An artificial intelligence (AI) system called “ENDOANGEL” was effective for real-time monitoring of endoscopic “blind spots” and improved detection of early gastric cancer (EGC) during esophagogastroduodenoscopy (EGD), according to research published recently.
While EGD is widely used to examine lesions found in the upper gastrointestinal tract, there is considerable variability among endoscopists regarding performance, resulting in a substantial miss rate for EGC. But in a study published in the journal Endoscopy, researchers suggest a more objective assessment of lesions with AI technology could improve detection rates in real time, thus improving the chances of establishing an early diagnosis and initiating prompt treatment of gastric cancer.
The researchers updated a developed AI system called WISENSE, which previously demonstrated an ability to monitor gastric areas overlooked during EGD (termed “blind spots”). The investigators integrated a trained real-time EGC detection model into the WISENSE system and changed the name of the updated system to ENDOANGEL.
Researchers from the Renmin Hospital of Wuhan (China) University used deep convolutional neural networks and deep reinforcement learning to develop the ENDOANGEL. A total of 1,050 patients from five hospitals in China who were undergoing EGD were randomized to either an ENDOANGEL-assisted protocol (n = 498) or a control group (n = 504) that did not use the ENDOANGEL system. Examination consisted of white-light imaging observation, magnifying image-enhanced endoscopy observation, and biopsy of suspicious lesions.
The investigators compared the groups in terms of the number of blind spots after the intervention. They assessed the performance of the AI-based ENDOANGEL system in its ability to predict EGC in a real-world clinical setting.
Patients assigned to ENDOANGEL had a significantly fewer mean number of blind spots compared with patients assigned to control (5.38 vs. 9.82, respectively; P < .001). Despite this advantage, patients in the ENDOANGEL group had significantly longer inspection time (5.40 minutes vs. 4.38 minutes; P < .001).
There were 819 lesions reported by endoscopists in the ENDOANGEL group, which included 196 gastric lesions with pathological results. According to the investigators, the ENDOANGEL system correctly predicted all three EGCs, including one mucosal carcinoma and two high grade neoplasias, as well as two advanced gastric cancers. The per-lesion accuracy was 84.7 %, while the sensitivity and specificity rates for detecting gastric cancer were 100% and 84.3%, respectively.
The authors noted limitations of the analysis itself and those stemming from the short follow-up, as well as possible bias introduced by unblinded statisticians. Further research is warranted, they wrote.
“In conclusion, ENDOANGEL, a system for improving endoscopy quality based on deep learning, achieved real-time monitoring of endoscopic blind spots, timing, and EGC detection during EGD,” according to the authors. “ENDOANGEL greatly improved the quality of EGD in this multicenter study, and showed potential for detecting EGC in real clinical settings.”
Spotting the Blind Spots
An AI-based system such as ENDOANGEL could overcome some of the natural weaknesses to standard diagnostic testing, thereby improving rates of EGC testing, David Hoffman, MD, a gastroenterology oncologist and medical director of Cedars-Sinai Cancer Beverly Hills, said in an interview. “I think that there are ethical questions that we’re going to have to grapple with respect to accessibility and data mining and what that really means,” said Hoffman, who wasn’t involved in the study. “But I think that in the optimistic view, using AI with machine learning and deep learning has tremendous potential for public health and for cancer medicine in particular.”
Hoffman added that beyond early detection of cancer, AI systems may hold additional benefits, particularly in regard to assisting decisions for personalized medicine and assisting in real-time surgical interventions. “Using AI with machine learning and deep learning has tremendous potential and I think it sort of is a natural offshoot into what we’re seeing in … algorithmic approaches to use of big data, so it’s sort of a natural evolution in terms of medical applications,” he explained.
Anuj Patel, MD, a medical oncology specialist at the Dana-Farber Cancer Institute, Boston, who wasn’t involved in the new research, explained that any strategy that helps detect gastric cancer at earlier stages could have a visible global impact. “We have a lower incidence of gastric cancer in the United States, but the training of and clinical volume of early gastric cancers seen by different providers can vary,” Patel said in an interview. “AI systems could provide a second layer of evaluation during procedures where an endoscopist might otherwise miss the subtle features associated with some early gastric cancers.”
While the findings from the ENDOANGEL study appear promising, Patel noted that the most important long-term question is whether this reduction of endoscopic blind spots as a result of implementing the system will translate to meaningful improvements in patient outcomes. “More broadly, I think that we will need to see how well these techniques can be applied across different populations,” he added. “Because AI models such as these need to be trained, it will be important to see if they need to be retrained when used in countries where gastric cancer might present differently or with distinctive endoscopic equipment and techniques.”
The study authors, as well as Patel and Hoffman, had no conflicts of interest to disclose.
This article originally appeared on MDedge.com, part of the Medscape Professional Network.