Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 6 de 6
Filter
1.
Front Psychiatry ; 14: 1110527, 2023.
Article in English | MEDLINE | ID: mdl-37032952

ABSTRACT

Introduction: With the increasing utilization of text-based suicide crisis counseling, new means of identifying at risk clients must be explored. Natural language processing (NLP) holds promise for evaluating the content of crisis counseling; here we use a data-driven approach to evaluate NLP methods in identifying client suicide risk. Methods: De-identified crisis counseling data from a regional text-based crisis encounter and mobile tipline application were used to evaluate two modeling approaches in classifying client suicide risk levels. A manual evaluation of model errors and system behavior was conducted. Results: The neural model outperformed a term frequency-inverse document frequency (tf-idf) model in the false-negative rate. While 75% of the neural model's false negative encounters had some discussion of suicidality, 62.5% saw a resolution of the client's initial concerns. Similarly, the neural model detected signals of suicidality in 60.6% of false-positive encounters. Discussion: The neural model demonstrated greater sensitivity in the detection of client suicide risk. A manual assessment of errors and model performance reflected these same findings, detecting higher levels of risk in many of the false-positive encounters and lower levels of risk in many of the false negatives. NLP-based models can detect the suicide risk of text-based crisis encounters from the encounter's content.

2.
Prehosp Emerg Care ; 24(6): 831-838, 2020.
Article in English | MEDLINE | ID: mdl-31961756

ABSTRACT

Introduction: One of the greatest casualty-care improvements resulting from US military operations in Iraq and Afghanistan has been the reduction of preventable death from massive extremity hemorrhage - largely due to the widespread use of limb tourniquets. More recently, tourniquet use in civilian, prehospital settings has shown promise in reducing deaths in cases of catastrophic arterial limb hemorrhage. Telephone instructions by trained emergency medical dispatchers (EMDs) on applying an available tourniquet may help achieve such a benefit.Objectives: The objective of the study was to determine whether layperson callers can effectively stop simulated bleeding using an improvised or a commercial tourniquet, when provided with scripted instructions via phone from a trained protocol-aided EMD.Methods: This was a prospective, randomized trial involving layperson volunteers, done at four locations in Salt Lake City, Utah, USA. Volunteers were assigned randomly to three groups: one for each of two commonly available commercial tourniquets and one for an improvised tourniquet.Results: A total of 246 subjects participated in the study at the four locations between February 11, 2019 and June 22, 2019. The overall median time for all trials (i.e., elapsed time from the start to the end of the simulation) was 3 minutes and 19 seconds. Median time to stop the bleeding (i.e., elapsed time from the start of the simulation to the time the participant was able to successfully stop the bleeding) was 2 minutes and 57 seconds. Median tourniquet pressure was 256 mmHg and median-end blood loss was 1,365 mL. A total of 198 participants (80.49%) were able to completely stop the bleeding while 16 participants (6.5%) had the tourniquet applied with some bleeding still occurring, and 32 participants (13.01%) exceeded the threshold of 2,500 mL of blood loss, resulting in the "patient" not surviving.Conclusions: The study findings demonstrated that untrained bystanders provided with instructions via phone from a trained Emergency Medical Dispatcher applied a tourniquet and successfully stopped the bleeding completely in most cases.


Subject(s)
Emergency Medical Dispatcher , First Aid/methods , Tourniquets , Emergency Medical Services , Hemorrhage/therapy , Humans , Patient Simulation , Prospective Studies , Time-to-Treatment , Utah
3.
Prehosp Emerg Care ; 23(5): 683-690, 2019.
Article in English | MEDLINE | ID: mdl-30572769

ABSTRACT

Objective: The aim of this study was to determine the frequency of automatic external defibrillator (AED) retrieval and placement by bystander callers when prompted by an Emergency Medical Dispatcher (EMD). Methods: This retrospective descriptive study utilized a convenience sample of emergency dispatch data collected from 23 Emergency Communication Centers (ECCs) spanning 14 states across the United States (U.S.) from July 11, 2014 to August 13, 2018, including all cases in which the EMD recorded any response to the AED availability prompt. Data were collected using ProQA, the software version of the Medical Priority Dispatch System. Primary outcome measures were (a) distribution of responses to the AED prompt; (b) percentage of cases in which an AED was retrieved; and (c) percentage of cases in which AED pads were placed by the bystander-caller. Results: A total of 2,200,285 cases were collected during the study period, in 18,904 (0.86%) of which the AED prompt was displayed (indicating suspected out of hospital cardiac arrest, or OHCA). Overall, an AED was reported as available 5.8% (n = 1,091) of the time the EMD recorded an answer to the AED prompt. In multiple-rescuer situations, a rescuer was sent to get the AED 2.8% (n = 523) of the time, as opposed to only 0.30% (n = 56) for single-rescuer calls. The AED was reported to be already on scene, by the patient, in 2.7% (n = 512) of the cases. A majority (72.0%; n = 417) of the time, rescuers who were sent to get an AED were unable to retrieve it, with single rescuers being successful more often (57.1% unable to retrieve, vs 73.6% for multiple rescuers). Conclusions: AEDs are reported as available by only a small percentage of callers to 911, and in the majority of cases in which a bystander rescuer is sent to retrieve an AED, one is never located or used. Sending someone to retrieve the AED may be more appropriate in multiple-rescuer situations than when a single bystander rescuer is alone on scene.


