Anaphylaxis Prediction and Tailored Medicine Prescription System Using CNN-Based Tabular Data Analysis

Allergic diseases encompass a wide range of conditions in which the immune system reacts abnormally to harmless substances, leading to various symptoms and health complications. Anaphylaxis is a serious life-threatening generalized or systemic hypersensitivity reaction.[1] Mainly it is thought to be a serious systemic hypersensitivity reaction that is usually rapid in onset and may cause death.[2] It is triggered by exposure to specific allergens, such as certain foods, medications, insect stings, or latex.[3] The conventional approach to diagnosing anaphylaxis involves in-person consultations with healthcare professionals, including physicians, allergists, and immunologists.[4] However, this process can be time-consuming, costly, and dependent on the availability of specialized medical expertise. Identifying anaphylaxis as positive or negative is complex due to the similarity of its symptoms with common ailments, requiring the physician's expertise. However, manual identification can cause accuracy issues, leading to incorrect diagnoses and prescriptions. To address these challenges and provide a more efficient disease diagnosis system, this research aims to harness machine learning techniques. Specifically, a CNN-based analysis is employed to predict whether a patient has anaphylaxis. Moreover, the system's functionality extends beyond diagnosis. If anaphylaxis is positively identified, the system initiates the process of recommending the administration of adrenaline. In the case of patients aged less than 12, a specialized mathematical equation is applied to calculate the appropriate dosage of adrenaline based on the patient's age. Conversely, if the system determines a negative anaphylaxis diagnosis, it reevaluates the input symptoms and matches them with suitable specialists. The system maintains a repository of physicians categorized by their areas of expertise, allowing it to output both the specialist's field and the name of the corresponding physician for patient referral.