Involuntary admissions to psychiatric hospitals are on the rise. If patients at elevated risk of involuntary admission could be identified, prevention may be possible. Our aim was to develop and validate a prediction model for involuntary admission of patients receiving care within a psychiatric service system using machine learning trained on routine clinical data from electronic health records (EHRs).

EHR data from all adult patients who had been in contact with the Psychiatric Services of the Central Denmark Region between 2013 and 2021 were retrieved. We derived 694 patient predictors (covering e.g. diagnoses, medication, and coercive measures) and 1134 predictors from free text using term frequency-inverse document frequency and sentence transformers. At every voluntary inpatient discharge (prediction time), without an involuntary admission in the 2 years prior, we predicted involuntary admission 180 days ahead. XGBoost and elastic net models were trained on 85% of the dataset. The models with the highest area under the receiver operating characteristic curve (AUROC) were tested on the remaining 15% of the data.

The model was trained on 50 634 voluntary inpatient discharges among 17 968 patients. The cohort comprised of 1672 voluntary inpatient discharges followed by an involuntary admission. The best XGBoost and elastic net model from the training phase obtained an AUROC of 0.84 and 0.83, respectively, in the test phase.

A machine learning model using routine clinical EHR data can accurately predict involuntary admission. If implemented as a clinical decision support tool, this model may guide interventions aimed at reducing the risk of involuntary admission.

The early recognition of patients with sepsis is difficult and the initial assessment outside of hospitals is challenging for ambulance clinicians (ACs). Indicators that ACs can use to recognize sepsis early are beneficial for patient outcomes. Research suggests that elevated point-of-care (POC) plasma glucose and serum lactate levels may help to predict sepsis in the ambulance service (AS) setting.

The aim of this study was to test the hypothesis that the elevation of POC plasma glucose and serum lactate levels may help to predict Sepsis-3 in the AS.

A prospective observational study was performed in the AS setting of Gothenburg in Sweden from the beginning of March 2018 through the end of September 2019. The criteria for sampling POC plasma glucose and serum lactate levels in the AS setting were high or intermediate risk according to the Rapid Emergency Triage and Treatment System (RETTS), as red, orange, yellow, and green if the respiratory rate was >22 breaths/minutes. Sepsis-3 were identified retrospectively. A primary and secondary analyses were carried out. The primary analysis included patients cared for in the AS and emergency department (ED) and were hospitalized. In the secondary analysis, patients who were only cared for in the AS and ED without being hospitalized were also included. To evaluate the predictive ability of these biomarkers, the area under the curve (AUC), sensitivity, specificity, and predictive values were used.

A total of 1,057 patients were included in the primary analysis and 1,841 patients were included in the secondary analysis. In total, 253 patients met the Sepsis-3 criteria (in both analyses). The AUC for POC plasma glucose and serum lactate levels showed low accuracy in predicting Sepsis-3 in both the primary and secondary analyses. Among all hospitalized patients, regardless of Sepsis-3, more than two-thirds had elevated plasma glucose and nearly one-half had elevated serum lactate when measured in the AS.

As individual biomarkers, an elevated POC plasma glucose and serum lactate were not associated with an increased likelihood of Sepsis-3 when measured in the AS in this study. However, the high rate of elevation of these biomarkers before arrival in hospital highlights that their role in clinical decision making at this early stage needs further evaluation, including other endpoints than Sepsis-3.

Acute gastroenteritis (AGE) is one of the most common clinical diagnoses globally, and dehydration in severe AGE cases can cause severe morbidity and mortality. Depending on the metabolic acidosis that occurs in dehydration, the respiratory rate per minute is increased, and the carbon dioxide pressure in the arterial blood is decreased. This condition correlates with end-tidal carbon dioxide (ETCO2). Therefore, this study primarily aims to evaluate whether ETCO2 measurement has a role in detecting metabolic fluid deficit, dehydration level, and regression in dehydration level after fluid replacement and its correlation with Vena Cava Collapsibility Index (VCCI).

