Citations

Background. Predicting long-term mortality postkidney transplantation (KT) using baseline clinical data presents significant challenges. This study aims to evaluate the predictive power of artificial intelligence (AI)-enabled analysis of preoperative electrocardiograms (ECGs) in forecasting long-term mortality following KT. Methods. We analyzed preoperative ECGs from KT recipients at three Mayo Clinic sites (Minnesota, Florida, and Arizona) between January 1, 2006, and July 30, 2021. The study involved 6 validated AI algorithms, each trained to predict future development of atrial fibrillation, aortic stenosis, low ejection fraction, hypertrophic cardiomyopathy, amyloid heart disease, and biological age. These algorithms’ outputs based on a single preoperative ECG were correlated with patient mortality data. Results. Among 6504 KT recipients included in the study, 1764 (27.1%) died within a median follow-up of 5.7 y (interquartile range: 3.00–9.29 y). All AI-ECG algorithms were independently associated with long-term all-cause mortality (P < 0.001). Notably, few patients had a clinical cardiac diagnosis at the time of transplant, indicating that AI-ECG scores were predictive even in asymptomatic patients. When adjusted for multiple clinical factors such as recipient age, diabetes, and pretransplant dialysis, AI algorithms for atrial fibrillation and aortic stenosis remained independently associated with long-term mortality. These algorithms also improved the C-statistic for predicting overall (C = 0.74) and cardiac-related deaths (C = 0.751). Conclusions. The findings suggest that AI-enabled preoperative ECG analysis can be a valuable tool in predicting long-term mortality following KT and could aid in identifying patients who may benefit from enhanced cardiac monitoring because of increased risk.

Abstract Aims Cardiac amyloidosis (CA) is common in patients with severe aortic stenosis (AS) undergoing transcatheter aortic valve replacement (TAVR). Cardiac amyloidosis has poor outcomes, and its assessment in all TAVR patients is costly and challenging. Electrocardiogram (ECG) artificial intelligence (AI) algorithms that screen for CA may be useful to identify at-risk patients. Methods and results In this retrospective analysis of our institutional National Cardiovascular Disease Registry (NCDR)-TAVR database, patients undergoing TAVR between January 2012 and December 2018 were included. Pre-TAVR CA probability was analysed by an ECG AI predictive model, with &gt;50% risk defined as high probability for CA. Univariable and propensity score covariate adjustment analyses using Cox regression were performed to compare clinical outcomes between patients with high CA probability vs. those with low probability at 1-year follow-up after TAVR. Of 1426 patients who underwent TAVR (mean age 81.0 ± 8.5 years, 57.6% male), 349 (24.4%) had high CA probability on pre-procedure ECG. Only 17 (1.2%) had a clinical diagnosis of CA. After multivariable adjustment, high probability of CA by ECG AI algorithm was significantly associated with increased all-cause mortality [hazard ratio (HR) 1.40, 95% confidence interval (CI) 1.01–1.96, P = 0.046] and higher rates of major adverse cardiovascular events (transient ischaemic attack (TIA)/stroke, myocardial infarction, and heart failure hospitalizations] (HR 1.36, 95% CI 1.01–1.82, P = 0.041), driven primarily by heart failure hospitalizations (HR 1.58, 95% CI 1.13–2.20, P = 0.008) at 1-year follow-up. There were no significant differences in TIA/stroke or myocardial infarction. Conclusion Artificial intelligence applied to pre-TAVR ECGs identifies a subgroup at higher risk of clinical events. These targeted patients may benefit from further diagnostic evaluation for CA.

