Taxiarchis Kourelis, Raymond Comenzo, Andrea Cortese, Justin L Grodin, Martha Grogan, Paolo Milani, Frederick L Ruberg, Yoshiki Sekijima, Lukas D Weberling, Efstathios Kastritis, Kevin M Alexander
Defining high-risk populations and integrating AI-based tools may enable risk-adapted screening that improves early diagnosis while avoiding indiscriminate population-level testing.
BACKGROUND: Systemic amyloidosis is a progressive disease in which misfolded protein toxicity and deposition lead to organ dysfunction. Early diagnosis is essential to enable timely treatment and prevent irreversible organ damage, yet the disease remains underrecognized. Although advances in imaging and biomarkers have raised suspicion in appropriate contexts, a major barrier is the absence of clearly defined factors identifying individuals at high risk who warrant timely screening.
METHODS: On behalf of the International Society of Amyloidosis (ISA), experts in the field reviewed the diagnostic landscape and identified unmet needs in the early detection of systemic amyloidosis.
RESULTS: The experts highlighted a lack of risk-adapted screening strategies capable of improving detection while avoiding inefficient population-level screening. They identified parameters that may help define high-risk populations, including biomarkers, susceptibility factors, demographic variables, and clinical 'red flags'. They further discussed how artificial intelligence (AI)-driven tools may support identification of at-risk individuals and accelerate diagnosis in suspected amyloidosis.
CONCLUSIONS: Defining high-risk populations and integrating AI-based tools may enable risk-adapted screening that improves early diagnosis while avoiding indiscriminate population-level testing.