- ICH GCP
- Amerikanska kliniska prövningsregistret
- Klinisk prövning NCT07825012
External Validation of the FedHist Dynamic Early Warning Model for Mortality Risk in Critically Ill Patients: A Prospective Multicenter Study
The purpose of this study is to assess how accurately FedHist, an artificial intelligence model, predicts the risk of death in critically ill patients. Patients in intensive care units (ICUs) can become worse quickly. Updating risk estimates as new clinical information becomes available may help identify patients at higher risk. FedHist uses routinely collected clinical information to estimate a patient's risk of dying in the ICU within the next 24 hours. These estimates are updated every 6 hours.
This study will evaluate FedHist prospectively across several hospitals. The model will be integrated into hospital clinical information systems, and its predictions will be compared with observed patient outcomes. The study aims to determine whether FedHist provides accurate predictions across hospitals with different patient populations and clinical practices.
Studieöversikt
Detaljerad beskrivning
Critically ill patients can deteriorate rapidly, creating a need for timely and repeated assessment of mortality risk. Conventional severity assessments, including the Acute Physiology and Chronic Health Evaluation II (APACHE II) and Sequential Organ Failure Assessment (SOFA) scores, provide clinically useful information. However, risk assessments based on data from defined assessment periods may not fully capture evolving clinical trajectories. Models that incorporate longitudinal clinical data may support more frequent assessment of short-term mortality risk.
Artificial intelligence offers opportunities to integrate clinical information collected over time for dynamic risk prediction. However, models developed using data from a single center or database may perform differently in other settings. Differences in patient characteristics, disease severity, measurement frequency, and clinical workflows can affect predictive performance. Privacy requirements, data governance policies, and institutional control over data also limit the pooling of patient records for conventional centralized model development.
FedHist was developed using a federated learning framework incorporating electronic health records from more than 250,000 critically ill patients across five countries and regions. This framework enabled collaborative model development while raw patient data remained at the contributing institutions. FedHist generates an updated estimate of the risk of ICU death within the next 24 hours at 6-hour intervals.
Previous evaluations showed a macro-averaged area under the receiver operating characteristic curve (AUROC) of 0.893 in internal validation. AUROCs were 0.881 in the NWICU external validation cohort and 0.961 in the prospective CDIC cohort. FedHist outperformed the corresponding locally trained models. When only 10% of the development data at each site were used, its performance approached or exceeded that of local models trained on the full development datasets. These findings support further prospective evaluation following integration into routine clinical information systems across multiple hospitals.
This prospective multicenter study will externally validate the previously developed FedHist model in participating ICUs. The model will be integrated into local clinical information systems to generate risk estimates using prospectively collected clinical data. Predictions will be compared with observed ICU outcomes to assess performance in predicting death within the subsequent 24 hours. The study will evaluate predictive performance across participating hospitals and assess the generalizability of FedHist under routine clinical conditions.
Studietyp
Inskrivning (Beräknad)
Kontakter och platser
Studiekontakt
- Namn: hui chen
- Telefonnummer: +86-18006138640
- E-post: huichen.icu@gmail.com
Deltagandekriterier
Urvalskriterier
Åldrar som är berättigade till studier
- Vuxen
- Äldre vuxen
Tar emot friska volontärer
Testmetod
Studera befolkning
Beskrivning
Inclusion Criteria:
- Admission to a participating ICU
Exclusion Criteria:
- Age younger than 18 years.
- Expected ICU length of stay shorter than 24 hours.
- Refusal to provide written informed consent.
Studieplan
Hur är studien utformad?
Designdetaljer
Vad mäter studien?
Primära resultatmått
Resultatmått |
Åtgärdsbeskrivning |
Tidsram |
|---|---|---|
|
ICU mortality
Tidsram: From ICU admission to ICU discharge or 90 days after ICU admission, whichever occurs first.
|
The proportion of patients who die from any cause during the ICU stay, with follow-up capped at 90 days after ICU admission.
For patients whose ICU stay exceeds 90 days, vital status at day 90 will be used to determine the mortality outcome.
|
From ICU admission to ICU discharge or 90 days after ICU admission, whichever occurs first.
|
Samarbetspartners och utredare
Sponsor
Studieavstämningsdatum
Studera stora datum
Studiestart (Beräknad)
Primärt slutförande (Beräknad)
Avslutad studie (Beräknad)
Studieregistreringsdatum
Först inskickad
Först inskickad som uppfyllde QC-kriterierna
Första postat (Faktisk)
Uppdateringar av studier
Senaste uppdatering publicerad (Faktisk)
Senaste inskickade uppdateringen som uppfyllde QC-kriterierna
Senast verifierad
Mer information
Termer relaterade till denna studie
Andra studie-ID-nummer
- 2026ZDSYLL335-P01
Plan för individuella deltagardata (IPD)
Planerar du att dela individuella deltagardata (IPD)?
Läkemedels- och apparatinformation, studiedokument
Studerar en amerikansk FDA-reglerad läkemedelsprodukt
Studerar en amerikansk FDA-reglerad produktprodukt
Denna information hämtades direkt från webbplatsen clinicaltrials.gov utan några ändringar. Om du har några önskemål om att ändra, ta bort eller uppdatera dina studieuppgifter, vänligen kontakta register@clinicaltrials.gov. Så snart en ändring har implementerats på clinicaltrials.gov, kommer denna att uppdateras automatiskt även på vår webbplats .