Early Detection of Clinical Deterioration in Patients With COVID-19 Using Machine Learning

• Conditions: Covid19
• Interventions: Other: Machine learning; Other: Machine based evaluation

• Registration Number: NCT04828915
• Lead Sponsor: University Hospital Tuebingen

Brief Summary

The aim of this study is to use artificial intelligence in the form of machine learning analysing vital signs as well as symptoms of patients suffering from Covid19 to identify predictors of disease progression and severe course of disease.

Detailed Description

Not available

Study Timeline

• Status Verified: 2021-01
• Study Start: 2021-02-01
• Study First Submitted: 2021-03-24
• Study First Submitted QC: 2021-03-30
• Last Update Submitted: 2021-03-30
• Study First Posted: 2021-04-02
• Last Update Posted: 2021-04-02
• Primary Completion: 2021-07-31
• Study Completion: 2021-12-31

Recruitment & Eligibility

• Status: UNKNOWN
• Sex: All
• Target Recruitment: 1000

Inclusion Criteria

• Written informed consent
• Age >= 18 years
• Detection of SARS-CoV2 within the past 5 days

Exclusion Criteria

• Inability to measure vital parameters and document symptoms

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Arm && Interventions

Group	Intervention	Description
Training cohort	Machine learning	Randomly selection of 80% of the study population. The machine learning algorithm is trained on this dataset
Validation cohort	Machine based evaluation	Randomly selection of 20% of the study population. The machine learning algorithm which was trained on the basis of the training data cohort is validated on the validation cohort.

Primary Outcome Measures

Name	Time	Method
Probability of Participants for Hospitalisation or Fatal Outcome	Detection of severe acute respiratory syndrome- Corona Virus 2 (SARS-CoV2) to recovery, hospitalisation or fatal outcome up to 5 weeks

Secondary Outcome Measures

Name	Time	Method
Probability of Participants for Intensive Care Unit Admission	Detection of SARS-CoV2 to recovery, hospitalisation or fatal outcome up to 5 weeks
Prediction of persisting health impairment by using standardized questionnaires	Detection of SARS-CoV2 to recovery, hospitalisation or fatal outcome up to 5 weeks
Detection of symptoms, vital parameters and comorbidities predicting clinical course	Detection of SARS-CoV2 to recovery, hospitalisation or fatal outcome up to 5 weeks
Influence of different virus variants on the course of disease/ clinical outcome	Detection of SARS-CoV2 to recovery, hospitalisation or fatal outcome up to 5 weeks
Influence of SARS-CoV2 vaccination (yes/no) on the course of disease/ clinical outcome	Detection of SARS-CoV2 to recovery, hospitalisation or fatal outcome up to 5 weeks
Probability of Participants for Fatal Outcome	Detection of SARS-CoV2 to recovery, hospitalisation or fatal outcome up to 5 weeks
Evaluation of parameters (symptoms, vital parameters, comorbidities) according to their potential of clinical course predictions	Detection of SARS-CoV2 to recovery, hospitalisation or fatal outcome up to 5 weeks
Influence of different SARS-CoV2 vaccines on the course of disease/ clinical outcome	Detection of SARS-CoV2 to recovery, hospitalisation or fatal outcome up to 5 weeks
Influence of size of training data set	Detection of SARS-CoV2 to recovery, hospitalisation or fatal outcome up to 5 weeks
Influence of viral load on the course of disease/ clinical outcome	Detection of SARS-CoV2 to recovery, hospitalisation or fatal outcome up to 5 weeks
Probability of Participants for hospitalisation	Detection of SARS-CoV2 to recovery, hospitalisation or fatal outcome up to 5 weeks

Trial Locations

Locations (1)

University Hospital of Tuebingen; 🇩🇪 Tuebingen, Germany