N | Author | Type of ED | Study Group (n) | Methods | Factors Analysed |
---|---|---|---|---|---|
1 | Lee S [16] | Adult | 4,645,483 | Artificial Neural Network (ANN) | Age, sex, ECI, insurance, alive |
2 | Zeleke AJ [17] | General | 12,858 | Random Forest (RF), Support Vector Machines (SVM), Gradient Boosting (GB), AdaBoost, K-Nearest Neighbors (KNN), and Logistic Regression (LR) | Gender, age, mode of arrival, triage categories, specialty, problems |
3 | Lee H [18] | Adult | 968 | C Logistic Regression, gradient boosting machine (GBM), Naïve Bayes | Triage level, sex, age, visit day, visit type, referral, severe disease, emergency operation, admission type, retransfer, consultation, diagnosis, disease |
4 | Kadri F [19] | Pediatric | 44,676 | generative adversarial network (GAN) | Arrival date/time, age, sex, diagnostic, biology, echo, radiology, scanner, LOS |
5 | Lee K.S [20] | General | 657,622 | Logistic Regression | age, sex, insurance, injury code, ambulance attendance, transferred-in, date and time, initial triage, ventilation, diagnosis codes, Charlson comorbidity index (CCI), discharge status |
6 | Srivastava S [21] | General | 33,727 | Logistic Regression | age, gender, insurance, hospital type, patient location, admission month, encounter cost, comorbidities |
7 | Etu EE [22] | General, Covid-19 | 3,301 | Logistic Regression (LR), gradient boosting (GB), decision tree (DT), random forest (RF) | Age, sex, race, covid symptoms, comorbidities, vital signs |
8 | Chang YH [23] | Adult | 92,528 | Random Forest (RF), Logistic Regression (LR), decision tree (DT), CatBoost, XGBoost | Age, sex, BMI, vital signs, consciousness, tracheotomy, transferred, arrival mode, bed request, comorbidity, pregnancy, complaints, LOS |
9 | d'Etienne JP [24] | Trauma | 110,471 | Logistic Regression, discrete event simulation | Age, sex, marital status, Ethnicity, Transfer mode, vital signs, Pox, complaint, ESI, ED crowding, Disposition |
10 | Laher AE [25] | Adult | 11,383 | Logistic Regression | Age, sex, race, HIV status, vital signs, laboratory results, |
11 | Bacchi S [15] | General | 313 | Artificial Neural Network (ANN), Random Forest (RF), convolutional neural network (CNN) | - |
12 | Sweeny A [26] | Geriatric | 16,791 | Multivariate regression | Age, sex, mode of arrival, day, time, triage type, arrival time, discharge destination |
13 | Sricharoen P [21] | General | 504 | Poisson regression | Age, sex, race, conditions, NYHA class, vital signs |
14 | Rahman MA [28] | Trauma | 80,512 | Data mining | visit type, Age, Gender Indigenous status, arrival, postcode, Triage category, problem, diagnostic, Day of week, Admit to ward, Mental health, referral, Consult, examination, Mental health request, Month, Hour |
15 | Curiati PK [29] | Geriatric | 5,025 | Logistic Regressions | Age, sex, No. of medications, diagnosis, fall, Hospitalization in the previous 6Â m |
16 | Chen C-H [30] | General | 12,962 | Natural Language Processing (NLP) | Age, sex, BMI, Vital signs, arrival time, Taiwan triage scale, LOS |
17 | Street, M [31] | Geriatric | 33,926 | Logistic Regressions | Age, sex, language, marital status, hospital, day of arrival, arrival overnight, arrival mode, triage type, time to visit, imaging |
18 | Gill, S. D [32] | General | 17,644 | gradient boosting machine (GBM) | Age, sex, mode of arrival, referral, clinician group |
19 | Zhu, T [33] | General | 894 | Coxian phase-type (PH) distribution | Region, age, sex, arrival mode, arrival time, ESI, treatment area, admission date/time |
20 | Chaou C-H [34] | General | 106,206 | accelerated failure time (AFT) | LOS, triage to physician, age, sex, triage level, transferred, patient entity, daily ED consus |
21 | Warren M [35] | Psychiatric | 6,335 | multivariate Regressions | Age, sex,race,insurance, arrival mode, diagnosis, disposition, arrival hour, visit day, visit month |
22 | Prisk D [36] | Trauma | 80,214 | Poisson regression | Age, ethnicity, Socioeconomic deprivation, practitioner type, disposition, complaint, Australasian triage scale category |
23 | Launay CP [37] | Geriatric | 993 | Artificial Neural Network (ANN) | Age, sex, drugs, falls history, Temporal disorientation, home service, Acute organ failure, home living, diagnosis, LOS |
24 | Stephens R [38] | General | 2,447 | Logistic Regressions | Age, diagnosis, complaints, LOS, sex, insurance, triage day, disposition, disposition day, severity, transport to ED, unit type, Race |
25 | Casalino E [39] | General | 20,845 | multivariate Regressions | Age, ED disposition, sex, arrival type, acuity level, ED outcome |
26 | Green N [40] | Pediatric | 780 | Statistics methods | acuity level, disposition, LOS, number of resources |
27 | van der Linden C [41] | General | 48,397 | Statistics methods | - |
28 | Nejtek V. A [42] | Psychiatric | 42 | Categorical regression | Age, sex, race, marital status, insurance, clinical diagnoses, pharmacotherapy |
29 | Ding R [43] | General | 48,896–58,316 | Quantile Regression | date and time of registration; bed placement, initial contact physician, disposition decision, ED discharge, disposition status, inpatient medicine bed occupancy rate, age, sex, insurance status, and mode of arrival, acuity level and chief complaint |
30 | Chi, C. H [44] | General, Pediatric, Trauma | 3,172 | Statistics methods | Age, Sex, shifts, disposition, ESI levels, setting, LOS |
31 | Walsh P [45] | General | 119 | Artificial Neural Network (ANN) | Age, vital signs |
32 | Tanabe P [46] | General | 403 | Statistics methods | - |
33 | Jimenez, J [47] | General | 32,758 | Statistics methods | time to triage, triage duration, patients without visit by a physician, waiting time |
34 | Tandberg D [48] | Trauma | 87,354 | Time series | - |