Artificial intelligence facilitates measuring reflux episodes and postreflux swallow-induced peristaltic wave index from impedance-pH studies in patients with reflux disease

Utility of the Post-Reflux Swallow-Induced Peristaltic Wave Index and Mean Nocturnal Baseline Impedance for the Diagnosis of Gastroesophageal Reflux Disease Phenotypes in Children

(1) Objectives: Assessment of novel impedance parameters such as the post-reflux swallow-induced peristaltic wave (PSPW) index and mean nocturnal baseline impedance (MNBI) have been proposed to enhance the accuracy of gastroesophageal reflux disease (GERD) diagnosis. We aimed to evaluate the clinical value of MNBI and the PSPW index in discerning different phenotypes of GERD in children. (2) Methods: We conducted a prospective, observational study that included 49 children aged 5-18 years, referred for MII-pH monitoring due to negative endoscopy and persisting gastroesophageal reflux symptoms despite acid-suppressant treatment. The PSPW index and MNBI were assessed along with conventional metrics. (3) Results: Using a receiver operating characteristic (ROC) curve analysis, MNBI (AUC 0.864) and the PSPW index (AUC 0.83) had very good performance in differentiating between non-erosive reflux disease (NERD) and functional phenotypes. The PSPW index (AUC 0.87) discriminated better between functional heartburn (FH) and reflux hypersensitivity (RH) compared to the MNBI (AUC 0.712). A PSPW cut-off value of 65% provided a sensitivity of 76.9% and a specificity of 90% in distinguishing FH and RH. The PSPW index (AUC 0.87) proved to have better performance than the MNBI (AUC 0.802) in differentiating between FH and non-FH patients. MNBI diagnosed FH with a sensitivity of 84% and a specificity of 80.6% at a cut-off value of 2563 Ω. (4) Conclusions: The PSPW index and MNBI are useful to distinguish between GERD phenotypes in pediatric patients.

Role of Artificial Intelligence in the Diagnosis of Gastroesophageal Reflux Disease

Gastroesophageal reflux disease (GERD) is a disorder that usually presents with heartburn. GERD is diagnosed clinically, but most patients are misdiagnosed due to atypical presentations. The increased use of artificial intelligence (AI) in healthcare has provided multiple ways of diagnosing and treating patients accurately. In this review, multiple studies in which AI models were used to diagnose GERD are discussed. According to the studies, using AI models helped to diagnose GERD in patients accurately. AI, although considered one of the most potent emerging aspects of medicine with its accuracy in patient diagnosis, presents limitations of its own, which explains why healthcare providers may hesitate to use AI in patient care. The challenges and limitations should be addressed before AI is fully incorporated into the healthcare system.

Artificial Intelligence Tools for Improving Manometric Diagnosis of Esophageal Dysmotility

PURPOSE OF REVIEW

Artificial intelligence (AI) is a broad term that pertains to a computer's ability to mimic and sometimes surpass human intelligence in interpretation of large datasets. The adoption of AI in gastrointestinal motility has been slower compared to other areas such as polyp detection and interpretation of histopathology.

RECENT FINDINGS

Within esophageal physiologic testing, AI can automate interpretation of image-based tests, especially high resolution manometry (HRM) and functional luminal imaging probe (FLIP) studies. Basic tasks such as identification of landmarks, determining adequacy of the HRM study and identification from achalasia from non-achalasia patterns are achieved with good accuracy. However, existing AI systems compare AI interpretation to expert analysis rather than to clinical outcome from management based on AI diagnosis. The use of AI methods is much less advanced within the field of ambulatory reflux monitoring, where challenges exist in assimilation of data from multiple impedance and pH channels. There remains potential for replication of the AI successes within esophageal physiologic testing to HRM of the anorectum, and to innovative and novel methods of evaluating gastric electrical activity and motor function. The use of AI has tremendous potential to improve detection of dysmotility within the esophagus using esophageal physiologic testing, as well as in other regions of the gastrointestinal tract. Eventually, integration of patient presentation, demographics and alternate test results to individual motility test interpretation will improve diagnostic precision and prognostication using AI tools.

Post-reflux swallow-induced peristaltic wave index: a new parameter for the identification of non-acid gastroesophageal reflux-related chronic cough

BACKGROUND

The current available diagnostic criteria for gastroesophageal reflux-related chronic cough (GERC) dominated by non-acid reflux is imperfect. The post-reflux swallow-induced peristaltic wave index (PSPWI) is a parameter reflecting esophageal clearance function.

OBJECTIVES

This study aims to investigate its diagnostic value for non-acid GERC.

DESIGN

This study sought to compare the diagnostic value of PSPWI in different types of GERC, particularly non-acid GERC, and explore the clinical significance of PSPWI in the diagnosis of non-acid GERC through diagnostic experiments.

