A black box algorithm is one whose logic of is not interpretable by humans either due to its complexity or due to its logic being represented in a convoluted manner. On the other hand, a white box algorithm is one whose logic is visible and understandable for a human. In other words, explainability helps the human brain to understand why an algorithm is giving specific results. The degree of explainability is the measure to which a particular algorithm is understandable for the human brain. Many classes of algorithms, especially those related to machine learning, are classified as black box. If the algorithms are used for critical decision-making, it may be important to understand the reasons behind the results generated by the algorithm. Converting black box algorithms into white box ones also provides better insights into the inner workings of the model. An explainable algorithm will guide doctors as to which features were actually used to classify patients as sick or not. If the doctor has any doubts about the results, they can go back and double-check those particular features for accuracy.