User simulation has long been important in computer science because it helps researchers build and test many kinds of systems. Since language is the main way people communicate, being able to simulate conversations has become especially valuable. Recent advances in large language models, or LLMs, have made this much more realistic by allowing computers to generate synthetic user conversations that closely resemble human dialogue. This paper reviews recent progress in LLM-based conversational user simulation. It introduces a new framework for organizing the field based on how detailed the simulated user is and what the simulation is meant to achieve. The paper also examines the main methods used and how researchers evaluate these systems. Overall, it aims to give readers a clear view of the latest developments in conversational user simulation and to identify the main challenges that still need to be solved.

This study looked at how different mental health symptom groups relate to one another, because that can help improve how psychiatric conditions are classified. The researchers focused on “internalizing” symptoms, which include fear, worry, sadness, avoidance, and feeling highly alert or tense. They analyzed responses from six questionnaires covering depression, generalized anxiety disorder, social anxiety disorder, panic disorder, posttraumatic stress disorder (PTSD), and obsessive-compulsive disorder (OCD) in a community sample of 2,051 young adults ages 17 to 23. Using a network approach, which treats symptoms as connected to one another rather than as isolated conditions, they measured how close different symptom groups were to each other. The results showed that depression and generalized anxiety were especially closely linked, and PTSD was also most similar to those two groups. By contrast, panic, social anxiety, and OCD did not clearly form one separate “fear” group and were less consistently related to the other symptom domains. Overall, the findings support the idea that depression, generalized anxiety, and possibly PTSD may share a common distress-related dimension, while providing less support for a distinct fear-based grouping of social anxiety, panic, and OCD.

FIG. 1

Exploratory graph analysis depicting the network structure of symptoms across six psychological constructs. Note: B = Beck Depression Inventory-II; G = Generalized Anxiety Disorder−7; S = Social Phobia Inventory; PD = Panic Disorder Severity Scale; PS = Posttraumatic Stress Disorder Scale-Self Report for DSM−5; O = Obsessive-Compulsive Inventory-Revised.

��This study examined whether a blood or fluid test for abnormal alpha-synuclein, a protein linked to Parkinson’s disease, was related to differences in brain scans in people with early Parkinson’s disease. The researchers used diffusion MRI, a type of brain imaging that can show how water moves through brain tissue and reveal subtle structural changes, and focused on a measure called free-water imaging, which can pick up signs of tissue damage or inflammation. They compared people who tested positive for alpha-synuclein seeding activity, meaning the biomarker was present, with those who tested negative. Among 462 participants, most had a positive test. People with a positive result were more likely to have loss of smell and a shorter time since their movement symptoms began. The brain scan analysis found one small difference in a pathway linked to movement, but overall the positive and negative groups were not very different on the broader scan measures. In other words, the biomarker confirmed Parkinson’s-related protein changes, but it did not strongly separate people by the degree of brain tissue change seen on these scans.

FIGURE 1

CONSORT flow diagram of participant selection. The numbers of individuals assessed for eligibility and included in each analysis group are shown. AIDP = Automated Imaging Differentiation for Parkinsonism; PPMI = Parkinson’s Progression Markers Initiative; SAA = seed amplification.

Hu, Ruiying; Hamilton, Nala; Wang, Yu; Tong, Xin; Yagan, Mahircan; Dadi, Prasanna K.; Harmelink, Cristina; Doss, Teri D.; Liu, Jinhua; Xu, Yanwen; Simmons, Alan J.; Lau, Ken S.; Stein, Roland; Balamurugan, Appakalai N.; Kaverina, Irina; Coate, Katie C.; Jacobson, David A.; Liu, Qi; Gu, Guoqiang. (2026).��.��Diabetologia.��

This study aimed to improve the My Diabetes Care (MDC) patient portal, a digital tool that helps people manage diabetes, by making the interface easier to use and adding more health information, such as weight, body mass index (BMI), and urine microalbumin, which is a marker used to check for kidney damage. The researchers also created a Spanish-language version designed to be more culturally appropriate and accessible for Spanish-speaking patients. To do this, they used a five-step design process and tested the prototype with 12 adults with type 2 diabetes from primary care clinics. Participants completed tasks in the portal and gave feedback through interviews and usability surveys. The team also worked with Spanish-speaking community consultants to help shape the language, design, and onboarding support for the Spanish version. After two rounds of testing, the portal was improved in terms of both layout and wording, and all participants were able to complete the tasks successfully in the final round. Usability scores were very high, suggesting that the system was easy to use. Overall, the study shows that involving users and community members in the design process can help create a diabetes self-management tool that is both practical and responsive to the needs of diverse patients.

Figure 2. Illustrative examples of selected design sprint activities. (a) Related “how might we” statements grouped into a category. (b) Design sketches with dot stickers to visually indicate individual preferences and collectively prioritize design components.

