Prediction of hospitalization using artificial intelligence for urgent patients in the emergency department

AbstractTimely assessment to accurately prioritize patients is crucial for emergency department (ED) management. Urgent (i.e., level-3, on a 5-level emergency severity index system) patients have become a challenge since under-triage and over-triage often occur. This study was aimed to develop a computational model by artificial intelligence (AI) methodologies to accurately predict urgent patient outcomes using data that are readily available in most ED triage systems. We retrospectively collected data from the ED of a tertiary teaching hospital between January 1, 2015 and December 31, 2019. Eleven variables were used for data analysis and prediction model building, including 1 response, 2 demographic, and 8 clinical variables. A model to predict hospital admission was developed using neural networks and machine learning methodologies. A total of 282,971 samples of urgent (level-3) visits were included in the analysis. Our model achieved a validation area under the curve (AUC) of 0.8004 (95% CI 0.7963–0.8045). The optimal cutoff value identified by Youden's index for determining hospital admission was 0.5517. Using this cutoff value, the sensitivity was 0.6721 (95% CI 0.6624–0.6818), and the specificity was 0.7814 (95% CI 0.7777–0.7851), with a positive predictive value of 0.3660 (95% CI 0.3586–0.3733) and a negative predictive value of 0.9270 (95% CI 0.9244–0.9295). Subgroup analysis revealed that this model performed better in the nontraumatic adult subgroup and achieved a validation AUC of 0.8166 (95% CI 0.8199–0.8212). Our AI model accurately assessed the need for hospitalization for urgent patients, which constituted nearly 70% of ED visits. This model demonstrates the potential for streamlining ED operations using a very limited number of variables that are readily available in most ED triage systems. Subgroup analysis is an important topic for future investigation.

Download Full-text

Clinical risk scores for the early prediction of severe outcomes in patients hospitalized for COVID-19

Internal and Emergency Medicine ◽

10.1007/s11739-020-02617-4 ◽

2021 ◽

Author(s):

Walter Ageno ◽

◽

Chiara Cogliati ◽

Martina Perego ◽

Domenico Girelli ◽

...

Keyword(s):

Hospital Admission ◽

Predictive Value ◽

Clinical Laboratory ◽

Area Under The Curve ◽

Orotracheal Intubation ◽

Risk Scores ◽

Algorithm Selection ◽

Derivation Cohort ◽

Neutrophil Lymphocyte Ratio ◽

Predictive Risk

AbstractCoronavirus disease of 2019 (COVID-19) is associated with severe acute respiratory failure. Early identification of high-risk COVID-19 patients is crucial. We aimed to derive and validate a simple score for the prediction of severe outcomes. A retrospective cohort study of patients hospitalized for COVID-19 was carried out by the Italian Society of Internal Medicine. Epidemiological, clinical, laboratory, and treatment variables were collected at hospital admission at five hospitals. Three algorithm selection models were used to construct a predictive risk score: backward Selection, Least Absolute Shrinkage and Selection Operator (LASSO), and Random Forest. Severe outcome was defined as the composite of need for non-invasive ventilation, need for orotracheal intubation, or death. A total of 610 patients were included in the analysis, 313 had a severe outcome. The subset for the derivation analysis included 335 patients, the subset for the validation analysis 275 patients. The LASSO selection identified 6 variables (age, history of coronary heart disease, CRP, AST, D-dimer, and neutrophil/lymphocyte ratio) and resulted in the best performing score with an area under the curve of 0.79 in the derivation cohort and 0.80 in the validation cohort. Using a cut-off of 7 out of 13 points, sensitivity was 0.93, specificity 0.34, positive predictive value 0.59, and negative predictive value 0.82. The proposed score can identify patients at low risk for severe outcome who can be safely managed in a low-intensity setting after hospital admission for COVID-19.

Download Full-text

P6472Novel cardiac imaging prognostic markers of clinical outcome in patients with bicuspid aortic valve and chronic aortic regurgitation

European Heart Journal ◽

10.1093/eurheartj/ehz746.1064 ◽

2019 ◽

Vol 40 (Supplement_1) ◽

Author(s):

R Kockova ◽

H Linkova ◽

Z Hlubocka ◽

A Praveckova ◽

A Polednova ◽

...

Keyword(s):

Heart Failure ◽

Surgical Treatment ◽

Disease Progression ◽

Predictive Value ◽

Area Under The Curve ◽

Early Disease ◽

Regurgitant Fraction ◽

Cutoff Value ◽

Vena Contracta ◽

Chronic Aortic Regurgitation

Abstract Background Patients with chronic aortic regurgitation (AR) can have a substantial myocardial damage despite being asymptomatic. Early surgical strategy might be beneficial. Bicuspid aortic valve (BAV) is a congenital heart disease present in almost 30% of these patients. Purpose Identify novel imaging predictors of early disease progression. Methods Prospective three-centre study of patients with chronic AR of at least moderate to severe (3+) grade and BAV morphology. Patients without currently recognised indication for surgical treatment were enrolled. Baseline examination included echocardiography (ECHO) with 3-dimensional (3D) vena contracta area and magnetic resonance (MR) with regurgitant fraction measured from flow sequence. All imaging studies were analysed in CoreLab. The primary endpoint was defined as a combination of cardiovascular death, surgical treatment or hospitalization for heart failure. Results A total of 83 patients with BAV and at least 3+ AR were enrolled during 2015–2018. Median follow-up was 759±455 days, primary composite endpoint occurred in 13 patients who met criteria for surgical treatment, no patient died or was hospitalized for heart failure. Baseline parameters were compared between two groups: patients with and without endpoint. Clinical and laboratory data did not differ between the two groups. Left ventricular (LV) ejection fraction was normal in all patients. LV diameters and volumes were significantly larger in patients with primary endpoint. This was most pronounced in MR measured indexed volumes in end-diastole and end-systole, P=0.003 and P=0.003. Non-invasive markers of diffuse myocardial fibrosis (native T1 relaxation time and global longitudinal strain, P=0.614 and P=0.137 respectively) were not different. Novel markers of AR severity were significantly increased in surgically treated patients: 3D vena contracta 0.26±0.10 cm2 versus 0.38±0.11 cm2 (P<0.001), MR regurgitant fraction 33.9±15.4 versus 50.2±12.2% (P=0.001). Both 3D vena contracta with cutoff value ≥0.4 cm2 (sensitivity=85%, specificity=84%, area under the curve=0.85) and MR regurgitant fraction with cutoff value ≥34% (sensitivity=94%, specificity=58%, area under the curve=0.76) showed high accuracy to identify patients who require early surgical intervention. Adding 3D vena contracta and MR regurgitant fraction to indexed LV end-systolic volumetric parameters significantly increases the predictive value for early disease progression with p=0.001 and p=0.006 (Likelihood-ratio test). 3D vena contracta predictive value Conclusions Novel imaging parameters of AR severity such as 3D vena contracta and MR derived regurgitant fraction predict early disease progression in patients with BAV and at least 3+ chronic AR. These values significantly increase the predictive value of traditional parameters based on LV size measures.

Download Full-text

Validation of an artificial intelligence algorithm applied to a metabolic substrate analysis of urine for detection of urothelial cancer.

Journal of Clinical Oncology ◽

10.1200/jco.2019.37.15_suppl.e16008 ◽

2019 ◽

Vol 37 (15_suppl) ◽

pp. e16008-e16008

Author(s):

Nikola Kaludov ◽

Mohummad Minhaj Siddiqui ◽

Max Kates ◽

Hemantkumar Tripathi ◽

Amatul Nasir Salma ◽

...

Keyword(s):

Artificial Intelligence ◽

Predictive Value ◽

Urothelial Cancer ◽

Profile Analysis ◽

Characteristic Curve ◽

Area Under The Curve ◽

Data Points ◽

Artificial Intelligence Algorithm ◽

Insight Into ◽

Made In

e16008 Background: Urine tests such as urine cytology are commonly used for the diagnosis and monitoring of urothelial cancer. These tests are often limited by issues related to sensitivity or specificity. It is well known that derangement of cellular metabolism is one of the hallmarks of carcinogenesis. As urothelial cancer is in constant contact with urine, we hypothesize that metabolite composition in the urine may provide insight into possible urothelial cancer presence in the urinary tract. In this study, we evaluated a metabolomics based urine test for the detection of urothelial cancer. Methods: In this prospective, multi-institutional IRB approved study, urine samples were collected from a total of 57 urothelial cancer patients and non-urothelial cancer controls. Gas chromatography profiles of urine small molecule metabolites were generated to yield over 2400 data points of metabolite peaks and troughs for every urine sample. A machine-learning based algorithm (Abilis Life Sciences) was constructed to predict urothelial cancer versus non-cancer controls through analysis of peaks and trough patterns of urine metabolomics profiles. Predictions were made in a blinded fashion and descriptive statistics of test sensitivity and specificity were generated. Results: The urine metabolite composition of 57 patients were analyzed and urothelial cancer predictions were generated. The test demonstrated an overall accuracy of 89.5% (51 out of 57 cases correctly predicted). The sensitivity of the test was 97.1% (34 out of 35) and specificity was 77.3% (17 out of 22). The Positive Predictive Value is 87.2%, while the Negative Predictive Value is 94.4%. The area under the curve for the receiver operating characteristic curve was 0.87. Conclusions: Urine based metabolic profile analysis using artificial intelligence algorithms is a promising potential diagnostic test for detection of urothelial cancer. Further testing is ongoing to increase robustness of the validation.

Download Full-text

Predictive value of qSOFA score for death in emergency department resuscitation room among adult trauma patients:a retrospective study

BMC Emergency Medicine ◽

10.1186/s12873-021-00498-0 ◽

2021 ◽

Vol 21 (1) ◽

Author(s):

Wenjuan Huang ◽

Peng Yang ◽

Feng Xu ◽

Du Chen

Keyword(s):

Emergency Department ◽

Predictive Value ◽

Univariate Analysis ◽

Area Under The Curve ◽

Study Endpoint ◽

Trauma Patients ◽

Roc Curve Analysis ◽

Resuscitation Room ◽

Failure Assessment ◽

Qsofa Score

Abstract Background To explore the predictive value of the quick Sequential Organ Failure Assessment (qSOFA) score for death in the emergency department (ED) resuscitation room among adult trauma patients. Methods During the period November 1, 2016 to November 30, 2019, data was retrospectively collected of adult trauma patients triaged to the ED resuscitation room in the First Affiliated Hospital of Soochow University. Death occurring in the ED resuscitation room was the study endpoint. Univariate and multivariate analyses were performed to explore the association between qSOFA score and death. Receiver operating characteristic (ROC) curve analysis was also performed for death. Results A total of 1739 trauma victims were admitted, including 1695 survivors and 44 non-survivors. The death proportion raised with qSOFA score: 0.60% for qSOFA = 0, 3.28% for qSOFA = 1, 12.06% for qSOFA = 2, and 15.38% for qSOFA = 3, p < 0.001. Subgroup of qSOFA = 0 was used as a reference. In univariate analysis, crude OR for death with qSOFA = 1 was 5.65 [95% CI 2.25 to 14.24, p < 0.001], qSOFA = 2 was 22.85 [95% CI 8.84 to 59.04, p < 0.001], and qSOFA = 3 was 30.30 [95% CI 5.50 to 167.05, p < 0.001]. In multivariate analysis, with an adjusted OR (aOR) of 2.87 (95% CI 0.84 to 9.87, p = 0.094) for qSOFA = 1, aOR 6.80 (95% CI 1.79 to 25.90, p = 0.005) for qSOFA = 2, and aOR 24.42 (95% CI 3.67 to 162.27, p = 0.001) for qSOFA = 3. The Area Under the Curve (AUC) for predicting death in the ED resuscitation room among trauma patients was 0.78 [95% CI, 0.72–0.85]. Conclusions The qSOFA score can assess the severity of emergency trauma patients and has good predictive value for death in the ED resuscitation room.

Download Full-text

Retrospective validation of a new volumetric capnography parameter for the exclusion of pulmonary embolism at the emergency department

ERJ Open Research ◽

10.1183/23120541.00099-2018 ◽

2018 ◽

Vol 4 (4) ◽

pp. 00099-2018

Author(s):

Timon M. Fabius ◽

Michiel M.M. Eijsvogel ◽

Marjolein G.J. Brusse-Keizer ◽

Olivier M. Sanchez ◽

Franck Verschuren ◽

...

Keyword(s):

Carbon Dioxide ◽

Emergency Department ◽

Pulmonary Embolism ◽

Diagnostic Accuracy ◽

Roc Curve ◽

Predictive Value ◽

Area Under The Curve ◽

Carbon Dioxide Production ◽

Pulmonary Angiography ◽

Volumetric Capnography

Volumetric capnography might be used to exclude pulmonary embolism (PE) without the need for computed tomography pulmonary angiography. In a pilot study, a new parameter (CapNoPE) combining the amount of carbon dioxide exhaled per breath (carbon dioxide production (VCO2)), the slope of phase 3 of the volumetric capnogram (slope 3) and respiratory rate (RR) showed promising diagnostic accuracy (where CapNoPE=(VCO2×slope 3)/RR).To retrospectively validate CapNoPE for the exclusion of PE, the volumetric capnograms of 205 subjects (68 with PE) were analysed, based on a large multicentre dataset of volumetric capnograms from subjects with suspected PE at the emergency department. The area under the curve (AUC) of the receiver operating characteristic (ROC) curve and diagnostic accuracy of the in-pilot established threshold (1.90 Pa·min) were calculated. CapNoPE was 1.56±0.97 Pa·min in subjects with PE versus 2.51±1.67 Pa·min in those without PE (p<0.001). The AUC of the ROC curve was 0.714 (95% CI 0.64–0.79). For the cut-off of ≥1.90 Pa·min, sensitivity was 64.7%, specificity was 59.9%, the negative predictive value was 77.4% and the positive predictive value was 44.4%.The CapNoPE parameter is decreased in patients with PE but its diagnostic accuracy seems too low to use in clinical practice.

Download Full-text

The Korean Triage and Acuity Scale: associations with admission, disposition, mortality and length of stay in the emergency department

International Journal for Quality in Health Care ◽

10.1093/intqhc/mzy184 ◽

2018 ◽

Vol 31 (6) ◽

pp. 449-455 ◽

Cited By ~ 8

Author(s):

Hyuksool Kwon ◽

Yu Jin Kim ◽

You Hwan Jo ◽

Jae Hyuk Lee ◽

Jin Hee Lee ◽

...

Keyword(s):

Emergency Department ◽

Length Of Stay ◽

Hospital Admission ◽

Total Mortality ◽

Inpatient Mortality ◽

Fully Integrated ◽

Tertiary Teaching ◽

Before And After ◽

Quasi Experimental ◽

Tertiary Teaching Hospital

Abstract Objective The Korean Triage and Acuity Scale (KTAS) was implemented in our emergency department (ED) in May 2016 and is fully integrated into the electronic medical record (EMR) system. Our objective was to determine whether the KTAS is associated with changes in admissions to the hospital, admission disposition, inpatient mortality and length of stay (LOS). Design Quasi-experimental, uncontrolled before-and-after study. Setting The urban tertiary teaching hospital with 1100 beds and receives approximately annual 90 000 ED visits. Participants 122 370 patients who visited the ED during the before-and-the after period. Interventions ED staff were educated on the KTAS for 1 month, after which the KTAS evaluation period began. Admission, disposition, mortality and LOS were compared between the ‘before’ period (1 June 2015 to 30 April 2016) and the ‘after’ period (1 June 2016 to 30 April 2017). Main outcome measures Admissions to the hospital, admission disposition, inpatient mortality and LOS. Results A total of 59 220 and 63 150 patients were included in the before-and-after periods of KTAS implementation, respectively. The pattern of admission and disposition changed significantly after implementation of the KTAS. The mean LOS was 343 min (standard deviation [SD] = 432 min) during the before period, which significantly decreased to 289 min (SD = 333 min) after implementation (P < 0.001). The total mortality rate was significantly reduced after implementation of the KTAS (213 (0.36%) vs. 179 (0.28%), P = 0.020). Conclusion Implementation of the KTAS changed admission and disposition patterns and reduced the LOS and mortality in the ED.

Download Full-text

Predicting in-hospital mortality for patients admitted from the emergency department: An initial alarm score for inpatient care

10.21203/rs.2.20794/v1 ◽

2020 ◽

Author(s):

Ming-Ju Hsieh ◽

Nin-Chieh Hsu ◽

Yu-Feng Lin ◽

Chin-Chung Shu ◽

Wen-Chu Chiang ◽

...

