Nomogram model and risk score to predict 5‐year risk of progression from prediabetes to diabetes in Chinese adults: Development and validation of a novel model
Authors' conclusion
We developed and validated a personalized prediction nomogram and risk score for 5-year diabetes risk among Chinese adults with prediabetes, identifying individuals at a high risk of developing diabetes. Doctors and other healthcare professionals can easily and quickly use our diabetes score model to assess the diabetes risk status in patients with prediabetes. In addition, the nomogram model and risk score we developed need to be validated in a prospective cohort study.
Study context
- Population
- Chinese adults with prediabetes at baseline
- Participants
- 26,018 adults
- Exposure
- Training vs Validation
- Trainingn = 12,947
- Validationn = 13,071
- Outcome
- Prediction of diabetes risk among adults with prediabetes (nomogram discrimination by AUC)
- Follow-up
- 5 years
Methodological detailsprediction model development and validation, random split into training and validation cohorts, least absolute shrinkage and selection operator (LASSO) and stepwise Cox proportional hazards model, nomogram and risk score
- Prediction model development and validation
- Random split into training and validation cohorts
- LASSO and stepwise Cox proportional hazards model
- Nomogram and risk score
Main finding
As reported in the abstract
Nomogram discrimination (AUC) for diabetes risk
| Group | AUC |
|---|---|
| Training | 0.8146 (95% CI 0.8035-0.8258) |
| Validation | 0.8147 (95% CI 0.8035-0.8259) |
AUC
Training0.8146 (95% CI 0.8035-0.8258)
Validation0.8147 (95% CI 0.8035-0.8259)
Observational data: associations, not effects.
Further findings
Calibration · 5 years
- Calibration curve showed a perfect fit between predicted and observed diabetes risks
Decision curve analysis
- Clinical use of nomogram shown, with a wide range of alternative threshold probability spectrums
Risk score categories
- Low risk
- 0 to 2.5
- Middle risk
- 3 to 4.5
- High risk
- 5 to 7.5
- Extremely high risk
- 8 to 13.5
Original publication
Nomogram model and risk score to predict 5‐year risk of progression from prediabetes to diabetes in Chinese adults: Development and validation of a novel model. Diabetes Obes Metab. Published 2 December 2022. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →