Get started
AnalyticsLive · in the productReportHand-crafted

CohortLens

Find every patient like this — in plain words.

Shown in the product as “Patient Lists”
Get CohortLensOpen the appAvailable nowHow pricing works →

What it is

Cohorts built from a closed set of criteria over the record — age, sex, a recorded diagnosis by code or by name, when somebody was last seen, a care-plan programme, a recent admission, an open recall, a medicine — any of which can be negated. The statement those criteria compile to is shown before it runs and kept with every run alongside its parameters, so a number can be checked afterwards. A plain-language question can be put to the assistant, which proposes criteria in that same language and never a query; nothing is saved until a person accepts what is in front of them, and they may edit it first.

Who uses it
Doctors, coordinators, researchBuilt for: Every specialty
Reads
Problems, labs, medicines
Writes
Saved lists
Never
Shows names to people without access
Access
Only people whose role includes it — the clinic owner decides who
Your data
Full PHI. Hosted in Boston, United States. On uninstall: All clinical data stays in the record.

How it works

  1. Build the criteria by handNew cohort takes a name, optionally the question in your own words, and criteria from a closed list — age, sex, condition code, condition text, last visit, programme, admitted within, open recall, medication text; a cohort with no criteria is every patient, so at least one is required.
  2. Ask the assistant insteadPropose criteria hands the question to the assistant, which answers in that same small language and never in SQL; what comes back lands in the same builder, editable, and every criterion is validated against the union before anything is compiled.
  3. Accept it, or say why notA proposal is a pending decision: Accept the proposal and save writes the cohort with whatever criteria are on screen, Reject the proposal takes your words, and while one is open Cancel stays disabled until those words are written.
  4. Read the statement that produced the numberRun prints the count with the statement exactly as it ran and the values as parameters beside it, and the run is kept, so the number can be checked afterwards.
  5. See who is in itWho is in it lists the members with MRN, sex and date of birth on a route that asks for patient reading rights on top — the count is a statistic, the list is a list of people.
  6. AI helpsTurns your question into a patient list, showing the rules it used. You stay in charge.

Rules it keeps

What it does not do, by design. A listing with only benefits is an advertisement.

It does not run anything a model wrote: a proposal is validated against a closed set of criteria and compiled by this product, with every value bound as a parameter.
There is no research export in this build — the member list is a list of patients, and the route asks for the patient-read permission on top.

AI in CohortLens

AskQuestions about what is on screen — “What needs attention in CohortLens today?” — answered with the records it read.
DraftSummaries and notes for the team, marked as drafts until a person signs.
In this appTurns your question into a patient list, showing the rules it used.
Every answer shows its sources. Nothing AI writes is saved until a person accepts it.

Its screen

BuildNew cohort
From the design, with its example clinic.

Try it

The design preview: every screen drawn with the product’s own blocks, on an example clinic’s demo data. Nothing here is a real patient.

Open full screen →
Design preview · Patient Lists · example clinic

Connected to

Read out of the code, not the brochure: each app below is here because one service queries the other’s tables. Install either side and the hand-over is already wired.

See the whole clinic →

Questions clinics ask

What does CohortLens do?
Ask a question of your patients and see the query that answered it. Cohorts built from a closed set of criteria over the record — age, sex, a recorded diagnosis by code or by name, when somebody was last seen, a care-plan programme, a recent admission, an open recall, a medicine — any of which can be negated. The statement those criteria compile to is shown before it runs and kept with every run alongside its parameters, so a number can be checked afterwards. A plain-language question can be put to the assistant, which proposes criteria in that same language and never a query; nothing is saved until a person accepts what is in front of them, and they may edit it first.
What data does CohortLens read and write?
CohortLens reads patient record, care-plan programmes, recalls and admissions and writes cohort definitions and the query each run executed. Its data class is Full PHI. Every app works on the same patient record — nothing is copied into a silo.
What does CohortLens deliberately not do?
It does not run anything a model wrote: a proposal is validated against a closed set of criteria and compiled by this product, with every value bound as a parameter. There is no research export in this build — the member list is a list of patients, and the route asks for the patient-read permission on top.
What happens to our data if we uninstall CohortLens?
All clinical data stays in the record.
Is CohortLens available today?
Yes — CohortLens is live in clinics today. Set up your practice on MedAppz and install it from your dashboard.

Want to see CohortLens running on your own patients?

Tell us what you run and we will show you this app inside a practice shaped like yours — or answer the question the page above did not.

We use your name, phone number and clinic name for one thing: to answer this enquiry about MedAppz. It is stored on our own server, in the single region our trust centre names, and it is not sold or passed to anyone else.

Email us

You can withdraw either at any time: write to hello@medappz.com, or tell whoever calls you, and we will delete what you gave us.

More in Analytics

All 30 →