Subject(s)
Cardiopulmonary Resuscitation/statistics & numerical data , Defibrillators/statistics & numerical data , Emergency Medical Dispatch , Emergency Medical Services/statistics & numerical data , Out-of-Hospital Cardiac Arrest/therapy , Emergency Medical Service Communication Systems , Female , Humans , Male , Out-of-Hospital Cardiac Arrest/diagnosis , Out-of-Hospital Cardiac Arrest/epidemiology , Retrospective Studies , United States
4.
Prehosp Disaster Med ; 33(4): 399-405, 2018 Aug.
Article in English | MEDLINE | ID: mdl-30033904

ABSTRACT

IntroductionImplementation of high-quality, dispatcher-assisted cardiopulmonary resuscitation (DA-CPR) is critical to improving survival from out-of-hospital cardiac arrest (OHCA). However, despite some studies demonstrating the use of a metronome in a stand-alone setting, no research has yet demonstrated the effectiveness of a metronome tool in improving DA-CPR in the context of a realistic 911 call or using instructions that have been tested in real-world emergency calls.HypothesisUse of the metronome tool will increase the proportion of callers able to perform CPR within the target rate without affecting depth. METHODS: The prospective, randomized, controlled study involved simulated 911 cardiac arrest calls made by layperson-callers and handled by certified emergency medical dispatchers (EMDs) at four locations in Salt Lake City, Utah USA. Participants were randomized into two groups. In the experimental group, layperson-callers received CPR pre-arrival instructions with metronome assistance. In the control group, layperson-callers received only pre-arrival instructions. The primary outcome measures were correct compression rate (counts per minute [cpm]) and depth (mm). RESULTS: A total of 148 layperson-callers (57.4% assigned to experimental group) participated in the study. There was a statistically significant association between the number of participants who achieved the target compression rate and experimental study group (P=.003), and the experimental group had a significantly higher median compression rate than the control group (100 cpm and 89 cpm, respectively; P=.013). Overall, there was no significant correlation between compression rate and depth. CONCLUSION: An automated software metronome tool is effective in getting layperson-callers to achieve the target compression rate and compression depth in a realistic DA-CPR scenario.Scott G, Barron T, Gardett I, Broadbent M, Downs H, Devey L, Hinterman EJ, Clawson J, Olola C. Can a software-based metronome tool enhance compression rate in a realistic 911 call scenario without adversely impacting compression depth for dispatcher-assisted CPR? Prehosp Disaster Med. 2018;33(4):399-405.


Subject(s)
Cardiopulmonary Resuscitation/instrumentation , Out-of-Hospital Cardiac Arrest/therapy , Adolescent , Adult , Aged , Aged, 80 and over , Cardiopulmonary Resuscitation/methods , Child , Emergency Medical Service Communication Systems , Emergency Medical Services , Female , Humans , Male , Middle Aged , Pressure , Prospective Studies , Software , Time Factors , Treatment Outcome , Utah , Young Adult
5.
Prehosp Disaster Med ; 33(1): 29-35, 2018 Feb.
Article in English | MEDLINE | ID: mdl-29223194

