Dataset Information

Predicting Flow Rate Escalation for Pediatric Patients on High Flow Nasal Cannula Using Machine Learning

ABSTRACT: Background: High flow nasal cannula (HFNC) is commonly used as non-invasive respiratory support in critically ill children. There are limited data to inform consensus on optimal device parameters, determinants of successful patient response, and indications for escalation of support. Clinical scores, such as the respiratory rate-oxygenation (ROX) index, have been described as a means to predict HFNC non-response, but are limited to evaluating for escalations to invasive mechanical ventilation (MV). In the presence of apparent HFNC non-response, a clinician may choose to increase the HFNC flow rate to hypothetically prevent further respiratory deterioration, transition to an alternative non-invasive interface, or intubation for MV. To date, no models have been assessed to predict subsequent escalations of HFNC flow rates after HFNC initiation. Objective: To evaluate the abilities of tree-based machine learning algorithms to predict HFNC flow rate escalations. Methods: We performed a retrospective, cohort study assessing children admitted for acute respiratory failure under 24 months of age placed on HFNC in the Johns Hopkins Children's Center pediatric intensive care unit from January 2019 through January 2020. We excluded encounters with gaps in recorded clinical data, encounters in which MV treatment occurred prior to HFNC, and cases electively intubated in the operating room. The primary study outcome was discriminatory capacity of generated machine learning algorithms to predict HFNC flow rate escalations as compared to each other and ROX indices using area under the receiver operating characteristic (AUROC) analyses. In an exploratory fashion, model feature importance rankings were assessed by comparing Shapley values. Results: Our gradient boosting model with a time window of 8 h and lead time of 1 h before HFNC flow rate escalation achieved an AUROC with a 95% confidence interval of 0.810 ± 0.003. In comparison, the ROX index achieved an AUROC of 0.525 ± 0.000. Conclusion: In this single-center, retrospective cohort study assessing children under 24 months of age receiving HFNC for acute respiratory failure, tree-based machine learning models outperformed the ROX index in predicting subsequent flow rate escalations. Further validation studies are needed to ensure generalizability for bedside application.

SUBMITTER: Krachman J

PROVIDER: S-EPMC8606666 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundHigh-flow nasal oxygen therapy (HFNC) may be an attractive first-line ventilatory support in COVID-19 patients. However, HNFC use for the management of COVID-19 patients and risk factors for HFNC failure remain to be determined.MethodsIn this retrospective study, we included all consecutive COVID-19 patients admitted to our intensive care unit (ICU) in the first (Mars-May 2020) and second (August 2020- February 202) French pandemic waves. Patients with limitations for intubation were excluded. HFNC failure was defined as the need for intubation after ICU admission. The impact of HFNC use was analyzed in the whole cohort and after constructing a propensity score. Risk factors for HNFC failure were identified through a landmark time-dependent cause-specific Cox model. The ability of the 6-h ROX index to detect HFNC failure was assessed by generating receiver operating characteristic (ROC) curve.Results200 patients were included: HFNC was used in 114(57%) patients, non-invasive ventilation in 25(12%) patients and 145(72%) patients were intubated with a median delay of 0 (0-2) days after ICU admission. Overall, 78(68%) patients had HFNC failure. Patients with HFNC failure had a higher ICU mortality rate (34 vs. 11%, p = 0.02) than those without. At landmark time of 48 and 72 h, SAPS-2 score, extent of CT-Scan abnormalities > 75% and HFNC duration (cause specific hazard ratio (CSH) = 0.11, 95% CI (0.04-0.28), per + 1 day, p < 0.001 at 48 h and CSH = 0.06, 95% CI (0.02-0.23), per + 1 day, p < 0.001 at 72 h) were associated with HFNC failure. The 6-h ROX index was lower in patients with HFNC failure but could not reliably predicted HFNC failure with an area under ROC curve of 0.65 (95% CI(0.52-0.78), p = 0.02). In the matched cohort, HFNC use was associated with a lower risk of intubation (CSH = 0.32, 95% CI (0.19-0.57), p < 0.001).ConclusionsIn critically-ill COVID-19 patients, while HFNC use as first-line ventilatory support was associated with a lower risk of intubation, more than half of patients had HFNC failure. Risk factors for HFNC failure were SAPS-2 score and extent of CT-Scan abnormalities > 75%. The risk of HFNC failure could not be predicted by the 6-h ROX index but decreased after a 48-h HFNC duration.

Dataset Information

Predicting Flow Rate Escalation for Pediatric Patients on High Flow Nasal Cannula Using Machine Learning

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets