Increasing Diagnosing Hydrocephalus Using Case-based Reasoning (CBR)

Abstract

Hydrocephalus is a medical condition characterized by the accumulation of cerebrospinal fluid in the brain, which can lead to increased intracranial pressure and neurological disturbances. Early and accurate diagnosis is crucial for medical professionals to determine the type of hydrocephalus the patient has and provide the appropriate solution. This study aims to develop a Case-Based Reasoning (CBR) system to assist healthcare providers in diagnosing hydrocephalus more effectively. With this system, medical professionals can identify the type of hydrocephalus based on the symptoms experienced by the patient and receive recommendations based on previous cases. The research method used in this study is Case-Based Reasoning (CBR), an experience-based approach that relies on documented cases to solve new problems by comparing them to similar past cases. Data for this study were obtained from Andalas University Hospital and consultations with experts. The dataset used includes 19 hydrocephalus symptom data points and two main classifications of hydrocephalus: congenital hydrocephalus and acquired hydrocephalus. The results show that the CBR method has an accuracy rate of 63.15% in diagnosing congenital hydrocephalus and 44% in diagnosing acquired hydrocephalus. Although the accuracy rate still requires improvement, this study demonstrates that the CBR method has significant potential as a tool to assist in diagnosing hydrocephalus. The system can provide analysis based on historical data and help healthcare providers make more informed decisions. This study emphasizes that CBR can be an alternative to expert systems in hydrocephalus diagnosis. However, to improve accuracy and reliability in clinical practice, further testing with a larger dataset and integration with other artificial intelligence methods is needed. With further development, this system has the potential to become a more precise diagnostic tool and be more widely implemented in the medical field.