Related Experiment Video
Updated: Mar 24, 2026
Assessment of Age-related Changes in Cognitive Functions Using EmoCogMeter, a Novel Tablet-computer Based Approach
Published on: February 14, 2014
Streamlining Eligibility Assessment for Alzheimer's Disease-Modifying Therapies: Prediction of MMSE Scores Using the
Ali Jannati1,2, Claudio Toro-Serey2, Marissa Ciesla2
1Department of Neurology, Harvard Medical School, 25 Shattuck Street, Boston, MA, 02115 USA.
Introduction:
The eligibility of anti-amyloid disease-modifying therapies (DMTs) and their integration into clinical practice in some institutions requires a specific range of Mini-Mental State Examination (MMSE) scores. Reliance on this pencil-and-paper psychometric instrument imposes operational burdens and risks perpetuating health disparities due to the test's known educational and cultural biases. This study evaluates the efficacy of the Digital Clock and Recall (DCR™) - a rapid, FDA-listed digital cognitive assessment - to crosswalk to MMSE scores using machine learning, thereby offering a faster, scalable, and equitable mechanism for patient triage.
Methods:
We conducted a retrospective analysis using data from the multi-site Bio-Hermes-001 study (NCT04733989, N=945). Participants were clinically classified as cognitively unimpaired, mild cognitive Impairment, or probable Alzheimer's dementia. We trained a Poisson elastic net regression model using age and multimodal digital features derived from the DCR (including drawing kinematics and voice acoustics) to predict MMSE scores. The model was tested for generalizability using an independent external validation cohort from the Apheleia study (NCT05364307, N=238).
Results:
The machine learning model predicted MMSE scores with a root mean squared error (RMSE) of 2.31 in the training cohort. This error margin falls within the established test-retest reliability range of the manual MMSE itself (2-4 points), suggesting the prediction is statistically non-inferior to human administration. External validation in the Apheleia cohort demonstrated robust generalizability (RMSE = 2.62). Crucially, the model exhibited demographic fairness, maintaining consistent accuracy across Race (White RMSE = 2.34; Non-White RMSE = 2.14) and Ethnicity (Hispanic RMSE = 2.26; Non-Hispanic RMSE = 2.31).
Discussion:
Machine learning can leverage multimodal features from the DCR to accurately and equitably crosswalk to MMSE scores in support of current guidelines, transforming a time-intensive manual test into a rapid, automated assessment. By deploying this "digital triage" engine, where traditional assessments are still used for DMT eligibility, healthcare systems can streamline the identification of DMT-eligible patients, reduce specialist referral bottlenecks, and ensure that access to life-altering therapies is determined by pathology rather than demography.
Insights
A new digital cognitive assessment, the Digital Clock and Recall (DCR™), can accurately predict Mini-Mental State Examination (MMSE) scores using machine learning. This offers a faster, more equitable alternative for assessing eligibility for anti-amyloid therapies.
Area of Science:
- Neuroscience
- Artificial Intelligence
- Medical Technology
Background:
- Anti-amyloid disease-modifying therapies (DMTs) require specific Mini-Mental State Examination (MMSE) scores for eligibility.
- The traditional MMSE is a paper-based test with operational burdens and potential health disparities due to educational and cultural biases.
- A digital alternative is needed for faster, scalable, and equitable patient triage.
Purpose of the Study:
- To evaluate the efficacy of the Digital Clock and Recall (DCR™) in crosswalking to MMSE scores using machine learning.
- To develop a rapid, automated assessment tool for patient triage.
- To offer a scalable and equitable mechanism for assessing DMT eligibility.
Main Methods:
- Retrospective analysis of 945 participants from the Bio-Hermes-001 study (NCT04733989).
- Classification of participants into cognitively unimpaired, mild cognitive impairment, or probable Alzheimer's dementia.
- Training a Poisson elastic net regression model using DCR multimodal digital features (drawing kinematics, voice acoustics) and age to predict MMSE scores.
- External validation using 238 participants from the Apheleia study (NCT05364307).
Main Results:
- The machine learning model predicted MMSE scores with a root mean squared error (RMSE) of 2.31 in the training cohort, comparable to MMSE test-retest reliability.
- External validation demonstrated robust generalizability with an RMSE of 2.62.
- The model showed demographic fairness, with consistent accuracy across different racial and ethnic groups.
Conclusions:
- Machine learning applied to DCR multimodal features can accurately and equitably predict MMSE scores.
- This digital triage approach transforms a time-intensive manual test into a rapid, automated assessment.
- Deploying this digital triage can streamline patient identification for DMT eligibility, reduce bottlenecks, and promote equitable access to therapies.
