Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 84 of the 88 references it cites were found in a registry or an index; 20 of the 40 sources its claims cite were checked for support.

AI-based differential diagnosis of dementia etiologies on multimodal data

Open access

Published version of a preprint

Abstract

Differential diagnosis of dementia remains a challenge in neurology due to symptom overlap across etiologies, yet it is crucial for formulating early, personalized management strategies. Here, we present an artificial intelligence (AI) model that harnesses a broad array of data, including demographics, individual and family medical history, medication use, neuropsychological assessments, functional evaluations and multimodal neuroimaging, to identify the etiologies contributing to dementia in individuals. The study, drawing on 51,269 participants across 9 independent, geographically diverse datasets, facilitated the identification of 10 distinct dementia etiologies. It aligns diagnoses with similar management strategies, ensuring robust predictions even with incomplete data. Our model achieved a microaveraged area under the receiver operating characteristic curve (AUROC) of 0.94 in classifying individuals with normal cognition, mild cognitive impairment and dementia. Also, the microaveraged AUROC was 0.96 in differentiating the dementia etiologies. Our model demonstrated proficiency in addressing mixed dementia cases, with a mean AUROC of 0.78 for two co-occurring pathologies. In a randomly selected subset of 100 cases, the AUROC of neurologist assessments augmented by our AI model exceeded neurologist-only evaluations by 26.25%. Furthermore, our model predictions aligned with biomarker evidence and its associations with different proteinopathies were substantiated through postmortem findings. Our framework has the potential to be integrated as a screening tool for dementia in clinical settings and drug trials. Further prospective studies are needed to confirm its ability to improve patient care.

Overview

CoChat Summary

## TL;DR

This study presents a transformer-based multimodal AI model for differential diagnosis of dementia etiologies, trained and tested across 9 cohorts with 51,269 participants. It achieved strong performance for cognitive-status classification and dementia-etiology prediction, and AI-augmented clinician assessments outperformed clinician-only assessments.

## Key findings

  • Across 51,269 participants from 9 cohorts, the model identified 10 dementia etiologies and classified normal cognition (NC), mild cognitive impairment (MCI), and dementia with microaveraged AUROC 0.94 and AUPR 0.90.
  • For differentiating dementia etiologies, the model achieved microaveraged AUROC 0.96 and AUPR 0.70; weighted-average AUROC/AUPR were 0.94/0.73, and macroaveraged AUROC/AUPR were 0.91/0.36.
  • In mixed dementia cases, performance varied by co-occurring pathologies, with AUROC ranging from 0.63 to 0.97 and the LBD+PSY combination performing best; the paper reports a mean AUROC of 0.78 for two co-occurring pathologies.
  • AI-augmented clinician assessments improved diagnostic performance versus clinicians alone, with a mean AUROC increase of 26.25% and mean AUPR increase of 73.23% for neurologists; for neuroradiologists, the average increase was 16.19% in AUROC and 41.79% in AUPR.

## Methods

  • Multimodal transformer model using demographics, medical/family history, medications, neuropsychological tests, functional assessments, and MRI; imaging was embedded with Swin UNETR and fed to a downstream transformer with random feature masking and label masking to handle missingness.
  • Training data came from 9 cohorts: NACC, ADNI, NIFD, PPMI, AIBL, OASIS, 4RTNI, LBDSU, and FHS; the paper reports 51,269 participants total, including 19,849 NC, 9,357 MCI, and 22,063 dementia cases.
  • Main analysis used ROC/PR curves and micro-, macro-, and weighted-average AUC/AUPR, plus subgroup analyses by age, gender, and race; model outputs were also compared with biomarkers, neuropathology, CatBoost baselines, and clinician ratings.

## Limitations

  • The paper states that generalizability across diverse populations and clinical settings remains uncertain because the dataset was predominantly White.
  • The paper states that performance may vary outside NACC, including on ADNI and FHS, and that the data were imbalanced toward AD, which may bias recognition of less common etiologies.
  • Evident from the text: some etiologies were harder to assess because of limited features and uncertain or inconsistent labels, and the model collapsed mild, moderate, and severe dementia into one category rather than staging severity.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1038/s41591-024-03118-z

