Product


A broader view of your symptoms

Sympify is a free web tool for exploring what else might explain what you are experiencing — and for turning that into something useful to bring to a clinician.

Walkthrough


How it works, step by step

Sympify runs in reverse compared with most symptom tools. It starts from a condition rather than a blank box, because a name you already have is a far better starting point than a guess.

  1. Step 1: Start with a condition

    Enter a condition — often one you have already been given, or one you have been wondering about. Sympify looks it up and, when several conditions match the name, asks which one you meant.

    In the app: Enter a condition

  2. Step 2: Review its commonly reported symptoms

    Sympify lists the symptoms commonly reported for that condition. For each one you answer Yes, No, or Unsure. Nothing is assumed on your behalf.

    In the app: Explore symptoms

  3. Step 3: Build a symptom profile

    Your answers build a symptom profile. Where a specific symptom belongs to a broader category, Sympify notes the broader category separately and labels it as inferred — it never claims you selected something you did not.

    In the app: Symptom profile

  4. Step 4: Explore other related conditions

    Sympify surfaces other conditions associated with the symptoms you reported, so you can keep looking rather than stopping at the first explanation. You can revisit anything you have already viewed.

    In the app: Continue matching

  5. Step 5: Generate a report to take to a professional

    Sympify assembles what you entered into a report you can download: the symptoms you reported, the ones you were unsure about, and the related conditions it surfaced — organized so it is easy to talk through with a clinician.

    In the app: Create report

Reviewing symptoms

Each symptom commonly reported for the condition is answered Yes, No or Unsure. Your answers build the profile on the right, and Sympify separately notes the broader categories it inferred — always labelled as inferred.

The report

The report collects the symptoms you reported, the ones you were unsure about, and the related conditions Sympify surfaced, grouped into match bands. It opens with a reminder that it is not a diagnosis.

These are representations of the Sympify interface, drawn with the application's own wording rather than captured from it.

Reading a result


What a match percentage does — and does not — mean

Sympify groups results into bands like “Possible matches (85%–100%)”. That number is a measure of overlap. It is not a probability, and treating it as one would be a serious misreading.

It is

  • A measure of how much of what you reported lines up with the symptoms commonly recorded for that condition
  • A way of ordering conditions so the ones worth asking about are easy to find
  • A starting point for a conversation, not a conclusion

It is not

  • A probability that you have the condition
  • A confidence level or a clinical risk score
  • A diagnosis, or a ranking of what is most likely wrong
  • A calibrated medical measurement of any kind

A condition can rank highly simply because it shares several common symptoms with what you described. Common symptoms are shared by many conditions — that is exactly why a clinician, not a ranking, does the diagnosing.

Sympify helps you explore. It does not diagnose.

Sympify can

  • Organize the symptom information you enter
  • Surface conditions associated with those symptoms
  • Help you look beyond the first explanation you were given
  • Produce a report you can bring to a healthcare professional
  • Show broader symptom categories it inferred, labelled as inferred

Sympify does not

  • Diagnose a condition
  • Prescribe or recommend treatment
  • Replace medical testing or examination
  • Replace a qualified clinician’s judgement
  • Provide emergency care
  • Tell you how likely any condition actually is

Sympify has not been clinically validated, and makes no claim to improve diagnostic accuracy. In an emergency, contact your local emergency services. Read the full medical disclaimer.

Who it's for


Two very different uses

If you are a patient

You have been given an explanation, and something about it does not fit. Or you have symptoms and no explanation at all. Sympify gives you a structured way to look at what else is associated with what you are experiencing, and a written summary so you are not trying to recall everything in a fifteen-minute appointment.

It will not tell you what you have. Bring the report to a clinician — that is what it is for.

If you are a healthcare professional

A Sympify report is a structured account of what a patient reports experiencing, plus the conditions associated with those symptoms in public reference material. Treat it the way you would treat notes a patient wrote down before the visit: potentially useful context, and a prompt for questions.

Sympify is not clinical decision support. It has not been clinically validated, its scores are not calibrated probabilities, and it should not be used to guide diagnosis or treatment.

Under the hood


How Sympify is actually built

A high-level description of the system. It is a retrieval and ranking system over structured reference information — not a predictive model, and not a large language model answering medical questions.

