Read medical reports and flag abnormal results automatically

Extracts test results from uploaded medical reports and generates personalized advice for anything out of range.

How the work actually flows

It branches. Exactly one path is taken; runs once per each test result.

Pattern: Exclusive Choice (4) · Multiple Instances without Synchronization (12)

flowchart TD trig>"medical report uploaded"]:::trig s0["extract report text via ocr"]:::svc s1["structure data into fields"]:::svc s2[["log each test result"]]:::mi s3["compare result to normal range"]:::task trig --> s0 s0 --> s1 s1 -->|"one per each test result"| s2 s2 --> s3 gx{"× is result outside normal range"}:::gate s3 --> gx p00["generate personalized advice"]:::task gx -->|"abnormal"| p00 p10["no action needed"]:::task gx -->|"normal"| p10 p00 --> out p10 --> out out[/"flagged results with tailored advice"/]:::out pay{{"catch abnormal results without manual review"}}:::pay out --> pay classDef task fill:#e7f6fe,stroke:#34b8f0,color:#2c2a29 classDef svc fill:#f6f8fa,stroke:#7c8795,color:#2c2a29 classDef mi fill:#e7f6fe,stroke:#0079a8,color:#2c2a29,stroke-width:2px classDef human fill:#fff,stroke:#0079a8,color:#0079a8 classDef store fill:#f6f8fa,stroke:#0079a8,color:#2c2a29 classDef trig fill:#00a4eb,stroke:#0079a8,color:#fff,font-weight:bold classDef trigtime fill:#00a4eb,stroke:#0079a8,color:#fff,font-weight:bold classDef trigdata fill:#8ad4f5,stroke:#0079a8,color:#06314c,font-weight:bold classDef gate fill:#fff,stroke:#e8a23d,color:#6b4708,font-weight:bold classDef out fill:#1f9d6b,stroke:#167a53,color:#fff,font-weight:bold classDef pay fill:#06314c,stroke:#021f33,color:#fff
Starts itA stepAn outside serviceRuns once per itemOne path onlyResultPayoff
Build size
Advanced

A larger build with multiple systems, AI reasoning, and custom rules.

Business functions
Document Processing & OCRSpreadsheet & Database OpsReporting & AnalyticsFile & Cloud Storage
Connects
Google DriveGoogle SheetsMistral AIOpenAI
Featured in

The problem it solves

You or your team get lab reports as PDFs or scanned images, and pulling out the actual numbers means squinting at formatting and typing them into a tracker by hand. Spotting which values are actually abnormal, and knowing what to do about it, takes even more time.

Who it fits

Health clinics, wellness coaches, or individuals tracking recurring lab results.

How it works

  1. A medical report is uploaded to a monitored Google Drive folder
  2. Mistral AI reads the document with OCR and pulls out the text
  3. GPT-4 structures the data into patient info, test names, results, and reference ranges
  4. Every result is logged to a Google Sheet and compared against its normal range
  5. For anything out of range, GPT-4 writes personalized dietary and lifestyle advice
What you get

Abnormal results caught before they're missed

You get every lab result checked against normal ranges automatically, with personalized advice generated for anything out of range.

What you get

A Google Sheet of every test result, with flagged abnormal values and tailored advice.

What you need

A Google Drive and Sheets account, a Mistral AI API key, and an OpenAI GPT-4 API key.

We can build this. But should you?

The hard question is not how to build it. It is whether this is the right thing to build first.

That is what a Fractional Chief AI Officer figures out with you, before anyone writes a line of code.

Let's Talk Strategy

Related automations

Back to the AI Playbook