Evaluation of FluSight influenza forecasting in the 2021-22 and 2022-23 seasons with a new target laboratory-confirmed influenza hospitalizations.
Sarabeth M MathisAlexander E WebberTomás M LeónErin L MurrayMonica SunLauren A WhiteLogan C BrooksAlden GreenAddison J HuDaniel J McDonaldRoni RosenfeldDmitry ShemetovRyan J TibshiraniSasikiran KandulaSen PeiJeffrey L ShamanRami YaariTeresa K YamanaPulak AgarwalSrikar BalusuGautham GururajanHarshavardhan KamarthiB Aditya PrakashRishi RamanAlexander RodríguezZhiyuan ZhaoAkilan MeiyappanShalina OmarPrasith BaccamHeidi L GurungSteve A StageBrad T SuchoskiMarco AjelliAllisandra G KummerMaria LitvinovaPaulo C VenturaSpencer WadsworthJarad NiemiErica CarcelenAlison L HillSung-Mok JungJoseph Chadi LemaitreJustin LesslerSara L LooClifton D McKeeKoji SatoClaire P SmithShaun A TrueloveThomas C McAndrewWenxuan YeNikos BosseWilliam S HlavacekYen Ting LinAbhishek MallelaYe ChenShelby M LammJaechoul LeeRichard G PosnerAmanda C PerofskyCecile ViboudLeonardo ClementeFred LuAustin G MeyerMauricio SantillanaMatteo ChinazziJessica T DavisKunpeng MuAna Pastore Y PionttiAlessandro VespignaniXinyue XiongMichal Ben-NunPete RileyJames A TurtleChis Hulme-LoweShakeel JessaV P NagrajStephen D TurnerDesiree WilliamsAvranil BasuJohn M DrakeSpencer J FoxGraham C GibsonEhsan SuezEdward W ThommesMonica G CojocaruEstee Y CramerAaron GerdingAriane StarkEvan L RayNicholas G ReichLi ShandrossNutcha WattanachitYijin WangMartha W ZornMajd Al AawarAjitesh SrivastavaLauren A MeyersAniruddha AdigaBenjamin HurtGursharn KaurBryan Leroy LewisPrashant RangarajanSrinivasan VenkatramananPatrick ButlerAndrew FarabowNikhil MuralidharNaren RamakrishnanCarrie ReedMatthew BiggerstaffRebecca K BorcheringPublished in: medRxiv : the preprint server for health sciences (2023)
Accurate forecasts can enable more effective public health responses during seasonal influenza epidemics. Forecasting teams were asked to provide national and jurisdiction-specific probabilistic predictions of weekly confirmed influenza hospital admissions for one through four weeks ahead for the 2021-22 and 2022-23 influenza seasons. Across both seasons, 26 teams submitted forecasts, with the submitting teams varying between seasons. Forecast skill was evaluated using the Weighted Interval Score (WIS), relative WIS, and coverage. Six out of 23 models outperformed the baseline model across forecast weeks and locations in 2021-22 and 12 out of 18 models in 2022-23. Averaging across all forecast targets, the FluSight ensemble was the 2 nd most accurate model measured by WIS in 2021-22 and the 5 th most accurate in the 2022-23 season. Forecast skill and 95% coverage for the FluSight ensemble and most component models degraded over longer forecast horizons and during periods of rapid change. Current influenza forecasting efforts help inform situational awareness, but research is needed to address limitations, including decreased performance during periods of changing epidemic dynamics.