Machine Learning for Diagnosis and Screening of Chronic Lymphocytic Leukemia Using Routine Complete Blood Count (CBC) Results

Regina Padmanabhan; Yousra El Alaoui; Adel Elomri; Marwa K. Qaraqe; Halima El Omri; Ruba Yasin Taha

doi:10.3233/SHTI230483

Machine Learning for Diagnosis and Screening of Chronic Lymphocytic Leukemia Using Routine Complete Blood Count (CBC) Results

Regina Padmanabhan^*, Yousra El Alaoui, Adel Elomri, Marwa K. Qaraqe, Halima El Omri, Ruba Yasin Taha

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

The comprehensive epidemiology and global disease burdens reported recently suggest that chronic lymphocytic leukemia (CLL) constitutes 25-30% of leukemias thus being the most common leukemia subtype. However, there is an insufficient presence of artificial intelligence (AI)-based techniques for CLL diagnosis. The novelty of this study is in the investigation of data-driven techniques to leverage the intricate CLL-related immune dysfunctions reflected in routine complete blood count (CBC) alone. We used statistical inferences, four feature selection methods, and multistage hyperparameter tuning to build robust classifiers. With respective accuracies of 97.05%, 97.63%, and 98.62% for Quadratic Discriminant Analysis (QDA), Logistic Regression (LR), and XGboost (XGb)-based models, CBC-driven AI methods promise timely medical care and improved patient outcome with lesser resource usage and related cost.

Original language	English
Title of host publication	Healthcare Transformation with Informatics and Artificial Intelligence
Editors	John Mantas, Parisis Gallos, Emmanouil Zoulias, Arie Hasman, Mowafa S. Househ, Martha Charalampidou, Andriana Magdalinou
Publisher	IOS Press BV
Pages	279-282
Number of pages	4
ISBN (Electronic)	9781643684000
DOIs	https://doi.org/10.3233/SHTI230483
Publication status	Published - 29 Jun 2023
Event	21st International Conference on Informatics, Management, and Technology in Healthcare, ICIMTH 2023 - Athens, Greece Duration: 1 Jul 2023 → 3 Jul 2023

Publication series

Name	Studies in Health Technology and Informatics
Volume	305
ISSN (Print)	0926-9630
ISSN (Electronic)	1879-8365

Conference

Conference	21st International Conference on Informatics, Management, and Technology in Healthcare, ICIMTH 2023
Country/Territory	Greece
City	Athens
Period	1/07/23 → 3/07/23

Keywords

Chronic lymphocytic leukemia
machine learning
routine blood test

Access to Document

10.3233/SHTI230483

Cite this

Padmanabhan, R., El Alaoui, Y., Elomri, A., Qaraqe, M. K., El Omri, H., & Yasin Taha, R. (2023). Machine Learning for Diagnosis and Screening of Chronic Lymphocytic Leukemia Using Routine Complete Blood Count (CBC) Results. In J. Mantas, P. Gallos, E. Zoulias, A. Hasman, M. S. Househ, M. Charalampidou, & A. Magdalinou (Eds.), Healthcare Transformation with Informatics and Artificial Intelligence (pp. 279-282). (Studies in Health Technology and Informatics; Vol. 305). IOS Press BV. https://doi.org/10.3233/SHTI230483

Padmanabhan, Regina ; El Alaoui, Yousra ; Elomri, Adel et al. / Machine Learning for Diagnosis and Screening of Chronic Lymphocytic Leukemia Using Routine Complete Blood Count (CBC) Results. Healthcare Transformation with Informatics and Artificial Intelligence. editor / John Mantas ; Parisis Gallos ; Emmanouil Zoulias ; Arie Hasman ; Mowafa S. Househ ; Martha Charalampidou ; Andriana Magdalinou. IOS Press BV, 2023. pp. 279-282 (Studies in Health Technology and Informatics).

@inproceedings{db756f6c5dae4e43b2e774dad50a8b1f,

title = "Machine Learning for Diagnosis and Screening of Chronic Lymphocytic Leukemia Using Routine Complete Blood Count (CBC) Results",

abstract = "The comprehensive epidemiology and global disease burdens reported recently suggest that chronic lymphocytic leukemia (CLL) constitutes 25-30% of leukemias thus being the most common leukemia subtype. However, there is an insufficient presence of artificial intelligence (AI)-based techniques for CLL diagnosis. The novelty of this study is in the investigation of data-driven techniques to leverage the intricate CLL-related immune dysfunctions reflected in routine complete blood count (CBC) alone. We used statistical inferences, four feature selection methods, and multistage hyperparameter tuning to build robust classifiers. With respective accuracies of 97.05%, 97.63%, and 98.62% for Quadratic Discriminant Analysis (QDA), Logistic Regression (LR), and XGboost (XGb)-based models, CBC-driven AI methods promise timely medical care and improved patient outcome with lesser resource usage and related cost.",

keywords = "Chronic lymphocytic leukemia, machine learning, routine blood test",

author = "Regina Padmanabhan and {El Alaoui}, Yousra and Adel Elomri and Qaraqe, {Marwa K.} and {El Omri}, Halima and {Yasin Taha}, Ruba",

note = "Publisher Copyright: {\textcopyright} 2023 The authors and IOS Press.; 21st International Conference on Informatics, Management, and Technology in Healthcare, ICIMTH 2023 ; Conference date: 01-07-2023 Through 03-07-2023",

year = "2023",

month = jun,

day = "29",

doi = "10.3233/SHTI230483",

language = "English",

series = "Studies in Health Technology and Informatics",

publisher = "IOS Press BV",

pages = "279--282",

editor = "John Mantas and Parisis Gallos and Emmanouil Zoulias and Arie Hasman and Househ, {Mowafa S.} and Martha Charalampidou and Andriana Magdalinou",

