AI-Enhanced Mobile APP to Aid in Early Detection of Cognitive Impairment

Charisse Litchman¹*, Larry Rubin¹, Caroline Stowe⁵, Charlotte Rubin³, Sydney Chatfield⁴ and Sharon Stoll²

¹BeCareLink, LLC, USA
²Stoll Medical Group, USA
³Chicago Medical School at Rosalind Franklin University, USA
⁴NYU Langone School of Medicine, USA
⁵George Mason University, School of Public Health, USA

*Corresponding Author: Charisse Litchman, BeCareLink, LLC, USA.

Received: October 30, 2025; Published: November 14, 2025

Abstract

Importance: The diagnosis of Alzheimer’s disease (AD) often relies on a “rule out” approach, yielding only a 60% accuracy rate [1]. Recent studies have shown that AI-based assessments can outperform traditional clinical testing in predicting disease progression [2]. With advancements in diagnostic tools for early cognitive impairment, there is a critical need for an accessible screening method to detect pre-clinical changes and improve patient outcomes. Digital technologies combined with artificial intelligence (AI) offer a novel strategy for early detection [3,4].

Objective: To determine the utility of a novel, currently available remote quantified neurologic assessment of cognitive and neurologic function on a mobile phone app in detecting cognitive impairment.

Design, Setting, and Participants: This cohort study of screening tests examined BeCare Neuro App data collected from user-reported symptoms and quantitative measures of neurologic function via quantified activities and questionnaires. The app assesses cognition across four domains using tasks similar to comprehensive in-clinic neuropsychological exams, reporting performance against normative scores of time and accuracy metrics [5,6]. tasks include: the “Cognitive Test” (decoding messages by pairing symbols with letters), the “Stroop Test” (naming the color of displayed words), the “Memory Test” (recalling a disappearing animal), and the “Tap Test” (tapping randomly appearing coins). The participants included users with subjective complaints of memory loss and/or cognitive impairment and users with neurologic complaints other than cognitive impairment.

Results: Data from sixty-five users who reported “cognitive” or “memory loss” and 212 users who did not report “cognitive” or “memory loss” and who completed all tests was analyzed. Users reporting cognitive impairment consistently scored in the bottom third of the population. Specifically, 90.8% (59/65) had at least one activity in the bottom third, 66.2% (43/65) had two or more, and 30.8% had three or more activities in that range. In contrast, users not complaining of memory loss or cognitive impairment, 21.7% (46/212) had at least one test in the bottom third, 9.0% (19/212) had two or more. and 2.4% (5/212) had three or more.

Conclusions and Relevance: The BeCare Neuro App demonstrates potential as a screening tool for early cognitive impairment, identifying patients who require further evaluation. Given the recent advances in new treatments for early-stage AD, early detection will greatly affect patient outcomes [7]. The expense of standard of care diagnostic tools and the rapidly increasing prevalence of AD makes an inexpensive, effective, and accessible screening tool such as BeCare Neuro App invaluable.

Keywords: Alzheimer’s Disease (AD); Artificial Intelligence (AI)

