Recruiting participants is a cornerstone of Human-Centric Computing (HCC) research, especially in Digital Health research and development. Effective recruitment ensures that the developed systems reflect the needs and experiences of the intended users. This paper explores recruitment strategies, challenges, and experiences encountered in a project focused on enhancing telehealth through technology co-design, development, and evaluation. By detailing recruitment efforts in the Palliative Care cohort through the think-aloud and simulation study phases, this paper provides insights and practical recommendations for future HCC research in the digital health area.

Histopathology image-based survival prediction aims to provide a precise assessment of cancer prognosis and can inform personalized treatment decision-making in order to improve patient outcomes. However, existing methods cannot automatically model the complex correlations between numerous morphologically diverse patches in each whole slide image (WSI), thereby preventing them from achieving a more profound understanding and inference of the patient status. To address this, here we propose a novel deep learning framework, termed dual-stream multi-dependency graph neural network (DM-GNN), to enable precise cancer patient survival analysis. Specifically, DM-GNN is structured with the feature updating and global analysis branches to better model each WSI as two graphs based on morphological affinity and global co-activating dependencies. As these two dependencies depict each WSI from distinct but complementary perspectives, the two designed branches of DM-GNN can jointly achieve the multi-view modeling of complex correlations between the patches. Moreover, DM-GNN is also capable of boosting the utilization of dependency information during graph construction by introducing the affinity-guided attention recalibration module as the readout function. This novel module offers increased robustness against feature perturbation, thereby ensuring more reliable and stable predictions. Extensive benchmarking experiments on five TCGA datasets demonstrate that DM-GNN outperforms other state-of-the-art methods and offers interpretable prediction insights based on the morphological depiction of high-attention patches. Overall, DM-GNN represents a powerful and auxiliary tool for personalized cancer prognosis from histopathology images and has great potential to assist clinicians in making personalized treatment decisions and improving patient outcomes.

COVID-19 regulations presented clinicians with a new set of challenges that affected their ability to efficiently provide patient care and, as a result, telemedicine was rapidly adopted to deliver care remotely. However, these telemedicine platforms undermine patient care due to clinicians' inability to acquire all the relevant patient information required to diagnose and treat the patient. To explore this gap, we conducted a requirements analysis for the development of a 3D remote patient monitoring and diagnosis platform, by using a user-centric design methodology. In this requirements analysis, we elicited information about the clinical domain, identified clinicians’ requirements, elicited clinicians’ insights, and documented the clinicians' requirements. The outcome was the emergence of refined clinicians' requirements to guide the implementation of the Digital Twin concept paired with holoportation for remote 3D monitoring and diagnosis of patients. We anticipate that the application of a 3D telemedicine platform with these requirements for patient care during a pandemic could potentially enhance clinicians' efficiency and the effectiveness of remote patient care.

MOTIVATION: Multiple instance learning (MIL) is a powerful technique to classify whole slide images (WSIs) for diagnostic pathology. The key challenge of MIL on WSI classification is to discover the critical instances that trigger the bag label. However, tumor heterogeneity significantly hinders the algorithm's performance. RESULTS: Here, we propose a novel multiplex-detection-based multiple instance learning (MDMIL) which targets tumor heterogeneity by multiplex detection strategy and feature constraints among samples. Specifically, the internal query generated after the probability distribution analysis and the variational query optimized throughout the training process are utilized to detect potential instances in the form of internal and external assistance, respectively. The multiplex detection strategy significantly improves the instance-mining capacity of the deep neural network. Meanwhile, a memory-based contrastive loss is proposed to reach consistency on various phenotypes in the feature space. The novel network and loss function jointly achieve high robustness towards tumor heterogeneity. We conduct experiments on three computational pathology datasets, e.g. CAMELYON16, TCGA-NSCLC, and TCGA-RCC. Benchmarking experiments on the three datasets illustrate that our proposed MDMIL approach achieves superior performance over several existing state-of-the-art methods. AVAILABILITY AND IMPLEMENTATION: MDMIL is available for academic purposes at https://github.com/ZacharyWang-007/MDMIL.

Secure management of healthcare records in dynamic contexts requires an understanding of the overall infrastructure of record flows and poses more challenges for vulnerable environments such as amongst the Rohingya refugees in Bangladesh. Understanding the overall infrastructure of how health clinics are providing medical treatments and how they are collecting and storing patient records is crucial as any changes or mismanagement in these records enables misuse or deliberate misinterpretations of medical data on various levels amongst individuals and Rohingya communities. Through an extensive field study in the Rohingya refugee camps in Bangladesh, we explored the management of healthcare records in different organizations. Over the course of our fieldwork, we interviewed 22 medical service providers from nine healthcare organizations connected to the Rohingya camps. Based on our findings, we design an abstract record management model and analyze it using a data provenance approach to identify the limitations of the existing record management. Our study shows vulnerabilities in ID management and security practices in healthcare record management. We further illustrate potential exploitation of these vulnerabilities through political, financial, and social lenses. To the best of our knowledge, this study is the first to discuss vulnerabilities in Rohingya refugees’ medical record management from political, social and economic views.

A successful application of an Internet of Things (IoT) based network depends on the accurate and successful delivery of a large amount of data collected from numerous sources. However, the highly dynamic nature of IoT network prevents the establishment of clear security perimeters and hampers the understanding of security aspects. Risk assessment in such networks requires good situational awareness with respect to security. Therefore, a comprehensive view of data propagation including information on security controls can improve security analysis and risk assessment in each layer of data propagation in an IoT architecture. Documentation of metadata is already used in data provenance to identify who generates which data, how, and when. However, documentation of security information is not seen as relevant for data provenance graphs. In this paper, we discuss the importance of adding security metadata in a data provenance graph. We propose a novel IoT Provenance model, Prov-IoT, which documents the history of data records considering data processing and aggregation along with security metadata to enable a foundation for trust in data. The model portrays a comprehensive framework and outlines the identification of information to be included in designing a security-aware provenance graph. This can be beneficial for uncovering system fault or intrusion. Also, it can be useful for decision-based systems for security analysis and risk estimation. We design an associated class diagram for the Prov-IoT model. Finally, we use an IoT healthcare example scenario to demonstrate the impact of the proposed model.