Analisis Perbandingan Teorema Bayes dan Case Based Reasoning Dalam Diagnosis Penyakit Myasthenia Gravis

Bagas Triaji (Universitas Teknologi Digital Indonesia, Yogyakarta)
Azanuddin Azanuddin (Politeknik Negeri Medan, Medan)
Ibnu Rusydi (Universitas Dharmawangsa, Medan)
Ita Mariami (STMIK Triguna Dharma, Medan)
Asyahri Hadi Nasyuha (Universitas Teknologi Digital Indonesia, Yogyakarta)

JURNAL MEDIA INFORMATIKA BUDIDARMA
Vol 7, No 3 (2023): Juli 2023

The medical industry faces several obstacles due to illness. Treatment of any condition, including myasthenia gravis, relies heavily on an accurate and precise diagnosis. Myasthenia gravis is an autoimmune disease that affects the neuromuscular junction and is characterized by sudden muscle weakness and fatigue due to the loss of acetylcholine receptors (AChRs) at the neuromuscular junction. Successful treatment planning and providing a good prognosis to the patient is highly dependent on accurate and rapid diagnosis. To diagnose Myasthenia Gravis, this study compares and contrasts Case Anthology with Bayes' Theorem. The neuromuscular condition called myasthenia gravis is characterized by a variable decrease in muscle strength. Correct and timely diagnosis is essential to start a successful course of therapy. Data from patients with Myasthenia Gravis symptoms and clinical indicators were collected for this study. To obtain an accurate diagnosis, the dataset was analyzed using Bayes' Theorem and Case Anthology techniques. Based on the current symptoms, Bayes' Theorem is used to estimate the probability of the condition, while Anthology of Cases is used to diagnose the patient. Based on symptoms, Bayes' Theorem predicts disease outcome probabilistically, but requires reliable initial assumptions and is susceptible to prior probabilities. On the other hand, Case Anthologies use information obtained from previous situations, but may be limited by the availability of relevant data and may experience difficulties in dealing with unique or unusual situations. This study helps us understand the benefits and limitations of each technique in diagnosing Myasthenia Gravis. A more accurate and effective diagnosis can be made by combining the two methods. These studies can serve as a foundation for creating more sophisticated diagnostic techniques integrated into clinical practice. The following is a summary of the percentages obtained using the Bayes Theorem and Case Anthology methods: For the diagnosis of Myasthenia Gravis, the Bayes Theorem technique produces a percentage value of 55% while the Case Anthology method only produces a percentage value of 26%. Therefore, the Bayes Theorem technique is better and more reliable in diagnosing Myasthenia Gravis.