TY - JOUR
T1 - Machine Learning Approach for Predicting Systemic Lupus Erythematosus in Oman-based Cohort
AU - AlShareedah, Al Hassan
AU - Zidoum, Hamza
AU - Al-Sawafi, Sumaya
AU - Al-Lawati, Batool
AU - Al-Ansari, Aliya
N1 - © Copyright 2023, Sultan Qaboos University Medical Journal, All Rights Reserved.
PY - 2023/8/28
Y1 - 2023/8/28
N2 - Objectives: This study aimed to design a machine learning-based prediction framework to predict the presence or absence of systemic lupus erythematosus (SLE) in a cohort of Omani patients. Methods: Data of 219 patients from 2006 to 2019 were extracted from Sultan Qaboos University Hospital’s electronic records. Among these, 138 patients had SLE, while the remaining 81 had other rheumatologic diseases. Clinical and demographic features were analysed to focus on the early stages of the disease. Recursive feature selection was implemented to choose the most informative features. The CatBoost classification algorithm was utilised to predict SLE, and the SHAP explainer algorithm was applied on top of the CatBoost model to provide individual prediction reasoning, which was then validated by rheumatologists. Results: CatBoost achieved an area under the receiver operating characteristic curve score of 0.95 and a sensitivity of 92%. The SHAP algorithm identified four clinical features (alopecia, renal disorders, acute cutaneous lupus and haemolytic anaemia) and the patient’s age as having the greatest contribution to the prediction. Conclusion: An explainable framework to predict SLE in patients and provide reasoning for its prediction was designed and validated. This framework enables clinicians to implement early interventions that will lead to positive healthcare outcomes.
AB - Objectives: This study aimed to design a machine learning-based prediction framework to predict the presence or absence of systemic lupus erythematosus (SLE) in a cohort of Omani patients. Methods: Data of 219 patients from 2006 to 2019 were extracted from Sultan Qaboos University Hospital’s electronic records. Among these, 138 patients had SLE, while the remaining 81 had other rheumatologic diseases. Clinical and demographic features were analysed to focus on the early stages of the disease. Recursive feature selection was implemented to choose the most informative features. The CatBoost classification algorithm was utilised to predict SLE, and the SHAP explainer algorithm was applied on top of the CatBoost model to provide individual prediction reasoning, which was then validated by rheumatologists. Results: CatBoost achieved an area under the receiver operating characteristic curve score of 0.95 and a sensitivity of 92%. The SHAP algorithm identified four clinical features (alopecia, renal disorders, acute cutaneous lupus and haemolytic anaemia) and the patient’s age as having the greatest contribution to the prediction. Conclusion: An explainable framework to predict SLE in patients and provide reasoning for its prediction was designed and validated. This framework enables clinicians to implement early interventions that will lead to positive healthcare outcomes.
KW - Clinical Decision Support System
KW - Data Analysis
KW - Interpretation
KW - Oman
KW - Statistical Data
KW - Supervised Machine Learning
KW - Systemic Lupus Erythematosus
KW - Lupus Erythematosus, Systemic/diagnosis
KW - Alopecia
KW - Humans
KW - ROC Curve
KW - Machine Learning
UR - http://www.scopus.com/inward/record.url?scp=85169355393&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85169355393&partnerID=8YFLogxK
UR - https://www.mendeley.com/catalogue/65ceeab1-095a-37e7-af7d-e4d0f21418c0/
U2 - 10.18295/squmj.12.2022.069
DO - 10.18295/squmj.12.2022.069
M3 - Article
C2 - 37655084
AN - SCOPUS:85169355393
SN - 2075-051X
VL - 23
SP - 328
EP - 335
JO - Sultan Qaboos University Medical Journal
JF - Sultan Qaboos University Medical Journal
IS - 3
ER -