ObjectiveWe hypothesized that specific mutations in the β‐glucocerebrosidase gene (GBA) causing neuropathic Gaucher's disease (GD) in homozygotes lead to aggressive cognitive decline in heterozygous Parkinson's disease (PD) patients, whereas non‐neuropathic GD mutations confer intermediate progression rates.MethodsA total of 2,304 patients with PD and 20,868 longitudinal visits for up to 12.8 years (median, 4.1) from seven cohorts were analyzed. Differential effects of four types of genetic variation in GBA on longitudinal cognitive decline were evaluated using mixed random and fixed effects and Cox proportional hazards models.ResultsOverall, 10.3% of patients with PD and GBA sequencing carried a mutation. Carriers of neuropathic GD mutations (1.4% of patients) had hazard ratios (HRs) for global cognitive impairment of 3.17 (95% confidence interval [CI], 1.60–6.25) and a hastened decline in Mini–Mental State Exam scores compared to noncarriers (p = 0.0009). Carriers of complex GBA alleles (0.7%) had an HR of 3.22 (95% CI, 1.18–8.73; p = 0.022). By contrast, the common, non‐neuropathic N370S mutation (1.5% of patients; HR, 1.96; 95% CI, 0.92–4.18) or nonpathogenic risk variants (6.6% of patients; HR, 1.36; 95% CI, 0.89–2.05) did not reach significance.InterpretationMutations in the GBA gene pathogenic for neuropathic GD and complex alleles shift longitudinal cognitive decline in PD into “high gear.” These findings suggest a relationship between specific types of GBA mutations and aggressive cognitive decline and have direct implications for improving the design of clinical trials. Ann Neurol 2016;80:674–685

Summary Background Cognitive decline is a debilitating manifestation of disease progression in Parkinson’s disease. We aimed to develop a clinical-genetic score to predict global cognitive impairment in patients with the disease. Methods A prediction algorithm for global cognitive impairment (defined as Mini Mental State Exam (MMSE) ≤25) was built using data from 1,350 patients with 5,165 longitudinal visits over 12.8 (median, 2.8) years. Age at onset, MMSE, education, motor exam score, gender, depression and GBA mutations, machine selected through stepwise Cox’ hazards analysis and Akaike’s information criterion, were used to compute the multivariable predictor. Independent validation was achieved in another 1,132 patients with 19,127 visits over 8.6 (median, 6.5) years. Findings The cognitive risk score accurately predicted cognitive impairment within ten years of disease onset with an area under the curve (AUC) of >0.85 in both the discovery (95% CI, 0.821–0.902) and validation populations (95% CI, 0.779 – 0.913). 72.6% of patients scoring in the highest quartile were cognitively impaired by ten years vs. 3.7% in the lowest quartile (hazard ratio, 18.4, 95% CI, 9.4 – 36.1). Dementia or disabling cognitive impairment was predicted with an AUC of 0.877 (95% CI 0.788–0.943) and high negative predictive value (0.920, 95% 0.877–0.954) at the predefined cutoff (0.196). Performance was stable in 10,000 randomly resampled subsets. Interpretation Our predictive algorithm provides a potential test for future cognitive health or impairment in patients with Parkinson’s. It could improve trials of cognitive interventions and inform on prognosis.

Background Chest x-ray is a relatively accessible, inexpensive, fast imaging modality that might be valuable in the prognostication of patients with COVID-19. We aimed to develop and evaluate an artificial intelligence system using chest x-rays and clinical data to predict disease severity and progression in patients with COVID-19. Methods We did a retrospective study in multiple hospitals in the University of Pennsylvania Health System in Philadelphia, PA, USA, and Brown University affiliated hospitals in Providence, RI, USA. Patients who presented to a hospital in the University of Pennsylvania Health System via the emergency department, with a diagnosis of COVID-19 confirmed by RT-PCR and with an available chest x-ray from their initial presentation or admission, were retrospectively identified and randomly divided into training, validation, and test sets (7:1:2). Using the chest x-rays as input to an EfficientNet deep neural network and clinical data, models were trained to predict the binary outcome of disease severity (ie, critical or non-critical). The deep-learning features extracted from the model and clinical data were used to build time-to-event models to predict the risk of disease progression. The models were externally tested on patients who presented to an independent multicentre institution, Brown University affiliated hospitals, and compared with severity scores provided by radiologists. Findings 1834 patients who presented via the University of Pennsylvania Health System between March 9 and July 20, 2020, were identified and assigned to the model training (n=1285), validation (n=183), or testing (n=366) sets. 475 patients who presented via the Brown University affiliated hospitals between March 1 and July 18, 2020, were identified for external testing of the models. When chest x-rays were added to clinical data for severity prediction, area under the receiver operating characteristic curve (ROC-AUC) increased from 0·821 (95% CI 0·796–0·828) to 0·846 (0·815–0·852; p<0·0001) on internal testing and 0·731 (0·712–0·738) to 0·792 (0·780–0 ·803; p<0·0001) on external testing. When deep-learning features were added to clinical data for progression prediction, the concordance index (C-index) increased from 0·769 (0·755–0·786) to 0·805 (0·800–0·820; p<0·0001) on internal testing and 0·707 (0·695–0·729) to 0·752 (0·739–0·764; p<0·0001) on external testing. The image and clinical data combined model had significantly better prognostic performance than combined severity scores and clinical data on internal testing (C-index 0·805 vs 0·781; p=0·0002) and external testing (C-inde 0·752 vs 0·715; p<0·0001). Interpretation In patients with COVID-19, artificial intelligence based on chest x-rays had better prognostic performance than clinical data or radiologist-derived severity scores. Using artificial intelligence, chest x-rays can augment clinical data i...