A Fuzzy Rule Based Expert System for Early Diagnosis of Osgood Schlatter Disease of Knee Joint

A Fuzzy Rule Based Expert System for Early Diagnosis of Osgood Schlatter Disease of Knee Joint

Gagandeep Kaur, Abhinav Hans, Anshu Vashisth
DOI: 10.4018/IJHISI.2020040103
Article PDF Download
Open access articles are freely available for download


The proposed research work is for the early diagnosis of the inflammatory disease named Osgood-Schlatter disease of the knee joint. As the system deals with fuzzy values, a MATLAB (R2013a) fuzzy logic controller is used for the implementation. The knowledge engineering phase is done with the help of an orthopedic expert. Four symptoms are used for diagnosing the severity of disease. Also, this diagnosis provides the treatment for the respective level of disease. Data collection is completed by the survey method and various defuzzification methods are used to check the accuracy. The proposed system was tested on 25 patients.
Article Preview


In recent years, many soft computing methods are evolved to improve the quality in medical field. As Medical field is very complex. Nowadays, artificial intelligence (AI) is the one of most emerging fields in all the domains. Expert system which comes under AI, is a human coded program having reasoning capability like human beings (Sethi, 2016). Expert system uses the concept of forward chaining which is a bottom up approach. Expert system is a program that performs the decision-making capabilities by using domain expertise knowledge in form of rules and facts. All the rules provided by domain expert is treated as the knowledge base of the expert system (Khamparia, 2018). From these all collected rules, inference engine which is processing unit of expert system, matches the fact which is stored in working memory. If the rule matches with the fact, then agenda will fire that active rule. The fired rule is basically the consequent part of the rule as the antecedent part is matched with the fact. Expert system provides aids to doctors and users without having knowledge of AI. The proposed system is developed to diagnose the orthopaedic disease named Osgood-Schlatter diseases of the main hinge joint, which is knee joint. Orthopaedic diseases deals with deformities, injuries. All the joint diseases come under the broad category of orthopaedic. The knee joint is comprised of three bones: the femur, tibia, and patella (Pandey, 2009).

Figure 1.

Knee part affected by Osgood Schlatter disease


Osgood-Schlatter disease is an inflammation disease which occurs mostly in adolescents. Figure 1 shows the affected parts of knee by Osgood-Schlatter disease. This is very common in sports as athletes do vigorous sports activities. This disease is usually more common in boys than girls (Domingues, 2013). It occurs in boys at the age 8-14 and in girls at the age of 10-13. At that age, children are doing many exercises by playing, running, jumping. It causes pain in the lower front part of knee which is tibial tubercle or patellar tendon region. As shown in figure 1 the bone shin inflames.

As a result, the need is for safe and healthy treatments. In artificial intelligence, an expert system is the most emerging field which uses domain expert knowledge to diagnose the disease accurately. In the 1970s when there is beginning of fuzzy logic, the first MES was developed to diagnose the infectious blood disease MYCIN. It was designed using the LISP language and by using 500 rules with various vague and incomplete input values. It deals with certain degrees of the belief using combining functions (Sethi, 2016). With the advancement in AI, many medical expert systems are evolved like DENDRAL, cancer, PROSPECTOR, cardiac disease, ENT, malaria, asthma, dengue, gynecology, and tumors.

Complete Article List

Search this Journal:
Volume 19: 1 Issue (2024)
Volume 18: 1 Issue (2023)
Volume 17: 2 Issues (2022)
Volume 16: 4 Issues (2021)
Volume 15: 4 Issues (2020)
Volume 14: 4 Issues (2019)
Volume 13: 4 Issues (2018)
Volume 12: 4 Issues (2017)
Volume 11: 4 Issues (2016)
Volume 10: 4 Issues (2015)
Volume 9: 4 Issues (2014)
Volume 8: 4 Issues (2013)
Volume 7: 4 Issues (2012)
Volume 6: 4 Issues (2011)
Volume 5: 4 Issues (2010)
Volume 4: 4 Issues (2009)
Volume 3: 4 Issues (2008)
Volume 2: 4 Issues (2007)
Volume 1: 4 Issues (2006)
View Complete Journal Contents Listing