Americans are increasingly relying on crowdfunding to pay for the costs of healthcare. In medical crowdfunding (MCF), online platforms allow individuals to appeal to social networks to request donations for health and medical needs. Users are often told that success depends on how they organize and share their campaigns to increase social network engagement. However, experts have cautioned that MCF could exacerbate health and social disparities by amplifying the choices (and biases) of the crowd and leveraging these to determine who has access to financial support for healthcare. To date, research on potential axes of disparity in MCF, and their impacts on fundraising outcomes, has been limited. To answer these questions, this paper presents an exploratory cross-sectional study of a randomized sample of 637 MCF campaigns on the popular platform Gofundme, for which the race, gender, age, and relationships of campaigners and campaign recipients were categorized alongside campaign characteristics and outcomes. Using both descriptive and inferential statistics, the analysis examines race, gender, and age disparities in MCF use, and tests how these are associated with differential campaign outcomes. The results show systemic disparities in MCF use and outcomes: non-white users (and black women in particular) are under-represented; there is significant evidence of an additional digital care labor burden on women organizers of campaigns; and marginalized race and gender groups are associated with poorer fundraising outcomes. Outcomes are only minimally associated with campaign characteristics under users' control, such as photos, videos, and updates. These results corroborate widespread concerns how technology fuels health inequities, and about how crowdfunding may be creating an unequal and biased marketplace for those seeking financial support to access healthcare. Further research and better data access are needed to explore these dynamics more deeply and inform policy for this largely unregulated industry.

No abstract

Identifying the targets of an antimicrobial peptide is a fundamental step in studying the innate immune response and combating antibiotic resistance, and more broadly, precision medicine and public health. There have been extensive studies on the statistical and computational approaches to identify (i) whether a peptide is an antimicrobial peptide (AMP) or a non-AMP and (ii) which targets are these sequences effective to (Gram-positive, Gram-negative, etc.). Despite the existing deep learning methods on this problem, most of them are unable to handle the small AMP classes (anti-insect, anti-parasite, etc.). And more importantly, some AMPs can have multiple targets, which the previous methods fail to consider. In this study, we build a diverse and comprehensive multi-label protein sequence database by collecting and cleaning amino acids from various AMP databases. To generate efficient representations and features for the small classes dataset, we take advantage of a protein language model trained on 250 million protein sequences. Based on that, we develop an end-to-end hierarchical multi-label deep forest framework, HMD-AMP, to annotate AMP comprehensively. After identifying an AMP, it will further predict what targets the AMP can effectively kill from eleven available classes. Extensive experiments suggest that our framework outperforms state-of-the-art models in both the binary classification task and the multi-label classification task, especially on the minor classes. Compared with the previous deep learning methods, our method improves the performance on macro-AUROC by 11%. The model is robust against reduced features and small perturbations and produces promising results. We believe HMD-AMP will both contribute to the future wet-lab investigations of the innate structural properties of different antimicrobial peptides and build promising empirical underpinnings for precise medicine with antibiotics.

Despite the growing popularity of human mobility studies that collect GPS location data, the problem of determining the minimum required length of GPS monitoring has not been addressed in the current statistical literature. In this paper we tackle this problem by laying out a theoretical framework for assessing the temporal stability of human mobility based on GPS location data. We define several measures of the temporal dynamics of human spatiotemporal trajectories based on the average velocity process, and on activity distributions in a spatial observation window. We demonstrate the use of our methods with data that comprise the GPS locations of 185 individuals over the course of 18 months. Our empirical results suggest that GPS monitoring should be performed over periods of time that are significantly longer than what has been previously suggested. Furthermore, we argue that GPS study designs should take into account demographic groups.

Identifying the targets of an antimicrobial peptide is a fundamental step in studying the innate immune response and combating antibiotic resistance, and more broadly, precision medicine and public health. There have been extensive studies on the statistical and computational approaches to identify (i) whether a peptide is an antimicrobial peptide (AMP) or a non-AMP and (ii) which targets are these sequences effective to (Gram-positive, Gram-negative, etc.). Despite the existing deep learning methods on this problem, most of them are unable to handle the small AMP classes (anti-insect, anti-parasite, etc.). And more importantly, some AMPs can have multiple targets, which the previous methods fail to consider. In this study, we build a diverse and comprehensive multi-label protein sequence database by collecting and cleaning amino acids from various AMP databases. To generate efficient representations and features for the small classes dataset, we take advantage of a protein language model trained on 250 million protein sequences. Based on that, we develop an end-to-end hierarchical multi-label deep forest framework, HMD-AMP, to annotate AMP comprehensively. After identifying an AMP, it will further predict what targets the AMP can effectively kill from eleven available classes. Extensive experiments suggest that our framework outperforms state-of-the-art models in both the binary classification task and the multi-label classification task, especially on the minor classes. Compared with the previous deep learning methods, our method improves the performance on macro-AUROC by 11%. The model is robust against reduced features and small perturbations and produces promising results. We believe HMD-AMP will both contribute to the future wet-lab investigations of the innate structural properties of different antimicrobial peptides and build promising empirical underpinnings for precise medicine with antibiotics.