Search for: All records

Effective communication between a clinician and their patient is critical for delivering healthcare maximizing outcomes. Unfortunately, traditional communication training approaches that use human standardized patients and expert coaches are difficult to scale. Here, we present the develop- ment and validation of a scalable, easily accessible, digital tool known as the Standardized Online Patient for Health Interaction Education (SOPHIE) for practicing and receiving feedback on doctor-patient communication skills. SOPHIE was validated by conducting an experiment with 30 participants. We found that participants who underwent SOPHIE performed significantly better than the control in overall communication, aggregate scores, empowering the patient, and showing empathy (p < 0.05 in all cases). One day, we hope that SOPHIE will help make communication training resources more accessible by providing a scalable option to supplement existing resources. 

Abstract Vascular hypo‐fibrinolysis is a historically underappreciated and understudied aspect of venous thromboembolism (VTE). This paper describes the development of a micro‐clot dissolution assay for quantifying the fibrinolytic capacity of endothelial cells – a key driver of VTE development. This assay is enabled using aqueous two‐phase systems (ATPS) to bioprint microscale fibrin clots over human umbilical vein endothelial cells (HUVECs). Importantly, these micro‐clots are orders of magnitude smaller than conventional fibrin constructs and allow HUVEC‐produced plasminogen activators to mediate visually quantifiable fibrinolysis. Using live‐cell time‐lapse imaging, micro‐clot dissolution by HUVECs is tracked, and fibrinolysis kinetics are quantified. The sensitivity of cell‐driven fibrinolysis to various stimuli is rapidly tested. The physiological relevance of this convenient high‐throughput assay is illustrated through treatments with lipopolysaccharide (LPS) and rosuvastatin that elicit anti‐ and pro‐fibrinolytic responses, respectively. Furthermore, treatment with baricitinib, an anti‐inflammatory therapeutic found to increase cardiovascular risks after market approval, provokes an anti‐fibrinolytic response – which highlights the potential role of endothelial cells in increasing VTE risk for patients receiving this drug. This endothelial cell fibrinolysis assay provides a high‐throughput and versatile drug testing platform – potentially allowing for early preclinical identification of therapeutics that may beneficially enhance or adversely impair endothelial fibrinolysis. 

We explore predictability and control in interactive systems where controls are easy to validate. Human-in-the-loop techniques allow users to guide unsupervised algorithms by exposing and supporting interaction with underlying model representations, increasing transparency and promising fine-grained control. However, these models must balance user input and the underlying data, meaning they sometimes update slowly, poorly, or unpredictably---either by not incorporating user input as expected (adherence) or by making other unexpected changes (instability). While prior work exposes model internals and supports user feedback, less attention has been paid to users' reactions when transparent models limit control. Focusing on interactive topic models, we explore user perceptions of control using a study where 100 participants organize documents with one of three distinct topic modeling approaches. These approaches incorporate input differently, resulting in varied adherence, stability, update speeds, and model quality. Participants disliked slow updates most, followed by lack of adherence. Instability was polarizing: some participants liked it when it surfaced interesting information, while others did not. Across modeling approaches, participants differed only in whether they noticed adherence. 

To address the lack of comparative evaluation of Human-in-the-Loop Topic Modeling (HLTM) systems, we implement and evaluate three contrasting HLTM modeling approaches using simulation experiments. These approaches extend previously proposed frameworks, including constraints and informed prior-based methods. Users should have a sense of control in HLTM systems, so we propose a control metric to measure whether refinement operations’ results match users’ expectations. Informed prior-based methods provide better control than constraints, but constraints yield higher quality topics.