Dataset Information

Development and Validation of a Simplified Prehospital Triage Model Using Neural Network to Predict Mortality in Trauma Patients: The Ability to Follow Commands, Age, Pulse Rate, Systolic Blood Pressure and Peripheral Oxygen Saturation (CAPSO) Model.

ABSTRACT: Objective: Most trauma scoring systems with high accuracy are difficult to use quickly in field triage, especially in the case of mass casualty events. We aimed to develop a machine learning model for trauma mortality prediction using variables easy to obtain in the prehospital setting. Methods: This was a retrospective prognostic study using the National Trauma Data Bank (NTDB). Data from 2013 to 2016 were used for model training and internal testing, and data from 2017 were used for validation. A neural network model (NN-CAPSO) was developed using the ability to follow commands (whether GCS-motor was <6), age, pulse rate, systolic blood pressure (SBP) and peripheral oxygen saturation, and a new score (the CAPSO score) was developed based on logistic regression. To achieve further simplification, a neural network model with the SBP variable removed (NN-CAPO) was also developed. The discrimination ability of different models and scores was compared based on the area under the receiver operating characteristic curve (AUROC). Furthermore, a reclassification table with three defined risk groups was used to compare NN-CAPSO and other models or scores. Results: The NN-CAPSO had an AUROC of 0.911(95% confidence interval 0.909 to 0.913) in the validation set, which was higher than the other trauma scores available for prehospital settings (all p < 0.001). The NN-CAPO and CAPSO score both reached the AUROC of 0.904 (95% confidence interval 0.902 to 0.906), and were no worse than other prehospital trauma scores. Compared with the NN-CAPO, CAPSO score, and the other trauma scores in reclassification tables, NN-CAPSO was found to more accurately classify patients to the right risk groups. Conclusions: The newly developed CAPSO system simplifies the method of consciousness assessment and has the potential to accurately predict trauma patient mortality in the prehospital setting.

SUBMITTER: Li Y

PROVIDER: S-EPMC8709125 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Importance:Prehospital trauma triage protocols are used worldwide to get the right patient to the right hospital and thereby improve the chance of survival and avert lifelong disabilities. The American College of Surgeons Committee on Trauma set target levels for undertriage rates of less than 5%. None of the existing triage protocols has been able to achieve this target in isolation. Objective:To develop and validate a new prehospital trauma triage protocol to improve current triage rates. Design, Setting, and Participants:In this multicenter cohort study, all patients with trauma who were 16 years and older and transported to a trauma center in 2 different regions of the Netherlands were included in the analysis. Data were collected from January 1, 2012, through June 30, 2014, in the Central Netherlands region for the design data cohort and from January 1 through December 31, 2015, in the Brabant region for the validation cohort. Data were analyzed from May 3, 2017, through July 19, 2018. Main Outcomes and Measures:A new prediction model was developed in the Central Netherlands region based on prehospital predictors associated with severe injury. Severe injury was defined as an Injury Severity Score greater than 15. A full-model strategy with penalized maximum likelihood estimation was used to construct a model with 8 predictors that were chosen based on clinical reasoning. Accuracy of the developed prediction model was assessed in terms of discrimination and calibration. The model was externally validated in the Brabant region. Results:Using data from 4950 patients with trauma from the Central Netherlands region for the design data set (58.3% male; mean [SD] age, 47 [21] years) and 6859 patients for the validation Brabant region (52.2% male; mean [SD] age, 51 [22] years), the following 8 significant predictors were selected for the prediction model: age; systolic blood pressure; Glasgow Coma Scale score; mechanism criteria; penetrating injury to the head, thorax, or abdomen; signs and/or symptoms of head or neck injury; expected injury in the Abbreviated Injury Scale thorax region; and expected injury in 2 or more Abbreviated Injury Scale regions. The prediction model showed a C statistic of 0.823 (95% CI, 0.813-0.832) and good calibration. The cutoff point with a minimum specificity of 50.0% (95% CI, 49.3%-50.7%) led to a sensitivity of 88.8% (95% CI, 87.5%-90.0%). External validation showed a C statistic of 0.831 (95% CI, 0.814-0.848) and adequate calibration. Conclusions and Relevance:The new prehospital trauma triage prediction model may lower undertriage rates to approximately 10% with an overtriage rate of 50%. The next step should be to implement this prediction model with the use of a mobile app for emergency medical services professionals.

Project description:ObjectiveOur aim was to develop a risk stratification model to predict the presence of a potentially more sinister injury in patients exposed to a whiplash trauma.MethodsThe study base comprised of 3,115 residents who first sought healthcare contact within one week after being exposed to a whiplash trauma between 1999-2008, from within a defined geographical area, Skaraborg County in south-western Sweden. Information about gender, age, time elapsed prior to seeking care, type of health care contact, and hospitalisation was retrieved. Seventeen potential risk factors were identified and evaluated using multivariable logistic regression.ResultsOf 3,115 patients, 215 (6.9%) required hospital admission so theoretically 93% could have been initially assessed by primary health care. However, only 46% had their first contact in primary health care. All patients had symptoms resulting in a diagnosis of whiplash injury. Four risk factors were found to be associated with hospital admission: commotio cerebri (OR 31, 19-51), fracture / luxation (OR 11, 5.1-22), serious injury (OR 41, 8.0-210), and the patient sought care during the same day as the trauma (OR 5.9, 3.7-9.5). These four risk factors explained 27% of the variation for hospital admission and the area under curve (AUC) was 0.77 (0.74-0.80). Ninety-six percent of patients (2,985) had only a whiplash injury with no other injury. These could be split into those attending health care the same day as the trauma, 1,737 (56%) with a 7.1% risk for hospital admission, and those attending health care later, 1,248 (40%) with a 1.3% risk for hospital admission.ConclusionPatients with no signs of commotio cerebri, no fracture/luxation injury, no serious injury, comprising 96% of all patients exposed to a whiplash trauma can initially be referred to primary health care for initial assessment. However, those contacting the health care the same day as the trauma should be referred to a hospital for evaluation if they can't get an appointment with a general practitioner the same day.

Project description:Background and Purpose- We used a decision analysis approach to analyze triage strategies for patients with acute stroke symptoms while accounting for prehospital large vessel occlusion (LVO) screening methods and key time metrics. Methods- Our decision analysis compared anticipated functional outcomes for patients within the IV-tPA (intravenous tissue-type plasminogen activator) treatment window in the mothership and drip-and-ship frameworks. Key branches of the model included IV-tPA eligibility, presence of an LVO, and endovascular therapy eligibility. Our decision analysis evaluated 2 prehospital LVO screening approaches: (1) no formal screening and (2) the use of clinical LVO screening scales. An excellent outcome was defined as modified Rankin Scale scores 0-1. Probabilities and workflow times were guideline-based or imputed from published studies. In sensitivity analyses, we individually and jointly varied transport time to the nearest primary stroke center, additional time required to transport directly to a comprehensive stroke center, and LVO screening scale predictive probabilities. We evaluated 2 separate scenarios: one in which ideal time metrics were achieved and one under current real-world metrics. Results- In the ideal metrics scenario, the drip-and-ship strategy was almost always favored in the absence of formal LVO screening. For patients screened positive for an LVO, mothership was favored if the additional transport time to the comprehensive stroke center was <3 to 23 minutes. Under real-world conditions, in which primary stroke center workflow is slower than ideal, the mothership strategy was favored in more scenarios, regardless of formal LVO screening. For example, mothership was favored with an additional transport time to the comprehensive stroke center of <32 to 99 minutes for patients screened positive for an LVO and <28 to 39 minutes in the absence of screening. Conclusions- Joint consideration of LVO probability, screening, workflow times, and transport times may improve prehospital stroke triage. Drip-and-ship was more favorable when more ideal primary stroke center workflow times were modeled.

Project description:BackgroundTriage is a critical component of prehospital emergency care. Effective triage of patients allows them to receive appropriate care and to judiciously use personnel and hospital resources. In many low-resource settings prehospital triage serves an additional role of determining the level of destination facility. In South Africa, the Western Cape Government innovatively implemented the South African Triage Scale (SATS) in the public Emergency Medical Services (EMS) service in 2012. The prehospital provider perspectives and experiences of using SATS in the field have not been previously studied.MethodsIn this qualitative study, focus group discussions with cohorts of basic, intermediate and advanced life support prehospital providers were conducted and transcribed. A content analysis using an inductive approach was used to code transcripts and identify themes.Results15 EMS providers participated in three focus group discussions. Data saturation was reached and four major themes emerged from the qualitative analysis: Implementation and use of SATS; Effectiveness of SATS; Limitations of the discriminator; and Special EMS considerations. Participants overall felt that SATS was easy to use and allowed improved communication with hospital providers during patient handover. Participants, however, described many clinical cases when their clinical gestalt triaged the patient to a different clinical acuity than generated by SATS. Additionally, they stated many clinical discriminators were too subjective to effectively apply or covered too broad a range of clinical severity (e.g., ingestions). Participants provided examples of how the prehospital environment presents additional challenges to using SATS such as changing patient clinical conditions, transport times and social needs of patients.ConclusionsOverall, participants felt that SATS was an effective tool in prehospital emergency care. However, they described many clinical scenarios where SATS was in conflict with their own assessment, the clinical care needs of the patient or the available prehospital and hospital resources. Many of the identified challenges to using SATS in the prehospital environment could be improved with small changes to SATS and provider re-training.

