Gleaning data from disaster: a hospital-based data mining method to study all-hazard triage after a chemical disaster

Application of artificial intelligence in triage in emergencies and disasters: a systematic review

INTRODUCTION AND OBJECTIVE

Modern and intelligent triage systems are used today due to the growing trend of disasters and emergencies worldwide and the increase in the number of injured people facing the challenge of using traditional triage methods. The main objective of this study is to investigate the application of artificial intelligence and Technology in the triage of patients injured by disasters and emergencies and the challenges of the implementation of intelligent triage systems.

METHOD

The present study is a systematic review and follows PRISMA guidelines. The protocol of this study was registered in PROSPERO with the code CRD42023471415. To find relevant studies, the databases PubMed, Scopus and Web of Science (ISI) were searched without a time limit until September 2024. The scientific search engine Google Scholar and the references of the final articles were read manually for the final review.

RESULTS

The search identified 2,630 articles, narrowing down to 19 high-quality studies on AI in triage, which improved patient care through optimized resource management and real-time data transmission. AI algorithms like OpenPose and YOLO enhanced efficiency in mass casualty incidents, while e-triage systems allowed for continuous vital sign monitoring and faster triaging. AI tools demonstrated high accuracy in diagnosing COVID-19 (94.57%). Implementing intelligent triage systems faced challenges such as trust issues, training needs, equipment shortages, and data privacy concerns.

CONCLUSION

Developing assessment systems using artificial intelligence enables timely treatment and better resuscitation services for people injured in disasters. For future studies, we recommend designing intelligent triage systems to remove the obstacles in triaging children and disabled people in disasters.

Strengthening emergency department response to chemical, biological, radiological, and nuclear disasters: A scoping review

INTRODUCTION

Natural hazards resulting in disasters are increasing globally, impacting communities and disrupting industries. In addition to planning for these natural hazard disasters, emergency departments (EDs) should prepare for chemical, biological, radiological, and nuclear (CBRN) incidents that result in surges of patient presentations. Chemical, biological, radiological, and nuclear incidents differ in preparedness to natural hazards, requiring an understanding of patient management and health system-related challenges.

METHODS

This scoping review used the Arksey and O'Malley five-step framework. Manuscripts were retrieved from four databases and search engines using keywords relating to impacts on the ED from real world CBRN event(s). Analysis focused on the characteristics of CBRN event, ED impact, and lessons learnt against four surge capacity domains that including staff, stuff, space, and systems.

RESULTS

A total of 44 paper were included in this review. Most of the incidents were chemical in nature (n = 36/44, 81.8 %). The majority of CBRN incidents were accidental (n = 34/44, 77.3 %). Between 1 and 1470 people (Mdn=56, IQR: 18-228) presented to an ED from each event. Most patients were discharged from the ED, but this was variably reported. Some key lessons related to secondary exposure to ED staff, repurposing spaces, and coordination of CBRN incidents.

CONCLUSION

With the increasing number of CBRN incidents, strategies to strengthen EDs and limit the impact from a surge in patient presentations are paramount. An understanding of local CBRN risk to inform a top-hazards approach to CBRN preparedness, and the implementation of pre-emptive CBRN clinical pathways is recommended. Additionally, strategies should be implemented to protect staff from the risk of secondary exposure to a CBRN event. These strategies may include adequate education, training, and personal protective equipment for staff.

Lessons learned from reviewing a hospital's disaster response to the hydrofluoric acid leak in Gumi city in 2012

Background

This study analyzed the characteristics of hydrogen fluoride-exposed patients (HFEPs) treated in the emergency department (ED) of a local university hospital, and reviewed the hospital’s disaster response according to space, staff, supplies, and systems (4Ss).

Methods

This retrospective observational chart review and descriptive study included 199 HFEPs among 2588 total ED patients who visited a local university emergency medical center for treatment between September 27, 2012 and October 20, 2012, following a hydrofluoric acid leak at the Hube Globe factory in Gumi City, Republic of Korea. Descriptive results concerning the 4Ss were obtained by interviewing ED specialist staff physicians on duty during the study period. In accordance with American Burn Association criteria, patients requiring burn center referral were assigned to the major burn group (MBG) as severe condition.

Results

During the acute phase (within 8 h after leak initiation), there were 43 patients in the ED, which was staffed with 3 doctors and 3 nurses, without 4S resources. Of these 43 patients, there were 8 HFEPs (100%) in the MBG and 0 in the non-MBG (NMBG). During the subacute phase (24 h after the acute phase), there were 262 patients in the ED including 167 HFEPs, of whom 45 (26.95%) were in the MBG and 122 (73.05%) were in the NMBG. The ED was then staffed with 6 doctors (3 on day shift and 3 on night shift) and 10 nurses (3 on day shift, 4 on evening shift, and 3 on night shift), and no 4S resources were available. Throughout the study period, no 4Ss were available. First, there was no expansion of ED space or secured disaster reserve beds. Second, there was no increase in manpower with duty time adjustments or duty relocation for ED working personnel. Third, there was no logistics reinforcement (e.g., antidote or personal protective equipment). Fourth, there were no disaster-related measures for the administration department, decontamination zone setup, safety diagnostic testing, or designated disaster triage implementation.