booktitle = "Healthcare Transformation with Informatics and Artificial Intelligence",

address = "Netherlands",

}

Padmanabhan, R, El Alaoui, Y, Elomri, A , Qaraqe, MK, El Omri, H & Yasin Taha, R 2023, Machine Learning for Diagnosis and Screening of Chronic Lymphocytic Leukemia Using Routine Complete Blood Count (CBC) Results. in J Mantas, P Gallos, E Zoulias, A Hasman, MS Househ, M Charalampidou & A Magdalinou (eds), Healthcare Transformation with Informatics and Artificial Intelligence. Studies in Health Technology and Informatics, vol. 305, IOS Press BV, pp. 279-282, 21st International Conference on Informatics, Management, and Technology in Healthcare, ICIMTH 2023, Athens, Greece, 1/07/23. https://doi.org/10.3233/SHTI230483

Machine Learning for Diagnosis and Screening of Chronic Lymphocytic Leukemia Using Routine Complete Blood Count (CBC) Results. / Padmanabhan, Regina; El Alaoui, Yousra; Elomri, Adel et al.
Healthcare Transformation with Informatics and Artificial Intelligence. ed. / John Mantas; Parisis Gallos; Emmanouil Zoulias; Arie Hasman; Mowafa S. Househ; Martha Charalampidou; Andriana Magdalinou. IOS Press BV, 2023. p. 279-282 (Studies in Health Technology and Informatics; Vol. 305).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Machine Learning for Diagnosis and Screening of Chronic Lymphocytic Leukemia Using Routine Complete Blood Count (CBC) Results

AU - Padmanabhan, Regina

AU - El Alaoui, Yousra

AU - Elomri, Adel

AU - Qaraqe, Marwa K.

AU - El Omri, Halima

AU - Yasin Taha, Ruba

PY - 2023/6/29

Y1 - 2023/6/29

N2 - The comprehensive epidemiology and global disease burdens reported recently suggest that chronic lymphocytic leukemia (CLL) constitutes 25-30% of leukemias thus being the most common leukemia subtype. However, there is an insufficient presence of artificial intelligence (AI)-based techniques for CLL diagnosis. The novelty of this study is in the investigation of data-driven techniques to leverage the intricate CLL-related immune dysfunctions reflected in routine complete blood count (CBC) alone. We used statistical inferences, four feature selection methods, and multistage hyperparameter tuning to build robust classifiers. With respective accuracies of 97.05%, 97.63%, and 98.62% for Quadratic Discriminant Analysis (QDA), Logistic Regression (LR), and XGboost (XGb)-based models, CBC-driven AI methods promise timely medical care and improved patient outcome with lesser resource usage and related cost.

AB - The comprehensive epidemiology and global disease burdens reported recently suggest that chronic lymphocytic leukemia (CLL) constitutes 25-30% of leukemias thus being the most common leukemia subtype. However, there is an insufficient presence of artificial intelligence (AI)-based techniques for CLL diagnosis. The novelty of this study is in the investigation of data-driven techniques to leverage the intricate CLL-related immune dysfunctions reflected in routine complete blood count (CBC) alone. We used statistical inferences, four feature selection methods, and multistage hyperparameter tuning to build robust classifiers. With respective accuracies of 97.05%, 97.63%, and 98.62% for Quadratic Discriminant Analysis (QDA), Logistic Regression (LR), and XGboost (XGb)-based models, CBC-driven AI methods promise timely medical care and improved patient outcome with lesser resource usage and related cost.

KW - Chronic lymphocytic leukemia

KW - machine learning

KW - routine blood test

UR - http://www.scopus.com/inward/record.url?scp=85164231377&partnerID=8YFLogxK

U2 - 10.3233/SHTI230483

DO - 10.3233/SHTI230483

M3 - Conference contribution

C2 - 37387017

AN - SCOPUS:85164231377

T3 - Studies in Health Technology and Informatics

SP - 279

EP - 282

BT - Healthcare Transformation with Informatics and Artificial Intelligence

A2 - Mantas, John

A2 - Gallos, Parisis

A2 - Zoulias, Emmanouil

A2 - Hasman, Arie

A2 - Househ, Mowafa S.

A2 - Charalampidou, Martha

A2 - Magdalinou, Andriana

PB - IOS Press BV

T2 - 21st International Conference on Informatics, Management, and Technology in Healthcare, ICIMTH 2023

Y2 - 1 July 2023 through 3 July 2023

ER -

Padmanabhan R, El Alaoui Y, Elomri A , Qaraqe MK, El Omri H, Yasin Taha R. Machine Learning for Diagnosis and Screening of Chronic Lymphocytic Leukemia Using Routine Complete Blood Count (CBC) Results. In Mantas J, Gallos P, Zoulias E, Hasman A, Househ MS, Charalampidou M, Magdalinou A, editors, Healthcare Transformation with Informatics and Artificial Intelligence. IOS Press BV. 2023. p. 279-282. (Studies in Health Technology and Informatics). doi: 10.3233/SHTI230483

Machine Learning for Diagnosis and Screening of Chronic Lymphocytic Leukemia Using Routine Complete Blood Count (CBC) Results

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

EX-QNRF-NPRPS-4: An Operations Management Approach for the Improvement of Cancer Care Delivery in Qatar: Predictive Models, Analysis, and Pathways Optimization for Patients with Hematological Malignancies.

Cite this

Machine Learning for Diagnosis and Screening of Chronic Lymphocytic Leukemia Using Routine Complete Blood Count (CBC) Results

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Projects

EX-QNRF-NPRPS-4: An Operations Management Approach for the Improvement of Cancer Care Delivery in Qatar: Predictive Models, Analysis, and Pathways Optimization for Patients with Hematological Malignancies.

Cite this