Project description:BackgroundThe Air Medical Prehospital Triage (AMPT) score was developed to identify injured patients who may benefit from scene helicopter emergency medical services (HEMS) transport. External validation using a different data set is essential to ensure reliable performance. The study objective was to validate the effectiveness of the AMPT score to identify patients with a survival benefit from HEMS using the Pennsylvania Trauma Outcomes Study registry.MethodsPatients 16 years or older undergoing scene HEMS or ground EMS (GEMS) transport in the Pennsylvania Trauma Outcomes Study registry 2000-2013 were included. Patients with 2 or higher AMPT score points were triaged to HEMS, while those with less than 2 points were triaged to GEMS. Multilevel Poisson regression determined the association of survival with actual transport mode across AMPT score triage assignments, adjusting for demographics, mechanism, vital signs, interventions, and injury severity. Successful validation was defined as no survival benefit for actual HEMS transport in patients triaged to GEMS by the AMPT score, with a survival benefit for actual HEMS transport in patients triaged to HEMS by the AMPT score. Subgroup analyses were performed in patients treated by advanced life support providers and patients with transport times longer than 10 minutes.ResultsThere were 222,827 patients included. For patients triaged to GEMS by the AMPT score, actual transport mode was not associated with survival (adjusted relative risk, 1.004; 95% confidence interval, 0.999-1.009; p = 0.08). For patients triaged to HEMS by the AMPT score, actual HEMS transport was associated with a 6.7% increase in the relative probability of survival (adjusted relative risk, 1.067; 95% confidence interval, 1.040-1.083, p < 0.001). Similar results were seen in all subgroups.ConclusionsThis study is the first to externally validate the AMPT score, demonstrating the ability of this tool to reliably identify trauma patients most likely to benefit from HEMS transport. The AMPT score should be considered when protocols for HEMS scene transport are developed and reviewed.Level of evidenceEpidemiologic/prognostic study, level III; therapeutic/care management study, level IV.

Project description:Background and Purpose- Prehospital routing algorithms for patients with suspected stroke because of large vessel occlusions should account for likelihood of benefit from endovascular therapy (EVT), risk of alteplase delays, and transport times. We built a mathematical model to give a real-time, location-based optimal emergency medical service routing location based on local resources, transport times, and patient characteristics. Methods- Using location, onset time, age, sex, and prehospital stroke severity, we calculated odds of a favorable outcome for a patient with suspected large vessel occlusions under 2 scenarios: direct to EVT-capable hospital versus transport to the nearest alteplase-capable hospital with transfer to EVT-capable hospital if appropriate. We project lifetime outcomes incorporating disability, quality of life utility, and cost. Multiple parameter sets of center-specific times (eg, door to alteplase) were randomly selected within a clinically plausible range to account for the model sensitivity to these estimates; for each iteration, the optimal strategy was defined as the most cost-effective outcome (threshold, $100?000 per quality-adjusted life-years gained). After 1000 simulations, the most frequently occurring optimal strategy was the final recommendation, with its strength measured as the proportion of runs for which it was optimal. Results- Routing recommendations were highly sensitive to small changes in model input parameters. Under many scenarios, the recommendations for direct transfer to the EVT site increased with increasing stroke severity and geographic proximity but did not vary substantially with respect to sex, age, or onset time. Conclusions- We present a mathematical decision model that determines ideal prehospital routing recommendations for patients with suspected stroke because of large vessel occlusions, with consideration of patient characteristics and location at onset. This model may be further refined by incorporating real-time data on traffic patterns and actual EVT and alteplase timeliness performance. Further studies are needed to verify model predictions.

Dataset Information

Development and Validation of a Simplified Prehospital Triage Model Using Neural Network to Predict Mortality in Trauma Patients: The Ability to Follow Commands, Age, Pulse Rate, Systolic Blood Pressure and Peripheral Oxygen Saturation (CAPSO) Model.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets