In acute ischemic stroke treatment, prediction of tissue survival outcome plays a fundamental role in the clinical decision-making process, as it can be used to assess the balance of risk vs. possible benefit when considering endovascular clot-retrieval intervention. For the first time, we construct a deep learning model of tissue fate based on randomly sampled local patches from the hypoperfusion (Tmax) feature observed in MRI immediately after symptom onset. We evaluate the model with respect to the ground truth established by an expert neurologist four days after intervention. Experiments on 19 acute stroke patients evaluated the accuracy of the model in predicting tissue fate. Results show the superiority of the proposed regional learning framework versus a single-voxel-based regression model.

No abstract

In many traditional labor markets, women earn less on average compared to men. However, it is unclear whether this discrepancy persists in the online gig economy, which bears important differences from the traditional labor market (e.g., more flexible work arrangements, shorter-term engagements, reputation systems). In this study, we collected self-determined hourly bill rates from the public profiles of 48,019 workers in the United States (48.8% women) on Upwork, a popular gig work platform. The median female worker set hourly bill rates that were 74% of the median man's hourly bill rates, a gap than cannot be entirely explained by online and offline work experience, education level, and job category. However, in some job categories, we found evidence of a more complex relationship between gender and earnings: women earned more overall than men by working more hours, outpacing the effect of lower hourly bill rates. To better support equality in the rapidly growing gig economy, we encourage continual evaluation of the complex gender dynamics on these platforms and discuss whose responsibility it is to address inequalities.

No abstract

Tech users currently have limited ability to act on concerns regarding the negative societal impacts of large tech companies. However, recent work suggests that users can exert leverage using their role in the generation of valuable data, for instance by withholding their data contributions to intelligent technologies. We propose and evaluate a new means to exert this type of leverage against tech companies: "conscious data contribution" (CDC). Users who participate in CDC exert leverage against a target tech company by contributing data to technologies operated by a competitor of that company. Using simulations, we find that CDC could be highly effective at reducing the gap in intelligent technologies performance between an incumbent and their competitors. In some cases, just 20% of users contributing data they have produced to a small competitor could help that competitor get 80% of the way towards the original company's best-case performance. We discuss the implications of CDC for policymakers, tech designers, and researchers.