Conclusions

The hospital’s disaster response was insufficient for all aspects of the 4Ss. Detailed guidance concerning a hospital disaster management plan is required.

Validation of a novel irritant gas syndrome triage algorithm

OBJECTIVE

Our objective was to validate a novel irritant gas syndrome agent (IGSA) triage algorithm for use in an emergency department (ED). We assessed efficiency, accuracy, and precision of our IGSA triage algorithm based on signs/symptoms of actual patients.

DESIGN

After characterizing the signs/symptoms of an actual IGSA exposure event, we developed and validated the IGSA triage algorithm using a simulated computer exercise to compare the IGSA triage algorithm to the preferred hospital triage algorithm, the Emergency Severity Index (ESI).

SETTING

This study was a simulated computer exercise using surveys developed in Research Electronic Data Capture software. Nurse volunteers simulated triaging 298 patients.

PARTICIPANTS

Patient data included 146 patients treated during the disaster as well as 152 unexposed patients. Twenty-six nurse volunteers were assigned to triage the patients using one of the algorithms in the simulated computer exercise.

MAIN OUTCOME MEASURE(S)

The precision of the IGSA triage algorithm was 0.82 (confidence interval [CI] 0.78-0.85) and ESI 0.73 (CI 0.69-0.77). Weighted κ for ESI and IGSA accuracy for exposed patients was 0.32 (95% CI 0.26-0.37) and 0.81 (95% CI 0.77-0.85), respectively.

RESULTS

The IGSA triage algorithm was more accurate and precise than the ESI algorithm for triaging patients exposed to an irritant gas.

CONCLUSIONS

This study validates the IGSA triage algorithm as the basis for the development of a prototype software application to quickly identify victims of a chemical disaster and triage patients efficiently and accurately with the potential to dramatically improve the processing of patients in EDs.

Data Capture and Analysis of Signs and Symptoms in a Chemically Exposed Population

This manuscript provides a practical case study to demonstrate data collection from paper-based medical records so that the occurrence of specific signs/symptoms indicative of a chemical exposure can be studied.

Exposure of neonatal mice to bromine impairs their alveolar development and lung function

The halogen bromine (Br₂) is used extensively in industry and stored and transported in large quantities. Its accidental or malicious release into the atmosphere has resulted in significant casualties. The pathophysiology of Br₂-induced lung injury has been studied in adult animals, but the consequences of Br₂ exposure to the developing lung are completely unknown. We exposed neonatal mouse littermates on postnatal day 3 (P3) to either Br₂ at 400 ppm for 30 min (400/30), to Br₂ at 600 ppm for 30 min (600/30), or to room air, then returned them to their dams and observed until P14. Mice exposed to Br₂ had decreased survival (S) and had decreased weight (W) at P14 in the 400/30 group (S = 63.5%, W = 6.67 ± 0.08) and in the 600/30 group (S = 36.1%, W = 5.13 ± 0.67) as compared with air breathing mice (S = 100%, W = 7.96 ± 0.30). Alveolar development was impaired, as evidenced by increased mean linear intercept at P14. At P14, Br₂ exposed mice also exhibited a decrease of arterial partial pressure of oxygen, decreased quasi-static lung compliance, as well as increased alpha smooth muscle actin mRNA and protein and increased mRNA for IL-1β, IL-6, CXCL1, and TNFα. Global gene expression, evaluated by RNA sequencing and Ingenuity Pathway Analysis, revealed persistent abnormalities in gene expression profiles at P14 involving pathways of "formation of lung" and "pulmonary development." The data indicate that Br₂ inhalation injury early in life results in severe lung developmental consequences, wherein persistent inflammation and global altered developmental gene expression are likely mechanistic contributors.

Clinical Data Reuse or Secondary Use: Current Status and Potential Future Progress

Objective: To perform a review of recent research in clinical data reuse or secondary use, and envision future advances in this field. Methods: The review is based on a large literature search in MEDLINE (through PubMed), conference proceedings, and the ACM Digital Library, focusing only on research published between 2005 and early 2016. Each selected publication was reviewed by the authors, and a structured analysis and summarization of its content was developed. Results: The initial search produced 359 publications, reduced after a manual examination of abstracts and full publications. The following aspects of clinical data reuse are discussed: motivations and challenges, privacy and ethical concerns, data integration and interoperability, data models and terminologies, unstructured data reuse, structured data mining, clinical practice and research integration, and examples of clinical data reuse (quality measurement and learning healthcare systems). Conclusion: Reuse of clinical data is a fast-growing field recognized as essential to realize the potentials for high quality healthcare, improved healthcare management, reduced healthcare costs, population health management, and effective clinical research.

