Back

icognition: a smartphone-based cognitive screening battery

Denissen, S.; Van Laethem, D.; Baijot, J.; Costers, L.; Descamps, A.; Van Remoortel, A.; Van Merhaegen-Wieleman, A.; D'hooghe, M. B.; D'Haeseleer, M.; Smeets, D.; Sima, D. M.; Van Schependom, J.; Nagels, G.

2023-07-23 neurology
10.1101/2023.07.19.23292824 medRxiv
Show abstract

BackgroundTelemedicine is feasible and well-accepted by people with multiple sclerosis (MS). ObjectiveThe aim of this study is to validate a smartphone-based cognitive screening battery, icognition, to faster signal cognitive deterioration. Methodsicognition consists of three tests (Symbol Test, Dot Test and visual Backwards Digit Span (vBDS)) that are equivalents of validated paper-pencil tests. These are the Symbol Digit Modalities Test (SDMT), the 10/36 Spatial Recall Test (SPART) and the auditory Backwards Digit Span (aBDS), respectively. To establish the validity of icognition, 101 people with MS and 82 healthy subjects completed all tests. 21 healthy subjects repeated testing 2 to 3 weeks later. ResultsAll tests in icognition correlate well with their paper-pencil equivalent (Symbol Test: r=.63, p<.001; Dot Test: r=.31, p=0.002; vBDS: r=.71, p<.001), negatively correlate with the Expanded Disability Status Scale (EDSS: Symbol Test: rho=-.27, p=.01; Dot Test: rho=-.29, p=.006; vBDS: rho=- .23, p=.027) and show high test-retest reliability (Symbol Test: r=.81, p<.001; Dot Test: r=.75, p<.001; vBDS: r=.84, p<.001). Test performance was not significantly different between people with MS and healthy subjects for all cognitive tests, both in icognition and their paper-pencil equivalents. Conclusionicognition is a valid and reliable tool to remotely screen for cognitive functioning in persons with MS.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.