Kumar, Nisith

e13574 Background: AL (amyloid light chain) amyloidosis is associated with poor prognosis especially if diagnosis occurs with cardiac involvement. Current AL treatments target the plasma cell clone producing the light chains that misfold, aggregate and deposit in various tissues. The multi-organ manifestations of AL amyloidosis require a multidisciplinary care team of hematologist-oncologists, cardiologists, and other healthcare providers (HCPs) for comprehensive, patient-centric management. Since 2022, Amyloidosis Stakeholder Partnerships for Impact, Reach & Equity (ASPIRE), facilitated by Amyloidosis Research Consortium (ARC) has been bringing together biotech and pharmaceutical companies with the shared goal of optimizing amyloidosis patient care. Through this study, ARC-ASPIRE sought to document and share the current best practices and key barriers to patient-centric amyloidosis care at US specialized amyloidosis centers (SACs). A broad range of stakeholders in amyloidosis care – healthcare providers at SACs, patients, referring physicians, and patient advocacy group representatives – were interviewed for this study. This abstract presents findings relevant to the management of patients with AL amyloidosis. Methods: Structured interviews were conducted between December 2023 and February 2024 with 77 amyloidosis stakeholders (physicians, advanced practice providers, registered nurses from 17 SACs, patients, referring physicians, and patient advocacy group representatives), including 12 hematology-oncologists and 8 AL patients. SACs were selected to be representative of current US amyloidosis care, based on geography, amyloidosis patient volume, years since establishment, and types of amyloidosis treated. Results: Three-quarters of participating SACs treat AL patients under a single multidisciplinary amyloidosis program. Multidisciplinary care is facilitated by regular team meetings, dedicated clinic days, and informal communications across specialties. At diagnosis, collaboration between cardiology and hematology-oncology ensures AL patients are accurately diagnosed and promptly treated. Sixty percent of SACs have a centralized intake system, and patients suspected with AL are prioritized to ensure an appointment within 1 week of referral. Key barriers were delayed or missed diagnosis due to low awareness of AL amyloidosis within community oncologists, travel burden to SACs, lack of seamless medical records sharing and telehealth regulations. Conclusions: The best practices outlined in this study serve to educate AL amyloidosis and non-AL amyloidosis HCPs for better multidisciplinary collaboration and early diagnosis. The key barriers identified should be addressed to improve patient care.

Nonspecific symptoms and other diagnostic challenges lead to underdiagnosis of cardiac amyloidosis (CA). Artificial intelligence (AI) could help address these challenges, but a summary of the performance of these tools is lacking. This narrative review of published literature describes the performance of AI tools that use data from ECGs and echocardiography to improve identification of CA and challenges that hinder adoption of these tools. Thirteen studies met inclusion criteria with sample sizes ranging from 50 to 2451 patients. Four studies used ECG data, 8 used echocardiography data, and 1 used both. The CA gold standard was typically defined as a CA diagnosis in an institutional or other database but the requirements for these diagnoses were heterogenous across studies, and many did not distinguish among CA subtypes. AI model development varied considerably, and only 4 studies included external validation. The ability of models to predict CA ranged from 0.71 to 1.00, sensitivity ranged from 16% to 100%, and specificity from 75% to 100%. Only 1 study reported model performance across strata of sex, age, race, and CA type. Persistent challenges to AI adoption include usability, cost, value added, electronic health record/information technology interoperability, patient‐related factors, regulation, and privacy and liability. Published studies on AI for improved identification of CA show favorable performance measures but numerous methodologic and other challenges must be addressed before these tools are more widely adopted.