Post-surgery care involves ongoing collaboration between provider teams and patients, which starts from post-surgery hospitalization through home recovery after discharge. While prior HCI research has primarily examined patients' challenges at home, less is known about how provider teams coordinate discharge preparation and care handoffs, and how breakdowns in communication and care pathways may affect patient recovery. To investigate this gap, we conducted semi-structured interviews with 13 healthcare providers and 4 patients in the context of gastrointestinal (GI) surgery. We found coordination boundaries between in- and out-patient teams, coupled with complex organizational structures within teams, impeded the "invisible work" of preparing patients' home care plans and triaging patient information. For patients, these breakdowns resulted in inadequate preparation for home transition and fragmented self-collected data, both of which undermine timely clinical decision-making. Based on these findings, we outline design opportunities to formalize task ownership and handoffs, contextualize co-temporal signals, and align care plans with home resources.

Serious Illness Conversations (SICs)—discussions about values and care preferences for patients with life-threatening illness—rarely occur in Emergency Departments (EDs), despite evidence that early conversations improve care alignment and reduce unnecessary interventions. We interviewed 11 ED providers to identify challenges in SICs and opportunities for technology support, with a focus on AI. Our analysis revealed a four-stage SIC workflow (identification, preparation, conduction, documentation) and barriers at each stage, including fragmented patient information, limited time and space, lack of conversational guidance, and burdensome documentation. Providers expressed interest in AI systems for synthesizing information, supporting real-time conversations, and automating documentation, but emphasized concerns about preserving human connection and clinical autonomy. This tension highlights the need for technologies that enhance efficiency without undermining the interpersonal nature of SICs. We propose design guidelines for ambient and peripheral AI systems to support providers while preserving the essential humanity of these conversations.

Using handheld electronic health record (EHR) devices to collect and document patient data poses significant challenges in dynamic, time-critical, and hands-busy medical settings. Prior research has proposed wearable technologies, such as smart glass, to enable hands-free clinical documentation. Building on this, we conducted a two-year, user-centered study to iteratively design and evaluate a smart glass application for enhancing real-time clinical documentation in settings like Emergency Medical Services (EMS). Our findings provide key design insights for addressing EMS documentation challenges through smart glass technology, as well as potential barriers for successful adoption. We conclude the paper by discussing the implications of these findings for developing smart glass to support documentation in fast-paced medical environments.

Effective communication is critical for emergency medical teams, especially when distributed providers must collaborate under high-stakes conditions to deliver timely, life-saving care. Traditional communication tools such as radios and phones, while commonly used, are limited to audio-only exchanges-often resulting in misunderstandings, communication breakdowns, and delays in treatment. This study explores the use of smart glasses as an alternative communication tool in prehospital emergency care and examines how their use influences communication dynamics between prehospital providers (e.g., paramedics) and remote emergency physicians, compared to traditional methods (radio and phone). Through simulation-based testing, we found that smart glasses reduced communication breakdowns and facilitated more in-depth, context-rich discussions about patient care. Both EMS providers and physicians viewed the smart glass technology as a promising solution for enabling multimodal communication (e.g., visual, auditory, gestures, text). However, we also identified several challenges associated with its use in near-realistic simulation environments, including the need for overhearing capabilities, issues with visual alignment and motion-induced discomfort, extended interaction times, and concerns around autonomy and privacy. We conclude with a discussion of the design and practical implications of these findings.

Community telehealth programs (CTPs) enable low-income older adults to receive telehealth services in community settings (e.g., retirement homes). The Telehealth Intervention Program for Seniors (TIPS) is a CTP that provides vital sign monitoring services managed by remote nurses. TIPS has successfully recruited and retained Limited English Proficient (LEP) participants, but lack of language services might hinder LEP participants’ equitable access to care. We conducted a two-part mixed-methods study. We first qualitatively analyzed 40 nurse notes to identify challenges nurses encounter gathering information due to language barriers and the workarounds they employed to address these. We then tested our qualitative findings on 23,975 nurse notes to quantify and compare how these challenges and workarounds scale between LEP and English-proficient TIPS participants. We present future research implications beyond low-hanging solutions, such as automated translation services, and discuss how novel technological solutions can support and ameliorate nurse workarounds and caregiver burden.

Clinical documentation is a time-consuming and challenging task, especially in time-critical medical settings. Even with a dedicated scribe person, timely and accurate documentation under time constraints is never easy. In this work, we present a unique type of fast-paced medical team--emergency medical services (EMS)--which has no designated role for documentation while constantly working outside in the field to provide urgent patient care. Through interviews with 13 EMS practitioners, we reveal several interesting and prominent characteristics of EMS documentation practice as well as their associated challenges: EMS practitioners self-organize and collaborate on documentation while in the meantime being both physically and cognitively preoccupied with high-acuity patients, having limited capability to use handheld documentation systems in real-time, and being overwhelmed by strict documentation requirements and regulations. Lastly, we use our findings to discuss both technical and non-technical implications to support timely and collaborative documentation in dynamic medical contexts while accounting for care providers' physical and cognitive constraints in using computing devices.

Artificial intelligence (AI) technology has been increasingly used in the implementation of advanced Clinical Decision Support Systems (CDSS). Research demonstrated the potential usefulness of AI-powered CDSS (AI-CDSS) in clinical decision making scenarios. However, post-adoption user perception and experience remain understudied, especially in developing countries. Through observations and interviews with 22 clinicians from 6 rural clinics in China, this paper reports the various tensions between the design of an AI-CDSS system (“Brilliant Doctor”) and the rural clinical context, such as the misalignment with local context and workflow, the technical limitations and usability barriers, as well as issues related to transparency and trustworthiness of AI-CDSS. Despite these tensions, all participants expressed positive attitudes toward the future of AI-CDSS, especially acting as “a doctor’s AI assistant” to realize a Human-AI Collaboration future in clinical settings. Finally we draw on our findings to discuss implications for designing AI-CDSS interventions for rural clinical contexts in developing countries.

Chatbots systems, despite their popularity in today's HCI and CSCW research, fall short for one of the two reasons: 1) many of the systems use a rule-based dialog flow, thus they can only respond to a limited number of pre-defined inputs with pre-scripted responses; or 2) they are designed with a focus on single-user scenarios, thus it is unclear how these systems may affect other users or the community. In this paper, we develop a generalizable chatbot architecture (CASS) to provide social support for community members in an online health community. The CASS architecture is based on advanced neural network algorithms, thus it can handle new inputs from users and generate a variety of responses to them. CASS is also generalizable as it can be easily migrate to other online communities. With a follow-up field experiment, CASS is proven useful in supporting individual members who seek emotional support. Our work also contributes to fill the research gap on how a chatbot may influence the whole community's engagement.

Emergency medical services (EMS) teams are first responders providing urgent medical care to severely ill or injured patients in the field. Despite their criticality, EMS work is one of the very few medical domains with limited technical support. This paper describes a study conducted to examine technology opportunities for supporting EMS data work and decision-making. We transcribed and analyzed 25 simulation videos. Using the distributed cognition framework, we examined EMS teams' work practices that support information acquisition and sharing. Our results showed that EMS teams leveraged various mechanisms (e.g., verbal communication and external cognitive aids) to distribute cognitive labor in managing, collecting, and using patient data. However, we observed a set of prominent challenges in EMS data work, including lack of detailed documentation in real time, situation recall issues, situation awareness problems, and challenges in decision making and communication. Based on the results, we discuss implications for technology opportunities to support rapid information acquisition, integration, and sharing in time-critical, high-risk medical settings.

In recent years, the social web has been increasingly used for health information seeking, sharing, and subsequent health-related research. Women often use the Internet or social networking sites to seek information related to pregnancy in different stages. They may ask questions about birth control, trying to conceive, labor, or taking care of a newborn or baby. Classifying different types of questions about pregnancy information (e.g., before, during, and after pregnancy) can inform the design of social media and professional websites for pregnancy education and support. This research aims to investigate the attention mechanism built-in or added on top of the BERT model in classifying and annotating the pregnancy-related questions posted on a community Q&A site. We evaluated two BERT-based models and compared them against the traditional machine learning models for question classification. Most importantly, we investigated two attention mechanisms: the built-in self-attention mechanism of BERT and the additional attention layer on top of BERT for relevant term annotation. The classification performance showed that the BERT-based models worked better than the traditional models, and BERT with an additional attention layer can achieve higher overall precision than the basic BERT model. The results also showed that both attention mechanisms work differently on annotating relevant content, and they could serve as feature selection methods for text mining in general.

