI 入門|Google Cloud 統合 ML プラットフォームの全機能 (GAIL/PMLE/PCD 必須知識)

Google Cloud Vertex AI の入門解説。Vertex AI Studio / Agent Builder / Model Garden / Search / Pipelines / Training の全機能、Gemini モデルファミリー (Pro/Flash/Ultra)、Azure OpenAI との比較、料金体系、Responsible AI 機能を日本語で整理。

Vertex AI + LangChain で RAG 構築チュートリアル|Vector Search・Gemini (GCP)

Google Vertex AI Vector Search + LangChain + Gemini で RAG 構築チュートリアル。Embedding (text-embedding-005)、Chunking、ANN 検索、ハイブリッド検索、コスト、Vertex AI Search との使い分けを 2026 年最新版で解説。

* Google Cloud is a trademark of Google LLC. For the latest information, see the official Cloud Healthcare API documentation.

Check what you learned with practice questions

Practice with certification-focused question sets

View GCP exam prep page
Author

NicheeLab Editorial Team

NicheeLab editorial team focused on data engineering and cloud certification learning. Content is structured around practical study needs and official exam domains.


Related articles
Google Cloud

Google Cloud Certification Roadmap (2026)

Choose your GCP certification path — Foundational, Associate...

Google Cloud

CDL Cloud Digital Leader: Complete Exam Guide (2026)

Pass the Cloud Digital Leader exam — cloud business value, G...

Google Cloud

GAIL Generative AI Leader: Complete Exam Guide (2026)

Pass the Generative AI Leader exam — Gemini, Vertex AI, Work...

Google Cloud

Vertex AI Fundamentals for GCP Certs (2026)

Vertex AI basics every cert candidate needs — Workbench, Pip...

Google Cloud

Associate Cloud Engineer (ACE): Complete Guide (2026)

Pass the Associate Cloud Engineer exam — Console, gcloud, pr...

Browse all Google Cloud articles (103)
© 2026 NicheeLab All rights reserved.