Back

The Independence of Discrimination and Calibration in Clinical Risk Prediction: Lessons from a Multi-Timeframe Diabetes Prediction Framework

2026-02-14 health informatics Title + abstract only
View on medRxiv
Show abstract

BackgroundClinical risk prediction models are typically evaluated by discrimination (area under the receiver operating characteristic curve, AUC), with calibration receiving less attention. We developed a multi-timeframe diabetes prediction framework emphasizing calibration and used synthetic data validation to investigate whether good discrimination guarantees good calibration. MethodsWe generated 500,000 synthetic patients using published epidemiological parameters from QDiabetes-2018, FINDRI...

Predicted journal destinations

1
Journal of the American Medical Informatics Association
53 training papers
Top 1.0% 14.3%
2
npj Digital Medicine
85 training papers
Top 0.6% 14.3%
3
PLOS Digital Health
88 training papers
Top 0.9% 10.7%
4
Scientific Reports
701 training papers
Top 28% 7.6%
5
Journal of Biomedical Informatics
37 training papers
Top 1% 6.3%
6
JAMIA Open
35 training papers
Top 2% 6.3%
7
BMC Medical Informatics and Decision Making
36 training papers
Top 2% 5.8%
8
PLOS ONE
1737 training papers
Top 82% 4.9%
9
BMC Medical Research Methodology
41 training papers
Top 0.6% 3.8%
10
PLOS Computational Biology
141 training papers
Top 6% 2.7%
11
Nature Communications
483 training papers
Top 33% 2.7%
12
International Journal of Medical Informatics
25 training papers
Top 3% 1.9%
13
Journal of Medical Internet Research
81 training papers
Top 9% 1.9%
14
BMJ Open
553 training papers
Top 50% 1.9%
15
JMIR Medical Informatics
16 training papers
Top 4% 1.5%
16
Computers in Biology and Medicine
39 training papers
Top 7% 1.2%
17
Communications Medicine
63 training papers
Top 4% 1.0%
18
JAMA Network Open
125 training papers
Top 24% 0.9%
19
Patterns
15 training papers
Top 4% 0.7%
20
Frontiers in Digital Health
18 training papers
Top 5% 0.7%
21
Bioinformatics
24 training papers
Top 4% 0.7%
22
Sensors
18 training papers
Top 2% 0.7%