Citations

Abstract INTRODUCTION The locus coeruleus (LC) degenerates early in Alzheimer's disease (AD). However, the extent of rostrocaudal degeneration across clinicopathologic heterogeneity remains underexplored in AD. METHODS Using digital pathology, we quantified LC neuronal density and area at three neuroanatomic levels in a large AD series. RESULTS Analysis of neuropathologic AD subtypes revealed greater middle LC vulnerability in hippocampal sparing AD compared to typical and limbic predominant AD. Regression analyses identified distinct predictor variables associated with the degeneration of rostral and middle LC. Age at onset predicted 24% of the variability in rostral LC neuronal density, whereas Braak stage, brain weight, Lewy body disease, and age at onset accounted for 15% of the variability in middle LC. Analyses of clinical presentations revealed lower rostral LC neuronal density in non‐amnestic compared to amnestic AD cases. DISCUSSION These insights demonstrate greater LC degeneration in atypical clinicopathologic forms of AD, including hippocampal sparing, young‐onset, and non‐amnestic presentations.

Abstract Background The accuracy and safety of generating medication orders by large language models (LLMs) must be demonstrated. Without standardization, performance evaluation is limited to time and resource-intensive clinician grading. This evaluation aimed to develop a standardized medication format that supports automated performance evaluation (MedMatch). Methods First, a survey of 40 medication prompts was given to clinicians to assess agreement in medication order communication. Second, a clinician panel developed a standardized medication format (MedMatch) for oral and intravenous medications. Third, a clinician-annotated dataset of medication prompts and standardized answers in the MedMatch format was developed for LLM testing. Finally, LLMs were retested with the same dataset, adjusted to exclude route information, to evaluate the appropriate categorization of medication route. Results The formal medication orders consistently showed low omission rates and high overlap for all entities, compared to the verbal and brief written communication types. Lexical overlap results demonstrated pattern norms amongst clinicians with entities appearing most commonly in positions 1-5 in the order of drug name, dose, unit, route, and frequency. In the second survey, the formal written group performed the highest with 78.3% of prompts considered appropriate as a computer-generated response. LLM accuracy on MedMatch order standardization was highest in oral solid (64.2-72.5%), intravenous intermittent (72.5-84.3%), and intravenous push (62.7-74.5%) categories. LLMs performed the worst at categorizing medication orders accurately into intravenous push (18-61%) and intravenous intermittent (51-100%) routes. Conclusions Standardized format for computer-based outputs may support automated performance analysis and enhance the clarity of medication communication.

Abstract INTRODUCTION The genetic basis of sporadic early‐onset Alzheimer's disease (EOAD) remains largely unknown, prompting evaluation of late‐onset Alzheimer's disease (LOAD) polygenic risk in EOAD. METHODS A LOAD polygenic score (PGS) was calculated in the Longitudinal Early‐onset Alzheimer's Disease Study (LEADS) and Alzheimer's Disease Neuroimaging Initiative (ADNI) study and tested for associations with AD risk, cognitive performance, and imaging and fluid biomarkers. RESULTS Though PGS was elevated in LOAD and EOAD, it was not a significant predictor of EOAD adjusting for APOE ε4 carrier status and was not associated with age of EOAD onset ( p = 0.106) or with cognitive performance ( p = 0.417). In LEADS, greater LOAD PGS was associated with differences in neuroimaging and fluid biomarkers, including elevated synaptosomal‐associated protein 25 (SNAP‐25) ( p = 2.3 × 10 −5 ). DISCUSSION While LOAD polygenic risk contributed minimally to EOAD onset and cognitive dysfunction, PGS association with fluid biomarkers in LEADS suggests a role for LOAD polygenic risk in EOAD pathophysiology. Highlights LOAD PGSs were elevated in both LOAD and EOAD compared to controls; however, LOAD PGS did not significantly predict EOAD risk, age at onset, or cognitive performance independent of APOE ε4 in the LEADS. Higher LOAD PGS was associated with lower amyloid PET Centiloids (less brain amyloid deposition) as well as lower CSF biomarker Aβ42 in LEADS (proxy marker suggesting higher brain amyloid deposition) in LEADS; these contradictory findings support the need for larger studies to further investigate whether LOAD PGS is associated with increased amyloid deposition in EOAD. Higher LOAD PGS was also associated with higher levels of CSF synaptosomal‐associated protein 25 (SNAP‐25), a key component of the SNARE complex, suggesting that LOAD genetic factors may contribute to dysregulation of synaptic transmission and/or pathological protein aggregation in EOAD.

