Heart failure & cardiomyopathies
Artificial Intelligence–Enabled Analysis of Thermography to Diagnose Acute Decompensated Heart Failure
Authors' conclusion
Thermography demonstrated differences between patients with ADHF and those with other cardiological disorders. In this proof of concept, combining thermography with artificial intelligence enabled the detection of ADHF in subjects hospitalized in a cardiac care unit.
Study context
- Population
- Patients hospitalized in a cardiac care unit with acute decompensated heart failure (ADHF) diagnosed by an expert heart failure team, and patients hospitalized for other cardiac disorders without ADHF as controls30 cases with ADHF and 30 controls · ADHF 30 · controls 30
- Participants
- 60 patients
- Index test or model
- Thermography with artificial intelligence (extreme gradient boosting) vs ADHF diagnosed by an expert heart failure team
- Target condition
- acute decompensated heart failure (ADHF)
Methodological detailsconsecutive patients, machine learning with the extreme gradient boosting model
- Consecutive patients
- Machine learning with the extreme gradient boosting model
Performance
As reported in the abstract
Sensitivity
84%
Specificity
52%
Area under the curve
0.82
95% CI 0.73–0.91
Further findings
Baseline characteristics
- Mean age
- 63.4 years (SD: 13.3)
- Males
- 38 (63.3%)
Thermal points, averages and gradients, ADHF vs controls
- Thermal points and averages showed lower temperature, while gradients were higher in the ADHF group, being all statistically significant between groups
Original publication
Artificial Intelligence–Enabled Analysis of Thermography to Diagnose Acute Decompensated Heart Failure. JACC Adv. Published 19 June 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →