CDC FluSight forecasts estimate future weekly influenza hospital admissions for the United States and individual jurisdictions. They are population-level forecasts—not a tool for calculating whether a particular person will be hospitalized. To read one correctly, check the location, issue date, target week, units, central estimate, uncertainty interval and reporting completeness together.
What a flu hospital forecast actually measures
CDC FluSight publishes short-horizon estimates of new weekly laboratory-confirmed influenza hospital admissions, alongside historical reported counts. Depending on the chart, the estimate is expressed as a count or a rate. The forecast is about the total for a jurisdiction and week, not a personal risk score or a prediction for an individual patient. CDC’s FluSight forecast page explains the current chart and its measures.
When reading a plotted value, identify these details before interpreting its size:
- Jurisdiction: the United States, a state or another listed jurisdiction.
- Forecast issue date: when the forecast was made. A forecast is a dated estimate, not a live count.
- Target week: the week for which admissions are being estimated.
- Unit: a count of admissions or a population-adjusted rate.
- Central estimate and interval: the summary forecast and the range of uncertainty around it.
- Reporting completeness: how many hospitals reported for the relevant recent week.
Counts answer how many admissions are forecast; rates help compare jurisdictions of different population sizes. A rate is not an exact per-resident risk: its population denominator may not reflect the populations served by hospitals in that jurisdiction.
Do these 3 things before closing this tab:
1Clear out junk files and repair common Windows errors2Scan for outdated or missing drivers - takes under a minute3Repair Windows errors before they cause bigger problems#1 Best Overall
How to read the median and prediction intervals
The median is a central forecast summary. It is not a guarantee that the eventual number will equal that value. CDC describes the colored graph areas as prediction intervals: they show bounds of uncertainty around forecast estimates. Wider intervals mean a broader range of plausible outcomes in the forecast; narrower intervals do not remove uncertainty.
An interval is not a promise that the observed result will fall inside it. Its coverage—the frequency with which intervals contain the eventual observations—can vary with forecast horizon, location and conditions. In particular, a model can have acceptable aggregate performance and still miss a sudden change in the epidemic curve.
Rank #2
For example, CDC’s evaluation found that fewer than 25% of FluSight ensemble two-week-horizon intervals across jurisdictions contained the observed values around the week ending December 27, 2025, near a hospitalization increase. Coverage stabilized near 95% beginning in February 2026. Those are observed results for that season and period, not guarantees about future intervals. CDC’s 2025–2026 evaluation reports coverage and forecast scoring.
What the 2025–2026 evaluation can—and cannot—tell you
CDC evaluated 39 eligible models drawn from 53 unique submissions by 34 teams. Its FluSight ensemble ranked seventh overall by average relative weighted interval score (WIS) for the season across jurisdictions, excluding national forecasts. Twelve models consistently beat the baseline in every jurisdiction; 33 of the 39 evaluated models performed better than the baseline. The best individual team submission was Google_SAI-FluEns.
Free tools Windows power users keep installed
One-click scans. No signup required.
Rank #3
- ✓All-in-One Health Record Keeper – Consolidate family history, childhood illnesses, adult conditions, allergies, surgeries, and medications in one trusted place. Have your complete medical story ready for any doctor visit or emergency—no more scattered papers or missed details.
- ✓Monthly Goal Setting + Action Plans + Medication Tracker – Stay on top of your wellness with dedicated monthly pages for your top health priorities and specific actions to feel better. The daily medication/supplement log (date, name, condition, dosage, time, notes) helps you track adherence and spot what works—so you can truly manage your health day by day.
- ✓Doctor Visit Notes & Lab Test Logs for Smarter Appointments – Pre fill your questions before each visit and record answers instantly with the structured “Visit to the Doctor” pages. The lab test table (date, test, results, notes) keeps all your numbers in one place, making it easy to monitor trends and share updates with your healthcare team.
- ✓Monthly Review & Key Dates to Build Better Habits – Reflect each month on your biggest wins, actions that improved your wellbeing, and what to do better next month. Combined with the yearly important dates spread, this helps you create a continuous improvement loop for lasting health changes.
- ✓Compact A5 Format with Premium Details – Take It Anywhere – Measuring 5.8" × 8.3", with smooth 100 gsm paper that resists bleed through, a sturdy elastic closure, built in pen loop, ribbon bookmarks, and a back pocket for loose notes or test reports. Available in elegant purple and rose gold—a practical companion for yourself or a thoughtful gift for someone you care about.
Relative WIS assesses how well forecast intervals align with observed values; lower is better, and a relative WIS below 1 indicates better performance than the baseline. CDC’s rankings are specific to the 2025–2026 evaluation design, included targets and season. They do not establish that every AI model is better than statistical or mechanistic models, or that any model will perform as well in a later season.
CDC also documented misses during the late-December 2025 increase and mid-January 2026 decrease: the ensemble’s 50% and 95% prediction intervals did not anticipate those observed changes. This illustrates why a forecast should be read as conditional on the information and methods available when it was issued, especially around seasonal onset, peaks and rapid shifts.
Rank #4
- All-in-One Health Record – Consolidate family history, allergies, surgeries, and medications in one trusted place. Have your complete story ready for any doctor visit or emergency.
- Daily Medication & Supplement Tracker – Log date, name, dosage, time, and notes each day, with space for up to 3 months of daily entries. Track adherence easily and discover what works best for your health.
- Doctor Visit & Lab Logs – Pre-fill your questions before appointments and record answers instantly. Keep all lab test results organized to monitor trends and share with your care team.
- Monthly Goals & Action Reviews – Set your top health priorities each month and plan specific actions. Reflect on your wins and improvements to build better habits over time.
- Sturdy Spiral Binding & Premium Paper – A5 format (5.5" × 8.3") with smooth 100gsm paper that resists bleed-through. The spiral binding lays flat for effortless daily writing.
What “AI” means in FluSight
“AI forecast” is not one standardized model type. For the evaluation, CDC classified components as statistical, mechanistic, and/or artificial intelligence or machine learning using method descriptions supplied by forecasting teams. Those categories can overlap. The CDC ensemble is the median forecast among models designated for inclusion, combining submitted forecasts into one estimate.
Consequently, an overall ensemble rank is not a head-to-head result for a single AI system. To compare models meaningfully, consider the metric, baseline, forecast horizon, jurisdictions, submission eligibility and performance during rapid changes—not just whether a model is labeled AI.
Best Value
- The 2024 DOT Medical Examination Guide Book provides a detailed guide to the physical standards to be qualified to drive a CMV. Medical exam handbook helps you understand medical qualification and the examination process.
- Regulation Alert. The FMCSA update to its Medical Advisory Criteria (Appendix A to Part 391) and accompanying medical guidance 1/24/24. All prior versions of medical guidance have been superseded. Certified Medical Examiners use the medical guidance but are not obligated by law to follow the guidance. No physical qualification regulatory standards in 391.41(b) have changed.
- Includes. Tabbed pages for quick and easy referencing, 100+ illustrations, handouts, and addresses the regulatory side of driver wellness. Alternative vision standard 391.44 and the Insulin-treated diabetes mellitus (ITDM) rule in 391.46.
- Variety of Topics. Purpose of exam, explanation, requirements, and guidelines for exam, Medical Registry, regulations, wellness and demands placed on commercial motor drivers, forms and recordkeeping, ADA and HIPAA info, and FAQs.
- Specifications: 5” x 7" Medical Exams Handbook, English, Spiralbound. Copyright 2024.
Why a population forecast is not your personal hospitalization risk
A forecast of 1,000 weekly admissions, for example, would describe an aggregate count for a particular place and week. It would not mean that any given resident has a particular probability of admission. FluSight evaluates jurisdiction-level weekly admissions, not an individual’s health history, exposure, age, vaccination status or clinical condition.
Likewise, a state admission rate is useful as a rough population-size adjustment, not as a personalized chance of hospitalization. It should not be used as a clinical decision rule. Individual medical concerns should be discussed with a qualified healthcare professional rather than inferred from a jurisdiction-wide forecast.
Check geography and reporting before comparing places
CDC calculates state admission rates using Census Vintage 2024 population estimates. Those denominators may not match the populations served by hospitals in each state, so rates support rough comparisons rather than precise catchment-area comparisons. CDC also flags jurisdictions where fewer than 80% of hospitals reported for the most recent week; lower reporting completeness may affect forecast validity.
Before comparing two places or weeks, confirm that the chart uses the same unit and target period, then inspect reporting completeness. A change in a count or rate is harder to interpret if hospital reporting is incomplete or the population adjustment does not align with the hospital catchment.
A dated example: the final listed 2025–2026 forecast
The most recent release listed for the 2025–2026 season was issued June 11, 2026, using observations current as of May 27. For the United States, it projected 320 to 2,000 new laboratory-confirmed influenza hospital admissions for the week ending June 13, 2026, and characterized the trend as stable or uncertain. This is historical context, not an estimate for the 2026–2027 season. CDC said reporting for that season would begin again in fall 2026. Check the issue date and target week on the forecast page before treating any displayed estimate as current.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
