Citations

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.

Abstract Generative artificial intelligence (AI) holds immense potential for medical applications, but the lack of a comprehensive evaluation framework and methodological deficiencies in existing studies hinder its effective implementation. Standardized assessment guidelines are crucial for ensuring reliable and consistent evaluation of generative AI in healthcare. Our objective is to develop robust, standardized guidelines tailored for evaluating generative AI performance in medical contexts. Through a rigorous literature review utilizing the Web of Sciences, Cochrane Library, PubMed, and Google Scholar, we focused on research testing generative AI capabilities in medicine. Our multidisciplinary team of experts conducted discussion sessions to develop a comprehensive 32‐item checklist. This checklist encompasses critical evaluation aspects of generative AI in medical applications, addressing key dimensions such as question collection, querying methodologies, and assessment techniques. The checklist and its broader assessment framework provide a holistic evaluation of AI systems, delineating a clear pathway from question gathering to result assessment. It guides researchers through potential challenges and pitfalls, enhancing research quality and reporting and aiding the evolution of generative AI in medicine and life sciences. Our framework furnishes a standardized, systematic approach for testing generative AI's applicability in medicine. For a concise checklist, please refer to Table S or visit GenAIMed.org .

AbstractTargeting NLRP3 inflammasome has been recognized as a promising therapeutic strategy for the treatment of numerous common diseases. UK5099, a long‐established inhibitor of mitochondrial pyruvate carrier (MPC), is previously found to inhibit macrophage inflammatory responses independent of MPC expression. However, the mechanisms by which UK5099 inhibit inflammatory responses remain unclear. Here, it is shown that UK5099 is a potent inhibitor of the NLRP3 inflammasome in both mouse and human primary macrophages. UK5099 selectively suppresses the activation of the NLRP3 but not the NLRC4 or AIM2 inflammasomes. Of note, UK5099 retains activities on NLRP3 in macrophages devoid of MPC expression, indicating this inhibitory effect is MPC‐independent. Mechanistically, UK5099 abrogates mitochondria‐NLRP3 interaction and in turn inhibits the assembly of the NLRP3 inflammasome. Further, a single dose of UK5099 persistently reduces IL‐1β production in an endotoxemia mouse model. Importantly, structure modification reveals that the inhibitory activities of UK5099 on NLRP3 are unrelated to the existence of the activated double bond within the UK5099 molecule. Thus, this study uncovers a previously unknown molecular target for UK5099, which not only offers a new candidate for the treatment of NLRP3‐driven diseases but also confounds its use as an MPC inhibitor in immunometabolism studies.

7532 Background: ABBV-383 is a BCMA x CD3 bispecific antibody with 2 high-affinity BCMA-binding domains and a low-affinity CD3 engaging arm that has been shown to decrease the negative impact of soluble BCMA (sBCMA) and drive sustained T-cell activation with reduced cytokine release in preclinical models of MM. Here, we describe correlative biomarker results of baseline and longitudinal sBCMA levels and immune profiles in the ongoing first-in-human trial that supports 60 mg Q4W as the optimal therapeutic dose of ABBV-383 monotherapy. Methods: Peripheral blood and serum samples from patients with RRMM enrolled in the phase 1 open-label, dose-expansion study (NCT03933735) who received ABBV-383 at 20, 40, or 60 mg Q3W or 60 mg Q4W were collected at baseline (post-dexamethasone, pre–ABBV-383), on treatment, and at disease progression. Samples were analyzed by flow cytometry for immune cell populations, Luminex for cytokines, and electrochemiluminescence ligand binding for sBCMA. Results: Median sBCMA levels at baseline were highly variable among patients, but did not associate with clinical response (≥ partial response [PR]) to ABBV-383 at the selected optimal dose level of 60 mg Q4W (<PR: 244.7 ng/mL; ≥PR: 52.2 ng/mL; P=0.13). Reduction in sBCMA levels over time associated with clinical response (Cmin at cycle 5: <PR, 244.7 ng/mL; ≥PR, 4.7 ng/mL; P=0.04). ABBV-383 treatment led to a rapid and transient increase of proinflammatory cytokines, including IL-6, IL-8, IL-10, TNF-α (Cmax within cycle 1: 29, 349.5, 1375, 456.5 pg/mL, respectively), and promoted T-cell redistribution (89% reduction of CD8+ T cells from periphery), activation (1.9-fold increase in CD69+CD8+ T cells), and proliferation (2-fold increase in Ki67+CD8+ T cells) within cycle 1 in 60-mg Q4W-treated patients. The frequency of baseline CD8+ T-cell exhaustion (PD-1/TIM3) did not impact clinical response at the optimal dose level of 60 mg Q4W ABBV-383 (<PR: 3.5%; ≥PR: 3.9%; P=0.9). Peak induction levels of proinflammatory cytokines during cycle 1 correlated with occurrence of cytokine release syndrome (≥G1) as well as clinical response across dose levels. Conclusions: High-avidity BCMA binding coupled to low-affinity T-cell engagement distinguishes the resulting mechanism of action for ABBV-383. Responses to 60 mg Q4W ABBV-383 were independent of baseline sBCMA levels and resulted in rapid and transient proinflammatory cytokine production that promoted robust T-cell redistribution, activation, and proliferation, indicating that the optimal dose of ABBV-383 maximizes its clinical potential as a convenient, safe, and effective therapy for MM. Clinical trial information: NCT03933735 .

