This study leverages a modernized digital version of a well-known cognitive screening tool to examine pre and post operative cognitive function after surgery in adults age 65 years or more. Machine learning algorithms will be applied to the hospital wide standard of care cognitive metric to identify risk for post-operative cognitive complications.
This proposal innovatively leverages a brief but informative digital test with machine learning to examine the subtlety of pre-surgery cognition within an extremely large number of older individuals screened preoperatively within an academic tertiary medical center. It also incorporates a unique group of well characterized non-surgery peers for demographic matching to assist with normal versus abnormal machine learning analyses.
Study Type
OBSERVATIONAL
Enrollment
25,240
The digital testing is hypothesized to identify latent features for differentiating cognitively impaired presurgical patient subgroups
UF Health
Gainesville, Florida, United States
Control and pre-surgery differences between digital behaviors
Measure range of digital outcome differences
Time frame: up to one year
Predictive validity of digital behaviors on outcome
Digital tools will predict clinician reported events
Time frame: up to 1 year
Change over time in digital behavior between groups
Surgery group and control group differences from baseline to 6-weeks
Time frame: up to 6-weeks
Change over time in digital behavior between groups
Surgery group and control group differences from baseline to 3-months
Time frame: up to 3-months
Change over time in digital behavior between groups
Surgery group and control group differences from baseline to one year
Time frame: up to one year
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.