Cites

84 of 84 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Figures

Fig. 1 Data, model architecture and modeling strategy. a, Our model for differential dementia diagnosis was developed using diverse data modalities, including individual-level demographics, health history, neurological testing, physical/neurological exams and multisequence MRI scans. These data sources whenever available were aggregated from nine independent cohorts: 4RTNI, ADNI, AIBL, FHS, LBDSU, NACC, NIFD, OASIS and PPMI (Tables 1 and S1). For model training, we merged data from NACC, AIBL, PPMI, NIFD, LBDSU, OASIS and 4RTNI. We used a subset of the NACC dataset for internal testing. For external validation, we utilized the ADNI and FHS cohorts. b, A transformer served as the scaffold for the model. Each feature was processed into a fixed-length vector using a modality-specific embedding (emb.) strategy and fed into the transformer as input. A linear layer was used to connect the transformer with the output prediction layer. c, A subset of the NACC testing dataset was randomly chosen to conduct a comparative analysis between neurologists' performance augmented with the AI model and their performance without AI assistance. Similarly, we carried out comparative evaluations with practicing neuroradiologists, who were provided with a randomly selected sample of confirmed dementia cases from the NACC testing cohort, to assess the impact of AI augmentation on their diagnostic performance. For both these evaluations, the model and clinicians had access to the same set of multimodal data. Finally, we assessed the model’s predictions by comparing them with biomarker profiles and pathology grades available from the NACC, ADNI and FHS cohorts.
Fig. 1 Data, model architecture and modeling strategy. a, Our model for differential dementia diagnosis was developed using diverse data modalities, including individual-level demographics, health history, neurological testing, physical/neurological exams and multisequence MRI scans. These data sources whenever available were aggregated from nine independent cohorts: 4RTNI, ADNI, AIBL, FHS, LBDSU, NACC, NIFD, OASIS and PPMI (Tables 1 and S1). For model training, we merged data from NACC, AIBL, PPMI, NIFD, LBDSU, OASIS and 4RTNI. We used a subset of the NACC dataset for internal testing. For external validation, we utilized the ADNI and FHS cohorts. b, A transformer served as the scaffold for the model. Each feature was processed into a fixed-length vector using a modality-specific embedding (emb.) strategy and fed into the transformer as input. A linear layer was used to connect the transformer with the output prediction layer. c, A subset of the NACC testing dataset was randomly chosen to conduct a comparative analysis between neurologists' performance augmented with the AI model and their performance without AI assistance. Similarly, we carried out comparative evaluations with practicing neuroradiologists, who were provided with a randomly selected sample of confirmed dementia cases from the NACC testing cohort, to assess the impact of AI augmentation on their diagnostic performance. For both these evaluations, the model and clinicians had access to the same set of multimodal data. Finally, we assessed the model’s predictions by comparing them with biomarker profiles and pathology grades available from the NACC, ADNI and FHS cohorts.CC BY · PubMed Central
Fig. 2 Model performance on individuals along the cognitive spectrum. a,b, ROC and PR curves, with their respective microaverage, macroaverage and weighted-average calculations based on the labels for NC, MCI and dementia. These averaging techniques consolidated the model’s performance across the spectrum of cognitive states. Cases from the NACC testing, along with all the cases from ADNI and FHS cohorts, were used. c, Diagram indicating varied levels of model performance in the presence of missing data. The inner concentric circles represent various scenarios in which particular test information was either omitted (masked) or included (unmasked). The three outer concentric rings depict the model’s performance as measured by the AUROC for the NC, MCI and dementia labels. d, Raincloud plots are used to demonstrate the model’s predicted AD probabilities for individuals with MCI and dementia in the NACC cohort. Two-sample two-sided unadjusted Kolmogorov-Smirnov (KS) test for goodness of fit was used to compare the cases where AD was a factor in cognitive impairment to those with non-AD etiologies in MCI (n = 1,486, KS = 0.09, P = 4.29 × 10−3) and dementia groups (n = 4,085, KS = 0.57, P < 1 × 10−200). e–g, Raincloud plots with violin and box diagrams are shown to denote the distribution of CDR scores (x axis) versus model-predicted probability of dementia (y axis), on the NACC, ADNI and FHS cohorts, respectively. We performed the Kruskal-Wallis H-test for independent samples in NACC (n = 8,895, H = 6,921.71, P < 1 × 10−200), ADNI (n = 2,400, H = 1,518.79, P < 1 × 10−200) and FHS (n = 1,651, H = 292.04, P = 3.84 × 10−64). These were followed by post-hoc Dunn’s testing with Bonferroni correction for multiple comparisons, and detailed statistical results are provided in Table S10. For d–g, each boxplot includes a box presenting the median value and interquartile range (IQR), with whiskers extending from the box to the maxima and minima no further than a distance of 1.5 times the IQR. Significance levels are denoted as ns (not significant) for P ≥ 0.05; *P < 0.05, **P < 0.01, ***P < 0.001, ****P < 0.0001. In g, ‘Normal’ indicates cognitively normal individuals, ‘Imp’ indicates those with cognitive impairment and ‘Dem’ indicates persons with mild, moderate and severe dementia.