Abstract Purpose: Epithelioid hemangioendothelioma (EHE) is a rare vascular cancer with pathogenic TAZ–CAMTA1 (calmodulinbinding transcription activator 1) operating as an oncogenic driver through activation of the MAPK pathway. Trametinib is an inhibitor of MEK, a critical kinase in the MAPK pathway. We sought to evaluate the effect of trametinib in patients with EHE. Patients and Methods: A phase 2 trial of trametinib was conducted in patients with locally advanced or metastatic EHE. Eligibility requirements included evidence of tumor progression or presence of EHE-related pain requiring opiates for management before enrollment. The primary endpoint was objective response rate (ORR) as per RECIST1.1 in cases with TAZ– CAMTA1 confirmed by fusion-FISH. Secondary objectives were to estimate ORR for all patients, median progression-free survival (PFS), 2-year overall survival (OS) rate, patient safety, and change in patient-reported global health and pain scores per PROMIS questionnaires. Results: 44 patients enrolled and 42 started trametinib. TAZ– CAMTA1 was detected in 27 tumor samples. TheORRwas 3.7%[95% confidence interval (CI), 0.094–19.0], median PFS was 10.4 months (95%CI, 7.1–NA), and 2-year OS rate was 33.3%(95%CI, 19.1–58.2) in the target population. Median pain intensity and interference scores improved significantly after 4 weeks of trametinib in patients using opiates. Common adverse events related to trametinib were rash, fatigue, nausea/vomiting, diarrhea/constipation, alopecia, and edema; one grade 5 ARDS/pneumonitis was related to trametinib. Conclusions: Trametinib was associated with reduction in EHE-related pain and median PFS of more than 6 months, providing palliative benefit in patients with advanced EHE, but the trial did not meet the ORR goal. See related commentary by Van Tine and Haarberg, p. 4552

Abstract Aims Augmenting echocardiography with artificial intelligence would allow for automated assessment of routine parameters and identification of disease patterns not easily recognized otherwise. View classification is an essential first step before deep learning can be applied to the echocardiogram. Methods and results We trained two- and three-dimensional convolutional neural networks (CNNs) using transthoracic echocardiographic (TTE) studies obtained from 909 patients to classify nine view categories (10 269 videos). Transthoracic echocardiographic studies from 229 patients were used in internal validation (2582 videos). Convolutional neural networks were tested on 100 patients with comprehensive TTE studies (where the two examples chosen by CNNs as most likely to represent a view were evaluated) and 408 patients with five view categories obtained via point-of-care ultrasound (POCUS). The overall accuracy of the two-dimensional CNN was 96.8%, and the averaged area under the curve (AUC) was 0.997 on the comprehensive TTE testing set; these numbers were 98.4% and 0.998, respectively, on the POCUS set. For the three-dimensional CNN, the accuracy and AUC were 96.3% and 0.998 for full TTE studies and 95.0% and 0.996 on POCUS videos, respectively. The positive predictive value, which defined correctly identified predicted views, was higher with two-dimensional rather than three-dimensional networks, exceeding 93% in apical, short-axis aortic valve, and parasternal long-axis left ventricle views. Conclusion An automated view classifier utilizing CNNs was able to classify cardiac views obtained using TTE and POCUS with high accuracy. The view classifier will facilitate the application of deep learning to echocardiography.

Background Recent studies have indicated high rates of future major adverse cardiovascular events in patients with Takotsubo cardiomyopathy (TC), but there is no well‐established tool for risk stratification. This study sought to evaluate the prognostic value of several artificial intelligence‐augmented ECG (AI‐ECG) algorithms in patients with TC. Methods and Results This study examined consecutive patients in the prospective and observational Mayo Clinic Takotsubo syndrome registry. Several previously validated AI‐ECG algorithms were used for the estimation of ECG‐ age, probability of low ejection fraction, and probability of atrial fibrillation. Multivariable models were constructed to evaluate the association of AI‐ECG and other clinical characteristics with major adverse cardiac events, defined as cardiovascular death, recurrence of TC, nonfatal myocardial infarction, hospitalization for congestive heart failure, and stroke. In the final analysis, 305 patients with TC were studied over a median follow‐up of 4.8 years. Patients with future major adverse cardiac events were more likely to be older, have a history of hypertension, congestive heart failure, worse renal function, as well as high‐risk AI‐ECG findings compared with those without. Multivariable Cox proportional hazards analysis indicated that the presence of 2 or 3 high‐risk findings detected by AI‐ECG remained a significant predictor of major adverse cardiac events in patients with TC after adjustment by conventional risk factors (hazard ratio, 4.419 [95% CI, 1.833–10.66], P =0.001). Conclusions The combined use of AI‐ECG algorithms derived from a single 12‐lead ECG might detect subtle underlying patterns associated with worse outcomes in patients with TC. This approach might be beneficial for stratifying high‐risk patients with TC.

TPS766 Background: Imatinib is the worldwide standard for first-line therapy of advanced KIT-mutant GIST. However, secondary resistance mutations in the KIT ATP-binding domain (exons 13, 14), activation loop (exons 17, 18), or both develop and result in loss of imatinib-sensitivity. While no single tyrosine kinase inhibitor (TKI) inhibits all KIT mutations, the combination of bezuclastinib + sunitinib targets commonly occurring primary (exons 9, 11) and secondary (exons 13, 14, 17, and 18) KIT mutations. In a Phase 1/2 clinical study, pts with relapsed and/or refractory GIST and a median of 3 prior lines of therapy treated with bezuclastinib + sunitinib (n=15) experienced clinical benefit and an acceptable safety profile, warranting further evaluation in a randomized trial. Methods: Peak (NCT05208047) is a global, randomized, open-label, multi-part Phase 3 study evaluating the efficacy and safety of bezuclastinib + sunitinib versus sunitinib as second-line treatment in adult pts who were intolerant to imatinib or whose tumors had imatinib-resistance. The lead-in portion, to test a new formulation of bezuclastinib, (Part 1) has completed enrollment. Based upon PK and safety, a dose of bezuclastinib 600 mg QD + sunitinib 37.5 mg QD has been determined for Part 2 of the Peak study. Part 2 will enroll ~388 pts to be randomized (1:1) to bezuclastinib 600 mg QD + sunitinib 37.5 mg QD or sunitinib 37.5 mg QD alone. Key inclusion: >1 measurable lesion per modified Response Evaluation Criteria in Solid Tumors (mRECIST) v1.1, Eastern Cooperative Oncology Group Performance Status 0-2, adequate organ function, and prior imatinib therapy (no other prior therapy). Key exclusion: PDGFR mutations or succinate dehydrogenase deficiency, clinically significant cardiac disease, and use of strong CYP3A4 inhibitors or inducers. The primary endpoint is progression-free survival (PFS) confirmed by blinded independent central review per mRECIST v1.1. Additional efficacy (including overall survival and objective response rate) and safety endpoints will be evaluated. Clinical trial information: NCT05208047 .

748 Background: Ripretinib is a switch-control tyrosine kinase inhibitor approved for patients (pts) with gastrointestinal stromal tumor (GIST) who received prior treatment with 3 or more kinase inhibitors, including imatinib. Sunitinib is approved for advanced GIST after imatinib failure. In the second interim analysis of overall survival (OS) from the phase 3 INTRIGUE study, the OS event rate was 41% in the all-patient (AP) intent-to-treat (ITT) population, and OS was similar between treatment arms in both the KIT exon 11 ITT and AP ITT populations. Here, we present the final OS and updated safety from INTRIGUE. Methods: INTRIGUE (NCT03673501) is an open-label, phase 3 study of adults with advanced GIST who had disease progression on or intolerance to imatinib. Randomization was 1:1 to ripretinib 150 mg once daily (QD) or sunitinib 50 mg QD (4 weeks on/2 weeks off) and was stratified by KIT mutational status and imatinib intolerance. OS was a key secondary endpoint (the primary endpoint of progression-free survival was reported previously); final OS analysis was prespecified to occur with ≥200 and ≥145 events in the AP ITT and KIT exon 11 ITT populations, respectively. Data cutoff was March 15, 2023. Results: Of 453 pts, 444 received treatment; 40 remain on treatment (ripretinib, 28/223 [13%]; sunitinib, 12/221 [5%]). Treatment discontinuation was due to progressive disease (PD) by independent radiologic review (56%), PD by investigator (11%), clinical PD (6%), withdrawal of consent (6%), and adverse events (AEs; 5%). Fewer pts discontinued treatment due to AEs with ripretinib vs sunitinib (3% vs 6%). There were 211 OS events (47%) in the AP ITT population and 151 OS events (46%) in the KIT exon 11 ITT population. OS was similar with ripretinib vs sunitinib in the 2 ITT populations (Table). Fewer pts had grade 3/4 treatment-emergent AEs with ripretinib vs sunitinib (43% vs 67%). Dose interruptions and reductions were lower with ripretinib vs sunitinib. Median treatment duration for ripretinib vs sunitinib was 7.9 vs 6.5 months. Conclusions: In the finalOS analysis from the INTRIGUE study, OS was similar between treatment arms. The safety profile remained consistent and more favorable for ripretinib vs sunitinib in pts with advanced GIST previously treated with imatinib. Clinical trial information: NCT03673501 . [Table: see text]