References

1. “2022 Alzheimer’s disease facts and figures”. Alzheimer’s and Dementia 4 (2022): 700-789.
2. Liz Yuanxi Lee., et al. "Robust and interpretable AI-guided marker for early dementia prediction in real-world clinical settings”. EClinicalMedicine 102725 (2024): 102725-102725.
3. Ali R., et al. "A self-training deep neural network for early prediction of cognitive deficits in very preterm infants using brain functional connectome data”. Pediatric Radiology 11 (2022): 2227-2240.
4. Pahar M., et al. "CognoSpeak: an Automatic, Remote Assessment of Early Cognitive Decline in Real-World Conversational Speech”. In (2025): 1-7.
5. Fristed E., et al. "A remote speechbased AI system to screen for early Alzheimer’s disease via smartphones”. Alzheimer’s and Dementia1 (2022): e12366.
6. Quek LJ., et al. "Use of artificial intelligence techniques for detection of mild cognitive impairment: A systematic scoping review. Journal of Clinical Nursing17-18 (2023): 5752-5762.
7. Chu C., et al. "Development and Validation of a Tool to Predict Onset of Mild Cognitive Impairment and Alzheimer Dementia”. JAMA Network Open1 (2025): e2453756.
8. Rasmussen J and Langerman H. “Alzheimer’s Disease – Why We Need Early Diagnosis”. Degenerative Neurological and Neuromuscular Disease 9 (2019): 123-130.
9. Rosenberg PB and Lkyetsos C. “Mild Cognitive impairment: Searching for the Prodrome of Alzheimer’s Disease”. World Psychiatry 2 (2008): 72-78.
10. Petersen RC. “Mild Cognitive Impairment. CONTINUUM: Lifelong Learning in Neurology 2 (2016): 404-418.
11. S. Census Bureau. “Population Estimates Program”. PEP Vintage 2019 Population and Housing Unit Estimates. Published online (2019).
12. Alzheimer's Association. “2025 Alzheimer’s Disease Facts and Figures”. Alzheimer’s and Dementia4 (2021).
13. Lin CC., et al. "Geographic Variation in Neurologist Density and Neurologic Care in the United States”. Neurology3 (2020): e309-e321.
14. Reiter-Campeau S and Moore F. “The Role of the Neurological Examination in Primary Care Referrals to Neurology”. The Canadian Journal of Neurological sciences Le Journal Canadien Des Sciences Neurologiques 6 (2022): 922-924.
15. Prince M., et al. "World Alzheimer Report 2011”. Alzheimer’s Disease International (ADI) (2011).
16. Rao A and Eaton R. “Dementia Neurology Deserts and Long-Term Care Insurance Claims Experience in the United States: How Does Limited Supply of Neurology Specialists Correlate with Claims Experience Data?” Society of Actuaries (2021).
17. Beyer L., et al. "Amyloid‐beta misfolding and GFAP predict risk of clinical Alzheimer’s disease diagnosis within 17 years”. Alzheimer’s and Dementia3 (2022): 1020-1028.
18. Francisco de A., et al. "Automatic detection of cognitive impairment in elderly people using an entertainment chatbot with Natural Language Processing capabilities”. Journal of Ambient Intelligence and Humanized Computing 12 (2023): 16283-16298.
19. Haghayegh Shahab., et al. "Predicting future risk of developing cognitive impairment using ambulatory sleep EEG: Integrating univariate analysis and multivariate information theory approach”. Journal of Alzheimer’s Disease (2025):
20. Li H and Fan Y. “Early prediction of Alzheimer’s disease dementia based on baseline Hippocampal MRI and 1-Year Follow-Up Cognitive Measures Using Deep Recurrent Neural Networks”. 2019 IEEE 16th International Symposium on Biomedical Imaging ISBI 2019). (2019): 368-371.
21. Benedict RH., et al. "Validity of the Symbol Digit Modalities Test as a cognition performance outcome measure for multiple sclerosis”. Multiple Sclerosis Journal5 (1997): 721-733.
22. MacLeod CM. “Half a century of research on the Stroop effect: An integrative review”. Psychological Bulletin2 (1991): 163-203.
23. Hall JB., et al. "Feasibility of Using a Novel, Multimodal Motor Function Assessment Platform with Machine Learning to Identify Individuals with Mild Cognitive Impairment”. Alzheimer Disease and Associated Disorders 4 (2024): 344-350.
24. Civitarese G., et al. "The SERENADE Project: SensorBased Explainable Detection of Cognitive Decline”. (2025).
25. Liew TM., et al. "PENSIEVE-AI a brief cognitive test to detect cognitive impairment across diverse literacy”. Nature Communications 1 (2025).
26. Shakespeare R., et al. "Retinal vasculometry associations with cognition status in UK Biobank”. Alzheimer’s and Dementia1 (2025): e270087.
27. Nasreddine Ziad S., et al. "The Montreal Cognitive Assessment, MoCA: A Brief Screening Tool For Mild Cognitive Impairment”. Journal of the American Geriatrics Society 4 (2025): 695-699.
28. Sperling RA., et al. "Toward defining the preclinical stages of Alzheimer’s disease: Recommendations from the National Institute on Aging Alzheimer’s Association workgroups on diagnostic guidelines for Alzheimer’s disease”. Alzheimer’s and Dementia3 (2011): 280-292.
29. Filardi M., et al. "The Relationship Between Muscle Strength and Cognitive Performance Across Alzheimer’s Disease Clinical Continuum”. Frontiers in Neurology 13 (2022):
30. Camicioli R., et al. "Motor slowing precedes cognitive impairment in the oldest old”. Neurology 5 (1998): 1496-1498.
31. Hebert LE., et al. "Upper and Lower Extremity Motor Performance and Functional Impairment in Alzheimer’s Disease”. American Journal of Alzheimer’s Disease and Other Dementiasry 5 (2025): 425-431.
32. Panwar D., et al. "Role of Artificial Intelligence in Cognitive Assessment and Early Detection of Alzheimer’s Disease”. In (2024): 190-210.
33. Insel TR. “Digital Phenotyping: Technology for a New Science of Behavior”. JAMA 13 (2017): 1215-1216.
34. Babulal Ganesh M., et al. "Perspectives on ethnic and racial disparities in Alzheimer’s disease and related dementias: Update and areas of immediate need”. Alzheimer’s and Dementia2 (2019): 292-312.
35. Ghosh S. “Alzheimer’s Therapeutics Market Share Analysis”. Future Market Insights (2025).
36. Torous J., et al. "New Tools for New Research in Psychiatry: A Scalable and Customizable Platform to Empower Data Driven Smartphone Research. JMIR Mental Health 2 (2016): e16.
37. Cummings J., et al. "Alzheimer’s disease drug development pipeline: 2021”. Alzheimer’s and Dementia1 (2021): e12179.
38. Lee LY., et al. "Robust and interpretable AIguided marker for early dementia prediction in realworld clinical settings”. eClinicalMedicine 74 (2024).
39. Wang D and Agapito G. “Editorial: Multi-omics approaches in the study of human disease mechanisms”. Frontiers in Bioinformatics 4 (2025).

Citation

Citation: Charisse Litchman., et al. “AI-Enhanced Mobile APP to Aid in Early Detection of Cognitive Impairment".Acta Scientific Neurology 8.12 (2025): 34-43.

Copyright

Copyright: © 2025 Charisse Litchman., et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.