AI flu forecasts combine surveillance data to estimate future activity, but there is no single standard recipe. CDC’s FluSight challenge forecasts weekly flu-related hospital admissions—not every infection—and participating models may use different data and methods. The results can help public-health planners prepare, but reporting delays, changing surveillance signals and sudden shifts in flu activity can make forecasts wrong.
What data do AI flu forecasting models use?
Start with the distinction between a forecast’s target—the outcome it tries to predict—and its input data. In CDC’s current FluSight challenge, the target is weekly flu-related hospital admissions reported through the National Healthcare Safety Network (NHSN). NHSN replaced FluSurv-NET as the basis for hospitalization forecasts in the 2021–2022 season; CDC said NHSN could provide a more complete picture of U.S. flu hospitalizations. For the 2025–2026 evaluation, target data came from NHSN and data.cdc.gov. CDC’s Flu Forecasting overview explains the program and its purpose.
As an Amazon Associate I earn from qualifying purchases.
That target is not a direct count of all flu infections. It is a measure of hospital admissions, and other signals can help a model estimate where admissions are heading.
FluSight’s scope is short-term and location-specific
For the 2025–2026 U.S. season, FluSight forecasts covered the current week through three weeks ahead at the national, state, Puerto Rico and Washington, D.C. levels. This is a limited-horizon forecast of hospital admissions, not an individual diagnosis or a prediction of every infection. CDC describes forecasting as a complement to surveillance: surveillance measures flu activity as it occurs, while forecasts can help planners look ahead to changes such as increases in hospitalizations.
#1 Best Overall
- FDA Authorized 15-Minute Flu A&B, COVID Test Kit: Over-the-counter flu and COVID test for home use with rapid results in just 15 minutes.
- Made for Ages 2 and Above; Parents Can Stop Guessing: Quickly identify whether you or your kids are dealing with coronavirus or influenza A & B. Adult-collection is required for those aged 2-13 years, and self-collection by individuals aged 14 years and older.
- Same Ease-of-Use; Get 3 Results in 1 Test: Utilizing the familiar 4 user-friendly steps of at-home COVID tests, you can now get all 3 results for COVID-19 and Flu A & B at once with 5 drops of sample.
- Fast and Convenient COVID and Flu Tests for Home: Use this COVID and influenza rapid test kit in the comfort of your home. Bypass the need for a doctor's visit and protect your loved ones from potential exposure to contagious illnesses at school, work, or public gatherings.
- Compact Design for On-the-Go Testing: Stay safe wherever you go with our COVID-19, Flu A & B 3-in-1 self-test. Its compact design ensures easy storage and convenient portability for your travel bag.
Inputs vary from model to model
CDC classifies FluSight submissions as statistical, mechanistic, AI/machine-learning or ensemble models; categories can overlap. Models do not all use the same inputs. Some rely on the target’s own history, while others combine it with additional indicators.
One documented example is Flusion, a particular model rather than a template for all AI flu forecasting. It combined three signals:
Rank #2
- FDA Authorized 15-Minute Flu A&B, COVID Test Kit: Over-the-counter flu and COVID test for home use with rapid results in just 15 minutes.
- Made for Ages 2 and Above; Parents Can Stop Guessing: Quickly identify whether you or your kids are dealing with coronavirus or influenza A & B. Adult-collection is required for those aged 2-13 years, and self-collection by individuals aged 14 years and older.
- Same Ease-of-Use; Get 3 Results in 1 Test: Utilizing the familiar 4 user-friendly steps of at-home COVID tests, you can now get all 3 results for COVID-19 and Flu A & B at once with 5 drops of sample.
- Fast and Convenient COVID and Flu Tests for Home: Use this COVID and influenza rapid test kit in the comfort of your home. Bypass the need for a doctor's visit and protect your loved ones from potential exposure to contagious illnesses at school, work, or public gatherings.
- Compact Design for On-the-Go Testing: Stay safe wherever you go with our COVID-19, Flu A & B 3-in-1 self-test. Its compact design ensures easy storage and convenient portability for your travel bag.
- NHSN hospital admissions;
- ILI+, an estimate of the share of outpatient doctor visits in which the patient has influenza; and
- laboratory-confirmed influenza hospitalization rates from a selected group of healthcare facilities.
Flusion used gradient-boosted quantile-regression models alongside a Bayesian autoregressive model. Its multi-signal gradient-boosting models were trained jointly across locations. The peer-reviewed Flusion study describes this specific approach.
Do these 3 things before closing this tab:
1Repair Windows errors before they cause bigger problems2Fix the driver behind crashes, sound loss and screen glitches3Clear out junk files and repair common Windows errorsEmergency-department visits are a separate surveillance signal
CDC also uses emergency-department data from the National Syndromic Surveillance Program (NSSP) in its estimates of respiratory-disease transmission trends, or Rt. That is distinct from FluSight’s hospitalization target. The Rt method assumes emergency-department visits represent a consistent fraction of new infections over time. CDC notes that this relationship may change when disease severity, access to care or care-seeking behavior changes. CDC’s explanation of its epidemic-trend tools details the approach.
Rank #3
- 3-In-1 Flu A B And COVID-19 Test Kit: Designed to check for multiple respiratory targets in one test, allowing users to complete a single test instead of using separate kits at home.
- Simple At-Home Testing Process: Step-by-step format with nasal swab, buffer tube, and test cassette designed for straightforward use during everyday situations when testing is needed.
- Quick Results In About 10 Minutes: Provides results in a short timeframe, making it a convenient Covid home test to use before travel, or gatherings.
- Designed For Family Use Ages 2 And Up: Suitable for a wide range of users, including adults and children, making it a practical option for shared household use.
