BackgroundThe triage of patients in prehospital care is a difficult task, and improved risk assessment tools are needed both at the dispatch center and on the ambulance to differentiate between low- and high-risk patients. This study validates a machine learning-based approach to generating risk scores based on hospital outcomes using routinely collected prehospital data.MethodsDispatch, ambulance, and hospital data were collected in one Swedish region from 2016–2017. Dispatch center and ambulance records were used to develop gradient boosting models predicting hospital admission, critical care (defined as admission to an intensive care unit or in-hospital mortality), and two-day mortality. Composite risk scores were generated based on the models and compared to National Early Warning Scores (NEWS) and actual dispatched priorities in a prospectively gathered dataset from 2018.ResultsA total of 38203 patients were included from 2016–2018. Concordance indexes (or areas under the receiver operating characteristics curve) for dispatched priorities ranged from 0.51–0.66, while those for NEWS ranged from 0.66–0.85. Concordance ranged from 0.70–0.79 for risk scores based only on dispatch data, and 0.79–0.89 for risk scores including ambulance data. Dispatch data-based risk scores consistently outperformed dispatched priorities in predicting hospital outcomes, while models including ambulance data also consistently outperformed NEWS. Model performance in the prospective test dataset was similar to that found using cross-validation, and calibration was comparable to that of NEWS.ConclusionsMachine learning-based risk scores outperformed a widely-used rule-based triage algorithm and human prioritization decisions in predicting hospital outcomes. Performance was robust in a prospectively gathered dataset, and scores demonstrated adequate calibration. Future research should explore the robustness of these methods when applied to other settings, establish appropriate outcome measures for use in determining the need for prehospital care, and investigate the clinical impact of interventions based on these methods.
Background: The triage of patients in pre-hospital care is a difficult task, and improved risk assessment tools are needed both at the dispatch center and on the ambulance to differentiate between low- and high-risk patients. This study develops and validates a machine learning-based approach to predicting hospital outcomes based on routinely collected prehospital data. Methods: Dispatch, ambulance, and hospital data were collected in one Swedish region from 2016 to 2017. Dispatch center and ambulance records were used to develop gradient boosting models predicting hospital admission, critical care (defined as admission to an intensive care unit or in-hospital mortality), and two-day mortality. Model predictions were used to generate composite risk scores which were compared to National Early Warning System (NEWS) scores and actual dispatched priorities in a similar but prospectively gathered dataset from 2018. Results: A total of 38203 patients were included from 2016-2018. Concordance indexes (or area under the receiver operating characteristics curve) for dispatched priorities ranged from 0.51 to 0.66, while those for NEWS scores ranged from 0.66 to 0.85. Concordance ranged from 0.71 to 0.80 for risk scores based only on dispatch data, and 0.79 to 0.89 for risk scores including ambulance data. Dispatch data-based risk scores consistently outperformed dispatched priorities in predicting hospital outcomes, while models including ambulance data also consistently outperformed NEWS scores. Model performance in the prospective test dataset was similar to that found using cross-validation, and calibration was comparable to that of NEWS scores.
Background: Trans-nasal evaporative cooling is an effective method to induce intra-arrest therapeutic hypothermia in out-of-hospital cardiac arrest (OHCA). The use of supraglottic airway devices (SGA) instead of endotracheal intubation may enable shorter time intervals to induce cooling. We aimed to study the outcomes in OHCA patients receiving endotracheal intubation (ETI) or a SGA during intra-arrest trans-nasal evaporative cooling. Methods: This is a pre-specified sub-study of the PRINCESS trial (NCT01400373) that included witnessed OHCA patients randomized during resuscitation to trans-nasal intra-arrest cooling vs. standard care followed by temperature control at 33 °C for 24 h. For this study, patients randomized to intra-arrest cooling were stratified according to the use of ETI vs. SGA prior to the induction of cooling. SGA was placed by paramedics in the first-tier ambulance or by physicians or anesthetic nurses in the second tier while ETI was performed only after the arrival of the second tier. Propensity score matching was used to adjust for differences at the baseline between the two groups. The primary outcome was survival with good neurological outcome, defined as cerebral performance category (CPC) 1–2 at 90 days. Secondary outcomes included time to place airway, overall survival at 90 days, survival with complete neurologic recovery (CPC 1) at 90 days and sustained return of spontaneous circulation (ROSC). Results: Of the 343 patients randomized to the intervention arm (median age 64 years, 24% were women), 328 received intra-arrest cooling and had data on the airway method (n = 259 with ETI vs. n = 69 with SGA). Median time from the arrival of the first-tier ambulance to successful airway management was 8 min for ETI performed by second tier and 4 min for SGA performed by the first or second tier (p = 0.001). No significant differences in the probability of good neurological outcome (OR 1.43, 95% CI 0.64–3.01), overall survival (OR 1.26, 95% CI 0.57–2.55), full neurological recovery (OR 1.17, 95% CI 0.52–2.73) or sustained ROSC (OR 0.88, 95% CI 0.50–1.52) were observed between ETI and SGA. Conclusions: Among the OHCA patients treated with trans-nasal evaporative intra-arrest cooling, the use of SGA was associated with a significantly shorter time to airway management and with similar outcomes compared to ETI.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.