Machine Learning Approach for Predicting Systemic Lupus Erythematosus in an Oman-Based Cohort

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.

Estimate of the HOMA-IR Cut-off Value for Identifying Subjects at Risk of Insulin Resistance Using a Machine Learning Approach

Objectives

This study describes an unsupervised machine learning approach used to estimate the homeostatic model assessment-insulin resistance (HOMA-IR) cut-off for identifying subjects at risk of IR in a given ethnic group based on the clinical data of a representative sample.

Methods

The approach was applied to analyse the clinical data of individuals with Arab ancestors, which was obtained from a family study conducted in Nizwa, Oman, between January 2000 and December 2004. First, HOMA-IR-correlated variables were identified to which a clustering algorithm was applied. Two clusters having the smallest overlap in their HOMA-IR values were retrieved. These clusters represented the samples of two populations, which are insulin-sensitive subjects and individuals at risk of IR. The cut-off value was estimated from intersections of the Gaussian functions, thereby modelling the HOMA-IR distributions of these populations.

Results

A HOMA-IR cut-off value of 1.62 ± 0.06 was identified. The validity of this cut-off was demonstrated by showing the following: 1) that the clinical characteristics of the identified groups matched the published research findings regarding IR; 2) that a strong relationship exists between the segmentations resulting from the proposed cut-off and those resulting from the two-hour glucose cut-off recommended by the World Health Organization for detecting prediabetes. Finally, the method was also able to identify the cut-off values for similar problems (e.g. fasting sugar cut-off for prediabetes).

Conclusion

The proposed method defines a HOMA-IR cut-off value for detecting individuals at risk of IR. Such methods can identify high-risk individuals at an early stage, which may prevent or delay the onset of chronic diseases such as type 2 diabetes.