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 Jan 2;15(1):505.
doi: 10.1038/s41598-024-84120-w.

Differential diagnosis of iron deficiency anemia from aplastic anemia using machine learning and explainable Artificial Intelligence utilizing blood attributes

B S Dhruva Darshan  1 , Niranjana Sampathila  2 , G Muralidhar Bairy  3 , Srikanth Prabhu  4 , Sushma Belurkar  5 , Krishnaraj Chadaga  4 , S Nandish  6
Affiliations

Differential diagnosis of iron deficiency anemia from aplastic anemia using machine learning and explainable Artificial Intelligence utilizing blood attributes

B S Dhruva Darshan et al. Sci Rep. .

Abstract

As per world health organization, Anemia is a most prevalent blood disorder all over the world. Reduced number of Red Blood Cells or decrease in the number of healthy red blood cells is considered as Anemia. This condition also leads to the decrease in the oxygen carrying capacity of the blood. The main goal of this research is to develop a dependable method for diagnosing Aplastic Anemia and Iron Deficiency Anemia by examining the blood test attributes. As of today, there are no studies which use Interpretable Artificial Intelligence to perform the above differential diagnosis. The dataset used in this study is collected from Kasturba Medical College, Manipal. The dataset consisted of various blood test attributes such as Red Blood cell count, Hemoglobin level, Mean Corpuscular Volume, etc. One of the trending topics in Machine Learning is Explainable Artificial Intelligence. They are known to demystify the machine learning outputs to all its stakeholders. Hence, Five XAI tools including SHAP, LIME, Eli5, Qlattice and Anchor are used to understand the model's predictions. The importance characteristics according to XAI models are PLT, PCT, MCV, PDW, HGB, ABS LYMP, WBC, MCH, and MCHC. are employed to train and test the data. The goal of using data analytic techniques is to give medical professionals a useful tool that improves decision-making, enhances resource management, and eventually raises the standard of patient care. By considering the unique qualities of each patient, medical professionals who must rely on AI-assisted diagnosis and treatment suggestions, XAI offers arguments to strengthen their faith in the model outcomes.

Keywords: Aplastic Anemia; Classification; Ensemble models; Explainable Artificial Intelligence; Iron deficiency anemia; Machine learning.

PubMed Disclaimer

Conflict of interest statement

Declarations. Competing interests: The authors declare no competing interests. Ethical approval: Ethical clearance has been obtained to collect patient data from Manipal Academy of Higher Education ethics committee with id IEC1 :229/2022. The need for informed consent was waived by ethics committee/ Institutional Review board of Manipal Academy of Higher Education, because of the retrospective nature of the study. All methods were carried out in accordance with relevant guidelines and regulations.

Figures

Fig. 1
Fig. 1
Classification of anemia based on mean corpuscular volume.
Fig. 2
Fig. 2
Violin plots with respect to (a) MCV, (b) HGB, (c)HCT.
Fig. 3
Fig. 3
Bar plot with respect to gender count.
Fig. 4
Fig. 4
Percentage of null values in the dataset.
Fig. 5
Fig. 5
Pearson’s correlation coefficient matrix.
Fig. 6
Fig. 6
Mutual information of important attributes.
Fig. 7
Fig. 7
Stacking architecture.
Fig. 8
Fig. 8
Pipelining of the IDA and AA diagnosis.
Fig. 9
Fig. 9
(a) Confusion matrix of stack (b) AUC curve of stack (c) Precision recall curve of stack model.
Fig. 10
Fig. 10
(a) Confusion matrix of ANN (b) Loss curve of ANN (c) Accuracy curve of ANN.
Fig. 11
Fig. 11
Bee swarm plot using SHAP.
Fig. 12
Fig. 12
Bar Chart using SHAP.
Fig. 13
Fig. 13
LIME conditions.
Fig. 14
Fig. 14
Top features using Eli5.
Fig. 15
Fig. 15
Qlattice output.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Vieth, J. T. & Lane, D. R. Anemia. Emerg. Med. Clin. 32 (3), 613–628. (2014). - PubMed
    1. World Health Organization. Worldwide prevalence of anaemia 1993–2005: WHO global database on anaemia. (2008).
    1. Milman, N. Anemia—still a major health problem in many parts of the world! Ann. Hematol.90, 369–377 (2011). - PubMed
    1. Salive, M. E. et al. Anemia and hemoglobin levels in older persons: Relationship with age, gender, and health status. J. Am. Geriatr. Soc.40 (5), 489–496 (1992). - PubMed
    1. Cappellini, M. D. & Motta, I. Anemia in clinical practice—definition and classification: Does hemoglobin change with aging?. Seminars Hematol. 52 (4), 261–269 (2015). - PubMed

Publication types