Clinical diagnostic patterns preceding the diagnosis of systemic light chain amyloidosis in patients with monoclonal gammopathy: a longitudinal, retrospective, cohort study
Year: 2026
Type: article
Abstract: Background Patients with monoclonal gammopathy of undetermined significance and smouldering myeloma (MGUS+) are at risk of developing light chain (AL) amyloidosis. We aimed to characterise longitudinal patterns of red-flag clinical diagnoses preceding AL amyloidosis among patients with MGUS+ from large-scale electronic health record data. Methods We conducted a retrospective, cohort study with TriNetX electronic health record data. Patients with MGUS+ between Jan 1, 2016, and Dec 31, 2023, were followed longitudinally for AL amyloidosis. 33 candidate diagnoses were evaluated across cardiac, renal, neurological, gastrointestinal/hepatic, and multisystem categories. Cause-specific penalised Cox regression and Bayesian additive regression trees machine learning established associations between time-dependent diagnoses and subsequent diagnosis of AL amyloidosis. Pairwise correlations were assessed to identify patterns between clinical diagnoses. Models were externally validated using Medicare data. Findings Of 26,482 MGUS+ patients in TriNetX, 835 (2%) developed AL amyloidosis and of 8871 MGUS+ cases in Medicare, 466 (5.3%) had subsequent AL amyloidosis diagnosis. AL amyloidosis patients who received chemotherapy (AL confirmed) or not (AL unconfirmed) were considered separately. Mean red-flag burden was 3.7 (SD 3.9) in the AL confirmed group, 4.2 (4.4) in the AL unconfirmed group, and 3.2 (3.9) in MGUS+ patients without AL amyloidosis. Renal and cardiac red flags, particularly incident diagnoses, showed the strongest associations; incident nephrotic syndrome, incident proteinuria, incident heart failure, incident chronic kidney disease, and incident dyspnoea, prevalent ecchymosis and prevalent proteinuria showed significantly higher hazards of developing AL confirmed. Moderate discrimination was seen with C indices of 0.67 and 0.66 for AL confirmed using penalised Cox and BART, respectively, with similar performance in the validation cohort (0.67 and 0.67). Interpretation MGUS+ patients developing AL amyloidosis exhibit early warning patterns of clinical diagnoses within electronic health records. Leveraging these patterns within longitudinal data may enable earlier recognition of AL amyloidosis and targeted surveillance in this high-risk population. Funding National Institutes of Health and Dean Krueger fund.
Source: EClinicalMedicine
Institution: Medical College of Wisconsin
Language: English
Subfield: Internal Medicine
Field: Medicine
Domain: Health Sciences
Open Access status: gold
Estimated APC paid: $5,780
OpenAlex ID: W7227370632
