Enise I. Incesoy
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Enise I. Incesoy has a total of 287 co-authors. Here are the top co-authors by number of shared publications:
- Jens Wiltfang
Universitätsmedizin Göttingen
17 shared publications - Josef Priller
Department of Psychiatry and Psychotherapy, Charité – Universitätsmedizin Berlin, Berlin, Germany
14 shared publications - Michael Wagner
Department of Psychiatry and Psychotherapy, University Hospital Bonn, Bonn, Germany
14 shared publications - Stefan Teipel
German Center for Neurodegenerative Diseases (DZNE), Rostock, Germany
13 shared publications - Anja Schneider
Department of Old Age Psychiatry and Cognitive Disorders, University Hospital Bonn, Bonn, Germany
12 shared publications - Annika Spottke
German Center for Neurodegenerative Diseases (DZNE), Bonn, Germany
12 shared publications
Latest Publications
- Open Access
- 17 October 2026
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- p. 1-11
Improving the fairness and robustness of deep learning classification models through bias mitigation and post hoc calibration
Purpose:: The goal of this study was to enhance the fairness and clinical applicability of deep learning models for classifying Alzheimer’s disease from structural MRI scans. To achieve this, we addressed two key challenges: age-related bias and unreliable probability estimates. Specifically, we investigated in-processing debiasing strategies to achieve age-invariant predictions while preserving diagnostic accuracy. We also systematically evaluated post hoc calibration methods to improve the reliability, interpretability, and clinical usefulness of predicted probabilities across diverse patient populations. Methods:: Structural MRI data from three independent cohorts (ADNI, AIBL, and DELCODE) were preprocessed using a standardized pipeline. Age-related bias was addressed using two in-processing strategies, adversarial training (CF-Net) and GLM-based feature residualization (PMDN), implemented in a shared 3D convolutional neural network (CNN) framework. Additionally, post hoc calibration was performed using four regression methods: logistic, probit, isotonic, and Bayesian binning. We evaluated model performance, fairness, and calibration using classification as well as calibration-specific metrics. Results:: PMDN achieved the best overall performance, with higher balanced accuracy (0.71) and improved calibration (Brier $$\approx $$ 0.22), showing substantially reduced variability compared to baseline and CF-Net. PMDN effectively removed age-related bias, achieving near-zero age prediction correlation; CF-Net, however, showed only partial and unstable debiasing. Post hoc calibration further improved probability reliability, with nonparametric methods (isotonic regression and Bayesian binning) yielding the lowest calibration errors (MCE $$\approx $$ 0.21−0.24). Conclusion:: This study shows that, although deep learning models achieve similar classification performance, they differ significantly in terms of calibration, stability, and fairness. PMDN provides more consistent and effective age bias mitigation than the CF-Net approach, particularly in clinically relevant subgroups. Post hoc calibration improves probability reliability further, with nonparametric methods achieving the best calibration.- 17 October 2026
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- p. 1-11
Open AccessImproving the fairness and robustness of deep learning classification models through bias mitigation and post hoc calibration
Purpose:: The goal of this study was to enhance the fairness and clinical applicability of deep learning models for classifying Alzheimer’s disease from structural MRI scans. To achieve this, we addressed two key challenges: age-related bias and unreliable probability estimates. Specifically, we investigated in-processing debiasing strategies to achieve age-invariant predictions while preserving diagnostic accuracy. We also systematically evaluated post hoc calibration methods to improve the reliability, interpretability, and clinical usefulness of predicted probabilities across diverse patient populations. Methods:: Structural MRI data from three independent cohorts (ADNI, AIBL, and DELCODE) were preprocessed using a standardized pipeline. Age-related bias was addressed using two in-processing strategies, adversarial training (CF-Net) and GLM-based feature residualization (PMDN), implemented in a shared 3D convolutional neural network (CNN) framework. Additionally, post hoc calibration was performed using four regression methods: logistic, probit, isotonic, and Bayesian binning. We evaluated model performance, fairness, and calibration using classification as well as calibration-specific metrics. Results:: PMDN achieved the best overall performance, with higher balanced accuracy (0.71) and improved calibration (Brier $$\approx $$ 0.22), showing substantially reduced variability compared to baseline and CF-Net. PMDN