7510 Background: The randomized Phase 3 CANOVA study’s (NCT03539744) primary analysis showed multiple numerically improved efficacy endpoints with VenDex v PomDex, but the primary endpoint of mPFS by IRC was not statistically significant. Here, we report correlative biomarker analyses from CANOVA. Methods: CANOVA is a randomized, global, open-label Phase 3 study of VenDex v PomDex in pts with t(11;14)+ RRMM and ≥2 prior lines of therapy (LOTs). The primary endpoint was mPFS by IRC. Key secondary endpoints included ORR, ≥VGPR, mOS, and MRD negativity (<10-5). In post hoc mPFS sensitivity analysis, disease progression, death, and start of next LOT were defined as events. BCL2 gene expression by RNAseq (3.7 log2 FPKM prespecified median cutoff for BCL2high v BCL2low) and chr1q abnormalities by whole-exome sequencing (normal, gain, or amp) were assessed centrally from pretreatment, CD138-enriched BM aspirates. Results: mPFS, post hoc mPFS, and mOS in the VenDex arm were similar by BCL2 status, with numerically higher ORR, ≥VGPR, and MRD negativity rates in the BCL2highsubgroup. In contrast, mPFS and mOS within the PomDex arm were numerically longer in the BCL2lowsubgroup, despite equal ORR in both subgroups (Table). Presence of 1q abnormalities was evenly distributed across BCL2high v BCL2low subgroups in the VenDex arm (51% v 45%) but not in the PomDex arm (59% v 31%). Normal 1q and gain(1q) subgroups had numerically improved mPFS, mOS, ORR, ≥VGPR, and MRD negativity with VenDex; pts with amp(1q) had poor outcomes regardless of treatment, albeit the sample size was small. Conclusions: Pts with BCL2high or gain(1q) had numerically improved clinical efficacy with VenDex v PomDex. Clinical benefit was consistent across BCL2 subgroups ( BCL2high or BCL2low) with VenDex but not PomDex. Pts with amp(1q) fared poorly irrespective of treatment arm. Clinical trial information: NCT03539744 . [Table: see text]

