Prediction models for progression from prediabetes to diabetes: a systematic review and meta-analysis

1

The study systematically evaluated the accuracy of prediction models for transitioning from prediabetes to type 2 diabetes mellitus (T2DM).
2

Sixteen studies involving 1,368,130 prediabetic individuals were included, with a pooled incidence of 42.3‰ progressing to T2DM.
3

The pooled C-indices for training and validation sets were 0.76 and 0.84, respectively, indicating varying predictive accuracy.
4

Logistic regression and random forest models yielded C-indices of 0.81 and 0.86, demonstrating their effectiveness in prediction.
5

The study highlights the need for improved external validation and reporting quality in prediction models for prediabetes progression.

1