An Interpretable Clinical Decision Support System aims to stage Age-Related Macular Degeneration using deep learning and imaging biomarkers

The use of intelligent clinical decision support systems (CDSS) has the potential to improve the accuracy and speed of diagnoses significantly. These systems can analyze a patient's medical data and generate comprehensive reports that enable specialists to better understand and evaluate the current clinical scenario. It is essential when dealing with medical images, as the high workload on healthcare professionals can hinder their ability to notice critical biomarkers, which may be difficult to detect with the naked eye due to stress and fatigue. Implementing a CDSS that uses computer vision (CV) techniques can alleviate this challenge. However, one of the main obstacles to the widespread use of CV and intelligent analysis methods in medical diagnostics is the lack of a clear understanding of how these systems operate among diagnosticians. A better understanding of how these systems work and the reliability of the identified biomarkers will enable medical professionals to more effectively grasp clinical problems. Additionally, it is essential to tailor the training process of machine learning models to fit medical data, which is often imbalanced due to varying probabilities of disease detection. If this factor is neglected, the quality of the developed CDSS may suffer. This article discusses the development of the CDSS module, which focuses on diagnosing age-related macular degeneration. Unlike traditional methods that classify diseases or their stages based on optical coherence tomography (OCT) images, the CDSS provides a more sophisticated and accurate analysis of biomarkers detected through a deep neural network. This approach combines an interpretative reasoning process with highly accurate models, although these models can be complex to describe. To address the issue of class imbalance, an algorithm has been developed to optimally select biomarkers, taking into account both their statistical and clinical significance. As a result, the algorithm prioritizes selecting classes that ensure high model accuracy while maintaining a sufficient level of clinical relevance in the responses generated by the CDSS module. The results obtained from this algorithm indicate that the overall accuracy of staging age-related macular degeneration increased by 63.3\% compared to traditional methods of direct stage classification using a similar machine learning model. This improvement suggests that the CDSS module can significantly enhance the diagnosis of this disease, especially in situations where there is class imbalance in the original dataset. To improve interpretability, the process of determining the most likely stage of the disease was organized into two stages. At each stage, the diagnostician could visually access information that explained the reasoning behind the intelligent diagnosis, aiding the expert in understanding how to make clinical decisions.