AI Analysis of X-Rays Simplifies Complex Achalasia Diagnosis

Researchers in Japan have developed an artificial intelligence model that simplifies the diagnosis of esophageal achalasia, a rare disorder affecting the movement of the esophagus, from routine chest X-ray images.

The condition typically causes symptoms such as food regurgitation and chest pain, and is currently diagnosed using upper gastrointestinal endoscopy or high-resolution manometry, both of which are invasive.

The new technique, outlined in Clinical Gastroenterology and Hepatology, promises a less invasive alternative.

Improved diagnosis using AI

Esophageal achalasia is characterized by abnormal features that can sometimes be observed on chest X-rays, including a dilated or twisted esophagus and fluid retention. However, these signs are not easily visible, making plain radiography alone unreliable for diagnosis. In clinical practice, a barium swallow test is typically used to make it easier to identify achalasia on an X-ray image.

In this new study, researchers from Osaka Metropolitan University present a diagnostic AI model that is trained to detect these subtle radiographic features without the need for barium contrast. 

The model was trained on 207 chest X-rays from 144 patients with achalasia and 240 chest X-rays from 240 individuals without the condition, matched by age and sex. The researchers then validated the model using a test dataset comprising 17 X-rays from achalasia patients and 64 X-rays from non-achalasia individuals.

The tool demonstrated a high diagnostic accuracy, with an area under the curve (AUC) of 0.964. Its sensitivity was 0.941 and its specificity was 0.891. These results were more accurate than those of physicians who reviewed the same test images.

Potential application in health screenings

Achalasia is frequently diagnosed years after the first onset of symptoms, which can impact the effectiveness of subsequent treatment.

“There are reports indicating that from the onset of symptoms to diagnosis, esophageal achalasia takes an average of 6.5 years," said study author Akinari Sawada, PhD. "Delayed diagnosis may worsen esophageal dilation and tortuosity and reduce treatment efficacy; therefore, early diagnosis is desirable."

While further validation in clinical settings will be needed, the team believes that this alternative approach to screening could drastically reduce the time between achalasia onset and diagnosis.

“In Japan, chest X-rays are commonly taken during regular health checkups. Based on the findings of this study, it may be possible to screen for esophageal achalasia in a simple and minimally invasive manner,” Sawada said.

Reference: Ochiai T, Ueda D, Sawada A, et al. Artificial intelligence-based detection of achalasia on plain chest radiography. Clin Gastroenterol Hepatol. 2025. doi: 10.1016/j.cgh.2025.08.024

This article has been republished from the following materials. Note: material may have been edited for length and content. For further information, please contact the cited source. Our press release publishing policy can be accessed here.

This content includes text that has been generated with the assistance of AI. Technology Networks' AI policy can be found here.