Citations

Abstract Background The determination of left ventricular diastolic dysfunction (LVDD) and filling pressure in patients with significant (>moderate) mitral regurgitation (MR) poses a complex challenge. We recently validated an artificial intelligence-enabled electrocardiogram (AI-ECG) algorithm to detect LVDD and estimate LV filling pressures. Methods This retrospective study sought to examine the risk of all-cause mortality across AI-ECG LVDD grades. Patients from the AI-ECG LVDD study test cohort who underwent transthoracic echocardiography confirming significant MR and an ECG within fourteen days of each other at Mayo Clinic between 09/2001 and 06/2022 were included. LVDD status was determined based on the index ECG, and patients were categorized into groups representing normal diastolic function (NDF) or LVDD grades 1 (G1), 2 (G2), or 3 (G3). Results Of 4,019 patients with significant MR (mean age 69.8, 49.0% women), 1,175 (29.2%), 1,881 (46.8%), and 963 (24.0%) were classified by AI-ECG as NDF/G1-LVDD, G2-LVDD, and G3-LVDD, respectively. The median mitral effective regurgitant orifice area was 26 mm² (interquartile range 20-36 mm²). Over a median follow-up of 3.5 years, 1,636 (40.7%) patients died. In multivariable survival analysis adjusted for multiple risk factors, a worse AI-ECG LVDD grade was independently associated with an increased death risk [G2DD: adjusted hazard ratio (aHR) 1.98 (95% confidence interval (95% CI) 1.63-2.40), G3DD: aHR 2.59 (95% CI 2.09-3.20)]. These findings were consistent when accounting for mitral valve intervention and among patients with >moderate MR or after mitral valve intervention. Conclusion In patients with significant MR, the grading of LVDD by AI-ECG is independently associated with all-cause mortality.

Abstract Aims Gender-affirming hormone therapy (GAHT) is used by some transgender individuals (TG), who comprise 1.4% of US population. However, the effects of GAHT on electrocardiogram (ECG) remain unknown. The objective is to assess the effects of GAHT on ECG changes in TG. Methods and results Twelve-lead ECGs of TG on GAHT at the Mayo Clinic were inspected using a validated artificial intelligence (AI) algorithm. The algorithm assigns a patient’s ECG male pattern probability on a scale of 0 (female) to 1 (male). In the primary analysis, done separately for transgender women (TGW) and transgender men (TGM), 12-lead ECGs were used to estimate the male pattern probability before and after GAHT. In a subanalysis, only patients with both pre- and post-GAHT EGCs were included. Further, the autopopulated PR, QRS, and QTc intervals were compared before and after GAHT. Among TGW (n = 86), the probability (mean ± SD) of an ECG male pattern was 0.84 ± 0.25 in the pre-GAHT group, and it was lowered to 0.59 ± 0.36 in the post-GAHT group (n = 173, P < 7.8 × 10−10). Conversely, among TGM, male pattern probability was 0.16 ± 0.28 (n = 47) in the pre-GAHT group, and it was higher at 0.41 ± 0.38 in the post-GAHT group (n = 53, P < 2.4×10−4). The trend persisted in the subanalysis. Furthermore, both the PR (P = 5.68 × 10−4) and QTc intervals (P = 6.65×10−6) prolonged among TGW. Among TGM, the QTc interval shortened (P = 4.8 × 10−2). Conclusion Among TG, GAHT is associated with ECG changes trending towards gender congruence, as determined by the AI algorithm and ECG intervals. Prospective studies are warranted to understand GAHT effects on cardiac structure and function.

