An automated artifact detection and rejection system for body surface gastric mapping

Abstract

Background Body surface gastric mapping (BSGM) is a new clinical tool for gastric motility diagnostics, providing high‐resolution data on gastric myoelectrical activity. Artifact contamination was a key challenge to reliable test interpretation in traditional electrogastrography. This study aimed to introduce and validate an automated artifact detection and rejection system for clinical BSGM applications. Methods Ten patients with chronic gastric symptoms generated a variety of artifacts according to a standardized protocol (176 recordings) using a commercial BSGM system (Alimetry, New Zealand). An automated artifact detection and rejection algorithm was developed, and its performance was compared with a reference standard comprising consensus labeling by 3 analysis experts, followed by comparison with 6 clinicians (3 untrained and 3 trained in artifact detection). Inter‐rater reliability was calculated using Fleiss' kappa. Key Results Inter‐rater reliability was 0.84 (95% CI:0.77–0.90) among experts, 0.76 (95% CI:0.68–0.83) among untrained clinicians, and 0.71 (95% CI:0.62–0.79) among trained clinicians. The sensitivity and specificity of the algorithm against experts was 96% (95% CI:91%–100%) and 95% (95% CI:90%–99%), respectively, vs 77% (95% CI:68%–85%) and 99% (95% CI:96%–100%) against untrained clinicians, and 97% (95% CI:92%–100%) and 88% (95% CI:82%–94%) against trained clinicians. Conclusions & Inferences An automated artifact detection and rejection algorithm was developed showing >95% sensitivity and specificity vs expert markers. This algorithm overcomes an important challenge in the clinical translation of BSGM and is now being routinely implemented in patient test interpretations.

Normative values for body surface gastric mapping evaluations of gastric motility using Gastric Alimetry: spectral analysis

“…Artifacts were automatically detected and rejected where possible using the validated Gastric Alimetry algorithm, 12 and tests with artifacts >50% of the total testing duration were excluded from the reference interval calculations. Spectral analysis of BSGM data is used to interpret the bioelectrical slow-waves that coordinate gastric motility, with gastric contractile activity also being registered as a power increase arising after a stimulus.…”

“…Test quality was assessed based on impedance (<200 kΩ optimal; <500 kΩ acceptable; ≥500 kΩ poor) and proportion of the recording duration affected by artifacts (defined per the Gastric Alimetry Report Interpretation Guidelines as <20% optimal; <50% acceptable; >50% interpret with caution). Artifacts were automatically detected and rejected where possible using the validated Gastric Alimetry algorithm, 12 and tests with artifacts >50% of the total testing duration were excluded from the reference interval calculations.…”

“…[9][10][11] Spectral metrics are derived from a spectral plot, and represent a form of HR-EGG, achieving robust improvements over traditional EGG metrics. 8,10,12,15 Spectral metrics are currently the most established form of analytics, with a recent BSGM study principally employing these to identify a distinct subgroup of patients with gastric neuromuscular abnormalities in nausea and vomiting syndromes. 11 The aim of this study was to establish normative reference intervals for spectral BSGM metrics for Gastric Alimetry, encompassing the Principal Gastric Frequency, Gastric Alimetry Rhythm Index (GA-RI), BMI-adjusted amplitude, and the fed:fasted amplitude ratio.…”

“…9–11 Spectral metrics are derived from a spectral plot, and represent a form of HR-EGG, achieving robust improvements over traditional EGG metrics. 8,10,12,15 Spectral metrics are currently the most established form of analytics, with a recent BSGM study principally employing these to identify a distinct subgroup of patients with gastric neuromuscular abnormalities in nausea and vomiting syndromes. 11…”

Revised spectral metrics for body surface measurements of gastric electrophysiology

“…Although EGG identified group-level differences between patients and controls in multiple adult and pediatric disorders, [5][6][7][8] it did not achieve common clinical adoption due to several technical limitations, including inability to account for gastric anatomical variability, poor spatial resolution, and pitfalls in handling artifacts. [9][10][11][12] Body surface gastric mapping (BSGM) overcomes these limitations, with recent studies showing capability to define novel disease subgroups with symptom correlations. 9,13,14 BSGM is performed using a recently-developed medical device (Gastric Alimetry®, Alimetry, New Zealand) comprising a conformable high-resolution array, wearable Reader, and validated symptom-logging App.…”