Fig. 2 Model performance on individuals along the cognitive spectrum. a,b, ROC and PR curves, with their respective microaverage, macroaverage and weighted-average calculations based on the labels for NC, MCI and dementia. These averaging techniques consolidated the model’s performance across the spectrum of cognitive states. Cases from the NACC testing, along with all the cases from ADNI and FHS cohorts, were used. c, Diagram indicating varied levels of model performance in the presence of missing data. The inner concentric circles represent various scenarios in which particular test information was either omitted (masked) or included (unmasked). The three outer concentric rings depict the model’s performance as measured by the AUROC for the NC, MCI and dementia labels. d, Raincloud plots are used to demonstrate the model’s predicted AD probabilities for individuals with MCI and dementia in the NACC cohort. Two-sample two-sided unadjusted Kolmogorov-Smirnov (KS) test for goodness of fit was used to compare the cases where AD was a factor in cognitive impairment to those with non-AD etiologies in MCI (n = 1,486, KS = 0.09, P = 4.29 × 10−3) and dementia groups (n = 4,085, KS = 0.57, P < 1 × 10−200). e–g, Raincloud plots with violin and box diagrams are shown to denote the distribution of CDR scores (x axis) versus model-predicted probability of dementia (y axis), on the NACC, ADNI and FHS cohorts, respectively. We performed the Kruskal-Wallis H-test for independent samples in NACC (n = 8,895, H = 6,921.71, P < 1 × 10−200), ADNI (n = 2,400, H = 1,518.79, P < 1 × 10−200) and FHS (n = 1,651, H = 292.04, P = 3.84 × 10−64). These were followed by post-hoc Dunn’s testing with Bonferroni correction for multiple comparisons, and detailed statistical results are provided in Table S10. For d–g, each boxplot includes a box presenting the median value and interquartile range (IQR), with whiskers extending from the box to the maxima and minima no further than a distance of 1.5 times the IQR. Significance levels are denoted as ns (not significant) for P ≥ 0.05; *P < 0.05, **P < 0.01, ***P < 0.001, ****P < 0.0001. In g, ‘Normal’ indicates cognitively normal individuals, ‘Imp’ indicates those with cognitive impairment and ‘Dem’ indicates persons with mild, moderate and severe dementia.CC BY · PubMed Central
Fig. 3 Model assessment on single and co-occurring dementias. a,b, ROC and PR curves are provided, using microaverage, macroaverage and weighted-average methods across all the dementia diagnostic labels. These averages were computed to synthesize the performance metrics across all dementia etiologies. Only cases from the NACC testing were used. c, Heatmaps are used to depict the model’s performance on co-occurring dementias. We considered all combinations where two or more etiologies co-occurred from the NACC testing cohort, provided there were at least 25 positive samples. This ensured that the maximum variance of the AUROC calculation over all possible continuous distributions was upper bounded by 0.01. The first row shows the AUROC values, and the second row shows the AUPR values. The table also displays the sample sizes for each case, with 1 representing a positive case and 0 indicating a negative sample. Only cases from the NACC testing were used.
Fig. 3 Model assessment on single and co-occurring dementias. a,b, ROC and PR curves are provided, using microaverage, macroaverage and weighted-average methods across all the dementia diagnostic labels. These averages were computed to synthesize the performance metrics across all dementia etiologies. Only cases from the NACC testing were used. c, Heatmaps are used to depict the model’s performance on co-occurring dementias. We considered all combinations where two or more etiologies co-occurred from the NACC testing cohort, provided there were at least 25 positive samples. This ensured that the maximum variance of the AUROC calculation over all possible continuous distributions was upper bounded by 0.01. The first row shows the AUROC values, and the second row shows the AUPR values. The table also displays the sample sizes for each case, with 1 representing a positive case and 0 indicating a negative sample. Only cases from the NACC testing were used.CC BY · PubMed Central
Fig. 4 Biomarker-level validation. Raincloud plots representing model probabilities for dementia etiologies across their respective biomarker-negative (blue) and positive groups (pink). a, Model-predicted probabilities for AD, P(AD), were analyzed in relation to amyloid β (Aβ) positivity status using a one-sided Mann-Whitney U test for the NACC cohort (n = 440, U = 10,303.50, P = 2.04 × 10−25) and a one-sided t-test for ADNI (n = 1,108, t = −12.06, P = 9.74 × 10−31). b, Differences in P(AD) between tau PET negative and positive biomarker groups were analyzed using the one-sided Mann-Whitney U tests for NACC (n = 132, U = 935.50, P = 6.48 × 10−8) and ADNI (n = 475, U = 5,857.50, P = 4.10 × 10−27). c, Similar analyses were run to differentiate P(AD) between fluorodeoxyglucose (FDG) PET biomarker groups in NACC (n = 261, U = 3,730.00, P = 3.00 × 10−15), and ADNI (n = 760, U = 14,924.00, P = 5.66 × 10−43). d, e, In the NACC cohort, model-predicted probabilities for frontotemporal lobar degeneration, P(FTD), were assessed across MRI (n = 1,494, 30,935.50, P = 1.52 × 10−51) and FDG PET biomarker groups (n = 233, U = 1,599.50, P = 2.08 × 10−13) using a one-sided Mann-Whitney U test. f, In NACC, LBD probabilities, P(LBD), were analyzed between DaTscan negative and positive groups using a one-sided Mann-Whitney U test (n = 91, U = 318.50, P = 6.26 × 10−6). All boxplots presented include a box presenting the median value and IQR, with whiskers extending from the box to the maxima and minima no further than a distance of 1.5 times the IQR. In all plots, ****P < 0.0001, and results were not corrected for multiple comparisons.
Fig. 4 Biomarker-level validation. Raincloud plots representing model probabilities for dementia etiologies across their respective biomarker-negative (blue) and positive groups (pink). a, Model-predicted probabilities for AD, P(AD), were analyzed in relation to amyloid β (Aβ) positivity status using a one-sided Mann-Whitney U test for the NACC cohort (n = 440, U = 10,303.50, P = 2.04 × 10−25) and a one-sided t-test for ADNI (n = 1,108, t = −12.06, P = 9.74 × 10−31). b, Differences in P(AD) between tau PET negative and positive biomarker groups were analyzed using the one-sided Mann-Whitney U tests for NACC (n = 132, U = 935.50, P = 6.48 × 10−8) and ADNI (n = 475, U = 5,857.50, P = 4.10 × 10−27). c, Similar analyses were run to differentiate P(AD) between fluorodeoxyglucose (FDG) PET biomarker groups in NACC (n = 261, U = 3,730.00, P = 3.00 × 10−15), and ADNI (n = 760, U = 14,924.00, P = 5.66 × 10−43). d, e, In the NACC cohort, model-predicted probabilities for frontotemporal lobar degeneration, P(FTD), were assessed across MRI (n = 1,494, 30,935.50, P = 1.52 × 10−51) and FDG PET biomarker groups (n = 233, U = 1,599.50, P = 2.08 × 10−13) using a one-sided Mann-Whitney U test. f, In NACC, LBD probabilities, P(LBD), were analyzed between DaTscan negative and positive groups using a one-sided Mann-Whitney U test (n = 91, U = 318.50, P = 6.26 × 10−6). All boxplots presented include a box presenting the median value and IQR, with whiskers extending from the box to the maxima and minima no further than a distance of 1.5 times the IQR. In all plots, ****P < 0.0001, and results were not corrected for multiple comparisons.CC BY · PubMed Central
Fig. 5 AI-augmented clinician assessments. Comparison between the performance of the assessments provided by practicing clinicians versus model-assisted clinicians is shown. a,b, For the analysis, neurologists (n = 12) were given 100 randomly selected cases encompassing individual-level demographics, health history, neurological tests, physical as well as neurological examinations, and multisequence MRI scans. The neurologists were then tasked with assigning confidence scores for NC, MCI, dementia and the 10 dementia etiologies: AD, LBD, VD, PRD, FTD, NPH, SEF, PSY, TBI and ODE (Glossary 1). The boxplots show AUROC in a and AUPR in b for individual neurologist and model-assisted neurologist performance (defined as the mean between model and neurologist confidence scores). Pairwise statistical comparisons were conducted using the one-tailed Wilcoxon signed-rank test without corrections made for multiple comparisons, with significance levels denoted as: ns (not significant) for P ≥ 0.05; *P < 0.05, **P < 0.01, ***P < 0.001 ****P < 0.0001. Detailed statistics and P values can be found in Table S14. The percent increase in mean performance for each etiology is also presented above each statistical annotation. c,d, Similarly, in a separate analysis, radiologists (n = 7) were given 70 randomly selected cases with a confirmed dementia diagnosis encompassing individual-level demographics and multisequence MRI scans. The radiologists were tasked with assigning confidence scores for the 10 dementia etiologies, and the boxplots show AUROC in c and AUPR in d for the individual radiologist and model-assisted radiologist performance for the 10 etiologies. Statistical annotations and percent increase in mean performance with respect to each etiology are shown in a similar fashion, with significance levels corresponding to the results of unadjusted one-tailed Wilcoxon signed-rank tests denoted as *, **, *** and ****. Detailed statistics and P values can be found in Table S15. Each boxplot includes a box presenting the median value and IQR, with whiskers extending from the box to the maxima and minima no further than a distance of 1.5 times the IQR.
Fig. 5 AI-augmented clinician assessments. Comparison between the performance of the assessments provided by practicing clinicians versus model-assisted clinicians is shown. a,b, For the analysis, neurologists (n = 12) were given 100 randomly selected cases encompassing individual-level demographics, health history, neurological tests, physical as well as neurological examinations, and multisequence MRI scans. The neurologists were then tasked with assigning confidence scores for NC, MCI, dementia and the 10 dementia etiologies: AD, LBD, VD, PRD, FTD, NPH, SEF, PSY, TBI and ODE (Glossary 1). The boxplots show AUROC in a and AUPR in b for individual neurologist and model-assisted neurologist performance (defined as the mean between model and neurologist confidence scores). Pairwise statistical comparisons were conducted using the one-tailed Wilcoxon signed-rank test without corrections made for multiple comparisons, with significance levels denoted as: ns (not significant) for P ≥ 0.05; *P < 0.05, **P < 0.01, ***P < 0.001 ****P < 0.0001. Detailed statistics and P values can be found in Table S14. The percent increase in mean performance for each etiology is also presented above each statistical annotation. c,d, Similarly, in a separate analysis, radiologists (n = 7) were given 70 randomly selected cases with a confirmed dementia diagnosis encompassing individual-level demographics and multisequence MRI scans. The radiologists were tasked with assigning confidence scores for the 10 dementia etiologies, and the boxplots show AUROC in c and AUPR in d for the individual radiologist and model-assisted radiologist performance for the 10 etiologies. Statistical annotations and percent increase in mean performance with respect to each etiology are shown in a similar fashion, with significance levels corresponding to the results of unadjusted one-tailed Wilcoxon signed-rank tests denoted as *, **, *** and ****. Detailed statistics and P values can be found in Table S15. Each boxplot includes a box presenting the median value and IQR, with whiskers extending from the box to the maxima and minima no further than a distance of 1.5 times the IQR.CC BY · PubMed Central
Extended Data Fig. 1 Shapley analysis on cases from the NACC test set comprising individuals along the cognitive spectrum. The figure presents the top twenty contributing features for the model’s positive predictions of a, NC, b, MCI, and c, DE labels, ranked by their mean Shapley values. These values, representing the average contribution of each feature to the model’s decision, guide the ranking from the highest to the lowest impact. For each diagnostic group, a subset of n = 500 cases with the most available features were selected for analysis.
Extended Data Fig. 1 Shapley analysis on cases from the NACC test set comprising individuals along the cognitive spectrum. The figure presents the top twenty contributing features for the model’s positive predictions of a, NC, b, MCI, and c, DE labels, ranked by their mean Shapley values. These values, representing the average contribution of each feature to the model’s decision, guide the ranking from the highest to the lowest impact. For each diagnostic group, a subset of n = 500 cases with the most available features were selected for analysis.CC BY · PubMed Central
Extended Data Fig. 2 UpSet plot depicting the distribution and model-predicted probabilities of the etiological categories in NACC testing. a, Single and co-occurring diagnostic categories are enumerated, offering a tally of each condition’s frequency within the dataset. b, A logarithmic scale is used to delineate the overlap among these categories, shedding light on their relative commonality and the extent of their coexistence. This method grants a refined perspective on the prevalence of comorbid conditions. c, Boxplots delineating the spread and central tendency of the model’s predicted probabilities for each combination of diagnostic categories. The legend in the upper right interprets the sizes within b and c, providing a reference for the logarithmic data representation. All boxplots include a box presenting the median value and interquartile range (IQR), with whiskers extending from the box to the maxima and minima no further than a distance of 1.5 times the IQR.
