Clinical diagnostic patterns preceding the diagnosis of systemic light chain amyloidosis in patients with monoclonal gammopathy: a longitudinal, retrospective, cohort study

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.

Authors

Institutions

Publication Details

Journal
EClinicalMedicine
Published
2026-11-14
DOI
https://doi.org/10.1016/j.eclinm.2026.104334
Primary Topic
Amyloidosis: Diagnosis, Treatment, Outcomes
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Clinical diagnostic patterns preceding the diagnosis of systemic light chain amyloidosis in patients with monoclonal gammopathy: a longitudinal, retrospective, cohort study

Anikó Szabó, Noel Estrada‐Merly, Anita D’Souza, Liliana E. Pezzin et al.
4 links
EClinicalMedicine
Amyloidosis: Diagnosis, Treatment, Outcomes
article

Clinical diagnostic patterns preceding the diagnosis of systemic light chain amyloidosis in patients with monoclonal gammopathy: a longitudinal, retrospective, cohort study

Anikó Szabó, Noel Estrada‐Merly, Anita D’Souza, Liliana E. Pezzin, Rodney Sparapani, Duo Yu
article en

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.

EClinicalMedicineVol. 102
Medical College of Wisconsin (US)
National Heart, Lung, and Blood Institute
Good health and well-being
Amyloidosis: Diagnosis, Treatment, Outcomes
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon