The Impact of Under-triage on Trauma Outcomes in Older Populations ≥65 Years

Knotts, Chelsea; Modarresi, Milad; Samanta, Damayanti; Richmond, Bryan K.

doi:10.1177/0003134820951456

Cited by 7 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Permutation-based variable importance showed that age and comorbidities (including hypertension, diabetes mellitus, cerebral infarction, and dementia) contribute to undertriage, which is consistent with the results of previous studies [ 27 , 28 ]. In addition, some chief complaint categories are highly crucial for undertriage.…”

Section: Discussionsupporting

confidence: 90%

Machine learning models predicting undertriage in telephone triage

et al. 2022

View full text Add to dashboard Cite

Background Undertriaged patients have worse outcomes than appropriately triaged patients. Machine learning provides better triage prediction than conventional triage in emergency departments, but no machine learning-based undertriage prediction models have yet been developed for prehospital telephone triage. We developed and validated machine learning models for telephone triage. Materials and methods We conducted a retrospective cohort study with the largest after-hour house-call (AHHC) service dataset in Japan. Participants were ≥16 years and used the AHHC service between 1 November 2018 and 31 January 2021. We developed five prediction models based on support vector machine (SVM), lasso regression (LR), random forest (RF), gradient-boosted decision tree (XGB), and deep neural network (DNN). The primary outcome was undertriage, and predictors were telephone triage level and routinely available telephone-based data, including age, sex, 80 chief complaint categories and 10 comorbidities. We measured the area under the receiver operating characteristic curve (AUROC) for all the models. Results We identified 15,442 eligible patients (age: 38.4 ± 16.6, male: 57.2%), including 298 (1.9%; age: 58.2 ± 23.9, male: 55.0%) undertriaged patients. RF and XGB outperformed the other models, with the AUROC values (95% confidence interval; 95% CI) of the SVM, LR, RF, XGB and DNN for undertriage being 0.62 (0.55–0.69), 0.79 (0.74–0.83), 0.81 (0.76–0.86), 0.80 (0.75–0.84) and 0.77 (0.73–0.82), respectively. Conclusions We found that RF and XGB outperformed other models. Our findings suggest that machine learning models can facilitate the early detection of undertriage and early intervention to yield substantially improved patient outcomes. KEY MESSAGES Undertriaged patients experience worse outcomes than appropriately triaged patients; thus, we developed machine learning models for predicting undertriage in the prehospital setting. In addition, we identified the predictors of risk factors associated with undertriage. Random forest and gradient-boosted decision tree models demonstrated better prediction performance, and the models identified the risk factors associated with undertriage. Machine learning models aid in the early detection of undertriage, leading to significantly improved patient outcomes and identifying undertriage-associated risk factors, including chief complaint categories, could help prioritize conventional telephone triage protocol revision.

show abstract

Section: Discussionsupporting

confidence: 90%

Machine learning models predicting undertriage in telephone triage

et al. 2022

View full text Add to dashboard Cite

show abstract

“…We found that old age, diabetes mellitus, dementia, and a history of cerebral infarction were associated with undertriage. A previous study conducted at a trauma center showed that age ≥ 65 years [ 19 ], female sex, dementia [ 20 ], history of cerebral infarction, and heart failure [ 21 ] were risk factors for undertriage of trauma patients. Among these risk factors for undertriage of trauma patients, old age, dementia, and history of stroke were also identified as risk factors in our study.…”

Section: Discussionmentioning

confidence: 99%

Factors associated with undertriage in patients classified by the need to visit a hospital by telephone triage: a retrospective cohort study

et al. 2021

View full text Add to dashboard Cite

Background Prehospital telephone triage stratifies patients into five categories, “need immediate hospital visit by ambulance,” “need to visit a hospital within 1 hour,” “need to visit a hospital within 6 hours,” “need to visit a hospital within 24 hours,” and “do not need a hospital visit” in Japan. However, studies on whether present and past histories cause undertriage are limited in patients triaged as need an early hospital visit. We investigated factors associated with undertriage by comparing patient assessed to be appropriately triaged with those assessed undertriaged. Methods We included all patients classified by telephone triage as need to visit a hospital within 1 h and 6 h who used a single after-hours house call (AHHC) medical service in Tokyo, Japan, between November 1, 2019, and November 31, 2020. After home consultation, AHHC doctors classified patients as grade 1 (treatable with over-the-counter medications), 2 (requires hospital or clinic visit), or 3 (requires ambulance transportation). Patients classified as grade 2 and 3 were defined as appropriately triaged and undertriaged, respectively. Results We identified 10,742 eligible patients triaged as need to visit a hospital within 1 h and 6 h, including 10,479 (97.6%) appropriately triaged and 263 (2.4%) undertriaged patients. Multivariable logistic regression analyses revealed patients aged 16–64, 65–74, and ≥ 75 years (adjusted odds ratio [OR], 2.40 [95% confidence interval {CI} 1.71–3.36], 8.57 [95% CI 4.83–15.2], and 14.9 [95% CI 9.65–23.0], respectively; reference patients aged < 15 years); those with diabetes mellitus (2.31 [95% CI 1.25–4.26]); those with dementia (2.32 [95% CI 1.05–5.10]); and those with a history of cerebral infarction (1.98 [95% CI 1.01–3.87]) as more likely to be undertriaged. Conclusions We found that older adults and patients with diabetes mellitus, dementia, or a history of cerebral infarction were at risk of undertriage in patients triaged as need to visit a hospital within 1 h and 6 h, but further studies are needed to validate these findings.

show abstract