Abstract Aims We aim to determine if our previously validated, diagnostic artificial intelligence (AI) electrocardiogram (ECG) model is prognostic for survival among patients with cardiac amyloidosis (CA). Methods A total of 2533 patients with CA (1834 with light chain amyloidosis (AL), 530 with wild-type transthyretin amyloid protein (ATTRwt) and 169 with hereditary transthyretin amyloid (ATTRv)] were included. An amyloid AI ECG (A2E) score was calculated for each patient reflecting the likelihood of CA. CA stage was calculated using the European modification of the Mayo 2004 criteria for AL and Mayo stage for transthyretin amyloid (ATTR). Risk of death was modelled using Cox proportional hazards, and Kaplan–Meier was used to estimate survival. Results Median age of the cohort was 67 [inter-quartile ratio (IQR) 59, 74], and 71.6% were male. The median overall survival for the cohort was 35.6 months [95% confidence interval (CI) 32.3, 39.5]. For AL, ATTRwt and ATTRv, respectively, median survival was 22.9 (95% CI 19.2, 28.2), 47.2 (95% CI 43.4, 52.3) and 61.4 (95% CI 48.7, 75.9) months. On univariate analysis, an increasing A2E score was associated with more than a two-fold risk of all-cause death. On multivariable analysis, the A2E score retained its importance with a risk ratio of 2.0 (95% CI 1.58, 2.55) in the AL group and 2.7 (95% CI 1.81, 4.24) in the ATTR group. Conclusions Among patients with AL and ATTR amyloidosis, the A2E model helps to stratify risk of CA and adds another dimension of prognostication.

Abstract Artificial intelligence (AI)–enabled interpretation of electrocardiogram (ECG) images (AI-ECGs) can identify patterns predictive of future adverse cardiac events. We hypothesized that such an approach would provide prognostic information for the risk of cardiac complications and mortality in patients undergoing hematopoietic cell transplantation (HCT). We retrospectively subjected ECGs obtained before HCT to an externally trained, deep-learning model designed to predict the risk of atrial fibrillation (AF). Included were 1377 patients (849 autologous [auto] HCT and 528 allogeneic [allo] HCT recipients). The median follow-up was 2.9 years. The 3-year cumulative incidence of AF was 9% (95% confidence interval [CI], 7-12) in patients who underwent auto HCT and 13% (10%-16%) in patients who underwent allo HCT. In the entire cohort, pre-HCT AI-ECG estimate of AF risk correlated highly with the development of clinical AF (hazard ratio [HR], 7.37; 95% CI, 3.53-15.4; P < .001), inferior survival (HR, 2.4; 95% CI, 1.3-4.5; P = .004), and greater risk of nonrelapse mortality (NRM; HR, 95% CI, 3.36; 1.39-8.13; P = .007), without increased risk of relapse. Association with mortality was only noted in allo HCT recipients, where the risk of NRM was greater. The use of cyclophosphamide after transplantation resulted in greater 90-day incidence of AF (13% vs 5%; P = .01) compared to calcineurin inhibitor–based graft-versus-host disease prophylaxis, corresponding to temporal changes in AI-ECG AF prediction after HCT. In summary, AI-ECG can inform risk of posttransplant cardiac outcomes and survival in HCT patients and represents a novel strategy for personalized risk assessment.

Abstract Introduction/ Background Holmium laser enucleation of the prostate (HoLEP) is an increasingly popular size-independent technique of treating male voiding dysfunction due to benign prostatic hypertrophy. Some patients after HoLEP may develop clinically significant prostate cancer and opt for definitive treatment with external beam radiation therapy (EBRT). Little is known about the safety of EBRT after HoLEP and how it may functionally impact voiding after HoLEP has altered the anatomy of the prostate. Our study aimed to assess patient-reported voiding outcomes following EBRT after HoLEP with a focus on incontinence related patient outcomes. Methods/ Materials This study was conducted with approval from our hospital’s institutional review board. Patients that underwent HoLEP followed by EBRT were identified and data was collected in a retrospective nature from a single surgeon HoLEP cohort over the past 4 years (2019–2023). Patient demographics, disease and radiation therapy characteristics, radiation therapy, and baseline voiding symptoms were recorded. Current functional voiding outcomes were also collected via phone-call or portal communication in a cross-sectional manner with questions pertaining to type of incontinence, IPSS quality of life score, and administration of the Michigan Incontinence Symptom Index (M-ISI). Adverse events encountered during follow-up were recorded. Results 24 patients were identified who received RT for prostate cancer after HoLEP with an average age of 73.6 (+/- 5.3). One third of patients reported no incontinence whatsoever after radiation and of those who experienced incontinence, the majority felt that it was not worsened after radiation. Median IPSS QoL score following radiation was 1 (range 0–6), median M-ISI Severity Score was 4 out of a maximum of 32, and median M-ISI Bother Score was 0 out of a maximum of 8. One patient developed a bladder neck contracture (BNC) approximately 1 year following his radiation therapy (approximately 18 months after HoLEP) causing bothersome incontinence and LUTS. Conclusions In our cohort most patients who received RT after HoLEP reported a high urinary-symptom related quality of life and a low rate of urinary incontinence. One patient who received SBRT suffered a BNC which is a known adverse event with RT but given our small sample size it remains unclear if the risk is higher in patients receiving RT after HoLEP. Larger studies should focus on examining the rate of bladder neck contracture in patients receiving RT after HoLEP, particularly focusing on whether the degree of dose fractionation may impact their development.

