University of Alberta

• ParkinsonNet: We propose a novel end-to-end network, ParkinsonNet, for automatically qualifying the severity of PD motor symptoms. This network is capable of processing multiple motor tests without any manual feature design. • Temporal Self-Attention Enhancement Module (TAEM): To accurately perceive the gradual progression of motor symptoms, we introduce TAEM, which combines temporal compression with long-term dependency modeling, enabling robust and comprehensive temporal feature extraction. • Similarity Matching Module (SMM): To address the challenges of class imbalance and limited datasets, we design the SMM, that transforms the conventional classification or regression task into a similarity matching problem. This module aligns skeleton features with their most similar text-based features, leveraging semantic relationships for improved performance. • Empirical evaluations: Extensive experiments are conducted on two recent PD datasets, demonstrating the superiority of ParkinsonNet, and providing essential benchmark performance for future algorithm development and evaluation. Parkinson’s Disease (PD) is a progressive neurodegenerative disorder characterized by worsening motor symptoms such as bradykinesia, imbalance, tremor, rigidity, and gait disturbances. Clinician assessments are often time-consuming and costly, and the limited availability of specialists, along with patient mobility issues, complicates frequent evaluations. In this paper, we propose a novel end-to-end network to automatically qualify the severity of motor symptoms in PD, referred to as ParkinsonNet. Unlike most existing methods that focus on isolated tests, ParkinsonNet provides a unified learning framework that is evaluated across multiple PD motor symptoms, as demonstrated on finger tapping and gait. Specifically, to accurately perceive the gradual progression of motor symptoms throughout an entire test cycle (e.g., decrementing amplitude), a temporal self-attention enhancement module is designed by combining temporal compression with long-term temporal dependency modeling. To ease the issues of class imbalance and limited datasets, a similarity matching module is proposed that transforms the conventional classification or regression task into a similarity matching problem, matching the skeleton feature with its most similar texture feature. Additionally, a vector quantization module is incorporated to encode spatiotemporal features into a discrete-valued space, compressing and abstracting motion representations while retaining critical information for more accurate classification. Extensive experiments on two newly identified benchmark datasets demonstrate the superiority of our ParkinsonNet and set new benchmark performance for future algorithm development and evaluation. Our code will be released at this https URL .

The authors declare no conflicts of interest. The data that support the findings of this study are available on request from the corresponding author. The data are not publicly available due to privacy or ethical restrictions.

This paper examines the causal role of face-to-face (F2F) interactions in generating local informational advantages for mutual fund managers. Using COVID-19 lockdowns as an exogenous shock, I show that fund managers’ performance on local stocks declined relative to distant stocks when in-person meetings were curtailed, driven by impaired investment timing rather than changes in firm fundamentals. I investigate two distinct benefits of F2F interactions arising from interpersonal cues: trust-building, which enhances the transmission of soft information, and impression management, which facilitates the transmission of favorable information. The results cannot be fully explained by changes in internal information flows or the use of public information, and are more pronounced for stocks in less transparent information environments and in regions with stronger social traits.

Physical activity (PA) during pregnancy and the postpartum period improves maternal and child health. However, there are no guidelines for Germany and it is not known to what extent midwives are informed about international PA guidelines. This study aimed to characterise midwives' beliefs, current practices, and knowledge of recommendations on PA during pregnancy and the postpartum period. A cross-sectional online survey was carried out among practising midwives (n=311) from May to August 2023. Data were descriptively analysed to characterize midwives' beliefs, current practices, and knowledge about PA, including awareness of international PA recommendations. Most midwives recognised the importance of PA and believed in the importance of their counselling. However, midwives' current practices and recommendations on PA varied widely. Only 16.1% of the midwives reported being aware of international PA guidelines during pregnancy and 5.8% during the postpartum period. Midwives are in a key position to influence maternal and child health, but their knowledge and guidance on PA recommendations leave room for improvement. This highlights the importance of optimized education and training in this area.

To provide insights into the potential impacts of release of oil sands process-affected water (OSPW) into the environment, chronic toxicity tests on early life stage rainbow trout (ELS-RBT) were conducted. The objective of the testing was to better characterize the effects of OSPW from the Alberta Oil sands on swim-up fry mortality, development (fish length and width, yolk sac development), and deformities (skeletal, craniofacial, finfold, and edemas) as a function of OSPW dilution (%) and ∑O2-naphthenic acid (NA) concentrations. More than 95% mortality in ELS-RBT was observed in the range of 22% to 100% OSPW. Lethal concentrations of 50% of the test population (LC50) values expressed in terms of OSPW dilutions were 13.7 (SE 0.7), 10.6 (SE 0.5), and 12.7 (SE 0.5) % for OSPW collected in 2019, 2021, and 2022, respectively. Corresponding LC50 values for ∑O2-NAs concentrations were 2.8 (SE 0.14), 2.0 (SE 0.11), and 2.2 (SE 0.09) mg/L, respectively. Primary sublethal effects included delayed development, craniofacial defects, and evidence of cardiovascular toxicity, including pericardial and yolk sac edema and hemorrhaging. Evidence of sublethal developmental effects was observed at OSPW dilutions above 10% and corresponding ∑O2-NA concentrations above 1.69 mg/L. The only exception was for 17.1 (SE 3.3) % craniofacial deformities at OSPW concentrations of 3.2% and corresponding ∑O2-NA concentrations of 0.66 mg/L, but only for OSPW collected in 2019. The results from this indicate that a 20-fold or greater dilution (or a corresponding removal of OSPW) of the tested OSPW from the Kearl site is sufficient to negate the chronic toxicity in rainbow trout investigated in this study.