Recalibrating probabilistic forecasts of epidemics

Distributional forecasts are important for a wide variety of applications, including forecasting epidemics. Often, forecasts are miscalibrated, or unreliable in assigning uncertainty to future events. We present a recalibration method that can be applied to a black-box forecaster given retrospective forecasts and observations, as well as an extension to make this method more effective in recalibrating epidemic forecasts. This method is guaranteed to improve calibration and log score performance when trained and measured in-sample. We also prove that the increase in expected log score of a recalibrated forecaster is equal to the entropy of the PIT distribution. We apply this recalibration method to the 27 influenza forecasters in the FluSight Network and show that recalibration reliably improves forecast accuracy and calibration. This method, available on Github, is effective, robust, and easy to use as a post-processing tool to improve epidemic forecasts.

Deep learning reveals disease-specific signatures of white matter pathology in tauopathies

Although pathology of tauopathies is characterized by abnormal tau protein aggregation in both gray and white matter regions of the brain, neuropathological investigations have generally focused on abnormalities in the cerebral cortex because the canonical aggregates that form the diagnostic criteria for these disorders predominate there. This corticocentric focus tends to deemphasize the relevance of the more complex white matter pathologies, which remain less well characterized and understood. We took a data-driven machine-learning approach to identify novel disease-specific morphologic signatures of white matter aggregates in three tauopathies: Alzheimer disease (AD), progressive supranuclear palsy (PSP), and corticobasal degeneration (CBD). We developed automated approaches using whole slide images of tau immunostained sections from 49 human autopsy brains (16 AD,13 CBD, 20 PSP) to identify cortex/white matter regions and individual tau aggregates, and compared tau-aggregate morphology across these diseases. Tau burden in the gray and white matter for individual subjects strongly correlated in a highly disease-specific fashion. We discovered previously unrecognized tau morphologies for AD, CBD and PSP that may be of importance in disease classification. Intriguingly, our models classified diseases equally well based on either white or gray matter tau staining. Our results suggest that tau pathology in white matter is informative, disease-specific, and linked to gray matter pathology. Machine learning has the potential to reveal latent information in histologic images that may represent previously unrecognized patterns of neuropathology, and additional studies of tau pathology in white matter could improve diagnostic accuracy.

Predictors of cognitive impairment in primary age-related tauopathy: an autopsy study

Primary age-related tauopathy (PART) is a form of Alzheimer-type neurofibrillary degeneration occurring in the absence of amyloid-beta (Aβ) plaques. While PART shares some features with Alzheimer disease (AD), such as progressive accumulation of neurofibrillary tangle pathology in the medial temporal lobe and other brain regions, it does not progress extensively to neocortical regions. Given this restricted pathoanatomical pattern and variable symptomatology, there is a need to reexamine and improve upon how PART is neuropathologically assessed and staged. We performed a retrospective autopsy study in a collection (n = 174) of post-mortem PART brains and used logistic regression to determine the extent to which a set of clinical and neuropathological features predict cognitive impairment. We compared Braak staging, which focuses on hierarchical neuroanatomical progression of AD tau and Aβ pathology, with quantitative assessments of neurofibrillary burden using computer-derived positive pixel counts on digitized whole slide images of sections stained immunohistochemically with antibodies targeting abnormal hyperphosphorylated tau (p-tau) in the entorhinal region and hippocampus. We also assessed other factors affecting cognition, including aging-related tau astrogliopathy (ARTAG) and atrophy. We found no association between Braak stage and cognitive impairment when controlling for age (p = 0.76). In contrast, p-tau burden was significantly correlated with cognitive impairment even when adjusting for age (p = 0.03). The strongest correlate of cognitive impairment was cerebrovascular disease, a well-known risk factor (p < 0.0001), but other features including ARTAG (p = 0.03) and hippocampal atrophy (p = 0.04) were also associated. In contrast, sex, APOE, psychiatric illness, education, argyrophilic grains, and incidental Lewy bodies were not. These findings support the hypothesis that comorbid pathologies contribute to cognitive impairment in subjects with PART. Quantitative approaches beyond Braak staging are critical for advancing our understanding of the extent to which age-related tauopathy changes impact cognitive function.