Zoghby, Ziad

Background: Total kidney volume (TKV), a prognostic biomarker in ADPKD, is used to stratify high risk individuals. eGFR measures may carry significant error in ADPKD compared to measured GFR(mGFR). This retrospective study investigates the association between height adjusted TKV (htTKV) and eGFR derived from race-free CKD-EPI equations utilizing creatinine and cystatin C. Methods: eGFR was calculated using 3 race-free CKD-EPI formulas: creatinine-based (CKD-EPI creatinine), cystatin C (CKD-EPI cys), and creatinine-cystatin C (CKD-EPI creatinine-cystatin C) equations on 697 Mayo Clinic ADPKD patients. Correlations between eGFR and TKV measures were estimated and stratified by MIC class risk groups and CKD. Linear regression models were computed to predict ln(htTKV) from the 3 eGFR data sets. The eGFR measures were compared to iothalamate-based mGFR in a subset of patients (n=50). Results: A correlation between eGFR measures and htTKV (Pearson correlation r of -0.53 to -0.54), varied by MIC stratification. Pearson correlation was -0.47 to -0.48 for MIC 1A and 1B, -0.67 to -0.71 for MIC 1C, and -0.67 to -0.68 for MIC 1D and 1E. All equations were significantly associated with htTKV levels, with similar adjusted beta values (95% CI) of -0.15 (-0.17 to -0.13), -0.14 (-0.16 to -0.12), -0.15 (-0.16 to -0.13), for CKD-EPI creatinine, CKD-EPI cystatin C, and CKD-EPI creatinine-cystatin C, respectively. Compared to mGFR, the CKD-EPI creatinine-cystatin C equation was the least biased (mean -0.86 (95% CI: -3.09 to 1.37)) versus CKD-EPI creatinine (2.31 (-0.73 to 5.34)) or CKD-EPI cystatin C (-3.54 (-5.86 to -1.21)), and most precise, with 1-P30 of 16% (95% CI 7.2% to 29.1%), compared to 18% (8.6% to 31.4%) for CKD-EPI creatinine, or 20% (10.0% to 33.7%) for CKD-EPI cystatin C. Conclusion: A moderate correlation between eGFR and htTKV associated with MIC stratification. Associations between htTKV and all 3 CKD-EPI equations were similar. CKDEPIcrcys tended to be the least biased and most precise equation when compared to mGFR and may be a reasonable alternative.

Background/Objective: Hypertension is the most prevalent chronic disease in primary care and a leading cause of cardiovascular morbidity and mortality. Despite existing guidelines, therapeutic inertia and suboptimal control persist. Large language models (LLMs) offer a potential valuable addition to augment clinical decision-making, yet their reliability for guideline-driven tasks remains unverified. This study evaluated the accuracy and safety of hypertension management recommendations generated by three LLMs compared to expert responses. Methods: Fifty-one clinical vignettes representing 17 core hypertension management concepts were constructed by hypertension experts. Each case was submitted to three LLMs (GPT-4, Gemini, MedLM) and a hypertension expert also wrote the “gold standard” answers. Three blinded expert reviewers rated each response on a 4-point accuracy scale, a binary safety (safe/unsafe) scale, and attempted to identify the source (LLM vs. expert) providing the response. Ratings were analyzed using mean scores, percentages of accurate and safe responses, and inter-rater agreement. Results: GPT-4 had the highest accuracy (83%) and safety (86%) scores among LLMs but remained inferior to expert responses (92% accuracy, 93% safety). Gemini and MedLM performed significantly worse (accuracy: 64% and 35%; safety: 73% and 39%, respectively). GPT-4 generated the most guideline-concordant responses (46%) among the three LLMs (Gemini 35%, MedLM 14%), but remains lower than experts’ responses (68%). Evaluators misidentified LLM responses as expert-written in 10 to 25% of cases, particularly with GPT-4. Inter-rater reliability for accuracy ratings was highest for expert-generated responses (ICC 0.81), with progressively lower agreement for GPT-4 (0.76), Gemini (0.70), and MedLM (0.68). A similar pattern was observed for safety and source discrimination ratings. The agreement was strongest for safety assessments and weakest for source discrimination. Conclusion: Among three tested LLMs, GPT-4 demonstrated closer agreement to expert decisions thereby showing greater potential for supporting hypertension management. However, current LLMs’ versions frequently produce inaccurate or unsafe recommendations and remain inferior to expert judgment. Human-in-the-loop supervision remains essential when deploying LLMs for clinical decision-making.