This study included spontaneously breathing patients admitted to the emergency department of a tertiary training and research hospital with symptoms of AGE and were thought to be moderately (6.0%-9.0%) and severely (>10.0%) dehydrated according to the Primary Options of Acute Care (POAC) Clinical Dehydration Scale. After the first evaluation, the patients’ vital signs, ETCO2 values, diameters of the inferior vena cava (IVC) in inspiration and expiration, and VCCI were measured and recorded. These measurements were repeated after intravenous (IV) fluid replacement, and finally, a comparison was made between the measurements.

A total of 49 patients, as 16 male (32.7%) and 33 female (67.3%), were included in the study. The mean fluid replacement value was calculated as 664.29 (SD = 259.41) ml. The mean increase in ETCO2 was 3.653 (SD = 2.554) mmHg (P <.001). The mean increase in inferior vena cava expirium (IVCexp) was calculated as 0.402 (SD = 0.280) cm (P <.001) and the mean increase in inferior vena cava inspirium (IVCinsp) as 0.476 (SD = 0.306) cm (P <.001). The VCCI (%) decreased by 12.556 (SD = 13.683) (P <.001). Post-replacement vital signs, ETCO2, and VCCI correlations of the patients were examined and no significant correlation was found between ETCO2 and VCCI (%). As a result of this study, a receiver operating characteristic (ROC) curve was established for the ETCO2 values predicting the level of dehydration and fluid response, and the area under the curve was calculated as 0.748. However, to classify the patient as moderately dehydrated, the ETCO2 cutoff value was determined as 28.5mmHg.

The sensitivity and specificity of ETCO2 levels were 71.43% and 74.29% in evaluating the level of dehydration, and no correlation was found with VCCI, which is known to have high sensitivity and specificity in previous studies in determining the level of dehydration and fluid response. Hence, VCCI measurement made through ultrasonography (USG) is a method that should be preferred more in determining the level of dehydration. Nevertheless, as per the results of this study, swift ETCO2 measurements may be helpful in monitoring the change in the degree of dehydration with treatment in patients who were admitted to the emergency department with dehydration findings and were administered IV fluid replacement therapy.

The European Society of Cardiology (ESC) 2020 guidelines propose an algorithm for in-hospital management of non-ST-elevation myocardial infarction (NSTEMI) based on risk stratification according to clinical, electrocardiographic, and biological data. However, out-of-hospital management is not codified.

The objective of the present study was to evaluate the role of high-sensitivity cardiac troponin-I in out-of-hospital management of NSTEMI by Emergency Medical Services (EMS).

This monocentric, retrospective, observational study analyzed the files of all patients having received a troponin assay in the EMS of Beaujon University Hospital, AP-HP (Paris region, France) from January 1, 2020 through December 31, 2020. Patients were classified as low risk, high risk, or very high risk according to the ESC 2020 algorithm at the time of their hospital treatment. The relationship between troponin in point-of-care and risk level according to time to onset of pain was analyzed using logistic regression. A search for predictors of risk level was performed using multivariate analysis. A P value <.05 was considered significant.

Out of 309 patients in the file, 233 were included. Men were 61% and the median age was 63 years. A positive troponin assay was associated with high-risk or very high-risk stratification regardless of the time to onset of pain (P <.0001). Predictive factors for being classified as high or very high risk in hospital were: a history of atrial fibrillation (P = .03), electrocardiogram (ECG) modifications such as negative T wave or ST-segment depression (P <.0001), and positive troponin (P <.0001).

The use of point-of-care troponin in EMS, combined with clinical and electrical criteria, allows risk stratification of NSTEMI patients from the prehospital management stage and optimization of referral to an appropriate care pathway. Patients classified as low risk should be referred to the emergency department (ED) and patients classified as high risk or very high risk to the cardiac intensive care unit or percutaneous coronary intervention (PCI) center.

Triage - the sorting of patients according to urgency of need for clinical care - is an essential part of delivering effective and efficient emergency care. But when frequent over- or under-triaging occurs, finite time and resources are diverted away from those in greatest need of care and the entire Emergency Medical Services (EMS) system is strained. In resource-constrained settings, such as South Africa, poor triage in EMS only serves to compound other contextual challenges. This study examined the accuracy of dispatcher triage over a one-year period in the Western Cape Government (WCG) EMS system in South Africa.