We describe an observational study of work coordination in an emergency communication center, where a collocated team of communication specialists engages in complex activities of communicating with pre-hospital medical teams, and coordinating patient care and transport. Unlike teams with clearly defined work roles and team structures that were introduced to increase work efficiency and minimize redundancy, the team we studied lacks the role differentiation. To better understand how complex work is accomplished under these conditions, we conducted in-situ observations in the center's control room and interviewed communication specialists. We found that communication specialists self-organized by using a mix of material and immaterial coordination mechanisms, including work schedules, computer systems, and tacit agreements to coordinate tasks. Using these findings, we then identified three features of self-organized, collocated and time-critical teamwork that require technology support: awareness of task ownership, task self-assignment, and informal team hierarchy. We conclude by discussing technology requirements to support these teamwork features.

This paper investigates coordination and real-time information sharing across four emergency medical teams in a high-risk and distributed setting as they provide care to critically injured patients within the first hour after injury. Through multiple field studies we explored how common understanding of critical patient data is established across these heterogeneous teams and what coordination mechanisms are being used to support information sharing and interpretation. To interpret the data, we drew on the concept of Common Information Spaces (CIS). Our results showed that teams faced many challenges in achieving efficient information sharing and coordination, including difficulties in locating and assembling team members, communicating and interpreting information from the field, and reconciling differences in team perspectives and information needs, all while having minimal technology support. We reflect on these challenges to suggest an extension of the classic CSCW time-space matrix, as well as future development of CIS as an analytical framework. The paper concludes with design opportunities for supporting highly distributed and heterogeneous teamwork in time-critical work environments.

In this paper, we describe how we developed an information display prototype for trauma resuscitation teams based on design ideas and feedback from clinicians. Our approach is grounded in participatory design, emphasizing the importance of gaining long-term commitment from clinicians in system development. Through a series of participatory design workshops, heuristic evaluation, and simulated resuscitation sessions, we identified the main information features to include on our display. Our results focus on how we balanced the design tensions that emerged when addressing the ad hoc, hierarchical, and multidisciplinary nature of trauma teamwork. We discuss the implications of balancing role-based differences for each information feature, as well as two major design tensions: process-based vs. state-based designs and role-based vs. team-based displays.

We examine the use of a paper-based checklist during 48 simulated trauma resuscitations to inform the design of digital cognitive aids for safety-critical medical teamwork. Our analysis focused on team communication and interaction behaviors as physician leaders led resuscitations and administered the checklist. We found that the checklist increased the amount of communication between the leader and the team, but did not compromise the leader's interactions with the environment. In addition, we observed several changes in team dynamics: the checklist facilitated collaborative decision making and process reflections, but it also made some team members reactive rather than proactive. As the push toward digitizing medical work continues, we expect that paper checklists will soon be replaced by their digital counterparts. Designing interactive cognitive aids for medical domains, however, poses many challenges. Our results offer directions for how these tools could be designed to support medical work in increasingly digital environments.

The purpose of this study was to understand how vital signs monitors support teamwork during trauma resuscitation -- the fast-paced and information-rich process of stabilizing critically injured patients. We analyzed 12 videos of simulated resuscitations to characterize trauma team monitor use. To structure our observations, we adopted the feedback loop concept. Our results showed that the monitor was used frequently, especially by team leaders and anesthesiologists. We identified three patterns of monitor use: (i) periods with a low frequency of short looks (glances) to maintain overall process awareness; (ii) periods with a medium frequency of long looks (scrutiny) to monitor trends in patient status; and (iii) peaks with a high frequency of glances to maintain attention on both the patient and monitor during critical tasks. Approximately 75% of looks were 3 seconds or shorter, but many looks (25%) ranged between 3 and 26 seconds. Our results have implications for improving displays by presenting the status of the patient's physiological systems and team activities.

We examine decision-making tasks and information sources during fast-paced, high-risk medical events, such as trauma resuscitation. Interviews with surgical team leaders and ED physicians reveal several environmental aspects that make decision making difficult, including diagnostic tradeoffs, missing and unreliable information, and managing multiple patients simultaneously. We discuss the implications of these findings for the design of wall displays to support decision making in time-critical medical settings.