Machine Learning and XAI approaches for Allergy Diagnosis. (August 2021)

• Record Type: Journal Article
• Authors: Kavya, Ramisetty; Christopher, Jabez; Panda, Subhrakanta; Lazarus, Y. Bakthasingh
• Is Part Of: Biomedical signal processing and control. Volume 69(2021)
• Publication Date: 2021-08
• Subjects: Ensemble classification -- Post-hoc explainability -- Clinical decision-making -- Allergy diagnosis -- Healthcare mobile application; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2021.102681
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: Diagnosing allergy comorbidities is difficult in the absence of domain-experts. Clinical Decision Support System is proposed to diagnose co-existing allergies. CDSS provides explanations for the classifier-predictions using XAI approaches. Clinical relevance of the CDSS is validated and compared with existing methods. CDSS integrated with smartphone supports clinicians in decision-making. Abstract: This work presents a computer-aided framework for allergy diagnosis which is capable of handling comorbidities. The system was developed using datasets collected from allergy testing centers in South India. Intradermal skin test results of 878 patients were recorded and it was observed that the data contained very few samples for comorbid conditions. Modified data sampling techniques were applied to handle this data imbalance for improving the efficiency of the learning algorithms. The algorithms were cross-validated to choose the optimal trained model for multi-label classification. The transparency of the machine learning models was ensured using post-hoc explainable artificial intelligence approaches. The system was tested by verifying the performance of a trained random forest model on the test data. The training and validation accuracy rate of the decision tree, support vector machine and random forest are 81.62, 81.04 and 83.07 respectively. During evaluation, random forest achieved a rate of 86.39 accuracy overall, and 75% sensitivity for the comorbid Rhinitis-Urticaria class. The framework along with all the functionalities were deployed on mobile devices. The average performance of the clinicians before and after using the decision support system were 77.21% and 81.80% respectively. The diagnosis system integrated with mobile applications serves as a source of information whereby junior clinicians can use it to confirm their diagnostic predictions.