Assessing the precision of artificial intelligence in ED triage decisions: Insights from a study with ChatGPT.

BACKGROUND: The rise in emergency department presentations globally poses challenges for efficient patient management. To address this, various strategies aim to expedite patient management. Artificial intelligence's (AI) consistent performance and rapid data interpretation extend its healthcare applications, especially in emergencies. The introduction of a robust AI tool like ChatGPT, based on GPT-4 developed by OpenAI, can benefit patients and healthcare professionals by improving the speed and accuracy of resource allocation. This study examines ChatGPT's capability to predict triage outcomes based on local emergency department rules. METHODS: This study is a single-center prospective observational study. The study population consists of all patients who presented to the emergency department with any symptoms and agreed to participate. The study was conducted on three non-consecutive days for a total of 72 h. Patients' chief complaints, vital parameters, medical history and the area to which they were directed by the triage team in the emergency department were recorded. Concurrently, an emergency medicine physician inputted the same data into previously trained GPT-4, according to local rules. According to this data, the triage decisions made by GPT-4 were recorded. In the same process, an emergency medicine specialist determined where the patient should be directed based on the data collected, and this decision was considered the gold standard. Accuracy rates and reliability for directing patients to specific areas by the triage team and GPT-4 were evaluated using Cohen's kappa test. Furthermore, the accuracy of the patient triage process performed by the triage team and GPT-4 was assessed by receiver operating characteristic (ROC) analysis. Statistical analysis considered a value of p < 0.05 as significant. RESULTS: The study was carried out on 758 patients. Among the participants, 416 (54.9%) were male and 342 (45.1%) were female. Evaluating the primary endpoints of our study - the agreement between the decisions of the triage team, GPT-4 decisions in emergency department triage, and the gold standard - we observed almost perfect agreement both between the triage team and the gold standard and between GPT-4 and the gold standard (Cohen's Kappa 0.893 and 0.899, respectively; p < 0.001 for each). CONCLUSION: Our findings suggest GPT-4 possess outstanding predictive skills in triaging patients in an emergency setting. GPT-4 can serve as an effective tool to support the triage process.

Diagnostic accuracy of apple watch ECG outputs in identifying dysrhythmias: A comparison with 12-Lead ECG in emergency department.

BACKGROUND: Wearable devices, particularly smartwatches like the Apple Watch (AW), can record important cardiac information, such as single­lead electrocardiograms (ECGs). Although they are increasingly used to detect conditions such as atrial fibrillation (AF), research on their effectiveness in detecting a wider range of dysrhythmias and abnormal ECG findings remains limited. The primary objective of this study is to evaluate the accuracy of the AW in detecting various cardiac rhythms by comparing it with standard ECG's lead-I. METHODS: This single-center prospective observational study was conducted in a tertiary care emergency department (ED) between 1.10.2023 and 31.10.2023. The study population consisted of all patients assessed in the critical care areas of the ED, all of whom underwent standard 12­lead ECGs for various clinical reasons. Participants in the study were included consecutively. An AW was attached to patients' wrists and an ECG lead-I printout was obtained. Heart rate, rhythm and abnormal findings were evaluated and compared with the lead-I of standard ECG. Two emergency medicine specialists performed the ECG evaluations. Rhythms were categorized as normal sinus rhythm and abnormal rhythms, while ECG findings were categorized as the presence or absence of abnormal findings. AW and 12­lead ECG outputs were compared using the McNemar test. Predictive performance analyses were also performed for subgroups. Bland-Altman analysis using absolute mean differences and concordance correlation coefficients was used to assess the level of heart rate agreement between devices. RESULTS: The study was carried out on 721 patients. When analyzing ECG rhythms and abnormal findings in lead-I, the effectiveness of AW in distinguishing between normal and abnormal rhythms was similar to standard ECGs (p = 0.52). However, there was a significant difference between AW and standard ECGs in identifying abnormal findings in lead-I (p < 0.05). Using Bland-Altman analysis for heart rate assessment, the absolute mean difference for heart rate was 0.81 ± 6.12 bpm (r = 0.94). There was strong agreement in 658 out of 700 (94%) heart rate measurements. CONCLUSION: Our study indicates that the AW has the potential to detect cardiac rhythms beyond AF. ECG tracings obtained from the AW may help evaluate cardiac rhythms prior to the patient's arrival in the ED. However, further research with a larger patient cohort is essential, especially for specific diagnoses.

Smart watch detected ventricular bigeminy during chest palpitations.

Smart watches, which are a rapidly developing technology that can record and store personal health data such as heart rate, oxygen saturation, ECG, and sports activities. We presented a patient who applied to the emergency department due to palpitation and he recorded an ECG output with a smart watch before admission. In this case, we emphasized that the use of smart watches in the prehospital period can help the diagnosis process of dysrhythmias in the hospital setting.

Simulation-Based Drone Assisted Search Operations in a River.

