Search for: All records

Transplantation provides patients suffering from end-stage kidney disease a better quality of life and long-term survival. However, over 20% of deceased donor kidneys are not utilized and never transplanted. While this is sometimes medically appropriate, this also reflects missed opportunities. We are designing Artificial Intelligence decision support for the kidney offer process to support both demand at the transplant center and supply at the organ procurement organization. This includes (1) developing deep learning models, (2) evaluating the effect of explainable interfaces, (3) improving fairness in the model output, (4) identifying factors that influence adoption decisions, and (5) conducting a randomized control trial using an ecologically valid and realistic simulation platform for behavioral experiments, to estimate the impact on kidney utilization. 

The rise of complex AI systems in healthcare and other sectors has led to a growing area of research called Explainable AI (XAI) designed to increase transparency. In this area, quantitative and qualitative studies focus on improving user trust and task performance by providing system- and prediction-level XAI features. We analyze stakeholder engagement events (interviews and workshops) on the use of AI for kidney transplantation. From this we identify themes which we use to frame a scoping literature review on current XAI features. The stakeholder engagement process lasted over nine months covering three stakeholder group's workflows, determining where AI could intervene and assessing a mock XAI decision support system. Based on the stakeholder engagement, we identify four major themes relevant to designing XAI systems – 1) use of AI predictions, 2) information included in AI predictions, 3) personalization of AI predictions for individual differences, and 4) customizing AI predictions for specific cases. Using these themes, our scoping literature review finds that providing AI predictions before, during, or after decision-making could be beneficial depending on the complexity of the stakeholder's task. Additionally, expert stakeholders like surgeons prefer minimal to no XAI features, AI prediction, and uncertainty estimates for easy use cases. However, almost all stakeholders prefer to have optional XAI features to review when needed, especially in hard-to-predict cases. The literature also suggests that providing both system and prediction-level information is necessary to build the user's mental model of the system appropriately. Although XAI features improve users' trust in the system, human-AI team performance is not always enhanced. Overall, stakeholders prefer to have agency over the XAI interface to control the level of information based on their needs and task complexity. We conclude with suggestions for future research, especially on customizing XAI features based on preferences and tasks. 

The use of Artificial Intelligence (AI) decision support is increasing in high-stakes contexts, such as healthcare, defense, and finance. Uncertainty information may help users better leverage AI predictions, especially when combined with their domain knowledge. We conducted a human-subject experiment with an online sample to examine the effects of presenting uncertainty information with AI recommendations. The experimental stimuli and task, which included identifying plant and animal images, are from an existing image recognition deep learning model, a popular approach to AI. The uncertainty information was predicted probabilities for whether each label was the true label. This information was presented numerically and visually. In the study, we tested the effect of AI recommendations in a within-subject comparison and uncertainty information in a between-subject comparison. The results suggest that AI recommendations increased both participants’ accuracy and confidence. Further, providing uncertainty information significantly increased accuracy but not confidence, suggesting that it may be effective for reducing overconfidence. In this task, participants tended to have higher domain knowledge for animals than plants based on a self-reported measure of domain knowledge. Participants with more domain knowledge were appropriately less confident when uncertainty information was provided. This suggests that people use AI and uncertainty information differently, such as an expert versus second opinion, depending on their level of domain knowledge. These results suggest that if presented appropriately, uncertainty information can potentially decrease overconfidence that is induced by using AI recommendations. 

Sustainable development requires an accelerated transition toward renewable energy. In particular, substantially scaling up solar photovoltaics (PV) adoption is a crucial component of reducing the impacts of climate change and promoting sustainable development. However, it is challenging to convince local governments to take action. This study uses a combination of propensity score matching (PSM) and difference-in-differences (DID) models to assess the effectiveness of a voluntary environmental program (VEP) called SolSmart that targets local governments to engage in solar-friendly practices to promote the local solar PV market in the United States. Via specific designation requirements and technical assistance, SolSmart simplifies the process of acting on interest in being solar friendly, has a wide coverage of basic solar-friendly actions with flexible implementation, and motivates completion with multiple levels of designation. We find that a local government’s participation in SolSmart is associated with an increased installed capacity of 18 to 19%/mo or with less statistical significance, an increased number of installations of 17%/mo in its jurisdiction. However, SolSmart has not shown a statistically significant impact on soft cost reductions to date. In evaluating the impact of the SolSmart program, this study improves our understanding of the causation between a VEP that encourages solar-friendly local government practices and multiple solar market outcomes. VEPs may be able to promote shifts toward sustainable development at the local level. Our findings have several implications for the design of VEPs that promote local sustainability.