- Compact Single-Test Kit For On-Demand Use: The portable design on these covid tests allows for easy storage in a drawer, bag, or travel kit for quick access when needed.
Older challenges used other data, too
A CDC-hosted review of FluSight challenges from 2013–14 through 2017–18 reported that most participants used combinations of historical flu data, Twitter, Google Flu Trends and weather data. These are examples from earlier challenges, not evidence that all current models use those sources.
Why can flu forecasts be wrong?
Reports arrive late or incomplete
A forecast can only use the information available when it is produced. In a multiyear U.S. assessment of seasonal influenza forecasts, reporting delays were strongly and negatively associated with forecast accuracy in some regions. The study also identified timely, accessible traditional and newer data as an ongoing need. If recent observations are delayed or incomplete, a model may be working from an outdated picture of activity.
Rank #4
- 3-in-1 Multiplex Detection: Detects SARS-CoV-2, Influenza A, and Influenza B antigens from a single anterior nasal swab sample.
- Designed for Symptomatic Testing: Intended for individuals experiencing symptoms of respiratory infection within the first 5 days of symptom onset.
- Simple Nasal Swab Collection: Uses a short anterior nasal swab sample with step-by-step instructions included in the kit.
- Fast Results in 10 Minutes: Provides results in approximately 10 minutes when used according to the instructions for use.
- 10 minute accuracy —why wait 15? With our rapid testing kit, get peace of mind in 10 minutes and precise results without the extra wait. Proven higher PPA than major competitors, based on IFUs.
A surveillance proxy can stop tracking infections consistently
Many signals measure contact with the health system rather than infections directly. CDC’s Rt approach, for example, depends on emergency-department visits maintaining a consistent relationship to new infections. A change in care-seeking, access or disease severity can disrupt that relationship. The same general caution applies when interpreting outpatient visits, laboratory-confirmed admissions or hospital reports: each captures a different part of the health system, and changes in observation or reporting practices can affect what the data represent.
The Tool Desk
Outbyte Driver Updater FREEScan for outdated or missing drivers - takes under a minuteDriver Scan →Outbyte PC Repair FREEClear out junk files and repair common Windows errorsFree Scan →Sudden rises and falls are especially difficult
CDC’s 2025–2026 evaluation found that the FluSight ensemble’s 50% and 95% prediction intervals did not anticipate the late-December 2025 rise and mid-January 2026 decline in hospitalizations. The ensemble had its lowest interval coverage around the national and most common jurisdictional peak and the steep decline. CDC cautions that even ensembles that have been among the most accurate forecasting approaches may not reliably predict rapid changes in disease trends, including increases at season onset and changes at the peak.
Best Value
- Comprehensive 3-in-1 Test: The INDICAID COVID-flu test combo is a convenient way to detect COVID-19, Flu A, and Flu B. Everything you need is in this test home kit. It’s a must-have over-the-counter solution for anyone experiencing cold and flu symptoms.
- Fast, Reliable Results: This rapid influenza and COVID home test kit gives you 3 results in just 10 minutes, and it’s incredibly easy to use. All it requires is a shallow nasal swab, and the test can be completed in four simple steps. No more guessing!
- Trusted Technology: This flu and COVID test kit at home is FDA 510(k)-cleared, ensuring high-quality and accurate results. The combo test uses the same technology as COVID-19 rapid tests and can detect multiple COVID-19 and Flu A&B variants and strains.
- Versatile Use: The INDICAID COVID and flu test kit comes in a compact package, perfect for travel, school, work, and home. It’s also family-friendly. Individuals ages 14 and over can self-check, while children ages 2-14 require adult assistance.
- Extended Shelf Life: The shelf life of the INDICAID COVID-19/Flu A and Flu B Rapid Antigen Test has been extended to 16 months and is regularly extending. Simply scan the QR code on the box to find out the tests’ expiry date. Made in the USA.
Longer horizons and unusual seasons add uncertainty
Historical findings should not be mistaken for a measurement of current-season performance, but they illustrate recurring challenges. A CDC-hosted 2020 review reported that forecast skill in earlier challenges was highest one week ahead and declined at two, three and four weeks; skill also declined around peak flu activity. It noted that atypical seasons—for example, seasons with unusually high severity or a late peak—can be harder to forecast because past seasons may be less relevant.
A high ranking is not a guarantee for every place or week
CDC’s 2025–2026 evaluation included 39 models in its analysis from 53 contributed models and 34 teams. The CDC FluSight ensemble ranked seventh overall by average relative weighted interval score across the season for jurisdictions excluding the national level; 33 of the 39 analyzed models beat the baseline. Those season-wide results do not mean a model will get every peak, location or rapid turn right. A good average score can coexist with a specific miss.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.How to read a flu forecast responsibly
Use forecasts as probabilistic planning support, not certainty. When comparing forecasts or interpreting a published result, check:
Quick wins for a faster PC:
Scan for outdated or missing drivers - takes under a minuteDriver Scan →Clear out junk files and repair common Windows errorsFree Scan →- Target: Is it predicting hospital admissions, outpatient illness, or another measure?
- Place and horizon: Which jurisdiction does it cover, and how many weeks ahead is the estimate?
- Uncertainty: Does it provide prediction intervals, and how often have those intervals covered observed outcomes?
- Data and timeliness: Which surveillance signals does it use, and are recent reports likely to be delayed or incomplete?
- Evaluation: What season, metric and baseline are used? CDC’s 2025–2026 evaluation reports relative weighted interval score (relative WIS); a value below 1 means the forecast performed better than the baseline on that metric.
CDC’s current-season results and historical studies answer different questions and use different targets or scoring setups. Compare results only with their season, geography, horizon and metric in view. For background on the multiyear U.S. assessment and its findings on reporting delays, see Reich et al.’s 2019 study.
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.
