Citations

Abstract Gross brain findings help guide differential diagnosis, but their diagnostic value across major neurodegenerative diseases remains incompletely characterized. We evaluated whether gross descriptions in autopsy reports could classify cases by final neuropathologic diagnosis. We analyzed 5,613 autopsy cases from the Mayo Clinic Brain Bank collected between 1998 and 2023, including seven diagnostic categories: Alzheimer disease (AD), Lewy body disease (LBD), combined AD and LBD (AD-LBD), frontotemporal lobar degeneration, corticobasal degeneration, progressive supranuclear palsy (PSP), and multiple system atrophy (MSA). A fine-tuned large language model (LLM) converted narrative gross descriptions into semi-quantitative scores for 39 features. Extraction accuracy was 0.95 in 200 manually annotated feature-level test examples. A CatBoost classifier used the extracted scores as input, whereas a second fine-tuned LLM used standardized textual descriptions of the same features. Both classifiers also included age at death, sex, and brain weight. Performance was evaluated in the same held-out test set of 562 cases. CatBoost achieved an accuracy of 0.73, a Cohen’s kappa of 0.65, and a macro-average area under the receiver operating characteristic curve of 0.92. The text-based LLM achieved an accuracy of 0.75 and a kappa of 0.68. Macro-average sensitivity was 0.66 for both models. PSP sensitivity was 0.92 with CatBoost and 0.93 with text-based LLM. Corresponding sensitivities were 0.87 and 0.92 for MSA, but only 0.21 and 0.03 for AD-LBD. Feature attribution analysis identified subthalamic nucleus atrophy and putaminal abnormalities as contributors to PSP and MSA predictions, respectively. Narrative gross descriptions contained diagnostic information, particularly for disorders with distinctive macroscopic patterns, whereas combined AD-LBD remained difficult to distinguish.

Objective Pre‐mortem diagnosis of parkinsonism is often challenging due to atypical presentations, overlapping syndromes, and co‐pathologies. This study aimed to develop a machine learning‐based algorithm predicting neuropathology in parkinsonism using chronological clinical presentations, which has previously been underexplored. Methods Clinical information was automatically abstracted from medical records of the Mayo Clinic Brain Bank using fine‐tuned Generative Pre‐trained Transformer 4 models. Patients who developed parkinsonism within 3 years of disease onset were included. Six machine learning models were trained with age, sex, family history, and 197 clinical presentations paired with onset information to predict neuropathologic diagnoses, including co‐pathologies. Results Among 7,825 donors, 949 met inclusion criteria, representing 9 neuropathologic categories: Lewy body disease (LBD; n = 128), LBD with Alzheimer's disease (AD; n = 136), progressive supranuclear palsy (PSP; n = 303), PSP with AD (n = 56), PSP with LBD (n = 27), multiple system atrophy (MSA; n = 120), corticobasal degeneration (CBD; n = 99), AD (n = 43), and frontotemporal lobar degeneration (FTLD; n = 37). The CatBoost algorithm achieved an area under the receiver operating characteristic curve of 0.83 across the 9 diagnostic categories at 3 years after onset. Important predictors included age at onset, restricted eye movement, and tremor. The model remained robust to incomplete data, requiring only 23 of 200 parameters for reliable predictions with an area under the curve of 0.80. The algorithm was implemented into a user‐friendly program providing diagnostic probabilities with visualizations of parameter contributions. Interpretation This neuropathology‐confirmed diagnostic algorithm provides a cost‐effective and interpretable screening tool for parkinsonism, bridging biomarker testing and molecular‐targeted therapies. ANN NEUROL 2026;99:1405–1414

