Recent advances in AI combine large language models (LLMs) with vision encoders that bring forward unprecedented technical capabilities to leverage for a wide range of healthcare applications. Focusing on the domain of radiology, vision-language models (VLMs) achieve good performance results for tasks such as generating radiology findings based on a patient’s medical image, or answering visual questions (e.g., “Where are the nodules in this chest X-ray?”). However, the clinical utility of potential applications of these capabilities is currently underexplored. We engaged in an iterative, multidisciplinary design process to envision clinically relevant VLM interactions, and co-designed four VLM use concepts: Draft Report Generation, Augmented Report Review, Visual Search and Querying, and Patient Imaging History Highlights. We studied these concepts with 13 radiologists and clinicians who assessed the VLM concepts as valuable, yet articulated many design considerations. Reflecting on our findings, we discuss implications for integrating VLM capabilities in radiology, and for healthcare AI more generally.

Hypotension during perioperative care, if undetected or uncontrolled, can lead to serious clinical complications. Predictive machine learning models, based on routinely collected EHR data, offer potential for early warning of hypotension to enable proactive clinical intervention. However, while research has demonstrated the feasibility of such machine learning models, little effort is made to ground their formulation and development in socio-technical context of perioperative care work. To address this, we present a study of collaborative work practices of clinical teams during and after surgery with specific emphasis on the organisation of hypotension management. The findings highlight where predictive insights could be usefully deployed to reconfigure care and facilitate more proactive management of hypotension. We further explore how the socio-technical insights help define key parameters of machine learning prediction tasks to align with the demands of collaborative clinical practice. We discuss more general implications for the design of predictive machine learning in hospital care.

Here, the authors combine a pure phase-encoded magnetic resonance imaging (MRI) method with a new tissue-classification technique to make geometric models of a human tooth. They demonstrate the feasibility of three-dimensional imaging of solids using a conventional 11.7-T NMR spectrometer. In solid-state imaging, confounding line-broadening effects are typically eliminated using coherent averaging methods. Instead, the authors circumvent them by detecting the proton signal at a fixed phase-encode time following the radio-frequency excitation. By a judicious choice of the phase-encode time in the MRI protocol, the authors differentiate enamel and dentine sufficiently to successfully apply a new classification algorithm. This tissue-classification algorithm identifies the distribution of different material types, such as enamel and dentine, in volumetric data. In this algorithm, the authors treat a voxel as a volume, not as a single point, and assume that each voxel may contain more than one material. They use the distribution of MR image intensities within each voxel-sized volume to estimate the relative proportion of each material using a probabilistic approach. This combined approach, involving MRI and data classification, is directly applicable to bone imaging and hard-tissue contrast-based modeling of biological solids.