Keyword(s):

Emergency Department ◽

Hospital Mortality ◽

Predictive Value ◽

Cancer Metastasis ◽

Validation Cohort ◽

Characteristic Curve ◽

High Sensitivity ◽

Cutoff Value ◽

Derivation Cohort ◽

Cox Proportional Hazard Regression

Abstract Background: The in-hospital mortality of patients admitted from the emergency department (ED) is high, but no appropriate initial alarm score is available. Methods: This prospective observational study enrolled ED-admitted patients in hospitalist-care wards and analyzed the predictors for seven-day in-hospital mortality from May 2010 to October 2016. Two-thirds were randomly assigned to a derivation cohort for development of the model and cross-validation was performed in the validation cohort. Results: During the study period, 8,649 patients were enrolled for analysis. The mean age was 71.05 years, and 51.91% were male. The most common admission diagnoses were pneumonia (36%) and urinary tract infection (20.05%). In the derivation cohort, multivariable Cox proportional hazard regression revealed that a low Barthel index score, triage level 1 at the ED, presence of cancer, metastasis, and admission diagnoses of pneumonia and sepsis were independently associated with seven-day in-hospital mortality. Based on the probability developed from the multivariable model, the area under the receiver operating characteristic curve in the derivation group was 0.81 [0.79–0.85]. The result in the validation cohort was comparable. The prediction score modified by the six independent factors had high sensitivity of 88.03% and a negative predictive value of 99.51% for a cutoff value of 4, whereas the specificity and positive predictive value were 89.61% and 10.55%, respectively, when the cutoff value was a score of 6. Conclusion: The seven-day in-hospital mortality in a hospitalist-care ward is 2.8%. The initial alarm score could help clinicians to prioritize or exclude patients who need urgent and intensive care.

Download Full-text

The Challenge of Using an Antigen Test as a Screening Tool for SARS-CoV-2 Infection in an Emergency Department: Experience of a Tertiary Care Hospital in Southern Italy

BioMed Research International ◽

10.1155/2021/3893733 ◽

2021 ◽

Vol 2021 ◽

pp. 1-7

Author(s):

Daniela Loconsole ◽

Francesca Centrone ◽

Caterina Morcavallo ◽

Silvia Campanella ◽

Anna Sallustio ◽

...

Keyword(s):

Emergency Department ◽

Predictive Value ◽

Demographic Data ◽

Tertiary Care ◽

Previous History ◽

Area Under The Curve ◽

Care Hospital ◽

Antigen Test ◽

Operating Characteristics ◽

Likelihood Ratios

Background. In emergency hospital settings, rapid diagnosis and isolation of SARS-CoV-2 patients are required. The aim of the study was to evaluate the performance of an antigen chemiluminescence enzymatic immunoassay (CLEIA) and compare it with that of Real-time Reverse transcription-Polymerase Chain Reaction (RT-qPCR), the gold standard assay, to assess its suitability as a rapid diagnostic method for managing patients in the emergency department (ED). Methods. Consecutive patients with no previous history of SARS-CoV-2 infection attending the ED of the Policlinico Hospital of Bari between 23rd October and 4th November 2020 were enrolled. Clinical and demographic data were collected for all patients. Nasopharyngeal swabs collected on admission were subjected both to molecular (RT-qPCR) and antigen (CLEIA) tests for SARS-CoV-2. The performance of the CLEIA antigen test was analyzed using R Studio software and Microsoft Excel. Receiver operating characteristics were also performed. Results. A total of 911 patients were enrolled, of whom 469 (51.5%) were male. Of the whole cohort, 23.7% tested positive for SARS-CoV-2 by RT-qPCR and 24.5% by CLEIA. The overall concordance rate was 96.8%. The sensitivity, specificity, positive predictive value, and negative predictive value of the antigen test were 94.9% (95% CI, 91.9–97.0), 97.4% (95% CI, 96.5–98.1), 91.9% (95% CI, 89.0–94.0), and 98.4% (95% CI, 97.4–99.1), respectively. The area under the curve (AUC) was 0.99. The kappa coefficient was 0.91. The overall positive and negative likelihood ratios were 37 (95% CI 23-58) and 0.05 (95% CI, 0.03–0.09), respectively. Conclusions. Data analysis demonstrated that the antigen test showed very good accuracy for discriminating SARS-CoV-2-infected patients from negative participants. The CLEIA is suitable for rapid clinical diagnosis of patients in hospital settings, particularly in EDs with a high prevalence of symptomatic patients and where a rapid turnaround time is critical. Timely and accurate testing for SARS-CoV-2 plays a crucial role in limiting the spread of the virus.

