# Medication Count by Drug Class Checklist

> A checklist to list every medication in a patient record, sort it by drug class, flag a missing dose, route or frequency, and count totals.

## What this checklist is for

Medication lists in discharge summaries, referral letters and clinic notes are often incomplete. A medication can appear in the plan but not in the list. A dose can have no frequency. The same medication can appear two times, once under a brand name and once under a generic name. This checklist turns one patient record into one clean list of medications.

For each medication, you record the drug class (a group of medications with a similar action or use). You also make sure that the entry has a name, a dose, a route and a frequency. Then you count the medications in each drug class and in total. A pharmacist, nurse or prescriber can then see which classes contain more than one medication.

The checklist supports medication reconciliation. AHRQ describes [medication reconciliation](https://psnet.ahrq.gov/primer/medication-reconciliation) as a review of all medications of a patient at admission, transfer and discharge. The review compares that list with the medications for the new setting of care. This checklist does not replace that review, and it is not medical advice. Only a qualified clinician can decide to start, stop or change a medication.

## The checklist

1. Find every medication in the document. Read the medication list, the history, the assessment, the plan and the discharge instructions. Also read any note from the pharmacy. People often miss medications that appear only in free text, for example "started amoxicillin for 7 days". Also look for as-needed (PRN) medications, inhalers, eye drops, creams, patches and injections. Include vitamins and over-the-counter products.
2. Copy each entry exactly as the document writes it. Record the name, strength, dose, route, frequency and any start or stop date. Do not correct, complete or guess an element.
3. Make sure that each entry has a name, a dose, a route and a frequency. Mark each element that is missing. "Metformin 500 mg" without a frequency is incomplete. "As directed" is not a frequency.
4. Look at how the document writes each dose. The FDA [labeling guidance on medication errors](https://www.fda.gov/media/158522/download) says that a missed decimal point can cause a tenfold dosing error. For example, a reader can see 4.0 mg as 40 mg, or .4 mg as 4 mg. The guidance recommends 4 mg without a trailing zero and 0.4 mg with a leading zero. If an entry uses the risky form, flag it for clarification. Do not write the dose again yourself.
5. Compare the brand names and the generic names. One medication can appear two times under two names. It can also appear once alone and once inside a combination product. If you find a possible duplicate, flag it for the reviewer. Do not merge the two entries.
6. Find the drug class in a reference. Do not use your memory. MedlinePlus drug pages give the class in plain words. For example, MedlinePlus says: "[Lisinopril is in a class of medications called angiotensin-converting enzyme (ACE) inhibitors](https://medlineplus.gov/druginfo/meds/a692051.html)." It also says: "[Metformin is in a class of drugs called biguanides](https://medlineplus.gov/druginfo/meds/a696005.html)." For a combination product, record the class of each ingredient. If you cannot find the class, write "unknown".
7. Mark the status of each entry: active, stopped, completed, held or unclear. Do not count a stopped medication or a finished antibiotic course as active.
8. Count the active medications in each drug class. Mark each class that has two or more medications. Two medications in one class can be intended. They can also be a duplicate. Only the reviewer can decide which.
9. Count all active medications. Polypharmacy is the use of many medications at the same time, and it has no single cutoff. A [2017 systematic review in BMC Geriatrics](https://pmc.ncbi.nlm.nih.gov/articles/PMC5635569/) found that the most common definition was five or more medications daily. The definitions in the review went from two or more to 11 or more. Record the number. Let the reviewer apply the definition of their organization.
10. List what you cannot determine. For example, list handwriting that you cannot read, a cut-off scan and an abbreviation that is not clear. Also list two sections that give different doses for one medication.

## How to record the result

Use one row for each medication entry:

| # | Medication as written | Drug class | Dose | Route | Frequency | Status | Missing or unclear | Where found |
|---|---|---|---|---|---|---|---|---|
| 1 | Lisinopril 10 mg PO daily | ACE inhibitor | 10 mg | oral | daily | active | none | Medication list |
| 2 | Metformin 500 mg | Biguanide | 500 mg | not stated | not stated | active | route, frequency | Discharge summary, plan |

Then add a short summary for each drug class:

| Drug class | Active count | Medications | Note for reviewer |
|---|---|---|---|
| ACE inhibitor | 1 | lisinopril | |
| Biguanide | 1 | metformin | frequency missing |

At the end, write these four numbers:

- Total active medications
- Entries with a missing element
- Possible duplicates
- Items that you cannot determine

## Use this checklist with Claude or ChatGPT

You can paste the checklist and a de-identified medication list into Claude or ChatGPT. De-identified means that you removed all patient identifiers. Ask the AI tool to work through each item. Ask it to show where it found each entry. Then you can compare each row with the source.

```text
You are helping me check a medication list. This is a documentation check, not a clinical decision.

Checklist:
1. Find every medication mentioned anywhere in the document, including free text, as-needed, topical, inhaled, eye drops, injections, vitamins and over-the-counter products.
2. For each entry, copy the drug name, dose, route and frequency exactly as written. Do not fill in anything that is not written.
3. Mark each missing or unclear element (name, dose, route, frequency).
4. Flag doses with a trailing zero (4.0 mg) or without a leading zero (.4 mg).
5. Flag the same drug listed twice, including brand and generic names and combination products.
6. Give the drug class for each medication and say how sure you are.
7. Mark each entry as active, stopped, completed, held or unclear.
8. Count active medications per drug class and in total.

Output:
- Table 1: one row per entry with the columns: medication as written, drug class, dose, route, frequency, status, missing or unclear, where you found it (section or page).
- Table 2: active count per drug class.
- For each checklist item, one or two lines on how you checked it.
- A list of everything you could not determine, and why.

Document (identifiers removed):
[paste the medication list or attach the file]
```

Before you use the result:

- Remove patient identifiers before you paste or upload anything. Identifiers include the name, date of birth, record number, address and phone number. Also read your workspace's data settings and the rules of your organization for patient data.
- Compare every row with the source document, not only a sample. AI tools can skip an entry, misread a dose or give the wrong drug class.
- Do not change a medication because of this result. The result is a draft for a pharmacist, nurse or prescriber to review, and it is not medical advice.

A docs portal with Ask AI
and support tickets

Connect a repository, or describe your product to start. Each docs site has search, Ask AI, an API console, an MCP server and support tickets.

Publishes from GitHub on every push

Works with Mintlify repositories

API console from your OpenAPI file

MCP server and llms.txt for AI agents

Ask AI and support tickets

Analytics for people and AI agents

Start Free →

Questions? Ask AI in our docs
No card required.

---

[View the canonical page](https://revdoku.com/blog/medication-count-review/) · [Browse llms.txt](https://revdoku.com/llms.txt)