Extended Data Fig. 2 UpSet plot depicting the distribution and model-predicted probabilities of the etiological categories in NACC testing. a, Single and co-occurring diagnostic categories are enumerated, offering a tally of each condition’s frequency within the dataset. b, A logarithmic scale is used to delineate the overlap among these categories, shedding light on their relative commonality and the extent of their coexistence. This method grants a refined perspective on the prevalence of comorbid conditions. c, Boxplots delineating the spread and central tendency of the model’s predicted probabilities for each combination of diagnostic categories. The legend in the upper right interprets the sizes within b and c, providing a reference for the logarithmic data representation. All boxplots include a box presenting the median value and interquartile range (IQR), with whiskers extending from the box to the maxima and minima no further than a distance of 1.5 times the IQR.CC BY · PubMed Central
Extended Data Fig. 3 Neuropathological validation. Array of violin plots with integrated boxplots, delineating the model-predicted probabilities for different neuropathological grades across AD, VD and FTD etiologies. A one-sided Mann-Whitney U test was performed on data from FHS, NACC and ADNI, each denoted by unique markers. AD probabilities, P(AD), were compared against three key AD pathological markers with progressive stages: a, Thal phases of Aβ plaques (N = 135, U = 282.5, p = 7.11e − 05), b, Braak stages of neurofibrillary degeneration (N = 249, U = 571.5, p = 6.07e − 06), and c, Consortium to Establish a Registry for Alzheimer’s Disease density scores of neocortical neuritic plaques (N = 278, U = 3916.5, p = 1.73e − 06). We further evaluated P(AD) against d, cerebral amyloid angiopathy (N = 274, U = 6938.5, p = 0.01) and e, arteriolosclerosis (N = 238, U = 2607.0, p = 0.01), both of which are common pathological findings in AD confirmed postmortem cases. Significant differences were also observed in model predicted probabilities for VD between cases with and without f, arteriolosclerosis (N = 230, U = 2085.5, p = 0.0002) and g, old microinfarcts (N = 178, U = 2289.5, p = 0.0001). h, Finally, model predicted probabilities for FTD differed significantly between cases with and without TDP-43 pathology (N = 136, U = 252.0, p = 0.0008). Table S13 also details these statistical results. No correction for multiple comparisons was performed and significance levels are illustrated as: * for p < 0.05; ** for p < 0.01; *** for p < 0.001; and **** for p < 0.0001. Each boxplot includes a box presenting the median value and interquartile range (IQR), with whiskers extending from the box to the maxima and minima no further than a distance of 1.5 times the IQR.
Extended Data Fig. 3 Neuropathological validation. Array of violin plots with integrated boxplots, delineating the model-predicted probabilities for different neuropathological grades across AD, VD and FTD etiologies. A one-sided Mann-Whitney U test was performed on data from FHS, NACC and ADNI, each denoted by unique markers. AD probabilities, P(AD), were compared against three key AD pathological markers with progressive stages: a, Thal phases of Aβ plaques (N = 135, U = 282.5, p = 7.11e − 05), b, Braak stages of neurofibrillary degeneration (N = 249, U = 571.5, p = 6.07e − 06), and c, Consortium to Establish a Registry for Alzheimer’s Disease density scores of neocortical neuritic plaques (N = 278, U = 3916.5, p = 1.73e − 06). We further evaluated P(AD) against d, cerebral amyloid angiopathy (N = 274, U = 6938.5, p = 0.01) and e, arteriolosclerosis (N = 238, U = 2607.0, p = 0.01), both of which are common pathological findings in AD confirmed postmortem cases. Significant differences were also observed in model predicted probabilities for VD between cases with and without f, arteriolosclerosis (N = 230, U = 2085.5, p = 0.0002) and g, old microinfarcts (N = 178, U = 2289.5, p = 0.0001). h, Finally, model predicted probabilities for FTD differed significantly between cases with and without TDP-43 pathology (N = 136, U = 252.0, p = 0.0008). Table S13 also details these statistical results. No correction for multiple comparisons was performed and significance levels are illustrated as: * for p < 0.05; ** for p < 0.01; *** for p < 0.001; and **** for p < 0.0001. Each boxplot includes a box presenting the median value and interquartile range (IQR), with whiskers extending from the box to the maxima and minima no further than a distance of 1.5 times the IQR.CC BY · PubMed Central
Extended Data Fig. 4 Head to head comparison between model and clinicians. Comparison between model-predicted probability scores and the assessments provided by practicing clinicians is shown. a, For the analysis, neurologists (n = 12) were given 100 randomly selected cases encompassing individual-level demographics, health history, neurological tests, physical as well as neurological examinations, and multisequence MRI scans. The neurologists were then tasked with assigning confidence scores for NC, MCI, DE, and the 10 dementia etiologies: AD, LBD, VD, PRD, FTD, NPH, SEF, PSY, TBI, and ODE (see Glossary 1). Neurologists’ confidence scores were averaged to produce a single consensus confidence score for each case. In the visual representation, the boxplot in blue indicates the distribution of confidence scores for true negative cases, while the boxplot in red signifies true positive cases. The symbol ‘+’ represents true positive cases, and ‘x’ denotes true negative cases. Significance levels are denoted as: ns (not significant) for p≥0.05; * for p < 0.05; ** for p < 0.01; *** for p < 0.001; and **** for p < 0.0001. These levels were determined using pairwise comparisons via the unadjusted two-sided Brunner-Munzel test, for which detailed pvalues and statistics can be found in Table S17. b, Similarly, in a separate analysis, radiologists (n = 7) were given 70 randomly selected cases with a confirmed dementia diagnosis encompassing individual-level demographics and multisequence MRI scans. The radiologists were tasked with assigning confidence scores for the 10 dementia etiologies. Similar to that of a, the visual representation consists of boxplots and scatterplots that represent the distribution of model and radiologists’ consensus confidence scores for true negative and true positive cases. Unadjusted two-sided Brunner-Munzel statistical test results are shown as pairwise annotations of ns, *, **, ***, or ****, and more detailed statistics and pvalues can be found in Table S18. Each boxplot presented includes a box presenting the median value and interquartile range (IQR), with whiskers extending from the box to the maxima and minima no further than a distance of 1.5 times the IQR.
Extended Data Fig. 4 Head to head comparison between model and clinicians. Comparison between model-predicted probability scores and the assessments provided by practicing clinicians is shown. a, For the analysis, neurologists (n = 12) were given 100 randomly selected cases encompassing individual-level demographics, health history, neurological tests, physical as well as neurological examinations, and multisequence MRI scans. The neurologists were then tasked with assigning confidence scores for NC, MCI, DE, and the 10 dementia etiologies: AD, LBD, VD, PRD, FTD, NPH, SEF, PSY, TBI, and ODE (see Glossary 1). Neurologists’ confidence scores were averaged to produce a single consensus confidence score for each case. In the visual representation, the boxplot in blue indicates the distribution of confidence scores for true negative cases, while the boxplot in red signifies true positive cases. The symbol ‘+’ represents true positive cases, and ‘x’ denotes true negative cases. Significance levels are denoted as: ns (not significant) for p≥0.05; * for p < 0.05; ** for p < 0.01; *** for p < 0.001; and **** for p < 0.0001. These levels were determined using pairwise comparisons via the unadjusted two-sided Brunner-Munzel test, for which detailed pvalues and statistics can be found in Table S17. b, Similarly, in a separate analysis, radiologists (n = 7) were given 70 randomly selected cases with a confirmed dementia diagnosis encompassing individual-level demographics and multisequence MRI scans. The radiologists were tasked with assigning confidence scores for the 10 dementia etiologies. Similar to that of a, the visual representation consists of boxplots and scatterplots that represent the distribution of model and radiologists’ consensus confidence scores for true negative and true positive cases. Unadjusted two-sided Brunner-Munzel statistical test results are shown as pairwise annotations of ns, *, **, ***, or ****, and more detailed statistics and pvalues can be found in Table S18. Each boxplot presented includes a box presenting the median value and interquartile range (IQR), with whiskers extending from the box to the maxima and minima no further than a distance of 1.5 times the IQR.CC BY · PubMed Central
Extended Data Fig. 5 Neurologist and model interrater agreement. a, The figure presents the Pearson correlation coefficient across different diagnostic categories, comparing assessments from the neurologists (n = 12) and the model, marked as ‘M’. Each diagnostic category from NC to ODE includes a matrix reflecting correlation coefficient values between individual neurologists and the model. Shades of green signify positive correlation, indicating agreement between the model and neurologists, whereas magenta shades suggest negative correlations, indicating potential discrepancies in assessments. The mean pairwise Pearson correlation coefficient for each etiology is presented along with a 95% confidence interval. The symbol ‘X’ denotes rater pairs where the Pearson correlation was not calculable, due to one or both raters giving label-specific confidence scores with no variance. b, The heatmap shows the mean Pearson correlation coefficients between model probabilities and neurologist confidence scores for each label, along with its 95% confidence interval. The correlation coefficient and its confidence interval for each etiology were estimated with a non-parametric bootstrapping approach.
Extended Data Fig. 5 Neurologist and model interrater agreement. a, The figure presents the Pearson correlation coefficient across different diagnostic categories, comparing assessments from the neurologists (n = 12) and the model, marked as ‘M’. Each diagnostic category from NC to ODE includes a matrix reflecting correlation coefficient values between individual neurologists and the model. Shades of green signify positive correlation, indicating agreement between the model and neurologists, whereas magenta shades suggest negative correlations, indicating potential discrepancies in assessments. The mean pairwise Pearson correlation coefficient for each etiology is presented along with a 95% confidence interval. The symbol ‘X’ denotes rater pairs where the Pearson correlation was not calculable, due to one or both raters giving label-specific confidence scores with no variance. b, The heatmap shows the mean Pearson correlation coefficients between model probabilities and neurologist confidence scores for each label, along with its 95% confidence interval. The correlation coefficient and its confidence interval for each etiology were estimated with a non-parametric bootstrapping approach.CC BY · PubMed Central
Extended Data Fig. 6 Image feature extraction. The Swin UNETR encoder, utilizing pre-trained weights, was leveraged to extract image embeddings from multi-sequence MRI scans into a latent space representation. Subsequently, these embeddings underwent a series of downsampling convolutional operations to achieve a condensed token dimension of 1 × 256. This dimensional reduction facilitated a consistent input format for both imaging and non-imaging data into the backbone transformer. Within this architecture, the Swin UNETR encoder’s weights remained static (frozen), ensuring the integrity of the pre-trained features, while the downsampling blocks were subject to optimization during the training phase, allowing for adaptive learning of the imaging feature vector.
Extended Data Fig. 6 Image feature extraction. The Swin UNETR encoder, utilizing pre-trained weights, was leveraged to extract image embeddings from multi-sequence MRI scans into a latent space representation. Subsequently, these embeddings underwent a series of downsampling convolutional operations to achieve a condensed token dimension of 1 × 256. This dimensional reduction facilitated a consistent input format for both imaging and non-imaging data into the backbone transformer. Within this architecture, the Swin UNETR encoder’s weights remained static (frozen), ensuring the integrity of the pre-trained features, while the downsampling blocks were subject to optimization during the training phase, allowing for adaptive learning of the imaging feature vector.CC BY · PubMed Central