Hypertension is among the most important risk factors for cardiovascular disease, chronic kidney disease, and dementia. The artificial intelligence (AI) field is advancing quickly, and there has been little discussion on how AI could be leveraged for improving the diagnosis and management of hypertension. AI technologies, including machine learning tools, could alter the way we diagnose and manage hypertension, with potential impacts for improving individual and population health. The development of successful AI tools in public health and health care systems requires diverse types of expertise with collaborative relationships between clinicians, engineers, and data scientists. Unbiased data sources, management, and analyses remain a foundational challenge. From a diagnostic standpoint, machine learning tools may improve the measurement of blood pressure and be useful in the prediction of incident hypertension. To advance the management of hypertension, machine learning tools may be useful to find personalized treatments for patients using analytics to predict response to antihypertension medications and the risk for hypertension-related complications. However, there are real-world implementation challenges to using AI tools in hypertension. Herein, we summarize key findings from a diverse group of stakeholders who participated in a workshop held by the National Heart, Lung, and Blood Institute in March 2023. Workshop participants presented information on communication gaps between clinical medicine, data science, and engineering in health care; novel approaches to estimating BP, hypertension risk, and BP control; and real-world implementation challenges and issues.

AbstractBackgroundThis was a single‐arm, phase 2 clinical trial of Bavarian Nordic (BN)‐Brachyury vaccine plus radiotherapy (RT) designed to determine the objective response rate (ORR), progression‐free survival (PFS), and safety of the combination in chordoma.MethodsA total of 29 adult patients with advanced chordoma were treated with two subcutaneous priming vaccine doses of modified vaccinia Ankara‐Bavarian Nordic (MVA‐BN)‐Brachyury and one vaccine dose of fowlpox virus (FPV)‐Brachyury before RT. After RT, booster vaccinations were given with FPV‐Brachyury every 4 weeks for 4 doses, then every 12 weeks (week 110). A minimum RT dose of >8 Gy in one fraction for each target was required. Response was evaluated by modified Response Evaluation Criteria in Solid Tumors 1.1 (mRECIST), where only radiated lesions were considered targets, and by standard RECIST 1.1 in a subset of patients.ResultsTwo of 26 evaluable patients experienced durable partial response (PR) (ORR of 7.7%; 90% confidence interval [CI], 2.6–20.8]) by mRECIST 1.1. A total of 21 patients (80.8%; 90% CI, 65.4–90.3) had stable disease, and three patients (11.5%; 90% CI, 4.7–25.6) had progressive disease as best response per mRECIST 1.1. Median PFS was not reached during the study.ConclusionsThis trial confirms the safety of BN‐Brachyury and RT. Although the study did not meet the predefined study goal of four responses in 29 patients, we did observe two PRs and a PFS of greater than 2 years. For a vaccine‐based study in chordoma, an ultra‐rare disease where response rates are low, a randomized study or novel trial designs may be required to confirm activity.