effectively removed age-related bias, achieving near-zero age prediction correlation; CF-Net, however, showed only partial and unstable debiasing. Post hoc calibration further improved probability reliability, with nonparametric methods (isotonic regression and Bayesian binning) yielding the lowest calibration errors (MCE $$\approx $$ 0.21−0.24). Conclusion:: This study shows that, although deep learning models achieve similar classification performance, they differ significantly in terms of calibration, stability, and fairness. PMDN provides more consistent and effective age bias mitigation than the CF-Net approach, particularly in clinically relevant subgroups. Post hoc calibration improves probability reliability further, with nonparametric methods achieving the best calibration. - Open Access
MRI-derived brain aging trajectories across the Alzheimer’s continuum: links to cognition, pathology and lifestyle risk factors
Background: The brain age gap (BAG), the difference between neuroimaging-predicted and chronological age, captures inter-individual variation in brain aging. Although sensitive to Alzheimer’s disease (AD) pathology, its longitudinal patterns across the clinical AD continuum and prognostic relevance remain unclear. Methods: 577 participants from the DELCODE cohort (>2,100 MRI scans) were analysed: healthy controls individuals (HC, N=202), and patients with subjective cognitive decline (SCD, N=248), mild cognitive impairment (N=93), and AD dementia (N=34). All underwent structural MRI, amyloid (Aβ 42/40 ) and phosphorylated tau181 assessment, and lifestyle-related dementia risk profiling (LIBRA). BAG was derived using brainageR. Associations with baseline cognition, cognitive decline, and clinical progression (up to eight years) were examined using mixed-effects and Cox models. Mediation analyses tested whether BAG accounted for LIBRA-cognition associations. Biomarker-related and clinical findings were replicated in ADNI (N=461). Findings: BAG showed excellent short-term reliability, increased stepwise across the clinical spectrum and was elevated in amyloid-positive SCD, but not in asymptomatic amyloid-positive HC. Longitudinal BAG increases were strongest in amyloid- and tau-positive participants (Aβ+T+). Higher BAG was associated with poorer baseline cognition and predicted cognitive decline, with strongest effects in Aβ+T+. All main findings replicated in ADNI. BAG was associated with LIBRA only in biomarker-negative participants and partly mediated associations with cognitive outcomes in DELCODE. Interpretation: BAG is a reliable non-invasive marker of structural brain health sensitive to AD pathology and to modifiable AD risk. Detectable divergence prior to objective cognitive impairment supports its relevance for early risk stratification and prevention-oriented research. Funding: Helmholtz AI Cooperation Unit (ZT-I-PF-5-163).
Open AccessMRI-derived brain aging trajectories across the Alzheimer’s continuum: links to cognition, pathology and lifestyle risk factors
Background: The brain age gap (BAG), the difference between neuroimaging-predicted and chronological age, captures inter-individual variation in brain aging. Although sensitive to Alzheimer’s disease (AD) pathology, its longitudinal patterns across the clinical AD continuum and prognostic relevance remain unclear. Methods: 577 participants from the DELCODE cohort (>2,100 MRI scans) were analysed: healthy controls individuals (HC, N=202), and patients with subjective cognitive decline (SCD, N=248), mild cognitive impairment (N=93), and AD dementia (N=34). All underwent structural MRI, amyloid (Aβ 42/40 ) and phosphorylated tau181 assessment, and lifestyle-related dementia risk profiling (LIBRA). BAG was derived using brainageR. Associations with baseline cognition, cognitive decline, and clinical progression (up to eight years) were examined using mixed-effects and Cox models. Mediation analyses tested whether BAG accounted for LIBRA-cognition associations. Biomarker-related and clinical findings were replicated in ADNI (N=461). Findings: BAG showed excellent short-term reliability, increased stepwise across the clinical spectrum and was elevated in amyloid-positive SCD, but not in asymptomatic amyloid-positive HC. Longitudinal BAG increases were strongest in amyloid- and tau-positive participants (Aβ+T+). Higher BAG was associated with poorer baseline cognition and predicted cognitive decline, with strongest effects in Aβ+T+. All main findings replicated in ADNI. BAG was associated with LIBRA only in biomarker-negative participants and partly mediated associations with cognitive outcomes in DELCODE. Interpretation: BAG is a reliable non-invasive marker of structural brain health sensitive to AD pathology and to modifiable AD risk. Detectable divergence prior to objective cognitive impairment supports its relevance for early risk stratification and prevention-oriented research. Funding: Helmholtz AI Cooperation Unit (ZT-I-PF-5-163).