Introduction: Blood pressure (BP) is a complex physiological marker. Cuffless devices, often based on photoplethysmography (PPG), enable frequent or continuous BP monitoring without arterial occlusion, enhancing comfort and usability in both inpatient and outpatient settings. Various devices have received regulatory clearance, but they are not yet included in clinical guidelines due to evolving validation standards. Aim: To evaluate accuracy of the Biobeat WP613 device for continuous BP monitoring using invasive intra-arterial pressure (IAP) monitoring in ICCU patients. Methods: This prospective, single-center study enrolled adults undergoing cardiac surgery at Chaim Sheba Medical Center (June 2020–January 2023) who had radial artery catheters for standard BP monitoring. Severe shock patients were excluded. Demographics and Fitzpatrick skin tone were recorded. ClinicalTrials.gov NCT04071015. Post-op, patients were simultaneously monitored with the standard IAP system and the Biobeat device. Continuous BP and HR were collected for up to five days. Data analyzed post hoc. Tested device The WP613 (Biobeat, Israel) is FDA-cleared, chest-worn, PPG-based device that uses multi-wavelength light and a sensor to monitor vital signs. It wirelessly transmits data to a cloud based algorithms to measure BP, cardiac output, stroke volume, and more. It also records a single-lead ECG and has a 5-day battery life. Results: A total of 96 patients were enrolled, with 88 included in the final BP analysis after excluding 8 due to technical issues. Of those, 80 received inotropic support. The average age was 63.2±12.2 years, with 33% female. Monitoring lasted an average of 25.6±17.2 hours, yielding over 78000 readings for each BP parameter and over 92000 HR readings (Fig 1) . Patients represented the full range of skin tones, classified using the Fitzpatrick scale I–VI. The Biobeat device showed excellent correlation with IAP monitoring: r=0.959 for SBP, 0.973 DBP, and 0.962 HR. Bland-Altman showed minimal bias (e.g., 0.1±4.8 for SBP) (Fig 2) . Correlation remained strong across BP ranges and skin tones. Heatmaps and representative cases confirmed close tracking between Biobeat and IAP (Fig 3) . Conclusion: The tested cuffless device (Biobeat) offers a high level of accuracy and agreement for BP and HR compared to data obtained by IAP monitoring in post-cardiac surgery patients. Further studies are needed to validate these findings in various populations and clinical settings.

Introduction: Photoplethysmography-based (PPG) devices represent a significant advancement in noninvasive cardiovascular monitoring. These cuffless technologies enable assessment of hemodynamic parameters with improved comfort, usability and compliance. Modern PPG systems have expanded their capabilities to include advanced metrics such as systemic vascular resistance (SVR) and cardiac output (CO). Many antihypertensive drugs lower blood pressure by reducing SVR through vasodilatation of the systemic and renal vasculature. Limited data is available on SVR during ambulatory monitoring. PPG devices become more common as they allow us to assess SVR in real life, in ambulatory blood pressure monitoring (ABPM) patients. Aim: To evaluate and compare SVR using the Biobeat (WP613) device across patient groups. Methods: Adults from the Hypertension Clinic at University of Miami, Florida, from Aug. 2023–Jan. 2025 underwent 24-h ABPM monitoring using Biobeat device. Patient data was matched with Biobeat. PPG data was available every 15 minutes; The raw data included SBP and DBP, the heart rate, stroke volume, CO and SVR. Results: A total of 539 patients underwent PPG ABPM during the study period. The median was 62 (IQR 54, 71) years, with 57% females (Tab 1) . Patients were defined as hypertensive per AHA 2017 guidelines [SBP≥130 and DBP≥80 mmHg]. Overall, 265 patients were classified as having normal BP, 95 as having isolated systolic hypertension, and 179 as having mixed hypertension. Within the Mix-HTN group, 42 patients had isolated diastolic hypertension and the remaining 137 systolic and diastolic hypertension (Fig 2) . In subgroup analysis (Fig 3); SVR was significantly different between the groups: lowerst in No/C-HTN and highest in Mix-HTN. particularly among the mixed-hypertension group, SVR was higher in the Systolic and Diastolic HTN compared to the Isolated diastolic HTN group. Among the No/C-HTN group, 60 patients were not hypertensives and 205, were hypertensives on at least 1 drug. The SVR was not statistically significant between these 2 subgroups, suggesting that SVR may be a helpful target biomarker used to up-titrate antihypertensives. Conclusion: PPG devices offer a valuable enhancement to conventional ABPM by providing additional physiological measurements such as SVR that can help differentiate between various hypertension phenotypes and potentially provide personalized therapy that target the driver of hypertension.

