Building Patient Timelines

What it does

When your agent uses it

• The user wants to build a patient timeline
• Order events from clinical notes
• Reconstruct a longitudinal history
• Plot a course of illness

Example prompts

• “/building-patient-timelines”

Requirements

• Python 3

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

1. 1De-identify if needed. If notes carry PHI, run openmed.deidentify(...)
2. 2Extract events. openmed.analyze_text(note) for conditions, drugs,
3. 3Resolve temporality. For each event, use resolving-clinical-context
4. 4Normalize dates. Map each event to a date
5. 5Build event records. One record per event: `(date, granularity, label,
6. 6Sort and de-duplicate. Sort by (date, granularity); merge repeated
7. 7Emit. A sorted list for a UI, or FHIR resources (see hand-off).

What it can do on your machine

Read from SKILL.md and the folder at commit 34d7b8c. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • hl7.org
  • iso.org
  • i2b2.org

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Building Patient Timelines loads about 1.9k tokens when it runs. Until then it costs about 202 tokens; SKILL.md has 643 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~202

When it runs · the whole SKILL.md, loaded when a task matches

~1.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from maziyarpanahi/openmed at commit 34d7b8c, republished under its Apache-2.0 licence (© maziyarpanahi). 643 words, ~1,917 tokens.

name

building-patient-timelines

description

Assemble a chronological patient timeline from OpenMed-extracted clinical events, normalizing dates and resolving relative time expressions on-device. Use when the user wants to build a patient timeline, order events from clinical notes, reconstruct a longitudinal history, plot a course of illness, or turn analyze_text/deidentify output into a sorted sequence of dated encounters, diagnoses, medications, and procedures. Covers temporal normalization (absolute and relative), event modeling toward FHIR Encounter/Condition.onsetDateTime, anchoring to a document/admission date, and handling undated or ambiguous events. Consumes OpenMed analyze_text entities plus clinical temporality (resolving-clinical-context); produces a sorted event list ready for charting or FHIR export.

license

Apache-2.0

metadata.project

OpenMed

metadata.category

analytics-reporting

metadata.pairs

after

metadata.version

1.0

import datetime as dt
import openmed

note = (
    "Discharge summary, 2024-03-12. Patient admitted 2024-03-08 with chest pain. "
    "History of type 2 diabetes diagnosed in 2019. Started on metformin two days "
    "after admission. Cardiac catheterization performed yesterday."
)

# 1) Extract clinical events (entities carry char offsets: start/end)
result = openmed.analyze_text(note, output_format="dict")
events = result["entities"]   # each: {text, label, confidence, start, end}

# 2) Normalize the temporal frame: an explicit document/anchor date drives
#    resolution of relative expressions ("two days after", "yesterday").
anchor = dt.date(2024, 3, 12)  # parsed from the note header or document metadata

def to_timeline(events, *, anchor, note_id):
    """events: list of {text,label,start,end,confidence}. anchor: date.
    Returns sorted [(date, granularity, label, text, confidence)]."""
    timeline = []
    for e in events:
        date, gran = resolve_event_date(e, note=note, anchor=anchor)  # your resolver
        if date is None:
            continue  # undated/unresolvable: route to an "undated" bucket, don't drop silently
        timeline.append((date, gran, e["label"], e["text"], e["confidence"]))
    # year-only ('Y') sorts before month ('M') before day ('D') on ties
    order = {"Y": 0, "M": 1, "D": 2}
    return sorted(timeline, key=lambda r: (r[0], order[r[1]]))

# resolve_event_date handles: ISO dates, "March 2019" (gran='M'),
# "yesterday"/"two days after admission" (relative to anchor/admission), POD-n, etc.

© maziyarpanahi, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/building-patient-timelines of maziyarpanahi/openmed.

Open the folder on GitHubat commit 34d7b8c