- Open Access
- 29 May 2026
- Published by Elsevier in The Journal Of Prevention of Alzheimer's Disease
- Vol. 13 (8) , 100609
Subjective cognition trajectories, Alzheimer biomarkers, and incident mild cognitive impairment
- 29 May 2026
- Published by Elsevier in The Journal Of Prevention of Alzheimer's Disease
- Vol. 13 (8) , 100609
Open AccessSubjective cognition trajectories, Alzheimer biomarkers, and incident mild cognitive impairment
- Open Access
- 28 March 2026
- Published by Elsevier in The Journal Of Prevention of Alzheimer's Disease
- Vol. 13 (5) , 100544
Plasma GFAP outperforms CSF GFAP in detecting amyloid pathology and is associated with increased risk of clinical progression in early Alzheimer’s disease
- 28 March 2026
- Published by Elsevier in The Journal Of Prevention of Alzheimer's Disease
- Vol. 13 (5) , 100544
Open AccessPlasma GFAP outperforms CSF GFAP in detecting amyloid pathology and is associated with increased risk of clinical progression in early Alzheimer’s disease
- Open Access
Subjective cognition trajectories, Alzheimer biomarkers, and incident mild cognitive impairment
Background: Subjective cognitive decline (SCD) is common in older adults and may precede mild cognitive impairment (MCI). Whether longitudinal changes in self- or study partner (SP)-reported SCD improve early identification of individuals at risk for clinical progression, particularly along the Alzheimer’s disease (AD) biological continuum, remains unclear. Methods: We pooled data from two longitudinal observational cohorts (DELCODE and ADNI). Cognitively unimpaired (CU) participants were recruited through public advertisement or memory clinics and included if baseline amyloid status, ≥2 SCD assessments, and clinical follow-up were available. SCD was assessed using the Everyday Cognition questionnaire (self- and SP-report). Linear mixed-effects models examined longitudinal associations between SCD trajectories, baseline AD biomarkers, and progression to incident MCI. Multivariable Cox proportional hazards models tested whether one-year changes in SCD predicted subsequent progression. Findings: Among 770 participants (median age 69·9years [IQR 66·0–74·6]; 52·6% women; median follow-up 5·0years [4·0-7·0]), amyloid-positive individuals and those who progressed to MCI showed steeper longitudinal increases in both SCD reports. In amyloid-positive participants, only increases in SP-reported SCD differentiated progressors from non-progressors. One-year increases in SP-reported SCD predicted a higher risk of subsequent MCI compared with unchanged scores (hazard ratio 3·24 [95%CI 1·73-6·07]), with effects confined to amyloid-positive participants. Interpretation: Longitudinal increases in SP-reported cognitive difficulties, particularly over short intervals, are associated with near-term progression to MCI in amyloid-positive CU older adults. SP-based longitudinal monitoring may represent a low-burden approach to support earlier clinical surveillance in aging populations. Funding: German Center for Neurodegenerative Diseases, US National Institutes of Health.
Open AccessSubjective cognition trajectories, Alzheimer biomarkers, and incident mild cognitive impairment
Background: Subjective cognitive decline (SCD) is common in older adults and may precede mild cognitive impairment (MCI). Whether longitudinal changes in self- or study partner (SP)-reported SCD improve early identification of individuals at risk for clinical progression, particularly along the Alzheimer’s disease (AD) biological continuum, remains unclear. Methods: We pooled data from two longitudinal observational cohorts (DELCODE and ADNI). Cognitively unimpaired (CU) participants were recruited through public advertisement or memory clinics and included if baseline amyloid status, ≥2 SCD assessments, and clinical follow-up were available. SCD was assessed using the Everyday Cognition questionnaire (self- and SP-report). Linear mixed-effects models examined longitudinal associations between SCD trajectories, baseline AD biomarkers, and progression to incident MCI. Multivariable Cox proportional hazards models tested whether one-year changes in SCD predicted subsequent progression. Findings: Among 770 participants (median age 69·9years [IQR 66·0–74·6]; 52·6% women; median follow-up 5·0years [4·0-7·0]), amyloid-positive individuals and those who progressed to MCI showed steeper longitudinal increases in both SCD reports. In amyloid-positive participants, only increases in SP-reported SCD differentiated progressors from non-progressors. One-year increases in SP-reported SCD predicted a higher risk of subsequent MCI compared with unchanged scores (hazard ratio 3·24 [95%CI 1·73-6·07]), with effects confined to amyloid-positive participants. Interpretation: Longitudinal increases in SP-reported cognitive difficulties, particularly over short intervals, are associated with near-term progression to MCI in amyloid-positive CU older adults. SP-based longitudinal monitoring may represent a low-burden approach to support earlier clinical surveillance in aging populations. Funding: German Center for Neurodegenerative Diseases, US National Institutes of Health.
