Back
#1
17.8%
Top 12%
11.9%
Top 1%
9.0%
Top 2%
7.8%
Top 18%
6.0%
Top 82%
5.1%
Top 6%
5.1%
Top 5%
4.2%
Top 3%
3.9%
Top 16%
2.8%
Top 3%
1.9%
Top 4%
1.9%
Top 4%
1.6%
Top 5%
1.6%
Top 13%
1.3%
Top 5%
1.2%
Top 62%
1.0%
Top 3%
1.0%
Top 7%
0.7%
Top 1%
0.7%
Top 7%
0.7%
Top 17%
0.7%
Top 10%
0.7%
Top 14%
0.7%
Top 34%
0.7%
Top 5%
0.7%
Top 3%
0.5%
Model uncertainty quantification: A post hoc calibration approach for heart disease prediction
2025-09-30
cardiovascular medicine
Title + abstract only
View on medRxiv
Show abstract
We investigate whether post-hoc calibration improves the clinical trustworthiness of heart-disease predictions beyond conventional accuracy metrics. Using a structured clinical dataset (1,025 records; 85/15 train-test split), we benchmarked six classifiers logistic regression, SVM, k-nearest neighbors, naive Bayes, random forest, and XGBoost on accuracy, ROC-AUC, precision, recall, and F1, and then evaluated probability quality before and after Platt (sigmoid) and isotonic calibration using Brie...
Predicted journal destinations
1
European Heart Journal - Digital Health
15 training papers
2
Scientific Reports
701 training papers
3
Circulation
37 training papers
4
npj Digital Medicine
85 training papers
5
Nature Communications
483 training papers
6
PLOS ONE
1737 training papers
7
Journal of the American Heart Association
92 training papers
8
Frontiers in Cardiovascular Medicine
33 training papers
9
Circulation: Genomic and Precision Medicine
30 training papers
10
eLife
262 training papers
11
Computers in Biology and Medicine
39 training papers
12
Open Heart
18 training papers
13
Heart Rhythm
16 training papers
14
The American Journal of Cardiology
15 training papers
15
PLOS Digital Health
88 training papers
16
Hypertension
20 training papers
17
BMJ Open
553 training papers
18
Frontiers in Physiology
18 training papers
19
Communications Medicine
63 training papers
20
EBioMedicine
21 training papers
21
BMC Medical Informatics and Decision Making
36 training papers
22
Nature Medicine
88 training papers
23
Nature Genetics
72 training papers
24
PLOS Computational Biology
141 training papers
25
BMC Medicine
155 training papers
26
Atherosclerosis
16 training papers
27
The Lancet Digital Health
25 training papers