This content will become publicly available on June 25, 2025
Title: Prediction of Alzheimer's disease progression within 6 years using speech: A novel approach leveraging language models
AbstractINTRODUCTION
Identification of individuals with mild cognitive impairment (MCI) who are at risk of developing Alzheimer's disease (AD) is crucial for early intervention and selection of clinical trials.
METHODS
We applied natural language processing techniques along with machine learning methods to develop a method for automated prediction of progression to AD within 6 years using speech. The study design was evaluated on the neuropsychological test interviews ofn = 166 participants from the Framingham Heart Study, comprising 90 progressive MCI and 76 stable MCI cases.
RESULTS
Our best models, which used features generated from speech data, as well as age, sex, and education level, achieved an accuracy of 78.5% and a sensitivity of 81.1% to predict MCI‐to‐AD progression within 6 years.
DISCUSSION
The proposed method offers a fully automated procedure, providing an opportunity to develop an inexpensive, broadly accessible, and easy‐to‐administer screening tool for MCI‐to‐AD progression prediction, facilitating development of remote assessment.
Highlights
Voice recordings from neuropsychological exams coupled with basic demographics can lead to strong predictive models of progression to dementia from mild cognitive impairment.
The study leveraged AI methods for speech recognition and processed the resulting text using language models.
The developed AI‐powered pipeline can lead to fully automated assessment that could enable remote and cost‐effective screening and prognosis for Alzehimer's disease.
Automated computational assessment of neuropsychological tests would enable widespread, cost‐effective screening for dementia.
Methods
A novel natural language processing approach is developed and validated to identify different stages of dementia based on automated transcription of digital voice recordings of subjects’ neuropsychological tests conducted by the Framingham Heart Study (n= 1084). Transcribed sentences from the test were encoded into quantitative data and several models were trained and tested using these data and the participants’ demographic characteristics.
Results
Average area under the curve (AUC) on the held‐out test data reached 92.6%, 88.0%, and 74.4% for differentiating Normal cognition from Dementia, Normal or Mild Cognitive Impairment (MCI) from Dementia, and Normal from MCI, respectively.
Discussion
The proposed approach offers a fully automated identification of MCI and dementia based on a recorded neuropsychological test, providing an opportunity to develop a remote screening tool that could be adapted easily to any language.
Alzheimer's disease (AD) initiates years prior to symptoms, underscoring the importance of early detection. While amyloid accumulation starts early, individuals with substantial amyloid burden may remain cognitively normal, implying that amyloid alone is not sufficient for early risk assessment.
METHODS
Given the genetic susceptibility of AD, a multi‐factorial pseudotime approach was proposed to integrate amyloid imaging and genotype data for estimating a risk score. Validation involved association with cognitive decline and survival analysis across risk‐stratified groups, focusing on patients with mild cognitive impairment (MCI).
RESULTS
Our risk score outperformed amyloid composite standardized uptake value ratio in correlation with cognitive scores. MCI subjects with lower pseudotime risk score showed substantial delayed onset of AD and slower cognitive decline. Moreover, pseudotime risk score demonstrated strong capability in risk stratification within traditionally defined subgroups such as early MCI, apolipoprotein E (APOE) ε4+ MCI,APOEε4– MCI, and amyloid+ MCI.
DISCUSSION
Our risk score holds great potential to improve the precision of early risk assessment.
Highlights
Accurate early risk assessment is critical for the success of clinical trials.
A new risk score was built from integrating amyloid imaging and genetic data.
Our risk score demonstrated improved capability in early risk stratification.
Hippocampal hyperactivity is a hallmark of prodromal Alzheimer's disease (AD) that predicts progression in patients with amnestic mild cognitive impairment (aMCI). AGB101 is an extended‐release formulation of levetiracetam in the dose range previously demonstrated to normalize hippocampal activity and improve cognitive performance in aMCI. The HOPE4MCI study was a 78‐week trial to assess the progression of MCI due to AD. As reported in Mohs et al., the decline in the Clinical Dementia Rating Sum of Boxes score (CDR‐SB) was reduced by 40% in apolipoprotein E (APOE) ε4 non‐carriers over the 78‐week duration of the study with a negligible effect in carriers. Here we report an exploratory analysis of the effects of AGB101 on neuroimaging and biomarker measures in the 44APOEε4 non‐carriers who completed the 78‐week protocol.
Methods
Structural magnetic resonance imaging scans obtained at baseline and after 78 weeks were analyzed using the Automated Segmentation of Hippocampal Subfields software providing volume measures of key structures of the medial temporal lobe relevant to AD progression. Blood samples collected at 78 weeks in the study were analyzed for plasma biomarkers.
Results
Treatment with AGB101 significantly reduced atrophy of the left entorhinal cortex (ERC) compared to placebo. This reduction in atrophy was correlated with less decline in the CDR‐SB score over 78 weeks and with lower neurofilament light chain (NfL), a marker of neurodegeneration.
Discussion
The HOPE4MCI study showed thatAPOEε4 non‐carriers treated with AGB101 demonstrated a substantially more favorable treatment effect compared to carriers. Here we report that treatment with AGB101 in non‐carriers ofAPOEε4 significantly reduced atrophy of the left ERC over 78 weeks. That reduction in atrophy was closely coupled with the change in CDR‐SB and with plasma NfL indicative of neurodegeneration in the brain. These exploratory analyses are consistent with a reduction in neurodegeneration inAPOEε4 non‐carriers treated with AGB101 before a clinical diagnosis of dementia.
Highlights
AGB101 slows entorhinal cortex (ERC) atrophy in apolipoprotein E (APOE) ε4 non‐carriers with mild cognitive impairment (MCI) due to Alzheimer's disease (AD).
Slowing ERC atrophy by AGB101 is associated with less Clinical Dementia Rating Sum of Boxes decline.
Slowing ERC atrophy by AGB101 is associated with lower neurofilament light chain.
AGB101 treatment reduces neurodegeneration inAPOEε4 non‐carriers with MCI due to AD.
Identifying mild cognitive impairment (MCI) patients at risk for dementia could facilitate early interventions. Using electronic health records (EHRs), we developed a model to predict MCI to all‐cause dementia (ACD) conversion at 5 years.
METHODS
Cox proportional hazards model was used to identify predictors of ACD conversion from EHR data in veterans with MCI. Model performance (area under the receiver operating characteristic curve [AUC] and Brier score) was evaluated on a held‐out data subset.
RESULTS
Of 59,782 MCI patients, 15,420 (25.8%) converted to ACD. The model had good discriminative performance (AUC 0.73 [95% confidence interval (CI) 0.72–0.74]), and calibration (Brier score 0.18 [95% CI 0.17–0.18]). Age, stroke, cerebrovascular disease, myocardial infarction, hypertension, and diabetes were risk factors, while body mass index, alcohol abuse, and sleep apnea were protective factors.
DISCUSSION
EHR‐based prediction model had good performance in identifying 5‐year MCI to ACD conversion and has potential to assist triaging of at‐risk patients.
Highlights
Of 59,782 veterans with mild cognitive impairment (MCI), 15,420 (25.8%) converted to all‐cause dementia within 5 years.
Electronic health record prediction models demonstrated good performance (area under the receiver operating characteristic curve 0.73; Brier 0.18).
Age and vascular‐related morbidities were predictors of dementia conversion.
Synthetic data was comparable to real data in modeling MCI to dementia conversion.
Key Points
An electronic health record–based model using demographic and co‐morbidity data had good performance in identifying veterans who convert from mild cognitive impairment (MCI) to all‐cause dementia (ACD) within 5 years.
Increased age, stroke, cerebrovascular disease, myocardial infarction, hypertension, and diabetes were risk factors for 5‐year conversion from MCI to ACD.
High body mass index, alcohol abuse, and sleep apnea were protective factors for 5‐year conversion from MCI to ACD.
Models using synthetic data, analogs of real patient data that retain the distribution, density, and covariance between variables of real patient data but are not attributable to any specific patient, performed just as well as models using real patient data. This could have significant implications in facilitating widely distributed computing of health‐care data with minimized patient privacy concern that could accelerate scientific discoveries.
