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:BackgroundThe ROX index (ratio of pulse oximetry/FIO2 to respiratory rate) has been validated to predict high flow nasal cannula therapy (HFNC) outcomes in patients with pneumonia. We evaluated a modified ROX index incorporating heart rate (HR) in patients initiated on HFNC for acute hypoxemic respiratory failure and as a preventative treatment following planned extubation.MethodsWe performed a prospective observational cohort study of 145 patients treated with HFNC. ROX-HR index was defined as the ratio of ROX index over HR (beats/min), multiplied by a factor of 100. Evaluation was performed using area under the receiving operating characteristic curve (AUROC) and cutoffs assessed for prediction of HFNC failure: defined as the need for mechanical ventilation.ResultsNinety-nine (68.3%) and 46 (31.7%) patients were initiated on HFNC for acute hypoxemic respiratory failure and following a planned extubation, respectively. The majority (86.9%) of patients had pneumonia as a primary diagnosis, and 85 (56.6%) patients were immunocompromised. Sixty-one (42.1%) patients required intubation (HFNC failure). Amongst patients on HFNC for acute respiratory failure, HFNC failure was associated with a lower ROX and ROX-HR index recorded at time points between 1 and 48 h. Within the first 12 h, both indices performed with the highest AUROC at 10 h as follows: 0.723 (95% CI 0.605-0.840) and 0.739 (95% CI 0.626-0.853) for the ROX and ROX-HR index respectively. A ROX-HR index of > 6.80 was significantly associated with a lower risk of HFNC failure (hazard ratio 0.301 (95% CI 0.143-0.663)) at 10 h. This association was also observed at 2, 6, 18, and 24h, even with correction for potential confounding factors. For HFNC initiated post-extubation, only the ROX-HR index remained significantly associated with HFNC failure at all recorded time points between 1 and 24 h. A ROX-HR > 8.00 at 10 h was significantly associated with a lower risk of HFNC failure (hazard ratio 0.176 (95% CI 0.051-0.604)).ConclusionWhile validation studies are required, the ROX-HR index appears to be a promising tool for early identification of treatment failure in patients initiated on HFNC for acute hypoxemic respiratory failure or as a preventative treatment after a planned extubation.

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