Being able to explain the prediction clinical end-users is a necessity leverage power of artificial intelligence (AI) models for decision support. For medical images, feature attribution map, or heatmap, most common form explanation that highlights important features AI models' prediction. However, it unknown how well heatmaps perform on explaining decisions multi-modal where each image modality channel visualizes distinct information same underlying biomedical phenomenon. Understanding such...

Pompe disease is an autosomal recessive lysosomal glycogen storage disorder that has been reported in different ethnic populations which carry common mutations of the acid alpha-glucosidase (GAA) gene. The GAA mutation pattern mainland Chinese patients with late-onset still not well understood. We presented clinical and genetic characteristics 27 from 24 families. analysis revealed 26 mutations, including 10 were novel. allelic frequency c.2238G > C (p.W746C) was found to be 27.08% this...

Cybersickness, which is also called Virtual Reality (VR) sickness, poses a significant challenge to the VR user experience. Previous work demonstrated viability of predicting cybersickness for 360°videos. Is it possible automatically predict level interactive games? In this paper, we present machine learning approach games. First, proposed novel ranking-rating (RR) score measure ground-truth annotations cybersickness. We then verified RR scores by comparing them with Simulator Sickness...

Chronic Pain (CP) has been identified as a complex medical condition, one that is difficult for sufferers to articulate and others discern. This may interfere with the ability of patient's family, friends healthcare practitioners understand what it like live CP, or even believe exists. A reluctance by CP patient in turn exacerbate pain sequelae common such depression, frustration, stigma social isolation. The goal this research help foster empathy patients experience designing evaluating...

The ability to explain decisions end-users is a necessity deploy AI as critical decision support. Yet making explainable non-technical relatively ignored and challenging problem. To bridge the gap, we first identify twelve end-user-friendly explanatory forms that do not require technical knowledge comprehend, including feature-, example-, rule-based explanations. We then instantiate prototyping cards in four AI-assisted decision-making tasks, conduct user study co-design low-fidelity...

Being able to explain the prediction clinical end-users is a necessity leverage power of artificial intelligence (AI) models for decision support. For medical images, feature attribution map, or heatmap, most common form explanation that highlights important features AI models' prediction. However, it unknown how well heatmaps perform on explaining decisions multi-modal where each image modality channel visualizes distinct information same underlying biomedical phenomenon. Understanding such...

Non-technical end-users are silent and invisible users of the state-of-the-art explainable artificial intelligence (XAI) technologies. Their demands requirements for AI explainability not incorporated into design evaluation XAI techniques, which developed to explain rationales decisions assist their critical decisions. This makes techniques ineffective or even harmful in high-stakes applications, such as healthcare, criminal justice, finance, autonomous driving systems. To systematically...

Setting proper evaluation objectives for explainable artificial intelligence (XAI) is vital making XAI algorithms follow human communication norms, support reasoning processes, and fulfill needs AI explanations. In this position paper, we examine the most pervasive human-grounded concept in evaluation, explanation plausibility. Plausibility measures how reasonable machine compared to explanation. has been conventionally formulated as an important objective explainability tasks. We argue...

For nearly two decades, immersive Virtual Reality (VR) has been used as a form of pain distraction and management for acute, chronic cancer pain. Moreover, in numerous studies, VR games virtual environments (VEs) have shown to be effective during chemotherapy treatment reducing anxiety. However, amongst all these research few focused on pediatric patients who are undergoing treatment. Furthermore, most the studies commercial video which were neither specifically tailored nor patients....

Being able to explain the prediction clinical end-users is a necessity leverage power of AI models for decision support. For medical images, saliency maps are most common form explanation. The highlight important features model's prediction. Although many map methods have been proposed, it unknown how well they perform on explaining decisions multi-modal where each modality/channel carries distinct meanings same underlying biomedical phenomenon. Understanding such modality-dependent...

Stigma is a common and serious problem for patients who suffer from depression other mental illnesses. We designed game to address this problem. The enables player experience strive overcome the disempowering aspects of during journey recovery. Through game's interaction, may gain better understanding relationship between patient disease, which in turn help change players' moral model with disease model, thereby diminish stigma depression.

The inappropriate prescription of antibiotics may cause severe medical outcomes such as antibiotic resistance. To prevent situations and facilitate appropriate prescribing, we designed developed an asynchronous collaborative visual analytics tool. It visualizes the antibiotics' coverage spectrum that allows users choose most antibiotics. collaboration around visualization mimics actual scenarios in clinical settings, provides supportive information during physician's decision-making process....

Pain is both a universal and unique experience for its sufferers. Nonetheless, pain also invisible incommunicable that it becomes difficult the public to understand or even believe suffering, especially persistent form of pain: Chronic Pain. Therefore, we designed developed game -- AS IF foster non-patients' empathy In this game, players engage with connecting dots tasks through whole body interaction. After they generate connection their virtual body, will certain degree activity limitation...

Wearable trackers and mobile applications can facilitate self-reflection of doing physical activity. The gamification process incorporates game design elements with persuasive systems in order to encourage more activities. In this paper, the a game, FitPet, is introduced. FitPet application that combines ubiquity simplicity devices engagement computing games, intended motivate people incorporate walking into their daily life routine.