BreatheEasy

Tomorrow's air forecast next to your asthma action plan.

BreatheEasy helps you follow the plan your doctor gave you. It does not diagnose, prescribe, or replace medical care.

Trouble walking or talking because of shortness of breath, or lips or fingernails that are blue, pale, or gray? Call 911 now. Call 911

Air outlook

Tomorrow

—

—AQI

What to do tomorrow

    Your personal outlook

    Next days

      Daily check-in

      Takes 20 seconds.

      Any of these?
      Any of these?
      Danger signs

      Houston daily count

      My action plan

      Copy these from the asthma action plan your doctor gave you. NHLBI Asthma Action Plan (PDF)

      My known triggers

      What your log is learning

      A small model trains right here in your browser on your own check-ins.

      Recent check-ins

        How much can you trust it?

        SYNTHETIC check: made-up people, not real patients

        Calibration (reliability)
        Model saidAverage saidActually roughDays
        More logged days, better model
        Logged daysRightGuess-commonBrier

        These numbers show the method works when a pattern exists. Real people are messier: a real log can be noisier, have triggers BreatheEasy does not measure, or have no pattern at all.

        Background

        About 4.8 million U.S. children (6.7%) have asthma right now, and 47% of them had at least one asthma attack in the past year (CDC, 2023 National Health Interview Survey). Doctors hand families a paper asthma action plan with green, yellow and red zones, but it rarely gets connected to tomorrow's air.

        That matters in Houston. The American Lung Association's State of the Air 2026 ranks the Houston-Pasadena metro 6th worst in the nation for ozone, with Harris County averaging 43.3 weighted unhealthy ozone days a year (2022–2024 data). EPA lists people with asthma and children and teenagers among the groups most sensitive to ozone.

        BreatheEasy puts the plan and the forecast on one screen: it computes tomorrow's AQI from the forecast using EPA's breakpoints, shows EPA's advice for that level, puts your doctor's own words next to it, and learns from your check-ins which conditions tend to come before your rough days.

        How the "AI" works

        A logistic-regression model trains in your browser on your own check-ins (a day is "rough" if you were in the yellow or red zone). Inputs: ozone AQI, PM2.5 AQI, pollen level, high temperature, humidity, and whether yesterday was rough. It shows its learned weights, explains each prediction feature by feature, and reports an honest held-out accuracy next to a naive baseline. It needs at least 14 days with some good and some rough days before it says anything. You can open any past day to see what it weighed, and a SYNTHETIC self-check on made-up people shows how well its percentages match reality and how it improves with more logged days. It finds patterns in your data; it does not diagnose and it is not a medical device.

        Limits

        • Forecasts are model estimates (Open-Meteo / Copernicus CAMS), not monitor readings. Check AirNow for official local forecasts and Ozone Action Days.
        • Open-Meteo has no pollen forecast for North America, so U.S. users log the Houston Health Department daily count themselves.
        • Guidance text is EPA's and NHLBI's general guidance. Treatment steps come only from the plan you type in from your doctor.

        Sources

        Your data

        Everything stays in this browser (localStorage). There is no account or server, and nothing is tracked.