Seek
Generic filters
Filter by input type
Select all
News
Pages
Events
Filter by category
Select all
AI ANALYTICS
Mobile Apps and Internet of Things
Advancement of science
big data
Connected communities
Coronavirus
Courses and training
DIAGNOSIS
Initial Editorial
Editorials
A world in the cloud
Events
Infographics
Artificial Intelligence and Science
IoT Apps
News
Digital platforms
Social networks
Review of scientific publications
Course Summary
Synopsis of essay
Overview of reference frames
Synopsis of recent publications
Use of Digital Platforms
Seek
Generic filters
Filter by input type
Select all
News
Pages
Events
Filter by category
Select all
AI ANALYTICS
Mobile Apps and Internet of Things
Advancement of science
big data
Connected communities
Coronavirus
Courses and training
DIAGNOSIS
Initial Editorial
Editorials
A world in the cloud
Events
Infographics
Artificial Intelligence and Science
IoT Apps
News
Digital platforms
Social networks
Review of scientific publications
Course Summary
Synopsis of essay
Overview of reference frames
Synopsis of recent publications
Use of Digital Platforms

Machine learning models show vital signs associated with severe cases of COVID-19

New research showed machine learning-based risk models indicating vital signs, lab test results, and age as factors associated with severe cases of COVID-19.

Magazine Scientific Reports of Nature, published the article “Risk factors for severe COVID-19 differ by age in hospitalized adults,” which used machine learning-based risk models to find that vital signs, lab test results, and age , were correlated with the level of complication of the COVID-19 infection.

The study analyzed data from 6,906 adults who were hospitalized for COVID-19, in five US states. In this sense, they developed risk models to predict the use of mechanical ventilation or the death of the patient between the first day and the 56th day of hospitalization.

In total, five machine learning models were trained for the study for a population of all ages and for two other subpopulations of different ages, 18 years or older and older than 50 years. Furthermore, risk models were trained using readily available clinical data.

In this way, the reference data available one hour after the admission of adult patients to the hospital, as well as the first positive test for COVID-19, were used, which were vital for the prediction of critical illnesses between the first day and 56 days later, as mentioned above.

“The models revealed differences in the statistical significance and relative predictive value of risk factors between older and younger patients, including age, BMI, vital signs, and laboratory results,” the study explained.

Likewise, variables such as gender and chronic comorbidities in hospitalized patients had a lower predictive value for the models than variables such as vital signs and laboratory results.

Another key finding of the research was that vital signs and laboratory results at admission were more important for prediction than the presence of comorbidities. Similarly, age-stratified models showed that the importance of the risk factor differs between young adults and older adults.

You can read the full investigation at the following link:

https://www.nature.com/articles/s41598-022-10344-3

Last Tweets

Digital Health Events

2022 October

Semana 1

Mon 26
tue 27
wed 28
Thu 29
Fri 30
Sat 1
Sun 2
Mon 3
tue 4
wed 5
Thu 6
Fri 7
Sat 8
Sun 9
Mon 10
tue 11
wed 12
Thu 13
Fri 14
Sat 15
Sun 16
Mon 17
tue 18
wed 19
Thu 20
Fri 21
Sat 22
Sun 23
Mon 24
tue 25
wed 26
Thu 27
Fri 28
Sat 29
Sun 30
Mon 31
tue 1
wed 2
Thu 3
Fri 4
Sat 5
Sun 6

Share

Digital Health in the world

  • — Science Brief: Omicron (B.1.1.529) Variant/CDC updates
    See more
  • —Coronavirus resource center/Johns Hopkins
    See more
  • — Epidemiological tracing of COVID-19 contacts / Johns Hopkins Course
    See more
  • — SARS-CoV-2 infection behavior / FCS calculator
    See more
  • — Omicron SARS-CoV-2 variant: a new chapter in the COVID-19 pandemic/ Article The Lancet
    See more
  • —Genomic Epidemiology Tracker/GISAID
    See more
  • — Mexican Genomic Surveillance Consortium
    See more