CoChat
Sign Up
Cited by 3ECG Monitoring and AnalysisArtificial Intelligence in HealthcareNon-Invasive Vital Sign Monitoring

Non-Invasive Hemoglobin Estimation with Outcome Prediction via Deep Learning Analysis of ECG-Derived Cardiac Micro-Dynamics

Open access
Yang, Chung-Chi, Lin, Chin-Sheng, Lin, Chin, Liu, Wei-Ting, Lai, Zih-Yin, Chuang, Yung-Jen·2026·Internal and Emergency Medicine
DOI 10.1007/s11739-025-04209-6PMC PMC13061774
Open this paper in CoChat — free accountOpen PDF

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.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1007/s11739-025-04209-6

Cites

2 of 2 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 45

  1. [1]Mason J, Martorell R, Saldanha L, Shrimpton R (2013) Reduction of anaemia. Lancet Glob Health 1:e4-6. 10.1016/s2214-109x(13)70009-3 25103585 · DOI
  2. [3]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. 10.3390/nu12061784 32560029 PMC7353365 · DOI
  3. [4]Merchant AA, Roy CN (2012) Not so benign haematology: anaemia of the elderly. Br J Haematol 156:173–185. 10.1111/j.1365-2141.2011.08920.x 22050828 PMC3245355 · DOI
  4. [5]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. 10.4082/kjfm.17.0089 30650952 PMC6536909 · DOI
  5. [6]Kaiafa G, Kanellos I, Savopoulos C, Kakaletsis N, Giannakoulas G, Hatzitolios AI (2015) Is anemia a new cardiovascular risk factor? Int J Cardiol 186:117–124. 10.1016/j.ijcard.2015.03.159 25814357 · DOI · Paper page
  6. [7]Tyburski EA, Gillespie SE, Stoy WA, Mannino RG, Weiss AJ, Siu AF, Bulloch RH, Thota K, Cardenas A, Session W, Khoury HJ, O’Connor S, Bunting ST, Boudreaux J, Forest CR, Gaddh M, Leong T, Lyon LA, Lam WA (2014) Disposable platform provides visual and color-based point-of-care anemia self-testing. J Clin Invest 124:4387–4394. 10.1172/jci76666 25157824 PMC4191020 · DOI
  7. [8]Garcia-Casal MN, Dary O, Jefferds ME, Pasricha SR (2023) Diagnosing anemia: challenges selecting methods, addressing underlying causes, and implementing actions at the public health level. Ann N Y Acad Sci 1524:37–50. 10.1111/nyas.14996 37061792 PMC10880862 · DOI
  8. [9]de Oliveira Deucher RA, de Sá Ferreirs A, da Silva Nascimento LPA, da Cal MS, Papathanasiou JV, Lopes AJ (2021) Heart rate variability in adults with sickle cell anemia during a multitasking field test. Asian J Sports Med 12(3):108537
  9. [11]Gv S, Pk S, Herur A, Chinagudi S, Patil SS, Ankad RB, Badami SV (2014) Correlation between haemoglobin level and electrocardiographic (ECG) findings in anaemia: a cross-sectional study. J Clin Diagn Res 8(4):BC04-06. 10.7860/jcdr/2014/8966.4202 24959433 PMC4064835 · DOI
  10. [12]Coppler PJ, Elmer J, Calderon L, Sabedra A, Doshi AA, Callaway CW, Rittenberger JC, Dezfulian C (2015) Validation of the Pittsburgh Cardiac Arrest Category illness severity score. Resuscitation 89:86–92. 10.1016/j.resuscitation.2015.01.020 25636896 PMC4580975 · DOI
  11. [13]Liu WC, Lin CS, Tsai CS, Tsao TP, Cheng CC, Liou JT, Lin WS, Cheng SM, Lou YS, Lee CC, Lin C (2021) A deep-learning algorithm for detecting acute myocardial infarction. EuroIntervention 17:765–773. 10.4244/eij-d-20-01155 33840640 PMC9724911 · DOI
  12. [14]Liu WC, Lin C, Lin CS, Tsai MC, Chen SJ, Tsai SH, Lin WS, Lee CC, Tsao TP, Cheng CC (2021) An artificial intelligence-based alarm strategy facilitates management of acute myocardial infarction. J Pers Med 11(11):1149. 10.3390/jpm11111149 34834501 PMC8623357 · DOI
  13. [15]Liu YL, Lin CS, Cheng CC, Lin C (2022) A deep learning algorithm for detecting acute pericarditis by electrocardiogram. J Pers Med 12:1150. 10.3390/jpm12071150 35887647 PMC9324403 · DOI
  14. [16]Chang DW, Lin CS, Tsao TP, Lee CC, Chen JT, Tsai CS, Lin WS, Lin C (2021) Detecting digoxin toxicity by artificial intelligence-assisted electrocardiography. Int J Environ Res Public Health 18:3839. 10.3390/ijerph18073839 33917563 PMC8038815 · DOI
  15. [17]Lee CC, Lin CS, Tsai CS, Tsao TP, Cheng CC, Liou JT, Lin WS, Lee CC, Chen JT, Lin C (2022) A deep learning-based system capable of detecting pneumothorax via electrocardiogram. Eur J Trauma Emerg Surg 48:3317–3326. 10.1007/s00068-022-01904-3 35166869 · DOI
  16. [18]Liu WT, Lin CS, Tsao TP, Lee CC, Cheng CC, Chen JT, Tsai CS, Lin WS, Lin C (2022) A deep-learning algorithm-enhanced system integrating electrocardiograms and chest X-rays for diagnosing aortic dissection. Can J Cardiol. 10.1016/j.cjca.2021.09.028 34619339 · DOI
  17. [19]Lin C, Lin CS, Lee DJ, Lee CC, Chen SJ, Tsai SH, Kuo FC, Chau T, Lin SH (2021) Artificial intelligence assisted electrocardiography for early diagnosis of thyrotoxic periodic paralysis. J Endocr Soc 5:bvab120. 10.1210/jendso/bvab120 34308091 PMC8294684 · DOI
  18. [20]Lin CS, Lin C, Fang WH, Hsu CJ, Chen SJ, Huang KH, Lin WS, Tsai CS, Kuo CC, Chau T, Yang SJ, Lin SH (2020) A deep-learning algorithm (ECG12Net) for detecting hypokalemia and hyperkalemia by electrocardiography: algorithm development. JMIR Med Inform 2020(3):e15931. 10.2196/15931 PMC7082733 32134388 · DOI · Paper page
  19. [21]Lou YS, Lin CS, Fang WH, Lee CC, Ho CL, Wang CH, Lin C (2022) Artificial intelligence-enabled electrocardiogram estimates left atrium enlargement as a predictor of future cardiovascular disease. J Pers Med 12:315. 10.3390/jpm12020315 35207802 PMC8879964 · DOI
  20. [22]Chen HY, Lin CS, Fang WH, Lou YS, Cheng CC, Lee CC, Lin C (2022) Artificial intelligence-enabled electrocardiography predicts left ventricular dysfunction and future cardiovascular outcomes: a retrospective analysis. J Pers Med 12:455. 10.3390/jpm12030455 35330455 PMC8950054 · DOI
  21. [23]Chen HY, Lin CS, Fang WH, Lee CC, Ho CL, Wang CH, Lin C (2022) Artificial intelligence-enabled electrocardiogram predicted left ventricle diameter as an independent risk factor of long-term cardiovascular outcome in patients with normal ejection fraction. Front Med 9:870523. 10.3389/fmed.2022.870523 PMC9035739 35479951 · DOI
  22. [24]Lee CH, Liu WT, Lou YS, Lin CS, Fang WH, Lee CC, Ho CL, Wang CH, Lin C (2022) Artificial intelligence-enabled electrocardiogram screens low left ventricular ejection fraction with a degree of confidence. Digital Health 8:20552076221143249. 10.1177/20552076221143249 36532114 PMC9751170 · DOI
  23. [25]Lin C, Chau T, Lin CS, Shang HS, Fang WH, Lee DJ, Lee CC, Tsai SH, Wang CH, Lin SH (2022) Point-of-care artificial intelligence-enabled ECG for dyskalemia: a retrospective cohort analysis for accuracy and outcome prediction. NPJ Digit Med 5:8. 10.1038/s41746-021-00550-0 35046489 PMC8770475 · DOI · Paper page
  24. [26]Chang CH, Lin CS, Luo YS, Lee YT, Lin C (2022) Electrocardiogram-based heart age estimation by a deep learning model provides more information on the incidence of cardiovascular disorders. Front Cardiovasc Med 9:754909. 10.3389/fcvm.2022.754909 35211522 PMC8860826 · DOI
  25. [27]Tsai DJ, Lou YS, Lin CS, Fang WH, Lee CC, Ho CL, Wang CH, Lin C (2023) Mortality risk prediction of the electrocardiogram as an informative indicator of cardiovascular diseases. Digital Health 9:20552076231187247. 10.1177/20552076231187247 37448781 PMC10336769 · DOI
  26. [28]Chen YJ, Lin CS, Lin C, Tsai DJ, Fang WH, Lee CC, Wang CH, Chen SJ (2023) An AI-enabled dynamic risk stratification for emergency department patients with ECG and CXR integration. J Med Syst 47(1):81. 10.1007/s10916-023-01980-x 37523102 · DOI
  27. [29]Kwon JM, Cho Y, Jeon KH, Cho S, Kim KH, Baek SD, Jeung S, Park J, Oh BH (2020) A deep learning algorithm to detect anaemia with ECGs: a retrospective, multicentre study. Lancet Digit Health 2(7):e358–e367. 10.1016/s2589-7500(20)30108-4 33328095 · DOI
  28. [30]Van Buuren S, Groothuis-Oudshoorn K (2011) Mice: multivariate imputation by chained equations in R. J Stat Softw 45(3):1–67 · DOI · Paper page
  29. [31]Sassi R, Cerutti S, Lombardi F, Malik M, Huikuri HV, Peng CK, Schmidt G, Yamamoto Y (2015) Advances in heart rate variability signal analysis: joint position statement by the e-Cardiology ESC Working Group and the European Heart Rhythm Association co-endorsed by the Asia Pacific Heart Rhythm Society. Europace 17:1341–1353. 10.1093/europace/euv015 26177817 · DOI · Paper page
  30. [32]Lou YS, Lin CS, Fang WH, Lee CC, Wang CH, Lin C (2023) Development and validation of a dynamic deep learning algorithm using electrocardiogram to predict dyskalaemias in patients with multiple visits. Eur Heart J Digit Health 4(1):22–32. 10.1093/ehjdh/ztac072 36743876 PMC9890087 · DOI
  31. [33]Lou YS, Lin CS, Fang WH, Lee CC, Lin C (2023) Extensive deep learning model to enhance electrocardiogram application via latent cardiovascular feature extraction from identity identification. Comput Methods Programs Biomed 231:107359. 10.1016/j.cmpb.2023.107359 36738606 · DOI