Objectives Multiple system atrophy (MSA) is classified into parkinsonian (MSA‐P) and cerebellar (MSA‐C) phenotypes based on predominant motor features, with corresponding pathological classifications of striatonigral (SN) degeneration and olivopontocerebellar (OPC) atrophy; however, disease progression patterns remain poorly understood. We aimed to identify novel MSA subtypes based on neuronal loss patterns using unsupervised machine learning. Methods We applied the Subtype and Stage Inference (SuStaIn) algorithm to analyze neuronal loss patterns in 167 autopsy‐confirmed MSA. Neuronal loss was semi‐quantitatively assessed in 5 brain regions: putamen, substantia nigra, pontine nucleus, inferior olivary nucleus, and cerebellar Purkinje cells. Obtained subtypes were validated by clinicopathological information. Results Three distinct subtypes were identified: SN‐early subtype (54% [86/160]) with initial SN neuronal loss, OPC‐early subtype (28% [44/160]) with early OPC involvement, and SN‐OPC‐synchronous subtype (19% [30/160]) with concurrent early neuronal loss in both systems. These subtypes corresponded well with clinical phenotypes. The SN‐OPC‐synchronous subtype exhibited significantly shorter survival (median 6.2 years vs 6.9 and 7.4 years in SN‐early and OPC‐early subtypes; p = 0.0049), more frequent rapid progression (57% vs 24% and 41% in SN‐early and OPC‐early subtypes; p = 0.0048), and more frequent early falls (70% vs 36% and 50% in SN‐early and OPC‐early subtypes; p = 0.0039). Immunohistochemical validation confirmed extensive α‐synuclein pathology in both SN and OPC systems in the SN‐OPC‐synchronous subtype. Interpretation The SN‐OPC‐synchronous subtype provides insights into α‐synuclein propagation mechanisms, suggesting multiple initial seeding sites rather than unidirectional spread. This computational approach uncovered disease heterogeneity undetectable by conventional methods, potentially benefiting clinical trials through patient stratification. ANN NEUROL 2026;99:989–1000

Abstract INTRODUCTION Visual hallucinations (VHs) represent one of the core clinical features of dementia with Lewy bodies (DLB); however, their underlying pathology remains unclear. METHODS We employed proximity ligation assay (PLA) and phosphorylated α‐synuclein (αSYN) immunohistochemistry to compare αSYN oligomers and Lewy‐related pathology across brain regions along the ventral visual pathway in patients with and without VHs (five patients each). RESULTS Greater αSYN oligomer burden in the parahippocampal cortex was observed in patients with VHs compared to those without ( p = 0.041), whereas the burden of Lewy‐related pathology was similar between groups. DISCUSSION Our findings suggest that αSYN oligomers, rather than conventional Lewy‐related pathology, may be more closely associated with VHs in DLB. This provides novel evidence linking αSYN oligomers to a core clinical feature in DLB and suggests potential therapeutic targets for managing VH in these patients. Highlights Visualization of αSYN oligomers by PLA and quantitative neuropathologic analysis. Abundant αSYN oligomers in parahippocampal cortex of DLB with VHs. First human brain study linking αSYN oligomers to VHs. Potential oligomer‐targeted therapy for managing VH in DLB.

Objective Lewy body disease (LBD) is a complex neurodegenerative disorder characterized by the accumulation of misfolded α‐synuclein in the brain. Neuroinflammation has long been implicated in LBD pathogenesis, and recent genetic studies in Parkinson's disease (a clinical manifestation of LBD) have shown consistent association with the human leukocyte antigen (HLA) gene complex. Here, we assessed whether variation in HLA alleles influences neuropathological burden in a neuropathologically‐defined series of LBD cases. Methods We conducted a comprehensive analysis of HLA allelic variants in a cohort of 539 LBD cases of European descent from the Mayo Clinic brain bank. High‐resolution whole‐genome sequencing was used, and the HLA alleles of each sample were called using the HLA*LA tool and assessed for association with neuropathological outcomes. Results Our analysis identified 1 significant ( P < 3.43 × 10 −5 ) and 4 suggestive ( P < 0.001) associations between certain HLA alleles and specific neuropathological outcomes in LBD, suggesting a potential role for HLA‐mediated immune mechanisms in disease progression and subtype differentiation. Specifically, HLA‐DPB1*06:01 was significantly associated with lower Lewy body counts in the parahippocampal gyrus ( P = 3.30 × 10 −5 ), with weaker and suggestive associations observed in the middle frontal ( P = 1.80 × 10 −4 ) and inferior parietal gyrus ( P = 6.33 × 10 −4 ). Additionally, although only suggestive, HLA‐DRB1*11:01 correlated with a lower Thal amyloid phase ( P = 1.56 x 10 −4 ), and HLA‐B*15:01 correlated with an increased risk of diffuse LBD ( P = 7.58 x 10 −4 ). Interpretation This study provides a detailed evaluation of the relationship between HLA alleles and LBD pathology, highlighting the importance of immune‐related genetic factors in the etiology of LBD. ANN NEUROL 2026;99:492–501