BACKGROUND: Hypertension, the leading cause of cardiovascular mortality, remains suboptimally controlled. Large language models (LLMs) could improve hypertension control by augmenting clinical decision-making, but their reliability for guideline-driven tasks is unverified. This study evaluated the accuracy and safety of hypertension management recommendations generated by 3 LLMs. METHODS: Fifty-one vignettes were constructed and submitted to the LLMs (GPT-4, Gemini, Medical Large Language Model [by Google; MedLM]) and a hypertension expert to generate the responses. Three blinded reviewers rated each response on a 4-point accuracy scale, a binary safety (safe/unsafe) scale, and attempted to identify the source (LLM versus expert) providing the response. RESULTS: GPT-4 had the highest accuracy (83%) and safety (86%) scores among LLMs but remained inferior to expert responses (92% accuracy, 93% safety). Gemini and MedLM performed significantly worse (accuracy: 64% and 35%; safety: 73% and 39%, respectively). GPT-4 generated the most guideline-concordant responses (46%) among the 3 LLMs (Gemini 35%, MedLM 14%) but was lower than expert responses (68%). Interrater reliability for accuracy ratings was higher for LLM-generated responses (GPT-4 [intraclass correlation coefficient, 0.30], Gemini [intraclass correlation coefficient, 0.61], and MedLM [intraclass correlation coefficient, 0.58]), with lower agreement for expert responses (intraclass correlation coefficient, 0.23). A similar pattern was observed for safety and source discrimination ratings. The agreement was strongest for safety assessments and weakest for source discrimination. CONCLUSIONS: Among the 3 tested LLMs, GPT-4 demonstrated closer agreement to expert decisions, thereby showing greater potential for supporting hypertension management. Despite their potential, current LLM versions are inferior to expert recommendations. Human-in-the-loop supervision remains essential when deploying LLMs for clinical decision-making.

Key Points Patient-centered care in an interdisciplinary CKD clinic addresses complex needs and supports comprehensive CKD management. Implementation of an interdisciplinary CKD clinic reduced hospital admissions by 26%, emergency department visits by 30%, and increased nephrology consultations. Comprehensive care models with integrated registries enhance tailored interventions, leading to improved CKD management outcomes. Background CKD is a significant public health issue globally. Its progressive nature calls for innovative care models to mitigate disease progression and enhance patient outcomes. An interdisciplinary clinic model may offer comprehensive care tailored to the needs of patients with CKD. The aim of this study was to evaluate the effect of an interdisciplinary CKD clinic on disease progression, health care utilization, and social determinants of health (SDOH). Methods We conducted a retrospective cohort study at the Mayo Clinic in Rochester, Minnesota. The study included 534 patients enrolled in the CKD clinic between March 5, 2021, and May 31, 2022, excluding those who opted out of research. The intervention involved a clinical registry and an interdisciplinary team delivering evidence-based care pathways, patient education, shared decision making, and care coordination. The primary outcomes assessed were CKD progression and health care utilization, while secondary outcomes examined the effect of SDOH. Results At entry, the median age was 73 (interquartile range, 64–79) years, with 60% at stage 4 or lower. Clinic implementation correlated with a 26% decrease in hospital admissions (incidence rate ratio [IRR], 0.74; 95% confidence interval [CI], 0.60 to 0.91; P = 0.004) and a 30% reduction in emergency visits (IRR, 0.70; 95% CI, 0.57 to 0.87; P = 0.001). Nephrology consultations increased by 46% (IRR, 1.46; 95% CI, 1.34 to 1.60; P < 0.001), reflecting enhanced specialized care. Lower exercise frequency and unemployment were linked to increased CKD progression and health care usage. Conclusions An interdisciplinary CKD clinic supported by a registry can potentially reduce health care utilization among patients with CKD, with SDOH playing a critical role in disease management.