INTRODUCTION: Drones can transmit live video and geographic coordinates during the planning stages for search and rescue operations and the operations themselves. There are few simulation studies in which drones provided rescue support. However, the literature does not contain any simulation studies involving the use of drones to locate lost "victims" represented by dummies in rivers. We developed a simulation model to compare the first visual contact times for drone-assisted search techniques (DAST) and classic search techniques (CST). METHODS: In this prospective experimental simulation study, we used both DAST and CST to perform a series of river searches for unconscious victims (represented by dummies). We calculated the first visual contact times, total scanned area, scanned area per minute, flight-walking distances, and flight-walking speeds and compared the results between both groups. The data are presented as mean±SD. RESULTS: We performed 20 search and rescue operations, 10 with the CST and 10 with the DAST. The time to reach the victim was 823±177 s using CST and 80±14 s using DAST. The area scanned by unit time was 3091±54 m2·min-1 using CST and 22,640±1622 m2·min-1 using DAST. CONCLUSIONS: The drone-assisted search technique located a simulated victim drifting in a river faster than the classic search technique. The use of drones in search and rescue operations could improve the time to find victims.

Examination of the Effects of 4-Hour Nonvalved Filtering Facepiece Respirator Use on Blood Gas Values of Health Care Professionals: A Before and After Study.

INTRODUCTION: The use of personal protective equipment increased rapidly during the COVID-19 pandemic that began in 2019. The purpose of this study was to examine the effects of uninterrupted 4-hour use of internationally certified nonvalved filtering facepiece respirators on venous blood gas in health care workers during the COVID-19 pandemic. METHODS: A before-after design included venous blood gas analyses collected at the beginning of shifts before nonvalved filtering facepiece respirator had been put on and after 4-hour uninterrupted use of nonvalved filtering facepiece respirator. RESULTS: In this study, 33 volunteer health care workers took part. In terms of blood gas values, mean pCO2 values were 47.63 (SD = 5.16) before and 47.01 (SD = 5.07) after nonvalved filtering facepiece respirator use, mean HCO3 values were 23.68 (SD = 1.10) in first blood gas analysis and 24.06 (SD = 1.31) in second blood gas analysis, and no significant difference was observed between before and after the use of nonvalved filtering facepiece respirator (t = 0.67, P = .50, t = -2.0, P = .054, respectively). The only significant difference in parameters investigated between the groups was in pH levels, at pH = 7.35 (SD = 0.29) before and pH = 7.36 (SD = 0.20) after nonvalved filtering facepiece respirator use (t = -2.26, P = .03). CONCLUSION: Continuous nonvalved filtering facepiece respirator use for 4 hours was not associated with clinician impairment in blood gas and peripheral SpO2 levels during nonexertional clinical ED work.

The potential use of unmanned aircraft systems (drones) in mountain search and rescue operations.

OBJECTIVE: This study explores the potential use of drones in searching for and locating victims and of motorized transportation of search and rescue providers in a mountain environment using a simulation model. METHODS: This prospective randomized simulation study was performed in order to compare two different search and rescue techniques in searching for an unconscious victim on snow-covered ground. In the control arm, the Classical Line Search Technique (CLT) was used, in which the search is performed on foot and the victim is reached on foot. In the intervention arm, the Drone-snowmobile Technique (DST) was used, the search being performed by drone and the victim reached by snowmobile. The primary outcome of the study was the comparison of the two search and rescue techniques in terms of first human contact time. RESULTS: Twenty search and rescue operations were conducted in this study. Median time to arrival at the mannequin was 57.3min for CLT, compared to 8.9min for DST. The median value of the total searched area was 88,322.0m2 for CLT and 228,613.0m2 for DST. The median area searched per minute was 1489.6m2 for CLT and 32,979.9m2 for DST (p<0.01 for all comparisons). CONCLUSIONS: In conclusion, a wider area can be searched faster by drone using DST compared to the classical technique, and the victim can be located faster and reached earlier with rescuers transported by snowmobile.

The diagnostic value of the neutrophil-lymphocyte ratio in distinguishing between subarachnoid hemorrhage and migraine.

OBJECTIVE: Migraine and subarachnoid hemorrhage (SAH) patients present to emergency departments with the similar symptoms as headache, nausea, and vomiting. This study investigated whether the neutrophil-lymphocyte ratio (NLR) could distinguish patients with SAH from those with migraine. METHODS: This retrospective study was performed after research ethics committee approval. Data were gathered from the ED and neurology clinics of a university hospital between January 2015 and January 2016, from patients with symptoms of headache (primarily), nausea and vomiting. One hundred and twenty one with SAH, 123 patients with migraine and 987 with other primary headache syndromes were considered. Neutrophil-lymphocyte ratios (NLR-1) were compared between groups on admission. In SAH patients NLR taken on the 24th-30th hour of admission (NLR-2) was compared to admission NLR. RESULTS: NLR values, showed that the median NLR values of SAH patients were significantly higher than migraine and other headaches group values (p<0.001; p<0.001). There was no statistically significant difference between the NLR values of the migraine and control groups (p>0.05). An NLR cut-off value of 4.02 produced 85.95% sensitivity, 97.46% specificity, a 33.79 positive likelihood ratio (LR+), and a 0.14 negative likelihood ratio (LR-). A statistically significant increase was observed in median NLR-2 values compared to median NLR-1 values in SAH patients (p<0.001). CONCLUSION: In this retrospective analysis, NLR distinguished patients with SAH from those with migraine. Presence of SAH should be evaluated from discharged and readmitted patients (with headache symptoms) when an increase in NLR between initial and readmission levels is observed.

The Diagnostic Value of ischemia-modified albumin (IMA) and signal peptide-CUB-EGF domain-containing protein-1 (SCUBE-1) in an Experimental Model of Strangulated Mechanical Bowel Obstruction.

BACKGROUND: Mechanical bowel obstruction (MBO) is one of the principal pathologies requiring emergency surgery and a significant worldwide cause of morbidity. The identification of patients in whom bowel obstruction resolves spontaneously is important in terms of preventing unnecessary surgical interventions and future potential adhesions. The decision-making process is difficult in patients presenting without classic examination findings. METHODS: 36 female Sprague-Dawley rats randomly divided into six experimental groups. In Group 1, 3 and 5, laparotomy was performed, with blood and tissue specimens being collected after 1, 2 and 6 h, respectively. In Group 2, 4 and 6, the ileum segment was ligated following laparotomy, and blood and tissue specimens were collected after 1, 2 and 6 h, respectively. The ileum specimens were examined macroscopically, after which 1-cm sections were taken and examined in terms of histopathological changes. IMA and SCUBE-1 levels were determined for each group, and macro- and microscopic tissue examination findings were compared between the groups. RESULTS: Comparison within the groups exposed to waiting times of 1 h (groups 1 and 2), 2 h (groups 3 and 4) and 6 h (groups 5 and 6) revealed higher mean IMA and SCUBE-1 levels in rats undergoing ligation together with incision (groups 2, 4, and 6) compared to those undergoing laparotomy only (groups 1, 3, and 5). Correlation analysis was applied to determine the relationship between total scores obtained from histopathological examination and IMA and SCUBE-1 values. The analysis revealed strong, significant and positive correlation between histopathological examination scores and IMA (r=0.643, p=0.000) and SCUBE-1 (r=0.509, p=0.002) values. CONCLUSION: The study findings showed that both IMA and SCUBE-1 values increased in a strangulated MBO model in rats. We think that IMA and SCUBE-1 values can be used as a markers of damage in the early period in strangulated MBO, and that the patient's surgery requirement can thus be determined in the early period.

Potential therapeutic effects of ethyl pyruvate and N-acetyl cysteine in an experimental rat model of corrosive esophageal.

BACKGROUND AND STUDY AIMS: Esophageal burns due to ingestion of corrosive substances are frequently seen in both children and adults. However, there is no standard method of treatment to prevent associated mortality and morbidity. Therefore, this study aimed to evaluate the effects of known antioxidants, namely N-acetyl cysteine and ethyl pyruvate, on esophageal damage due to sodium hydroxide-induced corrosive burns. MATERIALS AND METHODS: Thirty-five female rats were randomly assigned to five equal groups. Group 1 was the sham group, while Group 2 was the control group. Group 3 received N-acetyl cysteine, Group 4 received ethyl pyruvate, and Group 5 received both N-acetyl cysteine and ethyl pyruvate. Rats in the "burn" groups were gavage-fed with 0.2mL of 25% NaOH. All esophagi were extracted on day 4 for histopathological evaluation. RESULTS: Total histopathological damage scores were evaluated at the end of the study. Groups 3 and 5 were significantly different from the control group in terms of total histopathological scores (p = 0.001), while no significant difference was seen with Group 4. Stenosis index results in groups 3 and 5 were similar to those seen with total histopathological scores (p = 0.004). CONCLUSION: N-acetyl cysteine, alone or in combination with ethyl pyruvate, may be useful in the treatment of esophageal damage associated with corrosive substances and in achieving histopathological improvement in an experimental setting.

Gastrointestinal and cutaneous anthrax: Case series.

INTRODUCTION: Anthrax is a zoonosis affecting herbivorous animals. Its agent is Bacillus anthracis and it is gram positive, aerobic or facultative anaerobic, immobile and has a capsule in the polypeptide structure. The incidence is gradually decreasing in the world and in our country. The disease is especially seen in areas where stock breeding is common. In this case series, 3 cases, one of them was mortal, took place after anthrax infected cow was eaten in February 2018 in Trabzon was shared. CASE PRESENTATIONS: In the first case, as a result of the animal's meat was eaten, gastrointestinal anthrax and associated sepsis were seen. This patient's blood culture was positive and she was died. Second case after contacting the patient who died, and third case after contacting the animal and eating its meat, diagnosed with cutaneous anthrax. Doxycycline treatment was started with cutaneous anthrax patients, these cases were recovered without any complications. CONCLUSION: We presented this article, to update our information about gastrointestinal anthrax and other anthrax types which are become a current issue again especially due to bioterrorism and also to keep it in mind in the differential diagnosis although it is rarely seen in our stock raising areas.