Accurate diagnosis of acute appendicitis in the emergency department: an artificial intelligence-based approach

被引:0
作者
Roshanaei, Ghodratollah [1 ]
Salimi, Rasoul [2 ]
Mahjub, Hossein [1 ]
Faradmal, Javad [1 ]
Yamini, Ali [3 ]
Tarokhian, Aidin [4 ]
机构
[1] Hamadan Univ Med Sci, Modeling Noncommunicable Dis Res Ctr, Hamadan, Iran
[2] Hamadan Univ Med Sci, Besat Hosp, Emergency Dept, Hamadan, Iran
[3] Hamadan Univ Med Sci, Besat Hosp, Dept Gen Surg, Hamadan, Iran
[4] Hamadan Univ Med Sci, Pajoohesh Blvd, Hamadan, Iran
关键词
Appendicitis; Abdominal pain; Artificial intelligence; Machine learning; Surgery; ABDOMINAL-PAIN;
D O I
10.1007/s11739-024-03738-w
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
The diagnosis of abdominal pain in emergency departments is challenging, and appendicitis is a common concern. Atypical symptoms often delay diagnosis. Although the Alvarado score aids in decision-making, its low specificity can lead to unnecessary surgeries. By leveraging machine learning, we aim to enhance diagnostic accuracy by predicting appendicitis and distinguishing it from other causes of abdominal pain in the emergency department. Data were collected from 534 patients who presented with acute abdominal pain. Patient characteristics, laboratory results, and causes of pain were recorded. Machine learning algorithms (support vector classifier, random forest classifier, gradient boosting classifier, and Gaussian naive Bayes) were used to predict the cause of pain. Model calibration was assessed using the Brier score. The mean age was 46.89 (20.3) years, with an almost equal sex distribution (49% male, 51% female). Cholecystitis was the most prevalent outcome (37.07%), followed by appendicitis (25.84%). The Gaussian naive Bayes model exhibited superior performance in terms of accuracy (95.03% 95% CI 90.44-97.83%), sensitivity (87.18% 95% CI 72.57-95.70%), and specificity (97.54% 95% CI 92.98-99.49%), while the random forest model showed a sensitivity of 79.49%, specificity of 96.72%, and accuracy of 92.55%. The gradient boosting algorithm achieved a sensitivity, specificity, and accuracy of 89.74%, 95.90%, and 94.41%, respectively. The support vector classifier demonstrated a sensitivity of 89.74%, specificity of 92.62%, and accuracy of 91.93%. The use of modern machine learning methods aids in the accurate diagnosis of appendicitis.
引用
收藏
页码:2347 / 2357
页数:11
相关论文
共 45 条
[31]   Comparison between single and serial computed tomography images in classification of acute appendicitis, acute right-sided diverticulitis, and normal appendix using EfficientNet [J].
Park, So Hyun ;
Kim, Young Jae ;
Kim, Kwang Gi ;
Chung, Jun-Won ;
Kim, Hyun Cheol ;
Choi, In Young ;
You, Myung-Won ;
Lee, Gi Pyo ;
Hwang, Jung Han .
PLOS ONE, 2023, 18 (05)
[32]   Evaluation of Sampling and Cross-Validation Tuning Strategies for Regional-Scale Machine Learning Classification [J].
Ramezan, Christopher A. ;
Warner, Timothy A. ;
Maxwell, Aaron E. .
REMOTE SENSING, 2019, 11 (02)
[33]   Diagnostic standards for acute pancreatitis [J].
Ranson, JHC .
WORLD JOURNAL OF SURGERY, 1997, 21 (02) :136-142
[34]  
Rigatti Steven J, 2017, J Insur Med, V47, P31, DOI 10.17849/insm-47-01-31-39.1
[35]  
Roelofs R, 2019, ADV NEUR IN, V32
[36]   Use of Brier score to assess binary predictions [J].
Rufibach, Kaspar .
JOURNAL OF CLINICAL EPIDEMIOLOGY, 2010, 63 (08) :938-939
[37]   How expertise develops in medicine: knowledge encapsulation and illness script formation [J].
Schmidt, Henk G. ;
Rikers, Remy M. J. P. .
MEDICAL EDUCATION, 2007, 41 (12) :1133-1139
[38]  
Seger C., 2018, An investigation of categorical variable encoding techniques in machine learning: binary versus one-hot and feature hashing. resreport
[39]  
Shahmoradi L, 2019, ACTA MED IRANICA, V56, P784
[40]   Effect of data standardization on neural network training [J].
Shanker, M ;
Hu, MY ;
Hung, MS .
OMEGA-INTERNATIONAL JOURNAL OF MANAGEMENT SCIENCE, 1996, 24 (04) :385-397