Nasogastric tube in mechanical ventilated patients: ETCO2 and pH measuring to confirm correct placement. A pilot study

Abstract

Introduction: Nasogastric tube (NGT) placement is a procedure commonly performed in mechanically ventilated (MV) patients. Chest X-Ray is the diagnostic gold-standard to confirm its correct placement, with the downsides of requiring MV patients' mobilization and of intrinsic actinic risk. Other potential methods to confirm NGT placement have shown lower accuracy compared to chest X-ray; end-tidal CO2 (ETCO2) and pH analysis have already been singularly investigated as an alternative to the gold standard. Aim of this study was to determine threshold values in ETCO2 and pH measurement at which correct NGT positioning can be confirmed with the highest accuracy.

Materials & methods: This was a prospective, multicenter, observational trial; a continuous cohort of eligible patients was allocated with site into two arms. Patients underwent general anesthesia, orotracheal intubation and MV; in the first and second group we respectively assessed the difference between tracheal and esophageal ETCO2 and between esophageal and gastric pH values.

Results: From November 2020 to March 2021, 85 consecutive patients were enrolled: 40 in the ETCO2 group and 45 in the pH group. The ETCO2 ROC analysis for predicting NGT tracheal misplacement demonstrated an optimal ETCO2 cutoff value of 25.5 mmHg, with both sensitivity and specificity reaching 1.0 (AUC 1.0, p < 0.001). The pH ROC analysis for predicting NGT correct gastric placement resulted in an optimal pH cutoff value of 4.25, with mild diagnostic accuracy (AUC 0.79, p < 0.001).

Discussion: In patients receiving MV, ETCO2 and pH measurements respectively identified incorrect and correct NGT placement, allowing the identification of threshold values potentially able to improve correct NGT positioning.

Trial registration: NCT03934515 (www.clinicaltrials.gov).

Fig 1. Patients distribution.

Study patients’ allocation and distribution.

Fig 2. Tracheal and esophageal ETCO₂ distribution.

Boxplots: The black bar indicates median ETCO₂ (38 mmHg and 14 mmHg respectively), while the blue areas include the interquartile ranges for each group.

Fig 3. Measured of esophageal and gastric pH.

Boxplot distribution in all patients and in patients without PPI use. Regarding the whole group analysis, a t-test score confirmed a significant difference between esophageal and gastric values (CI 99%, 0.9–2.9, p = 0.004). The subgroup analysis involving patients without PPI showed a greater difference (p < 0.001) compared to the whole group. The black bar indicates median pH, while the blue areas include the interquartile ranges for each group.

Fig 4. ROC curves of ETCO₂ and pH.

Receiver operating characteristic (ROC) curves showing the ability of the ETCO₂ method (Fig 4A) and pH method (Fig 4B) to respectively identify a tracheal NGT misplacement (ROC AUC 1.0, p < 0.001) or a gastric NGT correct placement (ROC AUC 0.79, CI 95% 0.67–0.90, p < 0.001).

Fig 5. Cumulative distribution analysis of pH detection.

Performed to determine the correct NGT gastric placement with ‘Fig 5A’ and without ‘Fig 5B’ PPI use. The red line indicates the cutoff limit according to Youden Index (pH below 4.25 and pH below 3.9, with J = 0.593 and J = 0.6 respectively); the grey zone is shown, with sensibility and specificity of 90%.

Fig 6. Cumulative distribution analysis of ETCO₂ detection.

Performed to exclude the NGT tracheal misplacement. The red line indicates the cutoff limit according to Youden Index (J = 1).