A retrospective analysis of existing dispatch and EMS data to assess the accuracy of dispatch-assigned priorities was conducted. The mismatch between dispatcher-assigned call priority and triage levels determined by EMS personnel was analyzed via over- and under-triage rates, sensitivity and specificity, and positive and negative predictive values (PPVs and NPVs, respectively).

A total of 185,166 records from December 2016 through November 2017 were analyzed. Across all dispatch complaints, the over-triage rate was 67.6% (95% CI, 66.34-68.76) and the under-triage rate was 16.2% (95% CI, 15.44-16.90). Dispatch triage sensitivity for all included records was 49.2% (95% CI, 48.10-50.38), specificity 71.9% (95% CI, 71.00-72.92), PPV 32.5% (95% CI, 30.02-34.88), and NPV 83.8% (95% CI, 81.93-85.73).

This study provides the first evaluation of dispatch triage accuracy in the WCG EMS system, identifying that the system is suffering from both under- and over-triage. Despite variance across dispatch complaints, both under- and over-triage remained higher than widely accepted norms, and all rates were significantly above acceptable target metrics described in similar studies. Results of this study will be used to motivate the development of more rigorous training programs and resources for WCG EMS dispatchers, including improved dispatch protocols for conditions suffering from high over- and under-triage.

Emergency Medical Services (EMS) systems have developed protocols for prehospital activation of the cardiac catheterization laboratory for patients with suspected ST-elevation myocardial infarction (STEMI) to decrease first-medical-contact-to-balloon time (FMC2B). The rate of “false positive” prehospital activations is high. In order to decrease this rate and expedite care for patients with true STEMI, the American Heart Association (AHA; Dallas, Texas USA) developed the Mission Lifeline PreAct STEMI algorithm, which was implemented in Los Angeles County (LAC; California USA) in 2015. The hypothesis of this study was that implementation of the PreAct algorithm would increase the positive predictive value (PPV) of prehospital activation.

This is an observational pre-/post-study of the effect of the implementation of the PreAct algorithm for patients with suspected STEMI transported to one of five STEMI Receiving Centers (SRCs) within the LAC Regional System. The primary outcome was the PPV of cardiac catheterization laboratory activation for percutaneous coronary intervention (PCI) or coronary artery bypass graft (CABG). The secondary outcome was FMC2B.

A total of 1,877 patients were analyzed for the primary outcome in the pre-intervention period and 405 patients in the post-intervention period. There was an overall decrease in cardiac catheterization laboratory activations, from 67% in the pre-intervention period to 49% in the post-intervention period (95% CI for the difference, -14% to -22%). The overall rate of cardiac catheterization declined in post-intervention period as compared the pre-intervention period, from 34% to 30% (95% CI, for the difference -7.6% to 0.4%), but actually increased for subjects who had activation (48% versus 58%; 95% CI, 4.6%-15.0%). Implementation of the PreAct algorithm was associated with an increase in the PPV of activation for PCI or CABG from 37.9% to 48.6%. The overall odds ratio (OR) associated with the intervention was 1.4 (95% CI, 1.1-1.8). The effect of the intervention was to decrease variability between medical centers. There was no associated change in average FMC2B.

The implementation of the PreAct algorithm in the LAC EMS system was associated with an overall increase in the PPV of cardiac catheterization laboratory activation.

Triaging plays an important role in providing suitable care to a large number of casualties in a disaster setting. A Pediatric Physiological and Anatomical Triage Score (PPATS) was developed as a new secondary triage method. This study aimed to validate the accuracy of the PPATS in identifying injured pediatric patients who are admitted at a high frequency and require immediate treatment in a disaster setting. The PPATS method was also compared with the current triage methods, such as the Triage Revised Trauma Score (TRTS).

A retrospective review of pediatric patients aged ≤15 years, registered in the Japan Trauma Data Bank (JTDB) from 2012 through 2016, was conducted and PPATS was performed. The PPATS method graded patients from zero to 22, and was calculated based on vital signs, anatomical abnormalities, and the need for life-saving interventions. It categorized patients based on their priority, and the intensive care unit (ICU)-indicated patients were assigned a PPATS ≥six. The accuracy of PPATS and TRTS in predicting the outcome of ICU-indicated patients was compared.

Of 2,005 pediatric patients, 1,002 (50%) were admitted to the ICU. The median age of the patients was nine years (interquartile range [IQR]: 6-13 years). The sensitivity and specificity of PPATS were 78.6% and 43.7%, respectively. The area under the receiver-operating characteristic (ROC) curve (AUC) was larger for PPATS (0.61; 95% confidence interval [CI], 0.59-0.63) than for TRTS (0.57; 95% CI, 0.56-0.59; P <.01). Regression analysis showed a significant correlation between PPATS and the Injury Severity Score (ISS; r2 = 0.353; P <.001), predicted survival rate (r2 = 0.396; P <.001), and duration of hospital stay (r2 = 0.252; P <.001).

The accuracy of PPATS for injured pediatric patients was superior to that of current secondary triage methods. The PPATS method is useful not only for identifying high-priority patients, but also for determining the priority ranking for medical treatments and evacuation.

Rapid identification of esophageal intubations is critical to avoid patient morbidity and mortality. Continuous waveform capnography remains the gold standard for endotracheal tube (ETT) confirmation, but it has limitations. Point-of-care ultrasound (POCUS) may be a useful alternative for confirming ETT placement. The objective of this study was to determine the accuracy of paramedic-performed POCUS identification of esophageal intubations with and without ETT manipulation.

A prospective, observational study using a cadaver model was conducted. Local paramedics were recruited as subjects and each completed a survey of their demographics, employment history, intubation experience, and prior POCUS training. Subjects participated in a didactic session in which they learned POCUS identification of ETT location. During each study session, investigators randomly placed an ETT in either the trachea or esophagus of four cadavers, confirmed with direct laryngoscopy. Subjects then attempted to determine position using POCUS both without and with manipulation of the ETT. Manipulation of the tube was performed by twisting the tube. Descriptive statistics and logistic regression were used to assess the results and the effects of previous paramedic experience.

During 12 study sessions, from March 2014 through December 2015, 57 subjects participated, evaluating a total of 228 intubations: 113 tracheal and 115 esophageal. Subjects were 84.0% male, mean age of 39 years (range: 22 - 62 years), with median experience of seven years (range: 0.6 - 39 years). Paramedics correctly identified ETT location in 158 (69.3%) cases without and 194 (85.1%) with ETT manipulation. The sensitivity and specificity of identifying esophageal location without ETT manipulation increased from 52.2% (95% confidence interval [CI], 43.0-61.0) and 86.7% (95% CI, 81.0-93.0) to 87.0% (95% CI, 81.0-93.0) and 83.2% (95% CI, 0.76-0.90) after manipulation (P<.0001), without affecting specificity (P=.45). Subjects correctly identified 41 previously incorrectly identified esophageal intubations. Paramedic experience, previous intubations, and POCUS experience did not correlate with ability to identify tube location.

Paramedics can accurately identify esophageal intubations with POCUS, and manipulation improves identification. Further studies of paramedic use of dynamic POCUS to identify inadvertent esophageal intubations are needed.

LemaPC, O’BrienM, WilsonJ, St. JamesE, LindstromH, DeAngelisJ, CaldwellJ, MayP, ClemencyB.Avoid the Goose! Paramedic Identification of Esophageal Intubation by Ultrasound. Prehosp Disaster Med.2018;33(4):406–410

Triage has an important role in providing suitable care to the largest number of casualties in a disaster setting, but there are no secondary triage methods suitable for children. This study developed a new secondary triage method named the Pediatric Physiological and Anatomical Triage Score (PPATS) and compared its accuracy with current triage methods.

A retrospective chart review of pediatric patients under 16 years old transferred to an emergency center from 2014 to 2016 was performed. The PPATS categorized the patients, defined the intensive care unit (ICU)-indicated patients if the category was highest, and compared the accuracy of prediction of ICU-indicated patients among PPATS, Physiological and Anatomical Triage (PAT), and Triage Revised Trauma Score (TRTS).