]]> /valiant/2026/06/17/spinal-cord-imaging-for-multiple-sclerosis-advances-priorities-and-opportunities/ Wed, 17 Jun 2026 18:39:55 +0000 /valiant/?p=6987 Laule, Cornelia; Cohen-Adad, Julien; Witt, Atlee A.; De Luca, Gabriele C.; Granziera, Cristina; Keegan, B. Mark; Kerbrat, Anne; Klawiter, Eric C.; Kolind, Shannon; O’Grady, Kristin P.; Oh, Jiwon; Schilling, Kurt G.; Sivakolundu, Dinesh K.; Smith, Seth A.; Tozlu, Ceren; Vavasour, Irene M.; Bagnato, Francesca; Gauthier, Susan A.; Mainero, Caterina; Alonso-Ortiz, Eva; Bakshi, Rohit; Beck, Erin S.; Brier, Matthew R.; Hemond, Christopher C.; Krieger, Stephen; Li, David K. B.; Shinohara, Russell T.; Henry, Roland G. (2026).��.��Multiple Sclerosis Journal.��

The spinal cord plays an important role in multiple sclerosis, or MS, but it has not been studied as much as the brain. This review summarizes the main takeaways from a 2025 workshop on spinal cord imaging in MS, including recent progress, ongoing problems, and future directions. It explains how damage to the spinal cord, such as lesions and shrinkage, can help doctors diagnose MS, predict how the disease may progress, and monitor how well treatment is working. The review also highlights new markers that may help track disease worsening even when patients are not having relapses. Studies comparing magnetic resonance imaging, or MRI, with tissue samples and patient outcomes support the usefulness of newer spinal cord imaging methods. At the same time, the review notes that spinal cord imaging still faces technical challenges, including the need for better analysis pipelines and more consistent results across studies. Overall, the authors argue that advanced, quantitative spinal cord imaging should be used more widely in clinical trials, research, and, when possible, patient care, because it can help show the full extent of MS and improve outcomes.

Figure 1. Spinal cord pathological features and MRI-pathology correlations. (a) Lesion frequency heatmaps of total demyelinated lesions in the cervical (top), thoracic (middle), and lumbar (bottom) spinal cord. Lesion predilection sites include the dorsal columns, lateral columns, and gray matter as a whole, with relative sparing of the subpial surface. (b) Myelin (proteolipid protein) and (c) fibrin(ogen) immunostaining in adjacent spinal cord sections from an MS case. Fibrin(ogen) deposition is consistently found in the central part of the cord, including gray matter, and mesial aspects of the lateral columns and central part of the dorsal column in areas outside demyelinated lesions. (d) Hematoxylin and eosin–stained section with magnified inset (e), demonstrating thickened vasculature in the MS spinal cord, a finding consistently found in younger cases. Perivascular space dilatation is also a common feature (not shown). (f) and (g) Palmgren silver-stained sections showing reduced axonal density in an MS case (g) compared with control (f), with predilection for loss of small diameter axons. (h) Luxol Fast Blue stain for myelin and (i) Bielschowsky stain for axons in the secondary progressive MS section demonstrate reduced staining in a focal lesion (arrow), which is visualized on 7 Tesla ex vivo MRI as (j) T2-weighted hyperintensity and (k) myelin water fraction imaging hypointensity. Comparison between Luxol Fast Blue myelin staining optical density and quantitative MRI, (l) radial diffusivity (RD), (m) inhomogeneous magnetization transfer (ihMT) and (n) myelin water fraction (MWF) show strong quantitative correlations between histology and MRI markers for myelin in the spinal cord. (a) Adapted from Waldman et al.,��Acta Neuropathol��2024; (f) and (g) adapted from DeLuca et al.,��Brain��2004.

]]> /valiant/2026/06/17/the-environmental-impact-of-diagnostic-imaging-opportunities-for-pediatric-radiologists/ Wed, 17 Jun 2026 18:38:47 +0000 /valiant/?p=6984

Gross, Jonathan; Pruthi, Sumit; Omary, Reed A.; Snyder, Elizabeth J. (2026).��.��Pediatric Radiology.��

Open Source Software for Social Good, or OSS4SG, refers to open-source projects that aim to solve social problems and create positive impact for society. Because these projects depend on people contributing over time, the researchers wanted to understand how contributors participate in them and what helps or hinders long-term involvement. They analyzed more than 2.2 million commits, which are saved changes to code, made by 5,860 contributors to OSS4SG and other open-source projects on GitHub. They found that people who contribute to OSS4SG usually contribute less overall and stay active for shorter periods than contributors to general open-source projects, but when they are active, their work tends to be more regular. The study also found that contributors from developing regions, such as Africa, and women were more likely to begin contributing to and keep contributing to OSS4SG, even though their overall contribution levels were lower than those of others. Based on these findings, the authors suggest ways to better support contributors and grow OSS4SG projects so they can have a greater social impact and help make open source more inclusive and sustainable.

Fig. 1.

Data Collection Process. Starting with 210 seed projects, the process results in a comprehensive dataset containing contributors’ complete historical commits and demographic details.

Lane, Kaitlyn T.; Stephan, Alexander P.; Soares-Furtado, Melinda; Stassun, Keivan G.; Yarza, Ricardo. (2026).��.��Astrophysical Journal, 1003(1).��

Spatial transcriptomics is a technology that measures which genes are active in a tissue while also showing where those gene signals come from inside the tissue. This gives scientists a much clearer picture of how tissues are organized and how different parts work together. So far, much of the progress in this field has come from bioinformatics, but many methods still treat space mainly as a set of coordinates and relationships, without fully using the detailed visual information available in tissue images. This paper reviews a newer approach that uses computer vision, a branch of artificial intelligence that analyzes images, to make better use of that visual detail and connect tissue shape and structure with gene activity. These methods could help address some major limits of spatial transcriptomics, such as its high cost, limited use in clinical settings, and the fact that many analyses are still based on two-dimensional images even though real tissues are three-dimensional. For example, some models can estimate spatial gene patterns directly from microscope images, which could reduce the need for expensive sequencing while still capturing important biological information. Other methods can rebuild three-dimensional tissue maps from image data. The paper is the first broad review of computer vision methods for spatial transcriptomics, organizing them by model type, learning approach, task, and dataset, and highlighting the main challenges and future opportunities in this fast-growing area.

Figure 1

Overview of some well-known vision-driven models for ST from 2020 to 2025.

]]>