Toward a generalizable machine learning workflow for neurodegenerative disease staging with focus on neurofibrillary tangles.

Machine learning (ML) has increasingly been used to assist and expand current practices in neuropathology. However, generating large imaging datasets with quality labels is challenging in fields which demand high levels of expertise. Further complicating matters is the often seen disagreement between experts in neuropathology-related tasks, both at the case level and at a more granular level. Neurofibrillary tangles (NFTs) are a hallmark pathological feature of Alzheimer disease, and are associated with disease progression which warrants further investigation and granular quantification at a scale not currently accessible in routine human assessment. In this work, we first provide a baseline of annotator/rater agreement for the tasks of Braak NFT staging between experts and NFT detection using both experts and novices in neuropathology. We use a whole-slide-image (WSI) cohort of neuropathology cases from Emory University Hospital immunohistochemically stained for Tau. We develop a workflow for gathering annotations of the early stage formation of NFTs (Pre-NFTs) and mature intracellular (iNFTs) and show ML models can be trained to learn annotator nuances for the task of NFT detection in WSIs. We utilize a model-assisted-labeling approach and demonstrate ML models can be used to aid in labeling large datasets efficiently. We also show these models can be used to extract case-level features, which predict Braak NFT stages comparable to expert human raters, and do so at scale. This study provides a generalizable workflow for various pathology and related fields, and also provides a technique for accomplishing a high-level neuropathology task with limited human annotations.

Human grooming in comparative perspective: People in six small-scale societies groom less but socialize just as much as expected for a typical primate.

OBJECTIVES: Grooming has important utilitarian and social functions in primates but little is known about grooming and its functional analogues in traditional human societies. We compare human grooming to typical primate patterns to test its hygienic and social functions. MATERIALS AND METHODS: Bayesian phylogenetic analyses were used to derive expected human grooming time given the potential associations between grooming, group size, body size, terrestriality, and several climatic variables across 69 primate species. This was compared against observed times dedicated to grooming, other hygienic behavior, and conversation among the Maya, Pumé, Sanöma, Tsimane', Yanomamö, and Ye'kwana (mean number of behavioral scans = 23,514). RESULTS: Expected grooming time for humans was 4% (95% Credible Interval = 0.07%-14%), similar to values observed in primates, based largely on terrestriality and phylogenetic signal (mean λ = 0.56). No other covariates strongly associated with grooming across primates. Observed grooming time across societies was 0.8%, lower than 89% of the expected values. However, the observed times dedicated to any hygienic behavior (3.0%) or "vocal grooming," that is conversation (7.3%), fell within the expected range. CONCLUSIONS: We found (i) that human grooming may be a (recent) phylogenetic outlier when defined narrowly as parasite removal but not defined broadly as personal hygiene, (ii) there was no support for thermoregulatory functions of grooming, and (iii) no support for the "vocal grooming" hypothesis of language having evolved as a less time-consuming means of bonding. Thus, human grooming reflects decreased hygienic needs, but similar social needs compared to primate grooming.