Among 137 patients, 24 (17.5%) were admitted to ICU. The median PPATS score of these patients was significantly higher than that of patients not admitted to ICU (11 [IQR: 9-13] versus three [IQR: 2-4]; P<.001). The optimal cut-off value of the PPTAS was six, yielding a sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of 95.8%, 86.7%, 60.5%, and 99.0%. The area under the receiver-operating characteristic curve (AUC) was larger for PPTAS than for PAT or TRTS (0.95 [95% CI, 0.87-1.00] versus 0.65 [95% CI, 0.58-0.72]; P<.001 and 0.79 [95% CI, 0.69-0.89]; P=.003, respectively). Regression analysis showed a significant association between the PPATS and the predicted mortality rate (r2=0.139; P<.001), ventilation time (r2=0.320; P<.001), ICU stay (r2=0.362; P<.001), and hospital stay (r2=0.308; P<.001).

The accuracy of PPATS was superior to other methods for secondary triage of children.

ToidaC, MugurumaT, AbeT, ShinoharaM, GakumazawaM, YogoN, ShirasawaA, MorimuraN. Introduction of Pediatric Physiological and Anatomical Triage Score in Mass-Casualty Incident. Prehosp Disaster Med. 2018;33(2):147–152.

The History, Electrocardiogram (ECG), Age, Risk Factors, and Troponin (HEART) score is a decision aid designed to risk stratify emergency department (ED) patients with acute chest pain. It has been validated for ED use, but it has yet to be evaluated in a prehospital setting.

A prehospital modified HEART score can predict major adverse cardiac events (MACE) among undifferentiated chest pain patients transported to the ED.

A retrospective cohort study of patients with chest pain transported by two county-based Emergency Medical Service (EMS) agencies to a tertiary care center was conducted. Adults without ST-elevation myocardial infarction (STEMI) were included. Inter-facility transfers and those without a prehospital 12-lead ECG or an ED troponin measurement were excluded. Modified HEART scores were calculated by study investigators using a standardized data collection tool for each patient. All MACE (death, myocardial infarction [MI], or coronary revascularization) were determined by record review at 30 days. The sensitivity and negative predictive values (NPVs) for MACE at 30 days were calculated.

Over the study period, 794 patients met inclusion criteria. A MACE at 30 days was present in 10.7% (85/794) of patients with 12 deaths (1.5%), 66 MIs (8.3%), and 12 coronary revascularizations without MI (1.5%). The modified HEART score identified 33.2% (264/794) of patients as low risk. Among low-risk patients, 1.9% (5/264) had MACE (two MIs and three revascularizations without MI). The sensitivity and NPV for 30-day MACE was 94.1% (95% CI, 86.8-98.1) and 98.1% (95% CI, 95.6-99.4), respectively.

Prehospital modified HEART scores have a high NPV for MACE at 30 days. A study in which prehospital providers prospectively apply this decision aid is warranted.

StopyraJP, HarperWS, HigginsTJ, ProkesovaJV, WinslowJE, NelsonRD, AlsonRL, DavisCA, RussellGB, MillerCD, MahlerSA. Prehospital Modified HEART Score Predictive of 30-Day Adverse Cardiac Events. Prehosp Disaster Med. 2018;33(1):58–62.

The goal of this search was to review the current literature regarding paramedic triage of primary care patients and the safety of paramedic-initiated non-transport of non-urgent patients.

A narrative literature review was conducted using the Medline (Medline Industries, Inc.; Mundelein, Illinois USA) database and a manual search of Google Scholar (Google; Mountain View, California USA).

Only 11 studies were found investigating paramedic triage and safety of non-transport of non-urgent patients. It was found that triage agreement between paramedic and emergency department staff generally is poor and that paramedics are limited in their abilities to predict the ultimate admission location of their patients. However, these triage decisions and admission predictions are much more accurate when the patient’s condition is the result of trauma and when the patient requires critical care services. Furthermore, the literature provides very limited support for the safety of paramedic triage in the refusal of non-urgent patient transport, especially without physician oversight. Though many non-transported patients are satisfied with the quality of non-urgent treatment that they receive from paramedics, the rates of under-triage and subsequent hospitalization reported in the literature are too high to suggest that this practice can be adopted widely.

