Early prediction of mastery of a computerized functional skills training program in participants with mild cognitive impairment.

BACKGROUND: Cognition in MCI has responded poorly to pharmacological interventions, leading to use of computerized training. Combining computerized cognitive training (CCT) and functional skills training software (FUNSAT) produced improvements in 6 functional skills in MCI, with effect sizes >0.75. However, 4% of HC and 35% of MCI participants failed to master all 6 tasks. We address early identification of characteristics that identify participants who do not graduate, to improve later interventions. METHODS: NC participants (n = 72) received FUNSAT and MCI (n = 92) participants received FUNSAT alone or combined FUNSAT and CCT on a fully remote basis. Participants trained twice a week for up to 12 weeks. Participants "graduated" each task when they made one or fewer errors on all 3-6 subtasks per task. Tasks were no longer trained after graduation. RESULTS: Between-group comparisons of graduation status on baseline completion time and errors found that failure to graduate was associated with more baseline errors on all tasks but no longer completion times. A discriminant analysis found that errors on the first task (Ticket purchase) uniquely separated the groups, F = 41.40, p < .001, correctly classifying 94% of graduators. An ROC analysis found an AUC of .83. MOCA scores did not increase classification accuracy. CONCLUSIONS: More baseline errors, but not completion times, predicted failure to master all FUNSAT tasks. Accuracy of identification of eventual mastery was exceptional. Detection of risk to fail to master training tasks is possible in the first 15 minutes of the baseline assessment. This information can guide future enhancements of computerized training.

Computerized Cognitive and Skills Training in Older People With Mild Cognitive Impairment: Using Ecological Momentary Assessment to Index Treatment-Related Changes in Real-World Performance of Technology-Dependent Functional Tasks.

OBJECTIVES: Cognitive and functional skills training improves skills and cognitive test performance, but the true test of efficacy is real-world transfer. We trained participants with mild cognitive impairment (MCI) or normal cognition (NC) for up to 12 weeks on six technology-related skills using remote computerized functional skills assessment and training (FUNSAT) software. Using ecological momentary assessment (EMA), we measured real-world performance of the technology-related skills over 6 months and related EMA-identified changes in performance to training gains. DESIGN: Randomized clinical trial with post-training follow-up. SETTING: A total of 14 Community centers in New York City and Miami. PARTICIPANTS: Older adults with normal cognition (n = 72) or well-defined MCI (n = 92), ranging in age from 60 to 90, primarily female, and racially and ethnically diverse. INTERVENTION: Computerized cognitive and skills training. MEASUREMENTS: EMA surveys measuring trained and untrained functional skills 3 or more days per week for 6 months and training gains from baseline to end of training. RESULTS: Training gains in completion times across all 6 tasks were significant (p <0.001) for both samples, with effect sizes more than 1.0 SD for all tasks. EMA surveys detected increases in performance for both trained (p <0.03) and untrained (p <0.001) technology-related skills for both samples. Training gains in completion times predicted increases in performance of both trained and untrained technology-related skills (all p <0.001). CONCLUSIONS: Computerized training produces increases in real-world performance of important technology-related skills. These gains continued after the end of training, with greater gains in MCI participants.