- Open Access
Physical fitness supports brain maintenance and cognitive reserve in cognitively normal aging: a cross-sectional examination
Background: Cognitive reserve (CR) and brain maintenance (BM) support preserved cognition by mitigating or slowing neural decline in aging. Physical fitness represents a plausible pathway to both CR and BM, yet the underlying neurobiological mechanisms remain insufficiently understood. This study examined the role of physical fitness in BM and CR by testing its associations with Alzheimer's disease related brain pathology and by assessing its moderating and mediating effects on the relationship between pathology and cognition. Methods: Data were obtained from 345 cognitively unimpaired older adults (mean age = 73.11, SD 8.03 years; 177 females) participating in the ongoing SFB1436 study. We assessed global cognition and delayed verbal memory performance, aerobic fitness (VO2max), and muscular capacity. Blood biomarkers included plasma Aβ1-42/Aβ1-40, p-tau217, and GFAP (glial fibrillary acidic protein), as well as serum BDNF (brain derived neurotrophic factor), VEGF (vascular endothelial growth factor), and Cathepsin-B (plasticity). Neuroimaging measures comprised medial temporal lobe (MTL) tau burden ([18F]PI-2620 PET), MRI-derived hippocampal volumes, white matter hyperintensities, perivascular spaces (PVS) in basal ganglia (BG) and centrum semiovale, total gray matter volume (GMV), and MTL thickness. To examine BM, we tested associations between fitness and brain pathology. To examine CR, we conducted moderation analyses assessing whether fitness attenuated the negative impact of MTL tau burden on cognition. Mediation analyses further evaluated whether hippocampal volume, total GMV, or MTL thickness mediated a potential association between fitness and cognition. All models controlled for age and sex (and education in mediation analyses), and multiple comparisons were FDR-corrected. Results: Physical fitness was not related to cognitive performance. Higher muscular capacity was associated with lower BG PVS volumes, while higher aerobic fitness was related to higher MTL thickness and total GMV. Elevated MTL tau burden was associated with poorer verbal memory performance. Although physical fitness did not significantly moderate the tau-memory relationship, model comparison indicated weak evidence for CR effects (p = .015). Conclusion: Muscular capacity was linked to lower BG PVS volumes, supporting resistance against pathology, while aerobic fitness related to preserved cortical integrity and tended to act as a CR proxy against MTL tau pathology. Physical fitness may support cerebrovascular and glymphatic function, providing weak CR-like protection against tau-related cognitive decline.