METHODS

A retrospective analysis was performed based on 223 patients with suspected GERC who underwent multichannel intraluminal impedance-pH monitoring (MII-pH) in the outpatient clinic of our department from August 2016 to June 2021. Their clinical information, laboratory test results, and treatment responses were assessed and the underlying etiologies of chronic cough were categorized. The predictive value of the PSPWI in diagnosing different types of GERC, especially non-acid GERC, was analyzed and compared.

RESULTS

A total of 195 patients with chronic cough who met the inclusion criteria underwent MII-pH monitoring. 143 patients had a definitive diagnosis of GERC, including 98 with acid GERC and 45 with non-acid GERC. The diagnostic value of PSPWI alone was moderate for GERC with an area under the working curve (AUC) 0.760, but poor for non-acid GERC with an AUC of 0.569. However, PSPWI < 39.8% combining with acid exposure time (AET) ⩽ 6.2% demonstrated a moderate diagnostic value for non-acid GERC, with an AUC of 0.722. When PSPWI < 39.8% combined with a non-acid reflux ratio >68.75%, the diagnostic value for non-acid GERC was improved (AUCROC = 0.80 versus AUCROC = 0.722, p < 0.05), which was significantly superior to non-acid symptom index (AUCROC = 0.804 versus AUCROC = 0.550, p < 0.05) and non-acid symptom association probability (AUCROC = 0.804 versus AUCROC = 0.571, p < 0.05).

CONCLUSION

PSPWI < 39.8% and AET ⩽ 6.2% have demonstrated good diagnostic value for non-acid GERC. The diagnostic value was further improved when combined with non-acid reflux ratio >68.75%.

Computer-Based Intelligent Solutions for the Diagnosis of Gastroesophageal Reflux Disease Phenotypes and Chicago Classification 3.0

Gastroesophageal reflux disease (GERD) is a multidisciplinary disease; therefore, when treating GERD, a large amount of data needs to be monitored and managed.The aim of our study was to develop a novel automation and decision support system for GERD, primarily to automatically determine GERD and its Chicago Classification 3.0 (CC 3.0) phenotypes. However, phenotyping is prone to errors and is not a strategy widely known by physicians, yet it is very important in patient treatment. In our study, the GERD phenotype algorithm was tested on a dataset with 2052 patients and the CC 3.0 algorithm was tested on a dataset with 133 patients. Based on these two algorithms, a system was developed with an artificial intelligence model for distinguishing four phenotypes per patient. When a physician makes a wrong phenotyping decision, the system warns them and provides the correct phenotype. An accuracy of 100% was obtained for both GERD phenotyping and CC 3.0 in these tests. Finally, since the transition to using this developed system in 2017, the annual number of cured patients, around 400 before, has increased to 800. Automatic phenotyping provides convenience in patient care, diagnosis, and treatment management. Thus, the developed system can substantially improve the performance of physicians.

On-therapy impedance-pH monitoring can efficiently characterize PPI-refractory GERD and support treatment escalation

BACKGROUND

On-therapy impedance-pH monitoring is recommended in patients with documented GERD and PPI-refractory heartburn in order to establish whether the unremitting symptom is reflux-related or not.

AIMS

To define on-PPI cut-offs of impedance-pH metrics allowing proper interpretation of on-therapy impedance-pH monitoring.

METHODS

Blinded expert review of impedance-pH tracings performed during double-dosage PPI, prospectively collected from 150 GERD patients with PPI-refractory heartburn and 45 GERD patients with PPI-responsive heartburn but persisting extra-esophageal symptoms. Acid exposure time (AET), number of total refluxes (TRs), post-reflux swallow-induced peristaltic wave (PSPW) index, and mean nocturnal baseline impedance (MNBI) were assessed. On-PPI cut-offs were defined and evaluated with ROC analysis and the area under curve (AUC).

RESULTS

All the four impedance-pH metrics significantly differed between PPI-refractory and PPI-responsive heartburn cases. At ROC analysis, AUC was 0.73 for AET, 0.75 for TRs, 0.81 for PSPW index, and 0.71 for MNBI; best cut-offs were ≥1.7% for AET, ≥45 for TRs, ≤36% for PSPW index, and ≤ 1847 Ω for MNBI; AUC of such cut-offs was 0.66, 0.71, 0.73, and 0.68, respectively. Analysis of PSPW index and MNBI added to assessment of AET and TRs significantly increased the yield of on-therapy impedance-pH monitoring in the PPI-refractory cohort (97% vs. 83%, p < 0.0001). Notably, suboptimal acid suppression as shown by AET ≥1.7% was detected in 43% of 150 PPI-refractory cases.

CONCLUSIONS

We have defined on-PPI cut-offs of impedance-pH metrics by which comprehensive assessment of impedance-pH tracings, including analysis of PSPW index and MNBI can efficiently characterize PPI-refractory GERD and support treatment escalation.