Download Full-text

Predictive factors for the medical hospitalisation of patients who visited the emergency department with suicide attempt

10.21203/rs.3.rs-51267/v3 ◽

2021 ◽

Author(s):

Hye Jin Kim ◽

Duk Hee Lee

Keyword(s):

Emergency Department ◽

Suicide Attempt ◽

Attempted Suicide ◽

Suicide Attempts ◽

Area Under The Curve ◽

Public Health Problem ◽

Teaching Hospitals ◽

Operating Characteristics ◽

Tertiary Teaching ◽

The Mean

Abstract Background Suicide is a significant public health problem. Individuals are estimated to make up to 20 suicide attempts before suicide. The emergency department (ED) is the first location where individuals are brought after a suicide attempt. This study investigated the factors related to delays in the medical hospitalisation of patients who attempted suicide and aimed to provide criteria for hospitalisation decisions by physicians. Methods This study included patients who had deliberately self-harmed (age ≥19 years) and presented at the EDs of two tertiary teaching hospitals between March 2017 and April 2020. Those for whom relevant demographic and clinical information were unavailable and those admitted to the psychiatric wards were excluded. Results This study included 414 patients in the hospitalisation group and 1,346 in the discharged group. The mean patient age was 50.3 ± 20.0 years and 40.7 ± 17.0 years in the hospitalised and discharged groups (p <0.001), respectively. The mean ED length of stay (LOS) was 4.2 ± 12.3 and 11.4 ± 18.8 h in the hospitalised and discharged groups, respectively. In the hospitalised group, the odds ratio and confidence interval for aged 35~64 (2.222, 1.343–3.678), aged over 65 (2.788, 1.416-5.492), sex -male (2.041, 1.302–3.119), and consciousness (1.840, 1.253–2.466). The Risk-Rescue Ratio Scale (RRRS) was (1.298, 1.255–1.343). A receiver operating characteristics analysis of RRRS for the decision to hospitalise patients who attempted suicide showed a cut-off value of 42, with sensitivity, specificity, and area under the curve being 85.7%, 85.5%, and 0.924, respectively.Conclusion The level of consciousness and the RRRS of patients who attempted suicide can be the factors to decide medical hospitalisation and reduce ED LOS and crowding.

Download Full-text

Predictive factors for the medical hospitalization of patients who visited to emergency department with suicide attempt

10.21203/rs.3.rs-51267/v2 ◽

2020 ◽

Author(s):

Hye Jin Kim ◽

Duk Hee Lee

Keyword(s):

Emergency Department ◽

Suicide Attempt ◽

Attempted Suicide ◽

Suicide Attempts ◽

Area Under The Curve ◽

Public Health Problem ◽

Teaching Hospitals ◽

Operating Characteristics ◽

Tertiary Teaching ◽

The Mean

Abstract Background Suicide is a significant public health problem. Individuals are estimated to make up to 20 suicide attempts before suicide. The emergency department (ED) is the first location where individuals are brought after a suicide attempt. This study investigated the factors related to delays in the medical hospitalization of patients who attempted suicide and aimed to provide criteria for hospitalization decisions for physicians. Methods This study included who had deliberately self-harmed (age ≥19 years) and who presented at the EDs of two tertiary teaching hospitals between March 2017 and April 2020. Those for whom relevant demographic and clinical information were unavailable and those who were admitted to the psychiatric wards were excluded. Results This study included 414 patients in the hospitalization group and 1,346 in the discharged group. The mean patient age was 50.3 ± 20.0 years and 40.7 ± 17.0 years in the hospitalized and discharged groups ( p <0.001), respectively. The mean ED length of stay (LOS) was 4.2 ± 12.3 and 11.4 ± 18.8 h in the hospitalized and discharged groups, respectively . In the hospitalized group, the odds ratio and confidence interval for aged 35~64 (2.222, 1.343–3.678), aged over 65 (2.788, 1.416-5.492), sex -male (2.041, 1.302–3.119), and consciousness (1.840, 1.253–2.466). The Risk-Rescue Ratio Scale (RRRS) was (1.298, 1.255–1.343). A receiver operating characteristics analysis of RRRS for the decision to hospitalize patients who attempted suicide showed a cut-off value of 42, with sensitivity, specificity, and area under the curve being 85.7%, 85.5%, and 0.924, respectively. Conclusion The level of consciousness and the RRRS of patients who attempted suicide can be the factors to decide medical hospitalization and reduce ED LOS and crowding.

Download Full-text