Open AccessPhysical fitness supports brain maintenance and cognitive reserve in cognitively normal aging: a cross-sectional examination
Background: Cognitive reserve (CR) and brain maintenance (BM) support preserved cognition by mitigating or slowing neural decline in aging. Physical fitness represents a plausible pathway to both CR and BM, yet the underlying neurobiological mechanisms remain insufficiently understood. This study examined the role of physical fitness in BM and CR by testing its associations with Alzheimer's disease related brain pathology and by assessing its moderating and mediating effects on the relationship between pathology and cognition. Methods: Data were obtained from 345 cognitively unimpaired older adults (mean age = 73.11, SD 8.03 years; 177 females) participating in the ongoing SFB1436 study. We assessed global cognition and delayed verbal memory performance, aerobic fitness (VO2max), and muscular capacity. Blood biomarkers included plasma Aβ1-42/Aβ1-40, p-tau217, and GFAP (glial fibrillary acidic protein), as well as serum BDNF (brain derived neurotrophic factor), VEGF (vascular endothelial growth factor), and Cathepsin-B (plasticity). Neuroimaging measures comprised medial temporal lobe (MTL) tau burden ([18F]PI-2620 PET), MRI-derived hippocampal volumes, white matter hyperintensities, perivascular spaces (PVS) in basal ganglia (BG) and centrum semiovale, total gray matter volume (GMV), and MTL thickness. To examine BM, we tested associations between fitness and brain pathology. To examine CR, we conducted moderation analyses assessing whether fitness attenuated the negative impact of MTL tau burden on cognition. Mediation analyses further evaluated whether hippocampal volume, total GMV, or MTL thickness mediated a potential association between fitness and cognition. All models controlled for age and sex (and education in mediation analyses), and multiple comparisons were FDR-corrected. Results: Physical fitness was not related to cognitive performance. Higher muscular capacity was associated with lower BG PVS volumes, while higher aerobic fitness was related to higher MTL thickness and total GMV. Elevated MTL tau burden was associated with poorer verbal memory performance. Although physical fitness did not significantly moderate the tau-memory relationship, model comparison indicated weak evidence for CR effects (p = .015). Conclusion: Muscular capacity was linked to lower BG PVS volumes, supporting resistance against pathology, while aerobic fitness related to preserved cortical integrity and tended to act as a CR proxy against MTL tau pathology. Physical fitness may support cerebrovascular and glymphatic function, providing weak CR-like protection against tau-related cognitive decline.
- Open Access
- 18 August 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 196 (Pt C) , 110829
SMAS: Structural MRI-based AD Score using Bayesian supervised VAE
- 18 August 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 196 (Pt C) , 110829
Open AccessSMAS: Structural MRI-based AD Score using Bayesian supervised VAE
- Open Access
- 20 July 2025
- Published by SAGE Publications in Journal of Alzheimer’s Disease
- Vol. 107 (1) , 154-169
Associations between digital speech features of automated cognitive tasks and trajectories of brain atrophy and cognitive decline in early Alzheimer's disease
Background: Speech-based features extracted from telephone-based cognitive tasks show promise for detecting cognitive decline in prodromal and manifest dementia. Little is known about the cerebral underpinnings of these speech features. Objective: To examine associations between speech features, brain atrophy, and longitudinal cognitive decline in individuals at risk for Alzheimer's disease (AD). Methods: Healthy volunteers, individuals with subjective cognitive decline, and those with mild cognitive impairment completed phonebot-guided semantic verbal fluency (SVF) and 15-word verbal learning task (VLT). Speech features were automatically extracted, and a global cognitive score (SB-C score) was computed. We analyzed data from 161 participants for cognitive trajectories, 141 for cross-sectional brain atrophy, and 102 for longitudinal brain changes. Analyses were conducted using multiple linear regressions, mixed-effects models, and voxel-based morphometry. Results: The SB-C score was associated with bilateral hippocampal volumes, SVF features were primarily associated with left hemisphere regions, including the inferior frontal, parahippocampal, and superior/middle temporal gyri ( p uncorr < 0.001). SB-C score, SVF correct counts, and VLT delayed recall were associated with atrophy rates in the hippocampal/parahippocampal gyrus and left middle/inferior temporal gyri ( p FDR < 0.05). These features were also associated with cognitive decline assessed via Preclinical Alzheimer's Cognitive Composite 5, SVF, and Wordlist learning delayed recall ( p FDR < 0.01). Word frequency and temporal cluster switches showed varying associations with cognitive trajectories. Other features did not show robust associations. Conclusions: In this study, we highlight the potential of digital speech features for identifying brain atrophy and cognitive decline over time in at-risk AD populations.
