Acute appendicitis has various clinical features, and it is sometimes misdiagnosed as another digestive disease because an abnormal appendix is not found even through a CT scan. If this AI model is put to practical use, it is expected to reduce misdiagnosis of appendicitis and enable faster patient care. It is also expected to help operate emergency room personnel more efficiently.
Hallym University Sacred Heart Hospital Surgery Research Team and Hallym University Medical Center Medical Artificial Intelligence Center recently developed an AI model that automatically detects appendicitis by observing CT images in real time.
Appendicitis, commonly known as appendicitis, refers to inflammation of the appendix, the end of the appendix. Symptoms include nausea, vomiting, nausea, etc., followed by gradually increasing pain intensity in the epigastric region and upper abdomen. Over time, pain in the upper abdomen passes around the navel and changes to pain in the right lower abdomen, which is the location of the appendix.
Acute appendicitis is a frequent disease that ranks fifth in surgical statistics, and is also a disease that can cause misdiagnosis.
Due to the nature of the disease, patients who visit the hospital with suspected symptoms of acute appendicitis often visit the hospital through the emergency room at night or on weekends. In this case, accurate reading by an abdominal radiologist may be limited. In addition, acute appendicitis has a variety of clinical features, and there are cases where an abnormal appendix is not found even through CT imaging, so it is misdiagnosed as another digestive disease.
The problem is that if the diagnosis of appendicitis is delayed, perforation may occur, and if inflammation of the right lower abdomen of appendicitis develops into peritonitis or intrapelvic abscess, surgical treatment beyond appendectomy may result. In addition, complications after surgery increase.
This AI model developed by the research team at Hallym University Sacred Heart Hospital observes CT images in real time to filter out diseases clinically similar to appendicitis, such as colitis, terminal ileitis, and ascending colonic diverticulitis, and accurately diagnose only appendicitis.
The research team analyzed the data of 4701 patients who had CT scans for appendicitis treatment at Hallym University Medical Center from 2013 to 2020 and the data of 4452 patients who visited the emergency room and had CT scans for abdominal pain from 2019 to May of this year.
Afterwards, the data of 1839 patients with appendicitis and 1782 patients diagnosed as non-appendicitis were filtered out and trained in a model using ‘3D Convolutional Neural Network (CNN)’.
Appendicitis diagnosis accuracy of the AI model that completed training was 89.4%.
The ‘Area Under the Curve’ (AUC) score used to evaluate the performance of the AI model was 0.890, showing excellent results that can be applied to actual clinical practice.
“This AI is significant in that it recognizes three-dimensional CT images in three dimensions, unlike existing models,” said Beomju Cho, head of the Center for Medical Artificial Intelligence.
Professor Son Il-tae said, “We are reviewing various methods to increase the sensitivity, area under the curve score, and F1 score of this AI model.” plan to do,” he said.
This AI model was presented at the recently held International Korean Society of Surgery and the Korean Surgeons Association Fall Conference and won the ‘Best Principle Investigator’ award. Reporter Jang Jong-ho [email protected]