Search

The goal of information-seeking dialogue is to respond to seeker queries with natural language utterances that are grounded on knowledge sources. However, dialogue systems often produce unsupported utterances, a phenomenon known as hallucination. To mitigate this behavior, we adopt a data-centric solution and create FaithDial, a new benchmark for hallucination-free dialogues, by editing hallucinated responses in the Wizard of Wikipedia (WoW) benchmark. We observe that FaithDial is more faithful than WoW while also maintaining engaging conversations. We show that FaithDial can serve as training signal for: i) a hallucination critic, which discriminates whether an utterance is faithful or not, and boosts the performance by 12.8 F1 score on the BEGIN benchmark compared to existing datasets for dialogue coherence; ii) high-quality dialogue generation. We benchmark a series of state-of-the-art models and propose an auxiliary contrastive objective that achieves the highest level of faithfulness and abstractiveness based on several automated metrics. Further, we find that the benefits of FaithDial generalize to zero-shot transfer on other datasets, such as CMU-Dog and TopicalChat. Finally, human evaluation reveals that responses generated by models trained on FaithDial are perceived as more interpretable, cooperative, and engaging.

Social network analysis encompasses the study of networked data and examines questions related to structures and patterns that can lead to the understanding of the data and the intrinsic relationships, such as identifying influential nodes, recognizing critical paths, predicting unobserved relationships, discovering communities, etc. All of these analyses, germane to a variety of application domains, are typically done on static information networks; that is, a fixed snapshot of the information network. Yet, a social network changes and understanding the evolution of the network and detecting these changes in the underlying structures is paramount for a multitude of applications. Looking at networks as fixed snapshots misses the opportunity to capture the evolutionary patterns. In this paper, we present a framework for modeling community evolution in social networks by tracking of events related to the life cycle of a community. We illustrate the capabilities of our framework by applying it to real datasets and validate the results using topics extracted from the tracked communities.

Recently, functional brain networks (FBN) have been used for the classification of neurological disorders, such as Autism Spectrum Disorders (ASD). Neurological disorder diagnosis with FBN is a challenging task due to the high heterogeneity in subjects and the noise correlations in brain networks. Meanwhile, it is challenging for the existing deep learning models to provide interpretable insights into the brain network. We propose a machine learning approach for the classification of neurological disorders while providing an interpretable framework.In this paper, we build upon graph neural network in order to learn effective representations for brain networks in an end-to-end fashion. Specifically, we present a prior brain structure learning-guided multi-view graph convolutional neural network (MVS-GCN), which collaborates the graph structure learning and multi-task graph embedding learning to improve the classification performance and identify the potential functional subnetworks.To demonstrate the effectiveness of our approach, we evaluate the performance of the proposed method on the Autism Brain Imaging Data Exchange (ABIDE) dataset and Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. The experimental results indicate that our MVS-GCN can achieve enhanced performance compared with state-of-the-art methods. Notably, MVS-GCN achieves an average accuracy/AUC of 69.38%/69.01% on the ABIDE dataset. Moreover, the obtained results from our model show high consistency with the previous neuroimaging derived evidence of within and between-networks biomarkers for ASD. The discovered subnetworks are used as evidence for the proposed MVS-GCN model.The proposed MVS-GCN method performs a graph embedding learning from the multi-views graph embedding learning perspective while considering eliminating the heterogeneity in brain networks and enhancing the feature representation of functional subnetworks, which can capture the essential embeddings to improve the classification performance of brain disorder diagnosis. The code is available at https://github.com/GuangqiWen/MVS-GCN.

BACKGROUND Approximately 1 in 3 Canadians will experience an addiction or mental health challenge at some point in their lifetime. Unfortunately, there are multiple barriers to accessing mental health care, including system fragmentation, episodic care, long wait times, and insufficient support for health system navigation. In addition, stigma may further reduce an individual’s likelihood of seeking support. Digital technologies present new and exciting opportunities to bridge significant gaps in mental health care service provision, reduce barriers pertaining to stigma, and improve health outcomes for patients and mental health system integration and efficiency. Chatbots (ie, software systems that use artificial intelligence to carry out conversations with people) may be explored to support those in need of information or access to services and present the opportunity to address gaps in traditional, fragmented, or episodic mental health system structures on demand with personalized attention. The recent COVID-19 pandemic has exacerbated even further the need for mental health support among Canadians and called attention to the inefficiencies of our system. As health care workers and their families are at an even greater risk of mental illness and psychological distress during the COVID-19 pandemic, this technology will be first piloted with the goal of supporting this vulnerable group. OBJECTIVE This pilot study seeks to evaluate the effectiveness of the Mental Health Intelligent Information Resource Assistant in supporting health care workers and their families in the Canadian provinces of Alberta and Nova Scotia with the provision of appropriate information on mental health issues, services, and programs based on personalized needs. METHODS The effectiveness of the technology will be assessed via voluntary follow-up surveys and an analysis of client interactions and engagement with the chatbot. Client satisfaction with the chatbot will also be assessed. RESULTS This project was initiated on April 1, 2021. Ethics approval was granted on August 12, 2021, by the University of Alberta Health Research Board (PRO00109148) and on April 21, 2022, by the Nova Scotia Health Authority Research Ethics Board (1027474). Data collection is anticipated to take place from May 2, 2022, to May 2, 2023. Publication of preliminary results will be sought in spring or summer 2022, with a more comprehensive evaluation completed by spring 2023 following the collection of a larger data set. CONCLUSIONS Our findings can be incorporated into public policy and planning around mental health system navigation by Canadian mental health care providers—from large public health authorities to small community-based, not-for-profit organizations. This may serve to support the development of an additional touch point, or point of entry, for individuals to access the appropriate services or care when they need them, wherever they are. INTERNATIONAL REGISTERED REPORT PRR1-10.2196/33717