- 20 July 2025
- Published by SAGE Publications in Journal of Alzheimer’s Disease
- Vol. 107 (1) , 154-169
Open AccessAssociations between digital speech features of automated cognitive tasks and trajectories of brain atrophy and cognitive decline in early Alzheimer's disease
Background: Speech-based features extracted from telephone-based cognitive tasks show promise for detecting cognitive decline in prodromal and manifest dementia. Little is known about the cerebral underpinnings of these speech features. Objective: To examine associations between speech features, brain atrophy, and longitudinal cognitive decline in individuals at risk for Alzheimer's disease (AD). Methods: Healthy volunteers, individuals with subjective cognitive decline, and those with mild cognitive impairment completed phonebot-guided semantic verbal fluency (SVF) and 15-word verbal learning task (VLT). Speech features were automatically extracted, and a global cognitive score (SB-C score) was computed. We analyzed data from 161 participants for cognitive trajectories, 141 for cross-sectional brain atrophy, and 102 for longitudinal brain changes. Analyses were conducted using multiple linear regressions, mixed-effects models, and voxel-based morphometry. Results: The SB-C score was associated with bilateral hippocampal volumes, SVF features were primarily associated with left hemisphere regions, including the inferior frontal, parahippocampal, and superior/middle temporal gyri ( p uncorr < 0.001). SB-C score, SVF correct counts, and VLT delayed recall were associated with atrophy rates in the hippocampal/parahippocampal gyrus and left middle/inferior temporal gyri ( p FDR < 0.05). These features were also associated with cognitive decline assessed via Preclinical Alzheimer's Cognitive Composite 5, SVF, and Wordlist learning delayed recall ( p FDR < 0.01). Word frequency and temporal cluster switches showed varying associations with cognitive trajectories. Other features did not show robust associations. Conclusions: In this study, we highlight the potential of digital speech features for identifying brain atrophy and cognitive decline over time in at-risk AD populations.
- Open Access
- 7 July 2025
- Published by Springer Nature in GeroScience
- Vol. 48 (2) , 1853-1873
A physically and mentally active lifestyle relates to younger brain and cognitive age
Resistance to age-related pathological changes (brain maintenance), including Alzheimer’s disease, cerebrovascular disease, and neurodegeneration may promote cognitive resilience in aging. However, how lifestyle and health profiles relate to successful cognitive and brain aging remains poorly understood. In a novel, deeply phenotyped cohort of 211 cognitively unimpaired older adults (age = 71.0 ± 7.4 years, 46% female), we characterized principal components of lifestyle and health using questionnaire, fitness, and blood data. We estimated cognitive age gap (CAG) based on comprehensive neuropsychological data and brain age gap (BAG) based on brain-pathology markers, including plasma biomarkers of Alzheimer’s pathology (pTau 217 and Aβ 1-42 /Aβ 1-40 ), MRI-based measures of white matter hyperintensities, perivascular spaces, and brain atrophy. Regression analyses tested how the observed lifestyle-health profiles were related to CAG and BAG. Seven principal components explained 49% of the variance in health and lifestyle. The second component, characterized by a mentally and physically active life and low cardiovascular risk, was associated with lower CAG ( β = − 0.66, p < 0.001) and BAG ( β = − 0.52, p = 0.003), reflecting a younger-than-expected brain and cognitive age, respectively. The association of an active lifestyle and lower CAG was partially mediated by BAG. Higher CAG was also associated with other lifestyle components characterized by low mental stimulation. APOE-ε4 carriers exhibited higher BAG. In conclusion, a lifestyle combining low cardiovascular risk, high mental engagement throughout life and high physical activity/fitness is jointly associated with less-than-expected brain pathology and better-than-expected cognitive performance, supporting its involvement in brain maintenance and cognitive resilience to aging.
- 7 July 2025
- Published by Springer Nature in GeroScience
- Vol. 48 (2) , 1853-1873
Open AccessA physically and mentally active lifestyle relates to younger brain and cognitive age
Resistance to age-related pathological changes (brain maintenance), including Alzheimer’s disease, cerebrovascular disease, and neurodegeneration may promote cognitive resilience in aging. However, how lifestyle and health profiles relate to successful cognitive and brain aging remains poorly understood. In a novel, deeply phenotyped cohort of 211 cognitively unimpaired older adults (age = 71.0 ± 7.4 years, 46% female), we characterized principal components of lifestyle and health using questionnaire, fitness, and blood data. We estimated cognitive age gap (CAG) based on comprehensive neuropsychological data and brain age gap (BAG) based on brain-pathology markers, including plasma biomarkers of Alzheimer’s pathology (pTau 217 and Aβ 1-42 /Aβ 1-40 ), MRI-based measures of white matter hyperintensities, perivascular spaces, and brain atrophy. Regression analyses tested how the observed lifestyle-health profiles were related to CAG and BAG. Seven principal components explained 49% of the variance in health and lifestyle. The second component, characterized by a mentally and physically active life and low cardiovascular risk, was associated with lower CAG ( β = − 0.66, p < 0.001) and BAG ( β = − 0.52, p = 0.003), reflecting a younger-than-expected brain and cognitive age, respectively. The association of an active lifestyle and lower CAG was partially mediated by BAG. Higher CAG was also associated with other lifestyle components characterized by low mental stimulation. APOE-ε4 carriers exhibited higher BAG. In conclusion, a lifestyle combining low cardiovascular risk, high mental engagement throughout life and high physical activity/fitness is jointly associated with less-than-expected brain pathology and better-than-expected cognitive performance, supporting its involvement in brain maintenance and cognitive resilience to aging.
