Consciousness Detection on Injured Simulated Patients Using Manual and Automatic Classification via Visible and Infrared Imaging

In a disaster scene, triage is a key principle for effectively rescuing injured people according to severity level. One main parameter of the used triage algorithm is the patient’s consciousness. Unmanned aerial vehicles (UAV) have been investigated toward (semi-)automatic triage. In addition to vital parameters, such as heart and respiratory rate, UAVs should detect victims’ mobility and consciousness from the video data. This paper presents an algorithm combining deep learning with image processing techniques to detect human bodies for further (un)consciousness classification. The algorithm was tested in a 20-subject group in an outside environment with static (RGB and thermal) cameras where participants performed different limb movements in different body positions and angles between the cameras and the bodies’ longitudinal axis. The results verified that the algorithm performed better in RGB. For the most probable case of 0 degrees, RGB data obtained the following results: Mathews correlation coefficient (MMC) of 0.943, F1-score of 0.951, and precision-recall area under curve AUC (PRC) score of 0.968. For the thermal data, the MMC was 0.913, F1-score averaged 0.923, and AUC (PRC) was 0.960. Overall, the algorithm may be promising along with others for a complete contactless triage assessment in disaster events during day and night.

The SALT and START Triage System for Classifying Patient Acuity Level: A Systematic Review

Background: Two common triage systems have been widely used in mass casualty incidents (MCIs) and disaster situations, namely START (simple triage algorithm and rapid treatment) and SALT (sort, assess, lifesaving, intervention, and treatment/transport). There is currently controversy regarding the effectiveness of SALT over the START triage system.Purpose: This systematic review aims to compare the accuracy of the SALT and START triage systems in disaster and MCI settings.Methods: The literature was searched using a systematic search strategy for articles published from 2009 to 2020 in the Medline, CINAHL, Web of Science, Scopus, PubMed, ProQuest databases, and the grey literature. This review included simulation-based and medical record-based studies investigating the accuracy and applicability of the SALT and START triage systems in adult and child populations during MCIs and disasters. All types of studies were included. The PRISMA flowchart was used to retain the articles, and the Joanna Briggs Institute critical appraisal tools were used to assess the quality of the reviewed studies.Results: Of 1,450 articles identified in the search, 10 articles were included. It was found that the START triage system had a wide range and inconsistent levels of accuracy (44% to 94.2%) compared to the SALT triage system (70% to 83%). The under-triage error of the START triage system ranged from 2.73% to 20%, which was slightly lower than the SALT triage system (7.6% to 23.3%). The over-triage error of the START triage system (2% to 53%) was slightly higher than the SALT triage system (2% to 22%). However, the time taken to apply START triage system (70 to 72.18 seconds) was faster than for the SALT triage system (78 seconds).Conclusion: The START triage system was simpler and faster than SALT. Conversely, the SALT triage system appeared to be slightly more accurate, more consistent, and had a lower rate of under- and over-triage error than START. It appears that neither the SALT nor the START triage system is superior to the other. Further research is needed to establish the most appropriate disaster and MCI triage system, especially for the Indonesian context.

Development and validation of a practical machine-learning triage algorithm for the detection of patients in need of critical care in the emergency department

Identifying critically ill patients is a key challenge in emergency department (ED) triage. Mis-triage errors are still widespread in triage systems around the world. Here, we present a machine learning system (MLS) to assist ED triage officers better recognize critically ill patients and provide a text-based explanation of the MLS recommendation. To derive the MLS, an existing dataset of 22,272 patient encounters from 2012 to 2019 from our institution’s electronic emergency triage system (EETS) was used for algorithm training and validation. The area under the receiver operating characteristic curve (AUC) was 0.875 ± 0.006 (CI:95%) in retrospective dataset using fivefold cross validation, higher than that of reference model (0.843 ± 0.005 (CI:95%)). In the prospective cohort study, compared to the traditional triage system’s 1.2% mis-triage rate, the mis-triage rate in the MLS-assisted group was 0.9%. This MLS method with a real-time explanation for triage officers was able to lower the mis-triage rate of critically ill ED patients.

Development and validity of the Korea psychiatric triage algorithm

Background Psychiatric emergencies require timely intervention because of the risk of harm to individuals and society, including others. The aim of the present study was to test the content validity of a psychiatric triage algorithm developed for use in South Korea. Methods The initial algorithm was developed through systematic literature review. Its validity was then verified by 10 experts. Based on results of expert validity, the algorithm was modified and the final algorithm was developed. Results Its clinical validity was then verified by 37 emergency room nurses who had used triage. Four questions of expert validity results with a CVI of 0.8 or less were revised to reflect expert opinion. The usefulness, adequacy, and convenience of the final modified algorithm was 2.98 ~ 3.53. Conclusion After sufficiently validated by follow-up studies, it is expected that the use of psychiatric classification algorithms in emergency room nurses will not only improve the quality of care, but also can improve patient outcomes and experience.

