Artificial Intelligence–Enabled Analysis of Thermography to Diagnose Acute Decompensated Heart Failure
Bibliographic record
Abstract
BACKGROUND: Analyzing skin temperature in heart failure is an important medical practice that could assist to identify poor perfusion. Thermography, a technique that captures infrared radiation from tissues, could quantify these temperatures and thermal gradients. It has not been evaluated in patients with acute decompensated heart failure (ADHF) before. OBJECTIVES: The purpose of this study was to assess the performance of thermography in the diagnosis of ADHF. METHODS: A cross-sectional study was performed, including consecutive patients hospitalized with ADHF diagnosed by an expert heart failure team. Patients hospitalized for other cardiac disorders without ADHF were included as controls. Ten thermal photos of each patient were taken within the first 4 hours after admission in a cardiac care unit. Specific thermal spots, averages, and gradients were analyzed. Thermography's diagnostic properties for ADHF detection were evaluated using machine learning with the extreme gradient boosting model. RESULTS: Sixty patients were included: 30 cases with ADHF and 30 controls. The mean age was 63.4 years (SD: 13.3), and 38 (63.3%) were males. Thermal points and averages showed lower temperature, while gradients were higher in the ADHF group, being all statistically significant between groups. The properties of the blend between thermography and artificial intelligence to detect ADHF had 84% sensitivity and 52% specificity. The area under the curve was 0.82 (95% CI: 0.73-0.91). CONCLUSIONS: 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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.008 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".