Providers often counsel young sexual/gender minority (YSGM) of color about HIV "risk" in ways that feel unrelatable and stigmatizing. Our study explored: (1) needs for sexual wellness-based HIV prevention among 18-29-year-old YSGM of color, (2) challenges and opportunities in using this counseling approach, and (3) preliminary feasibility and acceptability of a wellness-based counseling intervention. Aim 1 collected surveys and in-depth interviews with YSGM of color. Aim 2 recruited providers to understand their needs when counseling YSGM of color and implementing wellness-based approaches. Aim 3 piloted the intervention with providers and included exit surveys and focus groups to assess acceptability and feasibility; however, this aim was cut short due to funding cuts in early 2025. In Aim 1, 23 interviews and 70 surveys were completed, with 94.3% identifying as sexual minorities. Nearly two-thirds reported that consulting a health professional who uses a sex-positive approach for HIV prevention would increase their ability to effectively use pre-exposure prophylaxis (PrEP). In Aim 3, we trained 23 providers across three sites and conducted one site debrief. If feasibility and acceptability are demonstrated, this intervention is positioned for rapid dissemination to reduce HIV prevalence among a group that has historically benefitted less from PrEP.
Heart failure (HF) is a progressive and fatal disease that affects nearly 7 million individuals in the United States, with prevalence expected to surpass 10 million by 2040. Cardiopulmonary exercise testing (CPET) represents the gold standard for assessing functional capacity and predicting survival outcomes among HF patients but its widespread use is limited by practical constraints. Here we introduce a multimodal multi-instance learning framework that predicts peak oxygen consumption (peak VO₂), a critical indicator from CPET, using the more accessible transthoracic echocardiography (TTE) studies and electronic health records (EHR). By modeling the cross-modal interactions and the multi-instance structure of TTE studies, our approach significantly improves predictive accuracy and generalization. The model achieves an R² of 0.603 in peak VO₂ prediction and AUROC of 0.849 in high-risk patient identification, surpassing prior work (R² = 0.529, AUROC = 0.836). On the external validation cohort, the model achieves an R² of 0.541 compared to 0.395 and an AUROC of 0.870 compared to 0.797 from previous work. The improved performance more accurately allows for identification of patients who may benefit from advanced heart failure therapies that otherwise may have been missed.
OBJECTIVE:Understand the qualitative impact of an ambient artificial intelligence (AI) documentation platform on clinicians' experiences and workflows. MATERIALS AND METHODS:A quality improvement (QI) qualitative study using semi-structured interviews after pilot implementation of an ambient AI documentation platform at a large healthcare organization in Northern and Central California. Pragmatic thematic analysis was used to code and analyze the interviews. RESULTS:100 clinicians were invited and 42 (42%) participated in an interview. 23 (54.8%) were males and 28 (66.7%) in primary care. Many respondents noted that ambient AI had decreased their cognitive burden by eliminating the need to remember as many specific visit details and saved time for other tasks. They also liked how ambient AI generated transcripts in multiple languages and then created an English-language progress note. However, clinicians also reported challenges, particularly missed or inaccurate information that required them to review the transcript/audio and edit the note. Additionally, many clinicians, particularly specialists, disliked the note formatting and the inability to customize the note template as this resulted in additional manual editing. DISCUSSION:Results from these QI qualitative interviews suggest that ambient AI improved clinicians' overall experience at work. CONCLUSION:While there are many similarities, there may be key differences in clinician experience between ambient AI documentation platforms depending on unique features of each. Future research is needed to understand the potential range of experiences based on type of ambient AI platform and if these findings continue with longer use and broader expansion of this new and evolving technology.
Importance:The management of infectious and inflammatory lesions of the breast remains controversial. The expert panel focused on management recommendations for 3 of the most common infectious breast conditions, as very few evidence-based guidelines for the management of these conditions exist. Observations:Clinicians should distinguish between infectious and noninfectious lactational mastitis (LM) because the former often requires interventions whereas the latter requires supportive care only. Patients with infectious LM often have thick fluid collections that are not amenable to aspiration and usually require a stab incision with drain placement (but no packing) to resolve the infection. Operative drainage is only required if the patient cannot tolerate an office procedure. If a phlegmon is present, antibiotics should be prescribed for at least 10 days. The diagnosis of granulomatous mastitis (GM) requires pathology confirmation with characteristic findings on core biopsy. Cystic neutrophilic granulomatous mastitis (CNGM) is a specific form of GM associated with a granulomatous reaction to Corynebacterium infection and should be empirically treated with doxycycline. For patients without findings characteristic of CNGM and no other associated bacterium identified, there is no role for empiric antibiotic use. Granulomatous mastitis cases often recur and can take up to 18 months to resolve. Patients who have GM cases with worsening symptoms should be treated with repeated intralesional steroid injections; surgical excision or repeated aspirations should be avoided. Cases refractory to intralesional steroid injection may require oral steroids or even advanced biologic agents such as methotrexate or azathioprine. Periductal mastitis with squamous metaplasia of lactiferous ducts (PDM-SMOLD) is a distinct entity from other periductal mastitis cases that can present with recurrent abscesses and should be treated with antibiotics and aspiration for fluid collections. Operative excision for PDM-SMOLD is required for those patients who present with a fistula or recurrent episodes typically using a radial incision to remove the diseased ducts within and below the nipple. Conclusions and Relevance:Evidence-informed, consensus-, and expert opinion-based guidelines for the management of infectious and inflammatory conditions of the breast were developed. Clinicians can use these guidelines to appropriately manage these conditions for which clinical care often varied in the past.
Aims:Early detection is important given the availability of new disease-modifying therapies and the high prevalence of transthyretin amyloid cardiomyopathy (ATTR-CM) among patients with aortic stenosis (AS) undergoing transcatheter aortic valve replacement (TAVR). We developed a multi-modal artificial intelligence (AI) model for early detection of ATTR-CM using chest computed tomography (CT), echocardiography, and electrocardiography. This approach may provide a scalable strategy for preclinical monitoring. Methods and results:This retrospective study included patients who underwent technetium-99m-pyrophosphate (PYP) scintigraphy at two academic medical centres: Columbia University Irving Medical Center and Weill Cornell Medicine. ATTR-CM status was determined using a composite reference standard incorporating PYP scan interpretation, laboratory tests, and endomyocardial biopsy results when available. The diagnostic performance of the model was measured by the area under the receiver operating characteristic curve (AUROC), sensitivity, specificity, and predictive values at various thresholds. Among 816 patients (median age 79.0 years, 61.2% male), 127 (15.6%) had confirmed ATTR-CM. Patients with ATTR-CM were older, more often male, and had characteristic echocardiographic features, including increased wall thickness and reduced ejection fraction. In the independent TAVR test cohort, the multi-modal AI model achieved an AUROC of 0.85 [95% confidence interval (CI): 0.74-0.93], significantly outperforming single-modality approaches in our data. At the optimal threshold, the model demonstrated 73.3% sensitivity, 82.9% specificity, and 96% negative predictive value. Conclusion:A multi-modal AI approach using routinely acquired chest CT, echocardiography, and electrocardiography data can enable screening for ATTR-CM in TAVR patients, potentially facilitating earlier diagnosis and treatment initiation.