Utility of the FebriDx point-of-care assay in supporting a triage algorithm for medical admissions with possible COVID-19: an observational cohort study

ObjectiveTo evaluate a triage algorithm used to identify and isolate patients with suspected COVID-19 among medical patients needing admission to hospital using simple clinical criteria and the FebriDx assay.DesignRetrospective observational cohort.SettingLarge acute National Health Service hospital in London, UK.ParticipantsAll medical admissions from the emergency department between 10 August 2020 and 4 November 2020 with a valid SARS-CoV-2 RT-PCR result.InterventionsMedical admissions were triaged as likely, possible or unlikely COVID-19 based on clinical criteria. Patients triaged as possible COVID-19 underwent FebriDx lateral flow assay on capillary blood, and those positive for myxovirus resistance protein A (a host response protein) were managed as likely COVID-19.Primary outcome measuresDiagnostic accuracy (sensitivity, specificity and predictive values) of the algorithm and the FebriDx assay using SARS-CoV-2 RT-PCR from nasopharyngeal swabs as the reference standard.Results4.0% (136) of 3443 medical admissions had RT-PCR confirmed COVID-19. Prevalence of COVID-19 was 46% (80/175) in those triaged as likely, 4.1% (50/1225) in possible and 0.3% (6/2033) in unlikely COVID-19. Using a SARS-CoV-2 RT-PCR reference standard, clinical triage had sensitivity of 96% (95% CI 91% to 98%) and specificity of 61.5% (95% CI 59.8% to 63.1%), while the triage algorithm including FebriDx had sensitivity of 93% (95% CI 87% to 96%) and specificity of 86.4% (95% CI 85.2% to 87.5%). While 2033 patients were deemed not to require isolation using clinical criteria alone, the addition of FebriDx to clinical triage allowed a further 826 patients to be released from isolation, reducing the need for isolation rooms by 9.5 per day, 95% CI 8.9 to 10.2. Ten patients missed by the algorithm had mild or asymptomatic COVID-19.ConclusionsA triage algorithm including the FebriDx assay had good sensitivity and was useful to ‘rule-out’ COVID-19 among medical admissions to hospital.

Development of a pediatric obstructive sleep apnea triage algorithm

Introduction Diagnosis and treatment of obstructive sleep apnea (OSA) in children is often delayed due to the high prevalence and limited physician and sleep testing resources. As a result, children may be referred to multiple specialties, such as pediatric sleep medicine and pediatric otolaryngology, resulting in long waitlists. Method We used data from our pediatric OSA clinic to identify predictors of tonsillectomy and/or adenoidectomy (AT). Before being seen in the clinic, parents completed the Pediatric Sleep Questionnaire (PSQ) and screening questionnaires for restless leg syndrome (RLS), nasal rhinitis, and gastroesophageal reflux disease (GERD). Tonsil size data were obtained from patient charts and graded using the Brodsky-five grade scale. Children completed an overnight oximetry study before being seen in the clinic, and a McGill oximetry score (MOS) was assigned based on the number and depth of oxygen desaturations. Logistic regression, controlling for otolaryngology physician, was used to identify significant predictors of AT. Three triage algorithms were subsequently generated based on the univariate and multivariate results to predict AT. Results From the OSA cohort, there were 469 eligible children (47% female, mean age = 8.19 years, SD = 3.59), with 89% of children reported snoring. Significant predictors of AT in univariate analysis included tonsil size and four PSQ questions, (1) struggles to breathe at night, (2) apneas, (3) daytime mouth breathing, and (4) AM dry mouth. The first triage algorithm, only using the four PSQ questions, had an odds ratio (OR) of 4.02 for predicting AT (sensitivity = 0.28, specificity = 0.91). Using only tonsil size, the second algorithm had an OR to predict AT of 9.11 (sensitivity = 0.72, specificity = 0.78). The third algorithm, where MOS was used to stratify risk for AT among those children with 2+ tonsils, had the same OR, sensitivity, and specificity as the tonsil-only algorithm. Conclusion Tonsil size was the strongest predictor of AT, while oximetry helped stratify individual risk for AT. We recommend that referral letters for snoring children include graded tonsil size to aid in the triage based on our findings. Children with 2+ tonsil sizes should be triaged to otolaryngology, while the remainder should be referred to a pediatric sleep specialist. Graphical abstract

Development of the Aerial Remote Triage System using drones in mass casualty scenarios: A survey of international experts

The use of drones for triage in mass-casualty incidents has recently emerged as a promising technology. However, there is no triage system specifically adapted to a remote usage. Our study aimed to develop a remote triage procedure using drones. The research was performed in three stages: literature review, the development of a remote triage algorithm using drones and evaluation of the algorithm by experts. Qualitative synthesis and the calculation of content validity ratios were done to achieve the Aerial Remote Triage System. This algorithm assesses (in this order): major bleeding, walking, consciousness and signs of life; and then classify the injured people into several priority categories: priority 1 (red), priority 2 (yellow), priority 3 (green) and priority * (violet). It includes the possibility to indicate save-living interventions to injured people and bystanders, like the compression of bleeding injuries or the adoption of the recovery position. The Aerial Remote Triage System may be a useful way to perform triage by drone in complex emergencies when it is difficult to access to the scene due to physical, chemical or biological risks.

Mental health assessment and triage in an ambulance clinical contact centre

Background: With increasing numbers of emergency calls to ambulance services, exploration of the triage and management of mental health calls is valuable, given their volume and duration. Studies have explored these calls from patient and practitioner perspectives, but few have considered the perspective of the practitioners assessing patients over the phone in terms of clinical capability. Aim: This study aimed to explore the thoughts, feelings and educational requirements of paramedics and nurses working on emergency medical services clinical desks, focusing on mental health-related calls and the triage tools used. Methods: A service evaluation was conducted. A questionnaire was developed and distributed to 41 staff on clinical desks at the Welsh Ambulance Service Trust's (WAST) clinical contact centres in June 2019. Quantitative data was analysed using descriptive statistics and qualitative data by thematic analysis. Findings: Out of the 41 employees, 26 (63%) responded. Low levels of confidence were reported in managing mental health calls, along with inadequate detail in the mental health elements of their triage algorithm and deficiencies in referral pathways. Conclusion: Given the volume and complexity of mental health calls to ambulance services, more attention should be paid to the education and training of clinical desk professionals and the decision support tools available in WAST and other ambulance services. Further research is required with a larger sample size over multiple ambulance services.