1113 Background: Testing for BRCA1/BRCA2 mutations (BRCAm) aids systemic treatment decisions for patients (pts) with metastatic breast cancer (mBC). This retrospective study explored real-world germline/tumor (g/t) BRCA testing patterns and PARP inhibitor (PARPi) use in US pts with mBC. Methods: Data from pts ≥18 years old diagnosed with HER2-negative mBC from 2014–2022 were captured in the nationwide Flatiron Health electronic health record-derived deidentified database. Patterns and timing of prospective or incidental BRCA testing were compared across mBC subtypes (hormone receptor-positive [HR+ mBC]/triple-negative mBC [mTNBC]) and disease stage (recurrent/ de novo). BRCAm prevalence was compared by testing modality and mBC subtype. PARPi initiation was assessed in pts with mBC diagnosed from 2018 onwards and a positive BRCAm test result. Clinical characteristics were compared by receipt of a BRCA test, testing modality, and PARPi initiation. Real-world overall survival (OS) by PARPi use was estimated using the Kaplan-Meier method. Results: Of 15,006 pts (including 12,349 with HR+ mBC; 1998 with mTNBC), 8178 (54.5%) did not receive any type of BRCA test, 4654 (31.0%) received a gBRCA test, 3075 (20.5%) received a tumor tissue DNA (ttDNA) test, and 1418 (9.4%) received a circulating tumor DNA (ctDNA) test. BRCA testing prevalence was numerically higher in pts with mTNBC (n=1164; 58.3%) than in pts with HR+ mBC (n=5323; 43.1%). As expected, testing prevalence was higher with ttDNA than with ctDNA (mTNBC: n=569 [28.5%] vs n=137 [6.9%]; HR+ mBC: n=2339 [18.9%] vs n=1224 [9.9%]). Over 93% of pts (recurrent and de novo) who received a tBRCA test were tested after an mBC diagnosis, and >1/3 were tested after first-line therapy, with median times from diagnosis to a ttDNA and ctDNA test of 127 and 431 days, respectively. Both gBRCA and tBRCA testing rates increased from 2014–2022, and testing occurred earlier in pts with recurrent than de novo disease. Among pts with tBRCAm, 66.0% had HR+ mBC, and 25.6% had mTNBC. BRCA1 mutations were more common in mTNBC (59.0%) than in HR+ mBC (22.9%) tumors. Of 219 pts with tBRCAm tumors who were diagnosed with mBC from 2018 onwards, PARPi was initiated in 39/74 (52.7%) pts with gBRCAm, 15/71 (21.1%) pts who were gBRCAm-negative, and 19/74 (25.7%) pts with gBRCAm status unknown. Among pts with g or tBRCAm and available OS data, median OS was numerically longer in pts who received PARPi (32.3 months [95% CI: 24.2, 47.4], n=128) versus pts who did not (29.0 months [95% CI: 21.9, 31.9], n=204; median follow-up time 23.2 months). Conclusions: While NCCN guidelines recommend gBRCA testing for all pts with mBC, more than half of pts with HER2-negative mBC (56.9% of pts with HR+ mBC) did not receive any BRCA test. Among pts with tBRCAm, ~2/3 had HR+ disease. Despite the potential benefits of PARPi for pts with BRCAm mBC, utilization remained low from 2018–2022.

Abstract To address acute vaso-occlusive episodes (VOEs), the leading cause of emergency department (ED) visits among individuals with sickle cell disease (SCD), we conducted the clinical study, ALIGN (An Individualized Pain Plan with Patient and Provider Access for Emergency Department care of SCD), across 8 sites. We hypothesized an improvement of 0.5 standard deviations in perceived quality of ED pain treatment of a VOE after implementing individualized pain plans (IPPs) accessible to both patients and providers. Patients with SCD were aged 18 to 45 years, owned a cell phone, and had an ED VOE visit within 90 days prior. Patients completed the perceived quality of care surveys at baseline and within 96 hours after an ED VOE visit. Providers completed surveys regarding comfort managing VOEs at baseline and after managing an enrolled patient. Most of the 153 patients were African American (95.4%), female (64.7%), and had Hb SS/Sβ0 genotype (71.9%). The perceived quality of ED pain treatment was high at both baseline and after implementation of IPPs; our primary outcome hypothesis was not met, because no statistically significant change in the patient-perceived quality of ED treatment occurred. A total of 135 providers completed baseline and follow-up surveys. On a scale of 1 to 7, with 7 being extremely comfortable managing VOEs, 60.5% reported a score ≥6 after IPP implementation vs 57.8% at baseline. Almost all (97.6%) ordered the recommended medication, and 94.7% intended to use IPPs. In this implementation protocol, all sites successfully implemented IPPs. Patients and ED providers both endorsed the use of IPPs. This trial was registered at www.ClinicalTrials.gov as # NCT04584528.

