Skip to content
Build a chronologyMedical records

AI Medical Chronology Prompt for Lawyers

Build a date-ordered medical chronology from the complete record, with source citations for every encounter and explicit flags for treatment gaps, prior history, causation language, and missing records.

Report a correction

Direct answer

What is an AI medical chronology prompt?

It is a set of instructions for organizing a medical-record production into a date-ordered treatment table. This prompt requires a source cite for every encounter, keeps diagnoses and causation language as written, and separates treatment gaps, prior history, and missing records instead of asking the model to fill them in.

When to use this prompt

  • After collecting the medical production and before drafting a demand, exposure report, or examination outline.
  • When you need one dated view of encounters, imaging, procedures, therapy, restrictions, medications, and next-step plans.
  • When treatment gaps, prior complaints, causation statements, or missing records need their own review queues.

Record inputs to prepare

  • The complete medical production available for the review, including late-added or duplicate records.
  • Stable page, Bates, or PDF-page references and legible OCR or text for each source.
  • The claimant name, incident date, case type, reviewing role, and the injuries or conditions in scope.
  • Any known missing providers or date ranges so the final list can distinguish absent material from a silent record.

Worked example · Synthetic fictional details

Sample prompt

Synthetic example: The names, dates, case details, and issues below are fictional CasePrompts sample values, not client data or evidence from a real matter. They demonstrate the prompt format, not the accuracy of any AI model's output.

Preview the complete sample prompt
Customize in builder
CONTEXT:
You are a litigation support analyst assisting plaintiff's counsel in a motor vehicle negligence matter. The attached production is the medical records of Teresa Okafor. The incident at issue occurred on March 4, 2024. The injuries and conditions that matter are: cervical disc herniation at C5-6; post-concussive symptoms.

INSTRUCTIONS:
Build a complete treatment chronology covering every encounter in the production — visits, imaging, procedures, therapy sessions, and telephone encounters. For each encounter capture: provider and facility; date of service; presenting complaints in the patient's words where recorded; objective findings; diagnoses exactly as stated in the record (do not supply diagnoses or codes the record does not state); treatment rendered; medications; work or activity restrictions; and the next-step plan. Separately and explicitly:
1. Flag every gap in treatment longer than 30 days.
2. Flag every reference to symptoms, injuries, or treatment pre-dating March 4, 2024.
3. Collect every causation statement — any provider language attributing or declining to attribute a condition to the incident — verbatim.

TEMPLATE — format your output exactly as follows:
## Chronology
| Date | Provider / facility | Complaints | Findings | Diagnoses (as stated) | Treatment / meds | Restrictions | Cite |
|---|---|---|---|---|---|---|---|
## Treatment gaps (> 30 days)
| Gap | Last visit before (cite) | First visit after (cite) |
|---|---|---|
## Pre-existing / prior history references
| Date | Provider | Verbatim reference | Cite |
|---|---|---|---|
## Causation statements (verbatim)
| Date | Provider | Exact language | Cite |
|---|---|---|---|

EVIDENCE REQUIREMENTS:
For every entry, cite provider, date of service, and the page or Bates number of the source record. Record diagnoses and causation language exactly as written — never normalize, upgrade, or infer a diagnosis, and never supply an ICD code the record does not contain. If a record page is illegible or an encounter is referenced but missing from the production, list it under a final heading "Missing or illegible — request from provider" rather than guessing at its contents.

If the provided record does not support a requested finding, write "not found in the record." Do not infer or fill gaps from outside knowledge.
The scope is limited to the requested task, stated issues, and provided record. Do not introduce outside subjects or sources.
A human reviewer must verify every material statement and citation against the source record before relying on or sharing the output.

AI output is a starting point, not work product. Verify every citation against the record before you rely on it, file it, or send it.

What you'll fill in

  • 01Your role
  • 02Case typee.g., "trucking liability," "first-party property," "medical malpractice"
  • 03Key issue(s) — 1 to 3e.g., "vehicle speed at impact; brake maintenance; visibility"
  • 04Claimant / patient name
  • 05Date of incident / losse.g., "March 4, 2024"

Human review gate

Verification and common failure modes

  1. Compare every row to the cited page and confirm the patient, provider, date of service, and document date were not conflated.
  2. Check quoted diagnoses and causation statements word for word; models may normalize terminology or turn a history into a finding.
  3. Reconcile duplicate notes, late signatures, copied-forward histories, and references to outside care before treating the timeline as complete.
  4. Open every item labeled missing or illegible and decide whether to request a better copy or an additional provider record.

Boundaries

Limitations

  • The output is a working chronology, not a medical opinion, legal advice, or a substitute for reviewing the source records.
  • Scans, OCR errors, mixed patient files, inconsistent service dates, and incomplete productions can produce omissions or false chronology.
  • The prompt does not decide medical causation, reasonableness, necessity, or admissibility. Those judgments remain with qualified humans.
  • CasePrompts does not process the record on this page. If you paste the prompt or record into another service, your firm and that provider control data handling.

Keep working

Practice versions and related workflows

Provenance

Version and editorial method

Published by
CasePrompts, a DepoStack project
Template
Version 1
Page updated

Editorial owner: Andrew Mayes. The versioned CITE content is validated at build time, and this page's sample is assembled deterministically from the synthetic values above. No language model generates the sample page.

Review status: This template has not received independent legal review. “Published” describes its CasePrompts release status; it is not a claim of legal approval, jurisdictional sufficiency, or measured model accuracy.

Read the editorial methodology →

Pro tip The 'Missing or illegible' list doubles as your follow-up records request — send it to the provider the same day.