- Open Access
- 25 May 2025
- Published by SAGE Publications in Journal of Alzheimer’s Disease
- Vol. 108 (1_suppl) , S118-S131
Speech-based digital cognitive assessments for detection of mild cognitive impairment: Validation against paper-based neurocognitive assessment scores
Background: Cognitive decline in Alzheimer's disease (AD) often includes speech impairments, where subtle changes may precede clinical dementia onset. As clinical trials focus on early identification of patients for disease-modifying treatments, digital speech-based assessments for scalable screening have become crucial. Objective: This study aimed to validate a remote, speech-based digital cognitive assessment for mild cognitive impairment (MCI) detection through the comparison with gold-standard paper-based neurocognitive assessments. Methods: Within the PROSPECT-AD project, speech and clinical data were obtained from the German DELCODE and DESCRIBE cohorts, including 21 healthy controls (HC), 110 participants with subjective cognitive decline (SCD), and 59 with MCI. Spearman rank and partial correlations were computed between speech-based scores and clinical measures. Kruskal-Wallis tests assessed group differences. We trained machine learning models to classify diagnostic groups comparing classification accuracies between gold-standard assessment scores and a speech-based digital cognitive assessment composite score (SB-C). Results: Global cognition, as measured by SB-C, significantly differed between diagnostic groups ( H (2) = 30.93, p < 0.001). Speech-based scores were significantly correlated with global anchor scores (MMSE, CDR, PACC5). Speech-based composites for memory, executive function and processing speed were also correlated with respective domain-specific paper-based assessments. In logistic regression classification, the model combining SB-C and neuropsychological tests at baseline achieved a high discriminatory power in differentiating HC/SCD from MCI patients (Area Under the Curve = 0.86). Conclusions: Our findings support speech-based cognitive assessments as a promising avenue towards remote MCI screening, with implications for scalable screening in clinical trials and healthcare.
- 25 May 2025
- Published by SAGE Publications in Journal of Alzheimer’s Disease
- Vol. 108 (1_suppl) , S118-S131
Open AccessSpeech-based digital cognitive assessments for detection of mild cognitive impairment: Validation against paper-based neurocognitive assessment scores
Background: Cognitive decline in Alzheimer's disease (AD) often includes speech impairments, where subtle changes may precede clinical dementia onset. As clinical trials focus on early identification of patients for disease-modifying treatments, digital speech-based assessments for scalable screening have become crucial. Objective: This study aimed to validate a remote, speech-based digital cognitive assessment for mild cognitive impairment (MCI) detection through the comparison with gold-standard paper-based neurocognitive assessments. Methods: Within the PROSPECT-AD project, speech and clinical data were obtained from the German DELCODE and DESCRIBE cohorts, including 21 healthy controls (HC), 110 participants with subjective cognitive decline (SCD), and 59 with MCI. Spearman rank and partial correlations were computed between speech-based scores and clinical measures. Kruskal-Wallis tests assessed group differences. We trained machine learning models to classify diagnostic groups comparing classification accuracies between gold-standard assessment scores and a speech-based digital cognitive assessment composite score (SB-C). Results: Global cognition, as measured by SB-C, significantly differed between diagnostic groups ( H (2) = 30.93, p < 0.001). Speech-based scores were significantly correlated with global anchor scores (MMSE, CDR, PACC5). Speech-based composites for memory, executive function and processing speed were also correlated with respective domain-specific paper-based assessments. In logistic regression classification, the model combining SB-C and neuropsychological tests at baseline achieved a high discriminatory power in differentiating HC/SCD from MCI patients (Area Under the Curve = 0.86). Conclusions: Our findings support speech-based cognitive assessments as a promising avenue towards remote MCI screening, with implications for scalable screening in clinical trials and healthcare.