Key Points Measuring blood potassium has always required access to blood. The surface electrocardiogram, analyzed using an artificial intelligence algorithm, can detect hyperkalemia bloodlessly. The artificial intelligence-analyzed electrocardiogram exhibited a high negative predictive value but substantially lower positive predictive value. Background Artificial intelligence (AI) electrocardiogram (ECG) analysis can enable detection of hyperkalemia. In this validation, we assessed the algorithm's performance in two high acuity settings. Methods An emergency department (ED) cohort (February to August 2021) and a mixed intensive care unit (ICU) cohort (August 2017 to February 2018) were identified and analyzed separately. For each group, pairs of laboratory-collected potassium and 12 lead ECGs obtained within 4 hours of each other were identified. The previously developed AI ECG algorithm was subsequently applied to leads 1 and 2 of the 12 lead ECGs to screen for hyperkalemia (potassium >6.0 mEq/L). Results The ED cohort ( N =40,128) had a mean age of 60 years, 48% were male, and 1% ( N =351) had hyperkalemia. The area under the curve (AUC) of the AI-enhanced ECG (AI-ECG) to detect hyperkalemia was 0.88, with sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and positive likelihood ratio (LR+) of 80%, 80%, 3%, 99.8%, and 4.0, respectively, in the ED cohort. Low-eGFR (<30 ml/min) subanalysis yielded AUC, sensitivity, specificity, PPV, NPV, and LR+ of 0.83, 86%, 60%, 15%, 98%, and 2.2, respectively, in the ED cohort. The ICU cohort ( N =2636) had a mean age of 65 years, 60% were male, and 3% ( N =87) had hyperkalemia. The AUC for the AI-ECG was 0.88 and yielded sensitivity, specificity, PPV, NPV, and LR+ of 82%, 82%, 14%, 99%, and 4.6, respectively in the ICU cohort. Low-eGFR subanalysis yielded AUC, sensitivity, specificity, PPV, NPV, and LR+ of 0.85, 88%, 67%, 29%, 97%, and 2.7, respectively in the ICU cohort. Conclusions The AI-ECG algorithm demonstrated a high NPV, suggesting that it is useful for ruling out hyperkalemia, but a low PPV, suggesting that it is insufficient for treating hyperkalemia.

11558 Background: Nirogacestat (niro) is a targeted and selective gamma secretase inhibitor approved in the US for adults with progressing desmoid tumors (DT). In the phase 3 DeFi study, niro demonstrated significant improvement vs placebo (pbo) in progression-free survival (PFS: HR, 0.29 [95% CI: 0.15-0.55]; P<.001), objective response rate (ORR: 41% vs 8%; P<.001); and patient-reported outcomes (PROs) of pain, DT-specific symptom burden, physical and role functioning, and overall quality of life ( P≤.01, all). DT are driven by Wnt/β-catenin signaling pathway alterations and about 10-20% of DT are associated with mutations in the APC tumor suppressor gene, which may confer more aggressive DT behavior. Because patients with APC mutations may do worse, regardless of specific therapy, a post hoc analysis was conducted to assess effects of niro in patients with progressing DT and APC mutations. Methods: DeFi was a global, double-blind study that evaluated the efficacy, safety, and tolerability of niro in adults with progressing DT. Patients were randomized to oral niro (150 mg) or pbo twice-daily in continuous 28-day cycles. Descriptive post hoc analyses were conducted to assess effects of niro in patients with somatic and/or germline APC mutations. Results: Among 29 patients in DeFi with APC mutations (niro=13; pbo=16), 19 (66%) were female, 16 (55%) were aged ≤30 years, and 22 (76%) were refractory to prior treatment (with a median of 3 prior lines of treatment). In patients with APC mutation, PFS was improved with niro vs pbo (HR, 0.21 [95% CI: 0.05-1.00], P=.016). Confirmed ORR was 38% (5/13) for niro vs 13% (2/16) for pbo. Niro-treated patients also had greater reduction in median best percent change from baseline compared with pbo-treated patients in target tumor size (-29.5 vs +2.2), volumetric MRI (-71.0 vs +5.4), and T2 hyperintensity (-74.1 vs -21.0). Across all PROs assessed — Brief Pain Inventory, GODDESS DT Symptom Scale and DT Impact Scale, and European Organisation for Research and Treatment of Cancer Quality of Life Questionnaire-Core 30 — patients treated with niro had numerically greater improvement from baseline at cycle 10 than pbo. Analyses were limited due to the small sample size. Adverse events in >50% of niro-treated patients with APC mutation were diarrhea, nausea, rash maculopapular, and fatigue; ovarian toxicity occurred in 9 of 10 of females of reproductive potential (6 resolved, 2 lost to follow-up, 1 ongoing and receiving niro). Conclusions: Improvement in PFS, ORR, tumor imaging characteristics and PROs was observed with niro compared to pbo in patients with DT harboring APC mutations. Efficacy and safety of niro in patients with APC mutations were generally consistent with findings for the overall DeFi population, suggesting that niro can provide clinically meaningful benefit to patients with progressing DT and APCmutations. Clinical trial information: NCT03785964 .