Verification

Claims the paper makes

13 Valid · 3 Not valid · 6 Not checked · 107 Own results and interpretations

60 more claims · 1 with their cited sources checked

Create a free account to see all 129 claims and to verify the 9 references still open.

See all claims — free account
  • Probably not a substantial claim. 36
  • It may state two separate claims as one. 39
  • Borderline: one of the tests for a substantial claim is unclear. 1

Create a free account to see these claims.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Self-check results appear here once an independent check has confirmed them.

Cited works that were retracted

Works this paper cites that were later retracted, from the retraction notices publishers deposit. Major when the notice came out before this paper was published.

1 of 1

Citations

Cites

1 retracted

Show all 88 references

Research works printed but not linked: 3

  1. Dorogush, A. V., Ershov, V. & Gulin, A. Catboost: gradient boosting with categorical features support. Workshop on ML Systems at NIPS 2017 (2017). http://learningsys.org/nips17/assets/papers/paper_11.pdf
  2. Cortes, C. & Mohri, M. Confidence intervals for the area under the roc curve. In Saul, L., Weiss, Y. & Bottou, L. (eds.) Advances in Neural Information Processing Systems, vol. 17 (MIT Press, 2004).
  3. Kenton, J. D. M.-W. C. & Toutanova, L. K. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of NAACL-HLT (NAACL-HLT, 2019).