Background Approximately 1 in 3 Canadians will experience an addiction or mental health challenge at some point in their lifetime. Unfortunately, there are multiple barriers to accessing mental health care, including system fragmentation, episodic care, long wait times, and insufficient support for health system navigation. In addition, stigma may further reduce an individual’s likelihood of seeking support. Digital technologies present new and exciting opportunities to bridge significant gaps in mental health care service provision, reduce barriers pertaining to stigma, and improve health outcomes for patients and mental health system integration and efficiency. Chatbots (ie, software systems that use artificial intelligence to carry out conversations with people) may be explored to support those in need of information or access to services and present the opportunity to address gaps in traditional, fragmented, or episodic mental health system structures on demand with personalized attention. The recent COVID-19 pandemic has exacerbated even further the need for mental health support among Canadians and called attention to the inefficiencies of our system. As health care workers and their families are at an even greater risk of mental illness and psychological distress during the COVID-19 pandemic, this technology will be first piloted with the goal of supporting this vulnerable group. Objective This pilot study seeks to evaluate the effectiveness of the Mental Health Intelligent Information Resource Assistant in supporting health care workers and their families in the Canadian provinces of Alberta and Nova Scotia with the provision of appropriate information on mental health issues, services, and programs based on personalized needs. Methods The effectiveness of the technology will be assessed via voluntary follow-up surveys and an analysis of client interactions and engagement with the chatbot. Client satisfaction with the chatbot will also be assessed. Results This project was initiated on April 1, 2021. Ethics approval was granted on August 12, 2021, by the University of Alberta Health Research Board (PRO00109148) and on April 21, 2022, by the Nova Scotia Health Authority Research Ethics Board (1027474). Data collection is anticipated to take place from May 2, 2022, to May 2, 2023. Publication of preliminary results will be sought in spring or summer 2022, with a more comprehensive evaluation completed by spring 2023 following the collection of a larger data set. Conclusions Our findings can be incorporated into public policy and planning around mental health system navigation by Canadian mental health care providers—from large public health authorities to small community-based, not-for-profit organizations. This may serve to support the development of an additional touch point, or point of entry, for individuals to access the appropriate services or care when they need them, wherever they are. International Registered Report Identifier (IRRID) PRR1-10.2196/33717

Accurate diagnosis of psychiatric disorders plays a critical role in improving the quality of life for patients and potentially supports the development of new treatments. Graph convolutional networks (GCNs) are shown to be successful in modeling applications with graph structures. However, training an accurate GCNs model for brain networks faces several challenges, including high dimensional and noisy correlation in the brain networks, limited labeled training data, and depth limitation of GCN learning. Generalization and interpretability are important in developing predictive models for clinical diagnosis. To address these challenges, we proposed an ensemble framework involving hierarchical GCN and transfer learning for sparse brain networks, which allows GCN to capture the intrinsic correlation among the subjects and domains, to improve the network embedding learning for disease diagnosis. Extensive experiments on two real medical clinical applications: diagnosis of Autism spectrum disorder (ASD) and diagnosis of Alzheimer's disease (AD) on both the ADNI and ABIDE databases, showing the effectiveness of the proposed framework. We achieved state-of-the-art accuracy and AUC for AD/MCI and ASD/NC (Normal control) classification in comparison with studies that used functional connectivity as features or GCN models. The proposed TE-HI-GCN model achieves the best classification performance, leading to about 27.93% (31.38%) improvement for ASD and 16.86% (44.50%) for AD in terms of accuracy and AUC compared with the traditional GCN model. Moreover, the obtained clustering results show high correspondence with the previous neuroimaging derived evidence of within and between-networks biomarkers for ASD. The discovered subnetworks are used as evidence for the proposed TE-HI-GCN model. Furthermore, this work is the first attempt of transfer learning on the two related disorder domains to uncover the correlation among the two diseases with a transfer learning scheme.

Background Chatbots have been increasingly considered for applications in the health care field. However, it remains unclear how a chatbot can assist users with complex health needs, such as parents of children with neurodevelopmental disorders (NDDs) who need ongoing support. Often, this population must deal with complex and overwhelming health information, which can make parents less likely to use a software that may be very helpful. An approach to enhance user engagement is incorporating game elements in nongame contexts, known as gamification. Gamification needs to be tailored to users; however, there has been no previous assessment of gamification use in chatbots for NDDs. Objective We sought to examine how gamification elements are perceived and whether their implementation in chatbots will be well received among parents of children with NDDs. We have discussed some elements in detail as the initial step of the project. Methods We performed a narrative literature review of gamification elements, specifically those used in health and education. Among the elements identified in the literature, our health and social science experts in NDDs prioritized five elements for in-depth discussion: goal setting, customization, rewards, social networking, and unlockable content. We used a qualitative approach, which included focus groups and interviews with parents of children with NDDs (N=21), to assess the acceptability of the potential implementation of these elements in an NDD-focused chatbot. Parents were asked about their opinions on the 5 elements and to rate them. Video and audio recordings were transcribed and summarized for emerging themes, using deductive and inductive thematic approaches. Results From the responses obtained from 21 participants, we identified three main themes: parents of children with NDDs were familiar with and had positive experiences with gamification; a specific element (goal setting) was important to all parents, whereas others (customization, rewards, and unlockable content) received mixed opinions; and the social networking element received positive feedback, but concerns about information accuracy were raised. Conclusions We showed for the first time that parents of children with NDDs support gamification use in a chatbot for NDDs. Our study illustrates the need for a user-centered design in the medical domain and provides a foundation for researchers interested in developing chatbots for populations that are medically vulnerable. Future studies exploring wide range of gamification elements with large number of potential users are needed to understand the impact of gamification elements in enhancing knowledge mobilization.

BACKGROUND Chatbots have been increasingly considered for applications in the health and social care fields. Currently, it remains unclear how a chatbot could engage users coping with complex health needs, such as parents of individuals with neurodevelopmental disorders (NDDs), who often need frequent and ongoing support. One approach to enhancing user engagement is the use of game elements in non-game contexts, known as gamification. To be effective, gamification needs to be tailored to users. OBJECTIVE We sought to identify which gamification elements would be the most useful in a chatbot that focuses on supporting families of children and youths with NDDs. METHODS We performed a narrative literature review of gamification elements and their current implementation. We then used a qualitative approach, which included a series of focus groups and interviews with caregivers of individuals with NDDs (N = 21) to identify potential gamification elements that could be well-suited for a chatbot focused on NDDs. Transcripts were analyzed for emerging themes. RESULTS From our 21 participants, we identified 3 main themes: 1) parents of individuals with NDDs were familiar and had positive experiences with gamification; 2) specific gamification element (goal setting) was considered an important feature for a chatbot for NDDs, whereas others (customization, rewards, and unlockable content) received more mixed opinions; and 3) although social networking was viewed positively, it is a complex feature to implement due to the pertaining issue of medical fact-checking. CONCLUSIONS We show for the first time that prospective users (parents of individuals with NDDs) support the use of gamification in a chatbot for NDDs. Our study illustrates the importance of adopting a user-centred design when deciding which gamification elements to include, as some commonly used elements were perceived negatively by this specific group of users.

Early detection and treatment of diabetic retinopathy (DR) can significantly reduce the risk of vision loss in patients. In essence, we are faced with two challenges: (i) how to simultaneously achieve domain adaptation from the different domains and (ii) how to build an interpretable multi-instance learning (MIL) on the target domain in an end-to-end framework. In this paper, we address these issues and propose a unified weakly-supervised domain adaptation framework, which consists of three components: domain adaptation, instance progressive discriminator and multi-instance learning with attention. The method models the relationship between the patches and images in the target domain with a multi-instance learning scheme and an attention mechanism. Meanwhile, it incorporates all available information from both source and target domains for a jointly learning strategy. We validate the performance of the proposed framework for DR grading on the Messidor dataset and the large-scale Eyepacs dataset. The experimental results demonstrate that it achieves an average accuracy of 0.949 (95% CI 0.931-0.958)/0.764 (95% CI 0.755-0.772) and an average AUC value of 0.958 (95% CI 0.945-0.962)/0.749 (95% CI 0.732-0.761) for binary-class/multi-class classification tasks on the Messidor dataset. Moreover, the proposed method achieves an accuracy of 0.887 and a quadratic weighted kappa score value of 0.860 on the Eyepacs dataset, outperforming the state-of-the-art approaches. Comprehensive experiments confirm the effectiveness of the approach in terms of both grading performance and interpretability. The source code is available at https://github.com/HouQingshan/WAD-Net.

The aim of this paper is to describe a novel algorithm for False Positive Reduction in lung nodule Computer Aided Detection(CAD).In this paper, we describes a new CT lung CAD method which aims to detect solid nodules. Specially, we proposed a multi-kernel classifier with a ℓThe results demonstrates that the FISTA-style accelerated proximal descent method is efficient for the ℓThe proposed approach exhibits some remarkable advantages both in heterogeneous feature subsets fusion and classification phases. Compared with the fusion strategies of feature-level and decision level, the proposed ℓ