The Necessity of Data Mining in Clinical Emergency Medicine; A Narrative Review of the Current Literatrue

Clinical databases can be categorized as big data, include large quantities of information about patients and their medical conditions. Analyzing the quantitative and qualitative clinical data in addition with discovering relationships among huge number of samples using data mining techniques could unveil hidden medical knowledge in terms of correlation and association of apparently independent variables. The aim of this research is using predictive algorithm for prediction of trauma patients on admission to hospital to be able to predict the necessary treatment for patients and provided the necessary measures for the trauma patients who are before entering the critical situation. This study provides a review on data mining in clinical medicine. The relevant, recently-published studies of data mining on medical data with a focus on emergency medicine were investigated to tackle pros and cons of such approaches. The results of this study can be used in prediction of trauma patient’s status at six hours after admission to hospital.

Validating Signs and Symptoms From An Actual Mass Casualty Incident to Characterize An Irritant Gas Syndrome Agent (IGSA) Exposure: A First Step in The Development of a Novel IGSA Triage Algorithm

CONTRIBUTION TO EMERGENCY NURSING PRACTICE

• Chemical exposures daily pose a significant threat to life. Rapid assessment by first responders/emergency nurses is required to reduce death and disability. Currently, no informatics tools for Irritant Gas Syndrome Agents (IGSA) exposures exist to process victims efficiently, continuously monitor for latent signs/symptoms, or make triage recommendations. • This study uses actual patient data from a chemical incident to characterize and validate signs/symptoms of an IGSA Syndrome. Validating signs/symptoms is the first step in developing new emergency department informatics tools with the potential to revolutionize the process by which emergency nurses manage triage victims of chemical incidents.

ABSTRACTINTRODUCTION

Chemical exposures can pose a significant threat to life. Rapid assessment by first responders/emergency nurses is required to reduce death and disability. Currently, no informatics tools for irritant gas syndrome agents (IGSA) exposures exist to process victims efficiently, continuously monitor for latent signs/symptoms, or make triage recommendations. This study describes the first step in developing ED informatics tools for chemical incidents: validation of signs/symptoms that characterize an IGSA syndrome.

METHODS

Data abstracted from 146 patients treated for chlorine exposure in one emergency department during a 2005 train derailment and 152 patients not exposed to chlorine (a comparison group) were mapped to 93 possible signs/symptoms within 2 tools (WISER and CHEMM-IST) designed to assist emergency responders/emergency nurses with managing hazardous material exposures. Inferential statistics (χ²/Fisher's exact test) and diagnostics tests were used to examine mapped signs/symptoms of persons who were and were not exposed to chlorine.

RESULTS

Three clusters of signs/symptoms are statistically associated with an IGSA syndrome (P < .01): respiratory (shortness of breath, wheezing, coughing, and choking); chest discomfort (tightness, pain, and burning), and eye, nose and/or throat (pain, irritation, and burning). The syndrome requires the presence of signs/symptoms from at least 2 of these clusters. The latency period must also be considered for exposed/potentially exposed persons.

DISCUSSION

This study uses actual patient data from a chemical incident to characterize and validate signs/symptoms of an IGSA syndrome. Validating signs/symptoms is the first step in developing new ED informatics tools with the potential to revolutionize the process by which emergency nurses manage triage victims of chemical incidents.

A validation study of 5 triage systems using data from the 2005 Graniteville, South Carolina, chlorine spill

INTRODUCTION

Lack of outcomes-based research results in uncertainty about the effectiveness of any of the current triage systems in determining priority of care during actual chemical disasters. The purpose of this study was to determine whether the level of injury severity extrapolated from 5 triage systems correlated with actual injury severity outcomes of victims exposed to a chlorine disaster.

METHODS

Using secondary data analysis, data for 631 victims were merged, de-identified, and analyzed. Using logic models from the triage systems, the actual injury severity was compared with the extrapolated injury severity classifications.

RESULTS

Analysis showed weak to modest correlations between the extrapolated injury severity triage outcome classifications and the actual injury severity outcomes (Spearman correlation range 0.38 to 0.71, P < .0001). There was slight to fair agreement between the extrapolated injury severity triage outcome classifications and the actual injury severity outcomes (weighted κ = - 0.23 to 0.42).

DISCUSSION

The extrapolated injury severity triage outcome categories from the 5 triage systems did not agree with the actual injury severity categories. Oxygen saturation measured by pulse oximetry provides early indications and is very predictive of outcome severity in incidents involving irritant chemical exposures such as chlorine, and should be a part of a mass casualty protocol for any irritant chemical incident. Additional research is needed to identify the most sensitive clinical measures for triaging victims of toxic inhalation disasters.