:: Volume 20, Issue 4 (Iranian South Medical Journal 2017) ::
Iran South Med J 2017, 20(4): 339-348 Back to browse issues page
Better Diagnosis of Acute Appendicitis by Using Artificial Intelligence
Mir Mekaeal Hosseini *1, Reza Safdari 2, Lila Shahmoradi 2, Mojtaba Javaherzadeh 3
1- Medical Informatics Department, School of Allied Medical Sciences, Tehran University of Medical Sciences, Tehran, Iran , triplex.mmm@gmail.com
2- Medical Informatics Department, School of Allied Medical Sciences, Tehran University of Medical Sciences, Tehran, Iran
3- General Surgery Department, Shahid Modarres Hospital, Shahid Behehsti Medical University, Tehran, Iran
Abstract:   (382 Views)
Background: Acute appendicitis is the most common cause for referral of patients with abdominal pains to emergency department of hospitals and appendectomy is the most common emergency operation. Despite of introduction of the various diagnostic methods unnecessary appendectomy rate is significant. Therefore, the use of artificial intelligence and machine learning methods as a tool to aid in the diagnosis can be timely and more accurate diagnosis, reduce length of stay in hospital and improve the treatment costs.
Materials and Methods: During the developmental research, by studying literature and resources related to gastrointestinal diseases, variables affecting the diagnosis came together and were assessed by surgeons. During 2015, 181 cases of patients who underwent appendectomy was performed at the modarres Hospital constitute research database. Then, the support vector machine systems with different architectures implemented and compared to determine the best diagnostic function. Sensitivity, accuracy and specificity were used for evaluation.
Results: The output obtained from the system of vector machine had sensitivity, specificity and accuracy of 91/7 percent, 96/2 percent and 95 percent which expresses its proper function in detecting acute appendicitis.
Conclusion: According to the results, we can say that using designed support vector machine in diagnosis of acute appendicitiswill be effective in order to timely detect, prevent unnecessary appendectomy, reduction the patient's length of stay and health care costs.
Keywords: Appendicitis, diagnosis, support vector machine, artificial intelligence, machine learning.
Full-Text [PDF 573 kb]   (135 Downloads)    
Type of Study: Original | Subject: Surgery
Received: 2017/08/27 | Accepted: 2017/08/27 | Published: 2017/08/27



XML   Persian Abstract   Print


Volume 20, Issue 4 (Iranian South Medical Journal 2017) Back to browse issues page