Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Dec 2.
doi: 10.1007/s11739-025-04209-6. Online ahead of print.

Non-invasive hemoglobin estimation with outcome prediction via deep learning analysis of ECG-derived cardiac micro-dynamics

Chung-Chi Yang  1   2   3   4 , Chin-Sheng Lin  2 , Chin Lin  5   6   7 , Wei-Ting Liu  2 , Zih-Yin Lai  3   4 , Yung-Jen Chuang  8   9
Affiliations

Non-invasive hemoglobin estimation with outcome prediction via deep learning analysis of ECG-derived cardiac micro-dynamics

Chung-Chi Yang et al. Intern Emerg Med. .

Abstract

Background: Anemia is a global health issue, especially in resource-limited areas, where traditional hemoglobin (Hb) testing is invasive and costly. This study aimed to develop an electrocardiogram-hemoglobin (ECG-Hb) deep learning model (DLM) for detecting anemia and assess its impact on all-cause mortality and new-onset heart failure.

Methods: This retrospective study analyzed ECGs and corresponding Hb levels from two hospitals. The DLM was trained on 388,166 ECGs from 187,202 patients and tested on 24,279 and 29,247 patients in internal and external sets, respectively. Anemia was defined as moderate (Hb ≤ 10 g/dL) or severe (Hb ≤ 8 g/dL). Diagnostic performance was evaluated using receiver operating characteristic (ROC) curve analysis, and an 8-year follow-up assessed mortality and heart failure risk with Cox regression.

Results: The areas under the ROC curves (AUCs) for detecting moderate-to-severe anemia were 0.8545 (internal) and 0.8243 (external), with sensitivities of 65.9% and 71.0%, and specificities of 84.8% and 77.4%, respectively. ECG-Hb performed better in detecting severe anemia (AUC = 0.9038/0.8766) than in mild anemia. Pearson correlations between ECG-Hb and Hb were 0.56 (internal) and 0.53 (external). Key ECG features, including heart rate variability, significantly influenced ECG-Hb. Patients with severely low ECG-Hb had higher risks of mortality (hazard ratio [HR]: 1.71, 95% confidence interval [CI]: 1.42-2.06) and heart failure (HR: 2.47, 95% CI: 2.07-2.94) compared to those with standard ECG-Hb levels.

Conclusion: The ECG-Hb DLM offers strong diagnostic and prognostic potential for anemia and cardiovascular risks, making it a valuable, non-invasive screening tool in low-resource settings.

Keywords: Anemia detection; Deep learning model; Electrocardiogram; Heart rate variability; Prognostic value.

PubMed Disclaimer

Conflict of interest statement

Declarations. Competing interests: The authors have nothing to disclose. Consent to participate: This retrospective study was approved by the Ethics Committee of the Tri-Service General Hospital (C202105049) to collect medical data. As we utilized encrypted and de-identified data from the hospital, a waiver for informed consent was granted by the data controller for this study.

References

    1. Mason J, Martorell R, Saldanha L, Shrimpton R (2013) Reduction of anaemia. Lancet Glob Health 1:e4-6. https://doi.org/10.1016/s2214-109x(13)70009-3 - DOI - PubMed
    1. World Health Organization. (2023) Accelerating anaemia reduction: a comprehensive framework for action. https// www.who.int/publications/i/item/ 9789240074033
    1. Wiciński M, Liczner G, Cadelski K, Kołnierzak T, Nowaczewska M, Malinowski B (2020) Anemia of chronic diseases: wider diagnostics-better treatment? Nutrients 12(6):1784. https://doi.org/10.3390/nu12061784 - DOI - PubMed - PMC
    1. Merchant AA, Roy CN (2012) Not so benign haematology: anaemia of the elderly. Br J Haematol 156:173–185. https://doi.org/10.1111/j.1365-2141.2011.08920.x - DOI - PubMed
    1. Han SV, Park M, Kwon YM, Yoon HJ, Chang Y, Kim H, Lim YH, Kim SG, Ko A (2019) Mild anemia and risk for all-cause, cardiovascular and cancer deaths in apparently healthy elderly Koreans. Korean J Fam Med 40:151–158. https://doi.org/10.4082/kjfm.17.0089 - DOI - PubMed - PMC