A symptom concept graph, not a keyword list

Symptoms are stored as canonical concepts with explicit alias wording, connected by directed relationships from a more specific symptom to a broader one. The structure is a directed acyclic graph rather than a strict tree, because a symptom can legitimately belong under more than one broader concept — an itchy rash sits under both itching and rash.

Inference only runs one direction

Selecting a specific symptom can infer the broader categories it belongs to. Selecting a broad symptom never infers a more specific one. Inferred categories carry less weight than something you selected yourself, and reports show them in their own section, labelled as inferred and not selected by the user.

Transparent retrieval, not a black box

Conditions are ranked by how much of your reported symptom profile corroborates them. Where a condition is linked to both a specific symptom and its broader parent, only the strongest match counts, so a single answer cannot be double-counted. The weights involved are engineering parameters chosen for sensible behaviour — they are not clinically calibrated constants.

Evaluation, and what it does not yet cover

Internal evaluation covers graph structure and coverage, retrieval baselines, weighting ablations, robustness to reworded and misspelled symptoms, and checks that an identical symptom profile produces an identical report regardless of the path taken to reach it. External held-out evaluation and a two-reviewer failure analysis are planned but not yet complete, so no accuracy claim is made.

See the research behind it

Perspectives

Individual views from people who have seen Sympify. They describe personal impressions, not measured performance — Sympify has not been clinically validated and does not claim to improve diagnostic accuracy.

  • Sympify addresses the critical issue of misdiagnosis through its innovative interactive web application.

    Dr. Jing LiangResearch Professor of Clinical Pharmacy, University of Southern California
  • It helps to narrow down potential diagnoses with remarkable precision.

    Dr. Michael WangProfessor, The University of Texas MD Anderson Cancer Center

Questions


Common questions

What is Sympify?

Sympify is a free web tool that helps you explore health information. You start from a condition, review the symptoms commonly reported for it, and Sympify surfaces other conditions associated with the symptoms you report — then organizes all of it into a report you can bring to a healthcare professional. It is built by Fueling Futures Foundation, a 501(c)(3) nonprofit.

Does Sympify diagnose diseases?

No. Sympify does not diagnose, and it is not a substitute for a clinician. It organizes information you enter and shows you conditions associated with those symptoms so you have better questions to ask. Diagnosis requires examination, history and testing that no website can perform.

How are conditions identified?

Sympify stores symptoms as named concepts linked to the conditions they are commonly reported for, and connected to one another from more specific to broader. When you answer questions about symptoms, it retrieves conditions whose recorded symptoms overlap with your answers and orders them by how much of your profile lines up. It is a retrieval and ranking system over structured reference information — there is no attempt to predict what you have.

What does a result or a percentage mean?

It is a measure of overlap, not a probability. A high percentage means much of what you reported matches the symptoms recorded for that condition; it does not mean you are likely to have it. The score is an unnormalized measure of corroboration and is not a calibrated likelihood, a confidence level or a clinical risk score. Treat the ordering as a list of things worth asking about.

Where does the information come from?

Condition and symptom descriptions come from publicly available medical reference material, including Mayo Clinic reference pages, which Sympify links out to so you can read the original source. Sympify does not write its own medical content.

Can healthcare professionals use Sympify?

Clinicians are welcome to look at a patient’s Sympify report as one more piece of context a patient has brought to the visit — much like notes a patient wrote down beforehand. Sympify is not a clinical decision-support tool, has not been clinically validated, and should not be used to guide diagnosis or treatment.

How does Sympify handle my information?

Your session is kept in your own browser, not in an account. Sympify does not ask you to register, and the website you are reading now has no analytics or advertising trackers. There is one optional step in the application where a member can attach a Member ID to a report, which saves that report for the organization’s records and research. It is optional and clearly presented as a choice. Full detail is in the Privacy Policy.

What should I do in an emergency?

Do not use Sympify. Contact your local emergency services immediately. Seek urgent care for severe pain, trouble breathing, chest pain, signs of stroke, a rapidly spreading infection, a severe allergic reaction, or any other emergency.

See all questions


Try it on something you already know.

The clearest way to understand Sympify is to enter a condition you or someone close to you has been given, and see what else shares its symptoms.