Cited by

See all 182

Metadata

Authors
Xue, C., Kowshik, S. S., Lteif, D., Puducheri, S., Jasodanand, V. H., Zhou, O. T., Walia, A. S., Guney, O. B., Zhang, J. D., Poésy, S., Kaliaev, A., Andreu-Arasa, V. C., Dwyer, B. C., Farris, C. W., Hao, H., Kedar, S., Mian, A. Z., Murman, D. L., O’Shea, S. A., Paul, A. B., Rohatgi, S., Saint-Hilaire, M.-H., Sartor, E. A., Setty, B. N., Small, J. E., Swaminathan, A., Taraschenko, O., Yuan, J., Zhou, Y., Zhu, S., Karjadi, C., Alvin Ang, T. F., Bargal, S. A., Plummer, B. A., Poston, K. L., Ahangaran, M., Au, R., & Kolachalama, V. B.
Affiliations
  • Boston University (US)
  • Chinese Academy of Medical Sciences & Peking Union Medical College (CN)
  • Emory University (US)
  • University of Nebraska Medical Center (US)
  • Columbia University Irving Medical Center (US)
  • Massachusetts General Hospital (US)
  • Lahey Hospital and Medical Center (US)
  • Brigham and Women's Hospital (US)
  • Georgetown University (US)
  • Stanford University (US)
Corresponding author
Kolachalama, Vijaya B.
Venue
Nature Medicine
Published
2024-07-04
Volume
30
Issue
10
Pages
2977-2989
ISSN
  • 1078-8956 (ISSN-L)
  • 1546-170X
OpenAlex
W4400324640
Cited by
182
References
88
Citations by year
2026: 75 · 2025: 88 · 2024: 19
FWCI
53.23
Type
journal article
Language
en
Open access
Licence
Locations
  • Nature Medicine (publishedVersion, cc-by)
  • medRxiv (acceptedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • PubMed Central (submittedVersion, cc-by)
Funders
  • Alzheimer's Association (P30 AG072947, P30 AG062421, P30 AG062422, P30 AG066468)
  • American Heart Association (20SFRN35460031)
  • Bristol-Myers Squibb (AG024904)
  • Eli Lilly and Company (AG024904)
  • Pfizer (AG024904)
  • Biogen (AG024904)
  • University of Southern California
  • Meso Scale Diagnostics (AG024904)
  • BioClinica (AG024904)
  • Novartis Pharmaceuticals Corporation (AG024904)
  • Northern California Institute for Research and Education
  • Eisai (AG024904)
  • Servier (AG024904)
  • H. Lundbeck A/S (AG024904)
  • IXICO (AG024904)
  • National Institutes of Health (1r21ca253498-01, 4RTNI, 5u01ag024904-10, UL1TR001430, AG062421, AG072978, AG072946, U01-AG024904, AG072979, AG066509, AG024904, AG066519, AG066512, AG062677, CTSI 1UL1TR001430, AG047366, AG066515, AG066444, AG066514, AG068077, AG066518, AG066511, AG072972, AG066468, AG062429, AG066508)
  • Genentech (AG024904)
  • Canadian Institutes of Health Research
  • National Institute on Aging (AG072946, AG‐068753, U01-AG-024904, AG066468, AG062429, AG066546, AG066507, P30AG066512, P30AG079280, AG062421, AG072979, AG066518, AG047366, AG066519, AG066511, AG‐062109, AG072977, AG 024904, P30AG066506, AG072978, AG066509, AG072931, AG066444, AG062715, P20AG068053, AG072959, P50AG047366, P20AG068024, AG066462, AG066515, RF1AG062109, P20AG068077, P01AG003991, AG068082, AG068024, P20AG068082, AG062422, AG066512, AG066508, U19AG068753, P30AG073104, P30AG072978, P30AG066508, P30AG062429, R01AG079280, P30AG072931, P30AG072973, P30AG066468, P30AG066462, P30AG066518, P30AG066444, P30AG072972, P30AG066507, P30AG072976, P30AG072959, R01AG062109, P30AG062422, P30AG066515, P30AG066514, P30AG062677, P30AG066509, P30AG072958, P30AG062715, P30AG066530, U24AG072122, P30AG072946, P30AG072977, P30AG072979, P01AG026276, P30AG072947, P30AG062421, P30AG066546, P30AG066511, P30AG066519, P30AG072975)
  • National Heart, Lung, and Blood Institute (R01HL159620)
  • National Cancer Institute (R21‐CA253498)
  • National Institute of General Medical Sciences (P20GM130447)
  • National Institute of Diabetes and Digestive and Kidney Diseases (R43DK134273)
  • National Institute of Neurological Disorders and Stroke (K23NS075097, R01NS115114)
  • National Center for Advancing Translational Sciences
Topics
  • Health Sciences › Medicine › Psychiatry and Mental health › Dementia and Cognitive Impairment Research
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
Keywords
dementia etiology, differential diagnosis, multimodal data, multimodal neuroimaging, mild cognitive impairment, mixed dementia, proteinopathies, biomarkers, neuropsychological assessment, functional assessment, clinical decision support, dementia screening

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (gpt-6-sol).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: AI-based differential diagnosis of dementia etiologies on multimodal data. https://app.cochat.ai/papers/10.1038/s41591-024-03118-z
The paper
Xue, C., Kowshik, S. S., Lteif, D., Puducheri, S., Jasodanand, V. H., Zhou, O. T., Walia, A. S., Guney, O. B., Zhang, J. D., Poésy, S., Kaliaev, A., Andreu-Arasa, V. C., Dwyer, B. C., Farris, C. W., Hao, H., Kedar, S., Mian, A. Z., Murman, D. L., O’Shea, S. A., . . . Kolachalama, V. B. (2024). AI-based differential diagnosis of dementia etiologies on multimodal data. Nature Medicine. https://doi.org/10.1038/s41591-024-03118-z

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.