AbstractObjectivesWe aimed to develop consensus on comorbidities (frequency, severity, and prognosis) and overall outcomes in epilepsy, development, and cognition for the five phenotypes of SCN8A‐related disorders.MethodsA core panel consisting of 13 clinicians, 1 researcher, and 6 caregivers was formed and split into three workgroups. One group focused on comorbidities and prognosis. All groups performed a literature review and developed questions for use in a modified‐Delphi process. Twenty‐eight clinicians, one researcher, and 13 caregivers from 16 countries participated in three rounds of the modified‐Delphi process. Consensus was defined as follows: strong consensus ≥80% fully agree; moderate consensus ≥80% fully or partially agree, <10% disagree; and modest consensus 67%–79% fully or partially agree, <10% disagree.ResultsConsensus was reached on the presence of 14 comorbidities in patients with Severe Developmental and Epileptic Encephalopathy (Severe DEE) spanning non‐seizure neurological disorders and other organ systems; impacts were mostly severe and unlikely to improve or resolve. Across Mild/Moderate Developmental and Epileptic Encephalopathy (Mild/Moderate DEE), Neurodevelopmental Delay with Generalized Epilepsy (NDDwGE), and NDD without Epilepsy (NDDwoE) phenotypes, cognitive and sleep‐related comorbidities as well as fine and gross motor delays may be present but are less severe and more likely to improve compared to Severe DEE. There was no consensus on comorbidities in the SeL(F)IE phenotype but strong conesensus that seizures would largely resolve. Seizure freedom is rare in patients with Severe DEE but may occur in some with Mild/Moderate DEE and NDDwGE.SignificanceSignificant comorbidities are present in most phenotypes of SCN8A‐related disorders but are most severe and pervasive in the Severe DEE phenotype. We hope that this work will improve recognition, early intervention, and long‐term management for patients with these comorbidities and provide the basis for future evidence‐based studies on optimal treatments of SCN8A‐related disorders. Identifying the prognosis of patients with SCN8A‐related disorders will also improve care and quality‐of‐life for patients and their caregivers.

AbstractObjectiveWe aimed to develop consensus for diagnosis/management of SCN8A‐related disorders. Utilizing a modified Delphi process, a global cohort of experienced clinicians and caregivers provided input on diagnosis, phenotypes, treatment, and management of SCN8A‐related disorders.MethodsA Core Panel (13 clinicians, one researcher, six caregivers), divided into three subgroups (diagnosis/phenotypes, treatment, comorbidities/prognosis), performed a literature review and developed questions for the modified Delphi process. Twenty‐eight expert clinicians, one researcher, and 13 caregivers from 16 countries participated in the subsequent three survey rounds. We defined consensus as follows: strong consensus, ≥80% fully agree; moderate consensus, ≥80% fully/partially agree, <10% disagree; and modest consensus, 67%–79% fully/partially agree, <10% disagree.ResultsEarly diagnosis is important for long‐term clinical outcomes in SCN8A‐related disorders. There are five phenotypes: three with early seizure onset (severe developmental and epileptic encephalopathy [DEE], mild/moderate DEE, self‐limited (familial) infantile epilepsy [SeL(F)IE]) and two with later/no seizure onset (neurodevelopmental delay with generalized epilepsy [NDDwGE], NDD without epilepsy [NDDwoE]). Caregivers represented six patients with severe DEE, five mild/moderate DEE, one NDDwGE, and one NDDwoE. Phenotypes vary by age at seizures/developmental delay onset, seizure type, electroencephalographic/magnetic resonance imaging findings, and first‐line treatment. Gain of function (GOF) versus loss of function (LOF) is valuable for informing treatment. Sodium channel blockers are optimal first‐line treatment for GOF, severe DEE, mild/moderate DEE, and SeL(F)IE; levetiracetam is relatively contraindicated in GOF patients. First‐line treatment for NDDwGE is valproate, ethosuximide, or lamotrigine; sodium channel blockers are relatively contraindicated in LOF patients.SignificanceThis is the first‐ever global consensus for the diagnosis and treatment of SCN8A‐related disorders. This consensus will reduce knowledge gaps in disease recognition and inform preferred treatment across this heterogeneous disorder. Consensus of this type allows more clinicians to provide evidence‐based care and empowers SCN8A families to advocate for their children.