There is insufficient evidence to suggest that non-urgent patients can safely be refused transport based on paramedic triage alone. Further attempts to implement paramedic-initiated non-transport of non-urgent patients should be approached with careful triage protocol development, paramedic training, and pilot studies. Future primary research and systematic reviews also are required to build on the currently limited literature.

Fraess-PhillipsAJ. Can Paramedics Safely Refuse Transport of Non-Urgent Patients?Prehosp Disaster Med. 2016;31(6):667–674.

Shortening response time to an emergency call leads to the success of resuscitation by chest compression and defibrillation. However, response by ambulance or fire truck is not fast enough for resuscitation in Japan. In rural areas, response times can be more than 10 minutes. One possible way to shorten the response time is to establish a system of first responders (eg, police officers or firefighters) who are trained appropriately to perform resuscitation. Another possible way is to use a system of Community First Responders (CFRs) who are trained neighbors. At present, there are no call triage protocols to decide if dispatchers should activate CFRs.

The aim of this study was to determine the predictability to detect if dispatchers should activate CFRs.

Two CFR call triage protocols (CFR protocol Ver.0 and Ver.1) were established. The predictability of CFR protocols was examined by comparing the paramedic field reports. From the results of sensitivity of CFR protocol, the numbers of annual CFR activations were calculated. All data were collected, prospectively, for four months from October 1, 2012 through January 31, 2013.

The ROC-AUC values appear slightly higher in CFR protocol Ver.1 (0.857; 95% CI, 79.8-91.7) than in CFR protocol Ver.0 (0.847; 95% CI, 79.0-90.3). The number of annual CFR activations is higher in CFR protocol Ver.0 (7.47) than in CFR protocol Ver.1 (5.45).

Two call triage protocols have almost the same predictability as the Medical Priority Dispatch System (MPDS). The study indicates that CFR protocol Ver.1 is better than CFR protocol Ver.0 because of the higher predictability and low number of activations. Also, it indicates that CFRs who are not medical professionals can respond to a patient with cardiac arrest.

NarikawaK, SakamotoT, KubotaK, SuzukawaM, YonekawaC, YamashitaK, ToyokuniY, YasudaY, KobayashiA, IijimaK. Predictability of the Call Triage Protocol to Detect if Dispatchers Should Activate Community First Responders. Prehosp Disaster Med. 2014;29(5):1-5.

The aim of the present study was to determine whether a combination of baseline features and early post-baseline depressive symptom changes have clinical value in predicting out-patient non-response in depressed out-patients after 8 weeks of medication treatment.

We analysed data from the Combining Medications to Enhance Depression Outcomes study for 447 participants with complete 16-item Quick Inventory of Depressive Symptomatology – Self-Report (QIDS-SR16) ratings at baseline and at treatment weeks 2, 4 and 8. We used a multi-time point, recursive subsetting approach that included baseline features and changes in QIDS-SR16 scores from baseline to weeks 2 and 4, to identify non-responders (<50% reduction in QIDS-SR16) at week 8 with a pre-specified accuracy level.

Pretreatment clinical features alone were not clinically useful predictors of non-response after 8 weeks of treatment. Baseline to week 2 symptom change identified 48 non-responders (of which 36 were true non-responders). This approach gave a clinically meaningful negative predictive value of 0.75. Symptom change from baseline to week 4 identified 79 non-responders (of which 60 were true non-responders), achieving the same accuracy. Symptom change at both weeks 2 and 4 identified 87 participants (almost 20% of the sample) as non-responders with the same accuracy. More participants with chronic than non-chronic index episodes could be accurately identified by week 4.

Specific baseline clinical features combined with symptom changes by weeks 2–4 can provide clinically actionable results, enhancing the efficiency of care by personalizing the treatment of depression.