In the Alzheimer’s disease (AD) continuum, the prodromal state of mild cognitive impairment (MCI) precedes AD dementia and identifying MCI individuals at risk of progression is important for clinical management. Our goal was to develop generalizable multivariate models that integrate high-dimensional data (multimodal neuroimaging and cerebrospinal fluid biomarkers, genetic factors, and measures of cognitive resilience) for identification of MCI individuals who progress to AD within 3 years. Our main findings were i) we were able to build generalizable models with clinically relevant accuracy (~93%) for identifying MCI individuals who progress to AD within 3 years; ii) markers of AD pathophysiology (amyloid, tau, neuronal injury) accounted for large shares of the variance in predicting progression; iii) our methodology allowed us to discover that expression ofCR1(complement receptor 1), an AD susceptibility gene involved in immune pathways, uniquely added independent predictive value. This work highlights the value of optimized machine learning approaches for analyzing multimodal patient information for making predictive assessments.
Amini, Samad, Hao, Boran, Yang, Jingmei, Karjadi, Cody, Kolachalama, Vijaya B, Au, Rhoda, and Paschalidis, Ioannis C. Prediction of Alzheimer's disease progression within 6 years using speech: A novel approach leveraging language models. Retrieved from https://par.nsf.gov/biblio/10527249. Alzheimer's & Dementia . Web. doi:10.1002/alz.13886.
Amini, Samad, Hao, Boran, Yang, Jingmei, Karjadi, Cody, Kolachalama, Vijaya B, Au, Rhoda, & Paschalidis, Ioannis C. Prediction of Alzheimer's disease progression within 6 years using speech: A novel approach leveraging language models. Alzheimer's & Dementia, (). Retrieved from https://par.nsf.gov/biblio/10527249. https://doi.org/10.1002/alz.13886
Amini, Samad, Hao, Boran, Yang, Jingmei, Karjadi, Cody, Kolachalama, Vijaya B, Au, Rhoda, and Paschalidis, Ioannis C.
"Prediction of Alzheimer's disease progression within 6 years using speech: A novel approach leveraging language models". Alzheimer's & Dementia (). Country unknown/Code not available: Wiley. https://doi.org/10.1002/alz.13886.https://par.nsf.gov/biblio/10527249.
@article{osti_10527249,
place = {Country unknown/Code not available},
title = {Prediction of Alzheimer's disease progression within 6 years using speech: A novel approach leveraging language models},
url = {https://par.nsf.gov/biblio/10527249},
DOI = {10.1002/alz.13886},
abstractNote = {Abstract INTRODUCTIONIdentification of individuals with mild cognitive impairment (MCI) who are at risk of developing Alzheimer's disease (AD) is crucial for early intervention and selection of clinical trials. METHODSWe applied natural language processing techniques along with machine learning methods to develop a method for automated prediction of progression to AD within 6 years using speech. The study design was evaluated on the neuropsychological test interviews ofn = 166 participants from the Framingham Heart Study, comprising 90 progressive MCI and 76 stable MCI cases. RESULTSOur best models, which used features generated from speech data, as well as age, sex, and education level, achieved an accuracy of 78.5% and a sensitivity of 81.1% to predict MCI‐to‐AD progression within 6 years. DISCUSSIONThe proposed method offers a fully automated procedure, providing an opportunity to develop an inexpensive, broadly accessible, and easy‐to‐administer screening tool for MCI‐to‐AD progression prediction, facilitating development of remote assessment. HighlightsVoice recordings from neuropsychological exams coupled with basic demographics can lead to strong predictive models of progression to dementia from mild cognitive impairment.The study leveraged AI methods for speech recognition and processed the resulting text using language models.The developed AI‐powered pipeline can lead to fully automated assessment that could enable remote and cost‐effective screening and prognosis for Alzehimer's disease.},
journal = {Alzheimer's & Dementia},
publisher = {Wiley},
author = {Amini, Samad and Hao, Boran and Yang, Jingmei and Karjadi, Cody and Kolachalama, Vijaya B and Au, Rhoda and Paschalidis, Ioannis C},
}
Warning: Leaving National Science Foundation Website
You are now leaving the National Science Foundation website to go to a non-government website.
Website:
NSF takes no responsibility for and exercises no control over the views expressed or the accuracy of
the information contained on this site. Also be aware that NSF's privacy policy does not apply to this site.
