AI-900 Practice Question: Describe features of Natural Language Processing workloads on Azure

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

• ✗

  A health monitoring system that analyses patient wearable data for anomalies

  Why it's wrong here

  Wearable device data—such as heart rate, activity, and sleep—is structured, time-series information generated from IoT sensors, not the unstructured clinical narrative text that Text Analytics for Health is built to parse. TA4H performs named entity recognition and ontology linking on documents like clinical notes and discharge summaries, so it has no mechanism to consume or analyze sensor streams. Moreover, anomaly detection on streaming data is a separate AI workload (for example, Azure Anomaly Detector), not a pre-built healthcare NLP service.

• ✓

  A pre-built NLP service for extracting medical entities from clinical text, linked to standard terminologies

  Why this is correct

  Text Analytics for Health (TA4H) is a pre-built capability within Azure AI Language that uses pretrained NLP models to extract medical entities such as diagnoses, medications, procedures, symptoms, and body structures from unstructured clinical text. It automatically links these entities to well-known standard terminologies, including SNOMED CT, RxNorm, and ICD-10-CM, and also identifies relations and negation/assertion modifiers (for example, 'no signs of pneumonia' links to pneumonia with a negative assertion). Unlike custom machine learning models, TA4H requires no training or labeled data on your side—it can be called directly via REST API or SDK to power downstream healthcare applications.

• ✗

  A service for doctors to receive AI-generated medical advice based on their queries

  Why it's wrong here

  Text Analytics for Health is not a question-answering or clinical recommendation engine; it does not synthesize patient data to propose treatments or provide diagnostic advice. Generating medical advice based on user queries is a radically different and high-risk AI task that involves clinical reasoning, personalization, and strict regulatory approval—whereas TA4H is a read-only information extraction service that outputs structured entities and relations from text. Confusing extraction with advice generation misunderstands the core purpose of TA4H as an NLP pipeline rather than a decision-support system.

• ✗

  A healthcare compliance tool that checks medical records for documentation errors

  Why it's wrong here

  Checking medical records for documentation errors is primarily a rule-based or human-led quality assurance process that reviews completeness, consistency, and coding accuracy; TA4H does not evaluate documentation quality or flag errors. What TA4H does is transform free-text clinical narrative into structured data—entities, relations, and terminology codes—which could be used as input to a compliance dashboard, but the service itself is agnostic to documentation standards or audit criteria. Thus, it is an extraction tool rather than a compliance checker.

Go deeper

Related to this question