ABSTRACT

Introduction Early recognition of an acute myocardial infarction (AMI) can increase the patient's likelihood of survival. As the first point of contact for patients accessing medical care through emergency services, emergency medical dispatchers (EMDs) represent the earliest potential identification point for AMIs. The objective of the study was to determine how AMI cases were coded and prioritized at the dispatch point, and also to describe the distribution of these cases by patient age and gender. Hypothesis/Problem No studies currently exist that describe the EMD's ability to correctly triage AMIs into Advanced Life Support (ALS) response tiers. METHODS: The retrospective descriptive study utilized data from three sources: emergency medical dispatch, Emergency Medical Services (EMS), and emergency departments (EDs)/hospitals. The primary outcome measure was the distributions of AMI cases, as categorized by Chief Complaint Protocol, dispatch priority code and level, and patient age and gender. The EMS and ED/hospital data came from the Utah Department of Health (UDoH), Salt Lake City, Utah. Dispatch data came from two emergency communication centers covering the entirety of Salt Lake City and Salt Lake County, Utah. RESULTS: Overall, 89.9% of all the AMIs (n=606) were coded in one of the three highest dispatch priority levels, all of which call for ALS response (called CHARLIE, DELTA, and ECHO in the studied system). The percentage of AMIs significantly increased for patients aged 35 years and older, and varied significantly by gender, dispatch level, and chief complaint. A total of 85.7% of all deaths occurred among patients aged 55 years and older, and 88.9% of the deaths were handled in the ALS-recommended priority levels. CONCLUSION: Acute myocardial infarctions may present as a variety of clinical symptoms, and the study findings demonstrated that more than one-half were identified as having chief complaints of Chest Pain or Breathing Problems at the dispatch point, followed by Sick Person and Unconscious/Fainting. The 35-year age cutoff for assignment to higher priority levels is strongly supported. The Falls and Sick Person Protocols offer opportunities to capture atypical AMI presentations. Clawson JJ , Gardett I , Scott G , Fivaz C , Barron T , Broadbent M , Olola C . Hospital-confirmed acute myocardial infarction: prehospital identification using the Medical Priority Dispatch System. Prehosp Disaster Med. 2018;33(1):29-35.


Subject(s)
Emergency Medical Service Communication Systems/statistics & numerical data , Emergency Medical Services/organization & administration , Emergency Service, Hospital , Myocardial Infarction/diagnosis , Myocardial Infarction/mortality , Triage , Adult , Aged , Cohort Studies , Early Diagnosis , Electrocardiography/methods , Female , Humans , Male , Middle Aged , Myocardial Infarction/therapy , Outcome Assessment, Health Care , Retrospective Studies , Risk Assessment , Survival Rate , United States
6.
Prehosp Emerg Care ; 21(4): 525-534, 2017.
Article in English | MEDLINE | ID: mdl-28409655

ABSTRACT

OBJECTIVE: Chest pain is one of the most common reasons people seek emergency care-and one of the most critical. In the United States, chest pain is the second most common reason for emergency department (ED) visits. A patient's primary complaint of "chest pain" may reflect a broad range of underlying causes; therefore, it is important that emergency medical service (EMS) agencies gain a thorough understanding of these cases, beginning with the initial management of chest pain in the 9-1-1 center. The primary objective of this study was to compare hospital-confirmed patient discharge diagnoses to all calls handled by emergency medical dispatchers (EMDs) using the Chest Pain/Chest Discomfort (Non-Traumatic) Chief Complaint Protocol. METHODS: The retrospective descriptive study utilized emergency medical dispatch, EMS, and hospital datasets, collected at two emergency communication centers in North America, from January 1, 2013 to December 31, 2014. Patients who were dispatched using the Chest Pain/Chest Discomfort Chief Complaint Protocol and matched to hospital datasets were included. The primary outcome was the number and percentage of cases classified as ischemic heart disease (IHD), other cardiac-related conditions, or non-cardiac-related conditions associated with chest pain. We also evaluated the distribution of causes of chest pain across demographic indicators and dispatch determinants. RESULTS: 3,007 cases were identified as "chest pain" at dispatch for which corresponding hospital records were identified. Cases in the study were obtained by linking EMS/Hospital and Emergency Medical Dispatch datasets. Of these cases, 47.1% (n = 1,417) were due to cardiac-related causes of chest pain, 61.5% of which were Ischemic Heart Disease (IHD), while the rest had other cardiac-related causes. Of the IHDs, 32.1% were Acute Myocardial Infarction (AMI). CONCLUSIONS: Underlying causes of non-traumatic chest pain reported to 9-1-1 demonstrate a wide range of etiologies, with a mix similar to that of chest pain patients in several other healthcare settings, including hospital emergency departments. Most IHD events are triaged by EMDs to the (highest) DELTA priority level, while the CHARLIE level captures nearly all of the remaining IHD cases.


Subject(s)
Chest Pain/diagnosis , Emergency Medical Services/statistics & numerical data , Triage/methods , Adolescent , Adult , Aged , Chest Pain/etiology , Child , Child, Preschool , Databases, Factual , Emergency Medical Services/methods , Emergency Service, Hospital , Female , Hospitals , Humans , Infant , Male , Middle Aged , North America , Patient Discharge/statistics & numerical data , Retrospective Studies , Triage/statistics & numerical data , United States , Young Adult
SELECTION OF CITATIONS
SEARCH DETAIL
...