COMPASSTo Be Announced.
Collaborative Decision-Making Assistant for Healthcare Professionals: A Human-Centered AI Prototype Powered by Azure Open AI
Kenneth Yamikani Fukizi
This paper presents a demonstration of a collaborative decision-making assistant designed to support healthcare professionals in making informed and personalized treatment decisions for their patients. The prototype highlights the integration of advanced AI algorithms, explainable AI techniques, and the utilization of mainly Microsoft related technology stacks, including ASP.Net Core and Azure Open AI services. The significance of this prototype lies in its contribution to the field of human-computer interaction, design and critical perspectives, specifically within the sub-domain of Human-centered AI. The prototype demonstration highlights innovation in the design, usage, sociotechnical context, and application of the prototype, and emphasizes commitment to ethical AI practices and responsible AI development, with considerations for fairness, transparency, and mitigating bias in AI algorithms, promoting the ethical use of AI in healthcare.
Community Networks powered by Community Currencies
Keegan White, David Lloyd Johnson, Senka Hadzic, Melissa Densmore
In this demo, we will show how a mutual credit-based community voucher or currency integrated with a community-owned network and a local content server could incentivise users to become better custodians of commons infrastructure. This could lead to the generation of more locally relevant digital content and the expansion, use, and stability of a community voucher to support wider local markets that embrace local digital and physical goods and services.
Multi-Objective Portfolio Optimization Towards Sustainable Investments
Yong Zheng, Kumar Neelotpal Shukla, Jasmine Xu, David Xuejun Wang, Michael O’Leary
The process of financial portfolio optimization involves choosing the most suitable mix of assets to meet a particular investment goal. Conventional portfolio optimization primarily focuses on maximizing returns and minimizing risks while overlooking the importance of social responsibility or sustainability in financial investments. In this paper, we present a Python-based multi-objective portfolio optimization library for sustainable investments (MOPO-LSI). MOPO-LSI is able to take Environmental, Social and Governance (ESG) factors into consideration in financial portfolio, where investors assets can be well allocated to mutual funds towards the ESG optimization along with their financial goals in the investment. MOPO-LSI is easy to be configured and used, and it is capable of production solutions in two scenarios when client preferences are known or unknown. The developers can also easily customize the library to adapt it to their own financial objectives.
The BALTO Toolkit – A New Approach to Ethical and Sustainable Data Collection for Equitable Public Transit
Vanessa Frias-Martinez, Saad Abrar, Naman Awasthi, Sunyup Park, Jessica Vitak
In most American cities commuters on public transit have disproportionately lower incomes than commuters who use automobiles. Given the proven link between geographic and economic mobility, it is critical to offer quality public transit to improve access to jobs, health care and education opportunities. Departments of Transportation (DOTs) routinely measure public transit performance and quality perceptions to assess the need for improvements in the transit systems. Nevertheless, the performance metrics used fail to capture the experiences of low-income individuals who often endure complex, lengthy trips, requiring several modes or transfers. We propose BALTO, a novel toolkit to characterize transit system performance and passengers quality perceptions across all types of passengers and trips. We are designing the BALTO toolkit in collaboration with public housing residents from the Housing Authority of Baltimore City (HABC) and together with two local transit advocacy groups and the departments of transportation in Baltimore and in the state of Maryland.
Self-directed digital learning for maternity health workers A Choose-Your-Own-Adventure application for empathic care
Sharifa Negesa, Melissa Densmore
We explored the use of digital stories to support empathy skills training in maternity health workers. Our digital stories build on an existing in-person training approach; the Secret History (SH) that was developed by the Perinatal Mental Health Project. During SH training, health workers are invited to enact scenarios with patients, examining their reactions and responses as they learn more about the “history” of their patients and of their assumed characters as health workers. This training has resulted in improvement in empathic skills for health workers, but opportunities to scale the intervention are limited. The SH is costly to implement, requiring in-person workshops and facilitator training for small groups of workers. Our mobile application may either supplement or introduce the SH concepts at scale to health workers. The stories have been co-designed with mental health experts, midwives, and other trainers, and employ a “choose-your-own-adventure” approach, slowly revealing the histories of the characters, as in the original SH protocol. To inform decisions of the app design, data was collected through interviews, co-design workshops and focus group discussions as detailed in the methods section.
Digital Public Goods Interoperability: A Low-Code Middleware Approach
Andrew Amstrong Musoke, Jean Paul Nishimirwe, Nafiu Lawal, Assane Gueye
Digital Public Goods (DPGs) play a vital role in achieving the United Nations Sustainable Development Goals (SDGs) in low-income and middle-income countries. However, the lack of interoperability among different DPGs could lead to duplication of efforts and/or lack of (inter)-functionality since one DPG is not able to benefit from the features of another. This paper illustrates the need for interoperability, the difficulty of retrofitting interoperability in the numerous mature DPG projects and introduces a middleware application as a solution. The middleware application is a lightweight, technology-agnostic, portable, and modular application which facilitates transactions between the integrating system and the integrated system. By customizing and deploying the middleware, integrating system developers can save time and costs, reducing barriers to prototyping and increasing the adoption rate of DPGs. Furthermore, developers do not need to provision or access a sandbox as the middleware supports mocking responses. A use case involving the integration of two DPGs, a digital identity system and a health information system, is illustrated. The paper also describes future enhancements to the generalizability of the middleware from 1-to-any to any-to-any as well as improving security resilience with WebAuthn and custom cyber-security hardening tools and procedures.