Algorithms to Estimate P_aCO2and pH Using Noninvasive Parameters for Children with Hypoxemic Respiratory Failure

Abstract

BACKGROUND: Ventilator management for children with hypoxemic respiratory failure may benefit from ventilator protocols, which rely on blood gases. Accurate noninvasive estimates for pH or P aCO 2 could allow frequent ventilator changes to optimize lung-protective ventilation strategies. If these models are highly accurate, they can facilitate the development of closed-loop ventilator systems. We sought to develop and test algorithms for estimating pH and P aCO 2 from measures of ventilator support, pulse oximetry, and end-tidal carbon dioxide pressure (P ETCO 2 ). We also sought to determine whether surrogates for changes in dead space can improve prediction. METHODS: Algorithms were developed and tested using 2 data sets from previously published investigations. A baseline model estimated pH and P aCO 2 from P ETCO 2 using the previously observed relationship between P ETCO 2 and P aCO 2 or pH (using the Henderson-Hasselbalch equation). We developed a multivariate gaussian process (MGP) model incorporating other available noninvasive measurements. RESULTS: The training data set had 2,386 observations from 274 children, and the testing data set had 658 observations from 83 children. The baseline model predicted P aCO 2 within ؎ 7 mm Hg of the observed P aCO 2 80% of the time. The MGP model improved this to ؎ 6 mm Hg. When the MGP model predicted P aCO 2 between 35 and 60 mm Hg, the 80% prediction interval narrowed to ؎ 5 mm Hg. The baseline model predicted pH within ؎ 0.07 of the observed pH 80% of the time. The MGP model improved this to ؎ 0.05. CONCLUSIONS: We have demonstrated a conceptual first step for predictive models that estimate pH and P aCO 2 to facilitate clinical decision making for children with lung injury. These models may have some applicability when incorporated in ventilator protocols to encourage practitioners to maintain permissive hypercapnia when using high ventilator support. Refinement with additional data may improve model accuracy.

Computerized Decision Support Systems for Mechanical Ventilation in Children

“…4 There is a pressing need for further technological development and for rigorous large scale studies of open-and closed-loop mechanical ventilation CDSS in pediatrics. 13,56,68 Differences between adult and pediatric ICU practices, such as higher reliance in the PICU on noninvasive but continuous blood gas estimates (e.g., SpO 2 ), 1,48 highlight the need for pediatric-specific CDSS tools rather than direct adoption of adult ICU tools.…”

“…For example, pediatric intensivists more often monitor SpO 2 over PaO 2 . 1,48 In the absence of arterial blood gas data, other parameters also need to be estimated. There has been promising evidence using PetCO 2 over PaCO 2 as a surrogate for pH changes.…”

“…There has been promising evidence using PetCO 2 over PaCO 2 as a surrogate for pH changes. 48,49 Closed-Loop CDSS…”

Monitoring of Children With Pediatric Acute Respiratory Distress Syndrome

“…Strong agreement 6.3.3 Peripheral venous blood gas sampling is not recommended. Therefore, for patients with larger deadspace as expected in the acute phase of PARDS, endtidal Co 2 cannot be used as a reliable surrogate for arterial or capillary Co 2 until a correction method is validated (54). Strong agreement Rationale Regular analysis of arterial or capillary blood gas is important to assess PARDS severity and to adjust ventilator support.…”

Databases for Research in Pediatric Acute Respiratory Distress Syndrome

“…There have been countless examples of successful collaborations between intensivists, engineers, and computer scientists, which have resulted not only in interesting publications but in informatics-based solutions to critical care problems. [39][40][41][42][43][44][45] This has the potential to translate into smarter solutions for patient monitoring, predictive analytics to prevent complications or suggest therapies that may be beneficial for an individual patient, and personalized medicine approaches based simply on existing data. The analytic techniques are complicated given that most ICU data are inconsistently sampled, repeated time series analysis, which mandate specific mathematical techniques.…”