AbstractINTRODUCTIONIncreasing evidence indicates that α‐synuclein (αSYN) oligomers are toxic. We sought to determine whether αSYN oligomers were associated with faster cognitive decline in prospectively‐followed patients with dementia with Lewy bodies (DLB).METHODSEight autopsy‐confirmed patients with DLB were selected based on rapid or slow cognitive decline determined by the rate of change of Mini‐Mental State Examination (MMSE) scores. Quantitative neuropathologic analysis of αSYN oligomers, Lewy‐related pathology, phosphorylated tau, and amyloid‐β was conducted in hippocampal subfields (CA1‐4 and subiculum) and the entorhinal cortex.RESULTSDLB with rapid cognitive decline showed greater CA1 αSYN oligomer burden (p = 0.029) and tau burden (p = 0.029) than DLB with slow decline. The groups showed comparable burden of Lewy‐related pathology and amyloid‐β pathology in the hippocampal formation and entorhinal cortex.DISCUSSIONHippocampal accumulation of αSYN oligomers and phosphorylated tau is associated with rapid cognitive decline in DLB. Therapeutic strategies targeting αSYN oligomers warrant further investigation.Highlights Proximity ligation assay (PLA) and digital pathology for oligomer quantification. Abundant α‐synuclein (αSYN) oligomers in CA1 of patients with dementia with Lewy bodies (DLB) with rapid decline. First human brain study linking αSYN oligomers to cognitive trajectory. Potential therapeutic implications of targeting αSYN oligomers in DLB.

Abstract Objective To compare iron deposition in the substantia nigra (SN) as measured with quantitative susceptibility mapping (QSM) on antemortem magnetic resonance imaging (MRI) between individuals with and without Lewy‐related pathology at autopsy. Methods We performed a retrospective cohort study including 54 participants who underwent autopsy and antemortem MRI with QSM. Cases were classified as Lewy body disease (LBD)‐present (n = 13) if they had Lewy‐related pathology and LBD‐absent (n = 41) if they did not have Lewy‐related pathology. QSM was calculated for the whole SN and the two subregions: pars compacta (SNc) and pars reticulata (SNr). Nonparametric Wilcoxon rank‐sum tests were used to compare SN QSM values between LBD‐present and LBD‐absent cases. Area under the receiver operating characteristic (ROC) curve (AUC) analyses tested the accuracy of SN QSM values to distinguish the two groups. Associations of QSM values in the SN and its subregions with clinical features were tested with Spearman's correlations. Results The LBD‐present group had higher QSM values in the SNc ( P = 0.008) than the LBD‐absent group with no differences in SNr. QSM values of the SNc distinguished LBD‐present and LBD‐absent cases with good accuracy (AUC = 0.74) and correlated with the presence of parkinsonism and parkinsonism severity. Conclusions This study provides neuropathological confirmation of the utility of SNc QSM as an in vivo biomarker of Lewy‐related pathology. Imaging evidence of abnormal iron deposition in the SNc could potentially serve as a biomarker for inclusion in emerging research frameworks aimed at defining individuals with LBD based on their biological characteristics. Ultimately, this could facilitate more precise diagnoses and guide treatment strategies in LBD. © 2025 The Author(s). Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