  32. [34]Lin C, Chen CC, Chau T, Lin CS, Tsai SH, Lee DJ, Lee CC, Shang HS, Lin SH (2022) Artificial intelligence-enabled electrocardiography identifies severe dyscalcemias and has prognostic value. Clin Chim Acta 2022:126–134. 10.1016/j.cca.2022.09.021 36167147 · DOI · Paper page
  33. [35]Lee YT, Lin CS, Fang WH, Lee CC, Ho CL, Wang CH, Tsai DJ, Lin C (2022) Artificial intelligence-enabled electrocardiography detects hypoalbuminemia and identifies the mechanism of hepatorenal and cardiovascular events. Front Cardiovasc Med 2022(9):895201. 10.3389/fcvm.2022.895201 PMC9234125 35770216 · DOI
  34. [36]Liu PY, Lin C, Lin CS, Fang WH, Lee CC, Wang CH, Tsai DJ (2023) Artificial intelligence-enabled electrocardiography detects B-type natriuretic peptide and N-terminal pro-brain natriuretic peptide. Diagnostics 13:2723. 10.3390/diagnostics13172723 37685262 PMC10487184 · DOI
  35. [37]Lin CS, Lee YT, Fang WH, Lou YS, Kuo FC, Lee CC, Lin C (2021) Deep learning algorithm for management of diabetes mellitus via electrocardiogram-based glycated hemoglobin (ECG-HbA1c): a retrospective cohort study. J Pers Med 11:725. 10.3390/jpm11080725 34442369 PMC8398464 · DOI
  36. [38]Pisano ED, Gatsonis C, Hendrick E, Yaffe M, Baum JK, Acharyya S, Conant EF, Fajardo LL, Bassett L, D’Orsi C, Jong R (2005) Rebner M (2005) diagnostic performance of digital versus film mammography for breast-cancer screening. N Engl J Med 353(17):1773–1783. 10.1056/NEJMoa052911 16169887 · DOI
  37. [39]Haug U, Kuntz KM, Knudsen AB, Hundt S (2011) Brenner H (2011) sensitivity of immunochemical faecal occult blood testing for detecting left- vs right-sided colorectal neoplasia. Br J Cancer 104(11):1779–1785. 10.1038/bjc.2011.160 21559011 PMC3111170 · DOI
  38. [41]Gehi A, Ix J, Shlipak M, Pipkin SS, Whooley MA (2005) Relation of anemia to low heart rate variability in patients with coronary heart disease (from the Heart and Soul study). Am J Cardiol 2005(12):1474–1477. 10.1016/j.amjcard.2005.02.017 PMC2776675 15950576 · DOI
  39. [42]Metivier F, Marchais SJ, Guerin AP, Pannier B, London GM (2000) Pathophysiology of anaemia: focus on the heart and blood vessels. Nephrol Dial Transplant 2000(3):14–18. 10.1093/oxfordjournals.ndt.a027970 11032352 · DOI
  40. [44]Attia ZI, Harmon DM, Behr ER, Friedman PA (2021) Application of artificial intelligence to the electrocardiogram. Eur Heart J 2021(46):4717–4730. 10.1093/eurheartj/ehab649 PMC8500024 34534279 · DOI
  41. [45]Gladstone DJ, Spring M, Dorian P, Panzov V, Thorpe KE, Hall J, Vaid H, O’Donnell M, Laupacis A, Côté R, Sharma M, Blakely JA, Shuaib A, Hachinski V, Coutts SB, Sahlas DJ, Teal P, Yip S, Spence JD, Buck B, Verreault S, Casaubon LK, Penn A, Selchen D, Jin A, Howse D, Mehdiratta M, Boyle K, Aviv R, Kapral MK, Mamdani M (2014) Atrial fibrillation in patients with cryptogenic stroke. N Engl J Med 2014(26):2467–2477. 10.1056/NEJMoa1311376 24963566 · DOI · Paper page
  42. [46]Shenasa M (2018) Learning and teaching electrocardiography in the 21st century: a neglected art. J Electrocardiol. 10.1016/j.jelectrocard.2018.02.007 29499830 · DOI
  43. [47]Berland LL, Silverman SG, Gore RM, Mayo-Smith WW, Megibow AJ, Yee J, Brink JA, Baker ME, Federle MP, Foley WD, Francis IR, Herts BR, Israel GM, Krinsky G, Platt JF, Shuman WP, Taylor AJ (2010) Managing incidental findings on abdominal CT: white paper of the ACR incidental findings committee. J Am Coll Radiol 7(10):754–773. 10.1016/j.jacr.2010.06.013 20889105 · DOI
  44. [48]Pickhardt PJ, Summers RM, Garrett JW, Krishnaraj A, Agarwal S, Dreyer KJ, Nicola GN (2023) Opportunistic screening: radiology scientific expert panel. Radiology 307:e222044. 10.1148/radiol.222044 37219444 PMC10315516 · DOI
  45. [50]Yao X, Rushlow DR, Inselman JW, McCoy RG, Thacher TD, Behnken EM, Bernard ME, Rosas SL, Akfaly A, Misra A, Molling PE, Krien JS, Foss RM, Barry BA, Siontis KC, Kapa S, Pellikka PA, Lopez-Jimenez F, Attia ZI, Shah ND, Friedman PA, Noseworthy PA (2021) Artificial intelligence-enabled electrocardiograms for identification of patients with low ejection fraction: a pragmatic, randomized clinical trial. Nat Med 27:815–819. 10.1038/s41591-021-01335-4 33958795 · DOI · Paper page

