AI vs. traditional scores: which better predicts COVID-19 ICU outcomes?
NCT ID NCT06795880
First seen Aug 11, 2026 · Last updated Aug 12, 2026 · Updated 1 time
Summary
This study will use artificial intelligence to analyze data from 400 COVID-19 patients treated in intensive care units. The goal is to see if machine learning models, including deep learning, can predict which patients are most likely to die from the disease. The AI's performance will be compared with traditional scoring systems to determine if it offers greater accuracy and reliability. If successful, this approach could help doctors make more informed decisions for critically ill patients.
What this could mean
Our plain-language read of the trial. This is informational only, not medical advice or a prediction.
- What this could lead to
- If successful, this could lead to AI tools that help doctors predict which COVID-19 ICU patients are at highest risk, potentially improving care and resource allocation.
- What could go wrong
- This is a retrospective analysis, not a prospective trial, so results may not apply to future patients. AI models can also be biased or overfit to the data they are trained on, and their accuracy needs validation in real-world settings.
This is an AI summary of the original study and may miss details. Read our disclaimer.
Study facts
What this study's own registry entry says, in plain language.
- Participants
-
400 people
The number who actually took part.
- Started
-
Apr 2020
- Finished
-
Mar 2026
- Lead sponsor
-
A government agency
The lead sponsor is a government body.
Who can take part
This study's own entry requirements. Only the study team can say for certain whether you qualify.
Who is studied
An artificial intelligence-based analysis will be performed using retrospective data of patients treated in adult intensive care due to COVID-19.The dataset will include various parameters such as demographic information, laboratory results, vital signs, and clinical history.Among the ML models, logistic regression, support vector machines (SVM), decision trees, and deep learning techniques (e.g., artificial neural networks) will be used. The performance of the models will be compared with traditional scoring systems.
- Ages
-
18 years and older
- Sex
-
Anyone
- Healthy volunteers
-
Not accepted
This study is not open to healthy volunteers. The entry requirements below say who it is open to.
Show the full entry requirements Hide the full entry requirements
Copied word for word from the study's registry entry, so the wording is the study team's rather than ours.
Inclusion Criteria: * All patients diagnosed with Covid-19 in the anesthesia and reanimation adult intensive care unit Exclusion Criteria: * Participants who do not meet the inclusion criteria stated above will be excluded from the study.
Get updates
Get notified about this study
Sign up to get updates when this study changes or when new studies for COVID -19 are added.
Genom att skicka in godkänner du våra Användarvillkor
Conditions
The condition(s) this trial relates to.
As listed by the trial registrant
The condition terms exactly as the trial's registrant entered them.
Contacts and locations
Locations
-
Kocaeli City Hospital
İzmit, Kocaeli, 41060, Turkey (Türkiye)
More trials for these conditions
Other studies related to the condition(s) this trial covers.
- Home antibody tests put to the test: can you read your own COVID-19 result?
- Can lung ultrasound reveal COVID-19's signature in the lungs?
- When the immune system Can't fight back: tracking three respiratory viruses
- The household maze: how does COVID-19 move between family members?
- Can an oral drug stop COVID-19 from turning deadly?
- Can COVID-19 rapid tests slip into HIV and TB clinics without disrupting care?