Creating intervention messages for smoking cessation is a labor-intensive process. Advances in Large Language Models (LLMs) offer a promising alternative for automated message generation. Two critical questions remain: 1) How to optimize LLMs to mimic human expert writing, and 2) Do LLM-generated messages meet clinical standards? We systematically examined the message generation and evaluation processes through three studies investigating prompt engineering (Study 1), decoding optimization (Study 2), and expert review (Study 3). We employed computational linguistic analysis in LLM assessment and established a comprehensive evaluation framework, incorporating automated metrics, linguistic attributes, and expert evaluations. Certified tobacco treatment specialists assessed the quality, accuracy, credibility, and persuasiveness of LLM-generated messages, using expert-written messages as the benchmark. Results indicate that larger LLMs, including ChatGPT, OPT-13B, and OPT-30B, can effectively emulate expert writing to generate well-written, accurate, and persuasive messages, thereby demonstrating the capability of LLMs in augmenting clinical practices of smoking cessation interventions.
doi.org/10.1145/3613904.3641965
Underlying humanity’s social abilities is the brain’s capacity to interpersonally synchronize. Experimental, lab-based neuropsychological studies have demonstrated that inter-brain synchrony can be technologically mediated. However, knowledge in deploying these technologies in-the-wild and studying their user experience, an area HCI excels in, is lacking. With advances in mobile brain sensing and stimulation, we identify an opportunity for HCI to investigate the in-the-wild augmentation of inter-brain synchrony. We designed “PsiNet,” the first wearable brain-to-brain system aimed at augmenting inter-brain synchrony in-the-wild. Participant interviews illustrated three themes that describe the user experience of modulated inter-brain synchrony: hyper-awareness; relational interaction; and the dissolution of self. We contribute these three themes to assist HCI theorists’ discussions of inter-brain synchrony experiences. We also present three practical design tactics for HCI practitioners designing inter-brain synchrony, and hope that our work guides a HCI future of brain-to-brain experiences which fosters human connection.
doi.org/10.1145/3613904.3641983
From wearable health tracking to sensor-laden cities, AI-enhanced pervasive sensing platforms promise far-reaching benefits yet also introduce societal risks. How might designers of these platforms effectively navigate their complex ecology and sociotechnical dynamics? To explore this question, we interviewed designers building mental health technologies who undertook this challenge. They are hospital chief medical information officers and startup founders together striving to create new sensors/AI platforms and integrate them into the healthcare ecosystem. We found that, while all designers aspired to build comprehensive care platforms, their efforts focused on serving either consumers or physicians, delivering a subset of healthcare interventions, and demonstrating system effectiveness one metric at a time. Consequently, breakdowns in patient journeys are emerging; societal risks loom large. We describe how the data economy, designers' mindsets, and evaluation challenges led to these unintended design consequences. We discuss implications for designing pervasive sensing and AI platforms for social good.
doi.org/10.1145/3613904.3642793
Artificial Intelligence (AI) in medical applications holds great promise. However, the use of Machine Learning-based (ML) systems in clinical practice is still minimal. It is uniquely difficult to introduce clinician-facing ML-based systems in practice, which has been recognised in HCI and related fields. Recent publications have begun to address the sociotechnical challenges of designing, developing, and successfully deploying clinician-facing ML-based systems. We conducted a qualitative systematic review and provided answers to the question: “How can HCI researchers and practitioners contribute to the successful realisation of ML in medical practice?” We reviewed 25 eligible papers that investigated the real-world clinical implications of concrete clinician-facing ML-based systems. The main contributions of this systematic review are: (1) an overview of the technical aspects of ML innovation and their consequences for HCI researchers and practitioners; (2) a description of the different roles that ML-based systems can take in clinical settings; (3) a conceptualisation of the main activities of medical ML innovation processes; (4) identification of five sociotechnical interdependencies that emerge from medical ML innovation; and (5) implications for HCI researchers and practitioners on how to mitigate the sociotechnical challenges of medical ML innovation.
Graduate students are facing a mental health crisis due to a combination of individual, community, and societal factors. Many existing stress management interventions engage with one factor at a time, typically focusing on providing a user with data about their stress state. We conducted co-design workshops with graduate students who work closely together to explore their strategies for managing stress and to learn about what types of technologies they envision to help address their stress. Using Ecological Systems Theory as an conceptual framework, our analysis of the designs and discussions from these workshops contributes an expanded design space for stress management---one that foregrounds the affordances and challenges of designing interventions that cut across ecological systems levels along with designs that approach stress management using a broader diversity of strategies: controlling, disconnecting, and normalizing stress. We argue that this expanded design space embraces a more holistic and human approach to designing stress management technologies.