Cited by

Sorted by citations

Authors
Yang, C.-C., Lin, C.-S., Lin, C., Liu, W.-T., Lai, Z.-Y., & Chuang, Y.-J.
Affiliations
  • Tri-Service General Hospital (TW)
  • National Tsing Hua University (TW)
Corresponding author
Chuang, Yung-Jen
ORCID
Venue
Internal and Emergency Medicine
Publisher
Springer Science and Business Media LLC
Published
2025-12-02
Volume
21
Issue
2
Pages
525-536
ISSN
  • 1828-0447 (ISSN-L)
  • 1970-9366
DOI
10.1007/s11739-025-04209-6
PMC
PMC13061774
OpenAlex
W4416906811
Cited by
3
References
2
Citations by year
2026: 3
FWCI
2.10
Type
journal article
Language
en
Open access
Licence
Locations
  • Internal and Emergency Medicine (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
Funders
National Tsing Hua University
Topics
  • Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › ECG Monitoring and Analysis
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
  • Physical Sciences › Engineering › Biomedical Engineering › Non-Invasive Vital Sign Monitoring
Keywords
anemia, hemoglobin estimation, deep learning, non-invasive diagnosis, heart failure, all-cause mortality, heart rate variability, cardiovascular risk prediction, resource-limited settings, anemia screening
MeSH terms
Deep Learning, Aged, Anemia, Electrocardiography, Female, Heart Failure, Hemoglobins, Humans, Male, Middle Aged, Retrospective Studies, ROC Curve

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review