What is the clinical evidence from this study?

Study design: Cohort. Population: adult-onset diabetes (n=7081). Intervention: EHR-based classification algorithms vs. biomarker-defined diabetes subtypes. Primary outcome: positive predictive value (PPV), negative predictive value (NPV), and ROC AUC (PPV 23-79%, ROC AUC 0.65-0.78).

What does this research mean for the field?

Widely used EHR-based algorithms substantially misclassify adult-onset Type 1 Diabetes, demonstrating poor positive predictive value and modest discrimination when compared to biomarker-defined subtypes. Novelty: ClaimNovelty.NOVEL_FINDING. Consensus alignment: ConsensusAlignment.CHALLENGES_CONSENSUS.

What question did this study set out to answer?

To validate EHR-based diabetes classification algorithms against biomarker-defined adult-onset T1D.

June 7, 2026

2214-P: Biomarker Validation Reveals Substantial Misclassification of Adult-Onset Type 1 Diabetes by EHR-Based Algorithms: Implications for Research Accuracy and Clinical Care

Resultado clave

EHR-based classification algorithms poorly identified biomarker-defined adult-onset T1D, with PPVs ranging from 23-79% and modest discrimination (ROC AUC 0.65-0.78).

Puntos clave

To validate EHR-based diabetes classification algorithms against biomarker-defined adult-onset T1D.
Analyzed 7081 adult-onset diabetes cases from the MyCode cohort, including 3365 insulin-treated and 3152 non-insulin-treated individuals.
Measured random C-peptide and islet autoantibodies to define T1D and T2D.
Evaluated eight EHR-based algorithms for positive predictive value (PPV), negative predictive value (NPV), and ROC AUC.
Identified 3.1% adult-onset T1D and 71% T2D based on biomarkers.
Algorithms demonstrated poor identification of T1D, with PPV ranging from 23-79% and high NPV (96-97%).
The lipid model by Lynam et al. had the highest PPV at 79%, but ROC AUC was modest (0.65-0.78), especially lower for insulin-treated individuals.

Diseño del estudio

Tipo

Cohort (n=7,081)

PICO estructurado

Do EHR-based classification algorithms accurately identify biomarker-defined adult-onset T1D in patients with adult-onset diabetes?

Población

7,081 adult-onset diabetes cases (3,365 insulin-treated and 3,152 non-insulin-treated) from the MyCode cohort with a mean age of 59.8 years.

Exposición

Eight widely used EHR-based classification algorithms for adult-onset T1D

Comparador

Biomarker-defined diabetes subtypes (C-peptide and islet autoantibodies)

Resultado

Positive predictive value (PPV), negative predictive value (NPV), and ROC AUC for identifying adult-onset T1D

EHR-based algorithms substantially misclassify adult-onset Type 1 Diabetes compared to biomarker definitions, highlighting the need for biomarker-informed classification in research and clinical care.

Resultado numérico

Estimación del efecto: PPV 23-79%, ROC AUC 0.65-0.78

Resumen

Introduction and Objective: Electronic health records (EHRs) underpin diabetes research and trial recruitment yet widely used EHR-based algorithms have not been robustly validated against gold-standard biomarker-defined diabetes subtypes. We aimed to provide the first large-scale biomarker validation of EHR-based diabetes classification algorithms for adult-onset T1D. Methods: We studied 7081 adult-onset diabetes cases (3365 insulin-treated and 3152 non-insulin-treated) from the MyCode cohort. Random C-peptide and islet autoantibodies (GADA, IA-2A, ZnT8A) were measured outside the honeymoon period at a median diabetes duration of 9.0 years (91% 3 year duration). We defined type 1 diabetes (T1D) as insulin treatment with low C-peptide (200 pmol/l) or autoantibody positivity. We defined type 2 diabetes (T2D) as negative islet antibodies with preserved C-peptide (600 pmol/l for insulin-treated individuals or absence of insulin treatment for at least 3 year). We evaluated eight widely used EHR-based classification algorithms for positive predictive value (PPV), negative predictive value (NPV), and ROC AUC. Results: Mean age at diagnosis was 59.8 years (SD 14.9); 55% were female, and 95% were Europeans. Biomarkers identified 3.1% adult-onset T1D and 71% T2D. All algorithms showed poor T1D identification, with PPV ranging from 23-79% despite high NPV (96-97%). The lipid model by Lynam et al achieved the highest PPV at 79%. Discrimination was modest across all algorithms (ROC AUC 0.65-0.78), including 0.66 for the widely used eMERGE algorithm, and performance was worse in insulin-treated individuals for all algorithms (ROC AUC reduced to 0.62-0.73, NPV 96-97% and PPV 49-77%). Conclusion: EHR-based algorithms substantially misclassify biomarker-defined adult-onset T1D. These findings raise caution against use of current EHR tools for studying adult T1D and strongly support the need for biomarker-informed classification strategies. Disclosure J. Li: None. R. Stahl: None. A. Golden: None. J.S. Haley: None. A. Jones: None. R.A. Oram: Other - Research support, The University of Exeter has a licensing and royalty agreement for a 10 SNP T1D GRS with Randox; Current; Randox. Other - Advisory Panel, Consulting, Invited talks; Current; Sanofi. Other - invited talk, internal teaching talk on genetics; Ended; Novo Nordisk. D. Carey: None. K. Patel: None. U. Mirshahi: None. Funding Breakthrough T1D (3-SRA-2022-1241-S-B)

Me gusta

Guardar