Background Patients with peripheral artery disease are at increased risk for major adverse cardiac events, major adverse limb events, and all‐cause death. Developing tools capable of identifying those patients with peripheral artery disease at greatest risk for major adverse events is the first step for outcome prevention. This study aimed to determine whether computer‐assisted analysis of a resting Doppler waveform using deep neural networks can accurately identify patients with peripheral artery disease at greatest risk for adverse outcome events. Methods and Results Consecutive patients (April 1, 2015, to December 31, 2020) undergoing ankle–brachial index testing were included. Patients were randomly allocated to training, validation, and testing subsets (60%/20%/20%). Deep neural networks were trained on resting posterior tibial arterial Doppler waveforms to predict major adverse cardiac events, major adverse limb events, and all‐cause death at 5 years. Patients were then analyzed in groups based on the quartiles of each prediction score in the training set. Among 11 384 total patients, 10 437 patients met study inclusion criteria (mean age, 65.8±14.8 years; 40.6% women). The test subset included 2084 patients. During 5 years of follow‐up, there were 447 deaths, 585 major adverse cardiac events, and 161 MALE events. After adjusting for age, sex, and Charlson comorbidity index, deep neural network analysis of the posterior tibial artery waveform provided independent prediction of death (hazard ratio [HR], 2.44 [95% CI, 1.78–3.34]), major adverse cardiac events (HR, 1.97 [95% CI, 1.49–2.61]), and major adverse limb events (HR, 11.03 [95% CI, 5.43–22.39]) at 5 years. Conclusions An artificial intelligence–enabled analysis of Doppler arterial waveforms enables identification of major adverse outcomes among patients with peripheral artery disease, which may promote early adoption and adherence of risk factor modification.

AbstractUnesbulin is being investigated in combination with dacarbazine (DTIC) as a potential therapeutic agent in patients with advanced leiomyosarcoma (LMS). This paper reports the pharmacokinetics (PK) of unesbulin, DTIC, and its unreactive surrogate metabolite 5‐aminoimidazole‐4‐carboxamide (AIC) in 29 patients with advanced LMS. Drug interactions between DTIC (and AIC) and unesbulin were evaluated. DTIC (1000 mg/m2) was administered to patients with LMS via 1‐h intravenous (i.v.) infusion on day 1 of every 21‐day (q21d) cycle. Unesbulin dispersible tablets were administered orally twice weekly (b.i.w.), starting on day 2 of every cycle, except for cycle 2 (C2), where unesbulin was dosed either on day 1 together with DTIC or on day 2, 1 day after DTIC administration. The PK of DTIC, AIC, and unesbulin in cycle 1 (C1) and C2 were estimated using noncompartmental analysis. DTIC and AIC were measurable immediately after the start of infusion and reached maximum plasma concentration (Cmax) immediately or shortly after end of infusion at 1.0 and 1.4 h (time to Cmax), respectively. Co‐administration of unesbulin orally at 200 mg or above with DTIC inhibited cytochrome P450 (CYP)1A2‐mediated DTIC metabolism, resulting in 66.7% reduction of AIC exposures. Such inhibition could be mitigated when unesbulin was dosed the day following DTIC infusion. Repeated unesbulin dosing demonstrated evidence of clinical CYP1A2 induction and increased AIC Cmax by 69.4% and area under concentration‐time curve to infinity by 57.9%. No meaningful difference in unesbulin PK was observed between C2 and C1. The combination therapy of 1000 mg/m2 i.v. DTIC q21d and 300 mg unesbulin b.i.w. in a staggered regimen is well‐tolerated in patients with LMS.