ABSTRACT Aims Muscle morphology provides important information in differentiating disease aetiology, but its measurement remains challenging because of the lack of an efficient and objective method. This study aimed to quantitatively refine the morphological features of muscle fibres in neuromuscular diseases using machine learning. Methods In this retrospective study, we analysed muscle biopsy specimens on haematoxylin and eosin‐staining. Machine learning–based software was developed to segment muscle fibre contours and perform automated muscle morphometry and subsequent graph theory–based spatial analysis of atrophied fibre grouping. A decision tree–based framework, LightGBM, was trained to predict underlying aetiologies based on morphometric and spatial variables. Results The study included 100 muscle samples, including 20 normal muscles, 49 myopathies and 19 neuropathies. The fine‐tuned segmentation model, YOLOv8, achieved a mask average precision of 0.819. The muscle morphometry revealed the significance of fibre circularity. The mean circularity was higher in the myopathy group, and the SD of circularity was elevated in the neuropathy group. Although most cases were consistent with textbook findings, atypical presentations, such as dermatomyositis with angular atrophy and amyotrophic lateral sclerosis with round atrophy, were objectively documented. Spatial analysis quantified grouped atrophy, showing the potential to feature specific atrophy patterns. The LightGBM model successfully predicted the final clinical diagnosis of the myopathies and neuropathies with an accuracy of 0.852, which exceeded that of 0.808 by human annotation. Conclusion Automated muscle morphometry and spatial analysis provide quantification of muscle morphology and patterns of atrophy, which will facilitate objective and efficient investigation of neuromuscular diseases.

Abstract Studies assessing genetic associations with neuropathological features in Lewy body disease (LBD) have been limited to candidate gene investigations, and therefore, information is lacking regarding the genetic architecture of the neuropathology of LBD. In the current study, we examined a large series of neuropathologically confirmed LBD cases (n = 980 in the discovery series, n = 503 in the replication series) and performed genome-wide association studies of 11 different neuropathological outcome measures. The 11 neuropathological outcomes included Braak neurofibrillary tangle (NFT) stage, Thal amyloid phase, LBD subtype, Lewy body (LB) counts in five different brain regions, dorsolateral and ventromedial putaminal tyrosine hydroxylase immunoreactivity and neuronal loss in the ventrolateral part of the substantia nigra. Associations between variants and outcomes were assessed using regression models appropriate for the nature of the given neuropathological outcome and that were adjusted for age at death, sex and top principal components of genetic data. In the discovery series, APOE rs429358 (i.e. APOE ε4) was associated with a greater severity of each of Braak NFT stage [odds ratio (OR) = 3.07, P = 2.34 × 10−32], Thal amyloid phase (OR = 3.57, P = 3.28 × 10−29) and LBD subtype (OR = 1.78, P = 9.85 × 10−9), with similar findings observed in the independent replication series (Braak NFT stage, OR = 2.30, P = 2.70 × 10−11; Thal amyloid phase, OR = 3.17, P = 6.39 × 10−18; LBD subtype, OR = 2.68, P = 3.85 × 10−10). In the subgroup of cases with lower levels of Alzheimer's disease pathology (Braak NFT stage ≤ III and Thal amyloid phase ≤2), there was a strong association between APOE rs429358 and LBD subtype even when adjusting for Braak stage and Thal phase in the discovery series (n = 218, OR = 2.47, P = 0.007) and the replication series (n = 141, OR = 3.60, P = 0.006). Although additional genome-wide significant associations were identified in the discovery series between LINC01581/MCTP2 rs547411734 and lower middle frontal LB counts, between TLE3 rs3743309 and lower cingulate LB counts, and between GRIN2A/ATF7IP2 rs1097915 and lower parahippocampal LB counts, these findings were not observed in the replication series. Our results indicate that the APOE ε4 allele is the most prominent genetic determinant of severity of neuropathology in LBD. These findings represent a key step forward in our understanding of genetic drivers of neuropathological features in LBD. Future studies utilizing meta-analytical approaches will be important to more precisely assess other associations that were not quite genome-wide significant in the discovery series.