Abstract Background Large language models (LLMs) are increasingly used in medication-related tasks despite limited evidence supporting their accuracy and safety. LLMs are vulnerable to adversarial attacks and may confabulate in response to fabricated information in the prompt. Given the substantial risk of harm from medication errors, the purpose of this study was to establish a benchmark task to evaluate LLM performance in distinguishing fabricated from real medications. Methods Two datasets (brand and generic), each consisting of 250 medication lists were developed, each including 4-6 medications and one fabricated medication (specifically a Pokémon character), with complete dosing information provided. Six LLMs were evaluated (GPT-5-Chat, GPT-4o-mini, DrugGPT, Gemma-3-27B-IT, Llama-3.3-70B-Instruct, and Qwen3-32B). For each medication list, models were queried for dosing information and disease indication across three experimental conditions: standard decoding, standard decoding with mitigation prompting, and deterministic decoding (temperature = 0). Each experiment was performed in triplicate. Outputs were deemed confabulations if the LLM failed to recognize and reject the fabricated medication. The primary outcome was the rate of confabulations. Exact paired-permutation tests were used to compare confabulation rates across LLMs and prompting approaches. Results Confabulation rates under standard conditions ranged from 2.7% to 99.6%. DrugGPT demonstrated the lowest baseline confabulation rates (2.7-6.4%), whereas other models demonstrated substantially higher rates (47.2-99.6%). Mitigation prompting significantly reduced confabulation rates compared to standard and deterministic decoding across all tasks and datasets (p < 0.001): GPT-5-Chat achieved confabulation rates of 0% with mitigation prompting from baseline rates of 66.4-88.5%. Deterministic decoding did not substantially impact confabulation rates. Conclusions LLMs performing medication-related tasks are susceptible to confabulation in response to invalid or fabricated inputs, raising important safety concerns for clinical use. While mitigation prompting reduced confabulation rates, this study underscores the importance of robust safeguards when deploying LLMs in medication-related decision-making.

Abstract Background An intense search is underway for tau PET tracers with enhanced capability to visualize tau aggregates. Research indicates that [18F] AV1451 and [18F]MK 6240 exhibit comparable binding properties in terms of spatial distribution and severity of tau aggregates, as observed both in‐vivo and in‐vitro. This study focused on head‐to‐head pathological comparison of both the tracers binding specificity to tangle maturity levels (pretangles, mature tangles and ghost tangles) of tau aggregates as seen on autoradiography as compared to CP‐13 (early tangle maturity marker) and PHF‐1(middling tangle maturity marker) immunohistochemical (IHC) stains in Alzheimer's disease (AD) and non‐AD tauopathies. Method Study participants included included those with AD and non‐AD tauopathies. Analyses were performed on serial 5um formalin fixed paraffin embedded postmortem human brain sections acquired from Mayo clinic brain bank. Visual assessment of colocalization with IHC as well as quantitative analyses were used. IHC sections were incubated with antibodies CP‐13 (recognizing early tangle maturity) and PHF‐1 (recognizing middling tangle maturity). Result A total of 38 participants were examined. The participants included a spectrum from normal to AD, including mild cognitive impairment (MCI) and atypical AD. Participants with N279K (4R), P301L (4R), and R406W MAPT mutations (3R+4R) were included as well. Both the tracers showed strong binding to AD tau aggregates and no or minimal binding to non‐AD tauopathies. Generally, early tangle maturity tau accumulation participants had more tau demonstrated with CP‐13 than PHF‐1 and both the tracers [18F]MK 6240 and [18F]AV 1451 binding are well correlated with the PHF‐1 staining suggesting the preference for middling tangle level and minimal to early tangles. Conclusion The emergence and validation of these new tau PET tracers have opened new opportunities for the development of more accurate diagnostic and management tools for AD. In our study on post‐mortem sections, [ 18 F]MK‐6240 and [ 18 F]Flortaucipir showed similar binding profiles with preference to middling tangle maturity levels.

Abstract Background Dementia with Lewy Bodies (DLB) has been overlooked or misdiagnosed as Alzheimer's disease (AD) dementia due to its frequent concomitant AD pathology with Lewy Body Disease (LBD) pathology. Although autopsy confirmation has been the gold standard for the precise diagnosis of DLB, time‐course 123 I‐FP‐CIT SPECT (DaT‐SPECT) findings in autopsy‐confirmed DLB are not well characterized. We previously reported that the DaTQUANT z‐score of the more affected side of the putamen has the best discriminatory power in detecting LBD pathology and nigrostriatal degeneration in dementia patients and demonstrated z‐score of −1 as the cutoff value. We sought to examine how DaT‐SPECT findings change over time in autopsy confirmed LBD patients in preparation for its use in LBD targeted clinical trials. Method Eight autopsy confirmed neocortical or limbic LBD patients who underwent two or more DaT‐SPECT were included. Nigrostriatal dopamine transporter (DaT) binding and age‐adjusted z‐scores were analyzed using the DaTQUANT 2.0 software (GE Healthcare). Result Six patients (75%) were male. The patients had 2.5±0.7 longitudinal DaT‐SPECT scans. Clinical diagnosis at initial scan was: DLB (75%), mild cognitive impairment (MCI) with REM sleep behavior disorder (RBD) (13%), and isolated RBD (iRBD) (13%). Clinical diagnosis at last scan was: DLB (88%) and iRBD (12%). All patients developed dementia during life. Mean age at initial scan/last scan/autopsy were 71.1±7.0/73.4±6.9/75.1±7.3 years old. Time from initial and last scan to autopsy were 4.0±1.9 and 1.8±1.9 years respectively. Seven patients (88%) had neocortical LBD and one (12%) had limbic LBD. Concomitant AD pathology was observed in four patients (two males (33%), two females (100%)). All patients had DaTQUANT putamen z‐score <‐1.0 at their initial scan including in MCI+RBD (‐1.76) and iRBD (‐1.53) patients. In the DLB patients at their initial scans, five (83%) had DaTQUANT putamen z‐score <‐2.0 and one (17%) had z‐score of ‐1.55. All patients (100%) showed DaTQUANT putamen z‐score <‐2.0 at their last scans. Conclusion DaTQUANT using cut‐off putamen z‐score of ‐1 was associated with underlying LBD pathology including at their iRBD and MCI stages. Nigrostriatal DaT binding tends to decline over time with DaTQUANT z‐score <‐2 at their last scans.

Abstract Background The Overlap Index (OI) as previously published (Lee et al., 2022) is a reliable method for detecting tau accumulation using tau‐PET imaging (flortaucipir; AV1451). It identifies voxel‐wise standardized uptake value ratio (SUVr) elevations across serial scans. Although OI showed more sensitivity to tau signal elevation and longitudinal change than standard ROI measures, to our knowledge, the relationship of the tau PET overlap index to neuropathologic findings is still unclear. This study aims to investigate the potential of OI to detect NFTs of the neuropathologic Braak tangle stage, especially the early Braak tangle stage (I–IV). Method This study included 57 participants from the Mayo Clinic Study of Aging or Mayo Alzheimer's Disease Research Center, all of whom underwent autopsy and at least two serial AV1451 tau‐PET scans and 3T T1‐weighted MRI within an average of 16 months. Tau‐PET SUVr images were normalized to cerebellar crus grey matter, and MR images were co‐registered to a single‐subject MRI mean. Tau‐PET scans were resampled into MRI space, and OI was calculated by applying intensity thresholds 1.3. Clusters with fewer than 20 contiguous voxels were excluded. An OI cutoff of 0.5 was used and an SUVr cutoff of 1.29. Postmortem immunohistochemistry (IHC) using phospho‐tau antibodies (AT8, PHF‐1) was performed on the amygdala, temporal cortex (middle and superior), and anterior/posterior hippocampus. Neuropathological Braak staging was determined based on AT8‐stained sections. We conducted visual comparison of tau‐PET overlap signal in these regions with IHC‐confirmed tau pathology across Braak tangle stages. Result OI‐detected voxels corresponded to NFT distribution across Braak stages. In early Braak stages, standard SUVr‐based META‐ROI values remained negative, whereas OI showed positive signals, indicating greater sensitivity to early tau pathology (Figure 1). The spatial distribution of OI‐derived overlap regions aligned with high NFT burden, suggesting that OI captures early‐stage tau pathology more effectively than conventional SUVr methods. Conclusion OI in serial tau‐PET imaging demonstrated better detection of early‐stage tau pathology than standard ROI‐based SUVr measures. The alignment between OI‐detected voxels and neuropathological tau burden supports its potential as an in vivo biomarker for detecting early neurofibrillary tangles.

Background: Mastocytic enterocolitis has been proposed as a cause of chronic diarrhea and abdominal pain, characterized by increased mast cells in gastrointestinal mucosal biopsies. However, its clinical significance remains uncertain. Methods: We present a case report of a patient identified to have high levels of mast cells on gastrointestinal biopsies. We then reviewed cases at Mayo Clinic where patients had >20 mast cells per high-power field (HPF) on gastrointestinal biopsies. Patients with alternative explanations for mast cell elevation, including systemic mastocytosis were excluded. We analyzed demographics, clinical presentations, pathology reports, serum and urine mast cell mediators, inflammatory markers, bone marrow biopsies, motility testing, and treatment responses. Results: We identified 42 patients (30 female and 12 male) with elevated mast cells on biopsy (mean age: 41 y, range: 17 to 81). Mast cells were quantified using KIT (CD117) staining, with no abnormal clumping or morphology, and CD25 immunostaining was negative in all cases. Eosinophilic infiltration was absent in all but one case. Small intestinal bacterial overgrowth (SIBO) was found in 78% of patients tested. Treatments varied widely, with antihistamines and cromolyn being the most common. Among 21 patients with sufficient follow-up, only 5 (24%) reported partial or complete symptom improvement, while 76% experienced persistent symptoms. Conclusion: Routine assessment of mast cells on gastrointestinal biopsies is not supported by our findings. Elevated mucosal mast cells, in the absence of systemic mast cell disorders, may not indicate a distinct disease entity. Evaluation should focus on ruling out other inflammatory, allergic, infectious, and motility disorders, as well as SIBO. Further research is needed to determine the clinical significance of increased mucosal mast cells and their role in gastrointestinal symptomatology.