Skip to main content

Table 2 Prediction models of inpatients matching outcomes of interest

From: Predicting clinical outcomes among hospitalized COVID-19 patients using both local and published models

# Title Location Population timepoint/inclusion criteria N Outcome Methoda Features Performanceb
1 ADL-dependency, D-Dimers, LDH and absence of anticoagulation are independently associated with one-month mortality in older inpatients with Covid-19 [15] France Inpatients,  > 65-year-old 108 Mortality Cox regression ADL-dependency, D-Dimer, LDH, Anticoagulation AUC 0.83
2 Association of cardiac biomarkers and comorbidities with increased mortality, severity, and cardiac injury in COVID-19 patients: a meta-regression and decision tree analysis [16] Brazil, China, UK, USA Inpatients 17,364 Mortality, ICU, mixed Meta-analysis, decision tree Age, Troponin I, AST Precision 74% recall 86%
3 Prediction for progression risk in patients with COVID-19 pneumonia: the CALL Score [17] China Inpatients, excluding non-COVID-19 primary infection 248 Deterioration or worsening of CT lung Cox regression, nomogram Age, ALC, comorbidities LDH AUC 0.91
4 Clinical and laboratory predictors of in-hospital mortality in patients with COVID-19: a cohort study in Wuhan, China [18] China Inpatients excluding pregnancy & multiorgan failure 296 Mortality Logistic regression Age, ALC, SAT, ANC,CRP, D-Dimer, AST, eGFR AUC 0.88
5 Development and validation of a clinical risk score to predict the occurrence of critical illness of hospitalized patients with COVID-19 [19] China Inpatients 710 Criticality Logistic regression Age, CXR, Cancer, LDH, Hemoptysis, Dyspnea, Unconsciousness, NLR, comorbidities, Direct bilirubin AUC 0.88
6 Development and validation of prognosis model of mortality risk in patients with COVID-19 [20] China Inpatients 305 Mortality Logistic regression Age, CRP, LDH AUC 0.95
7 Laboratory predictors of death from coronavirus disease 2019 (COVID-19) in the area of Valcamonica, Italy [21] Italy Inpatients 144 Mortality Logistic regression Age, LDH, CRP, WBC, ANC, ALC, albumin, PTT 80% of variance
8 Prediction model and risk scores of ICU admission and mortality in COVID-19 [22] USA, New York Inpatients 641 Mortality Logistic regression LDH, PC, smoking, SAT, ALC AUC 0.82
9 Risk factors associated with clinical outcomes in 323 COVID-19 hospitalized patients in Wuhan, China [23] China Inpatients 323 Mortality Logistic regression Age, smoking, ALC, ANC, critical disease, DM, Troponin I Not Reported
10 Risk factors of fatal outcome in hospitalized subjects with coronavirus disease 2019 from a nationwide analysis in China [24] China Inpatients 1,590 Mortality Cox regression Age, CHD, dyspnea, CVA, PC, AST AUC 0.91
11 Development of a clinical decision support system for severity risk prediction and triage of COVID-19 patients at hospital admission: an international multicenter study [25] China, Italy & Belgium Inpatients, without other severe illness 725 "Severe disease" Logistic regression Age, ALC/WBC, CRP, LDH, CK, urea, calcium AUC 0.88
12 Diagnostic performance of initial blood urea nitrogen combined with D-dimer levels for predicting in-hospital mortality in COVID-19 patients [26] China Inpatients 305 Mortality Cox regression D-Dimer, BUN AUC 0.94
13 IL-6-based mortality risk model for hospitalized patients with COVID-19 [27] Spain Inpatients 501 Mortality Logistic regression ALT, IL6, CRP, LDH, ferritin, ANC, NLR, ALC, albumin, platelets, monocytes, SAT/FiO2 ratio AUC: 0.87
14 Laboratory findings and a combined multifactorial approach to predict death in critically ill patients with COVID-19: a retrospective study [28] China Inpatients, severe 336 Mortality Logistic regression D-Dimer, ALC/WBC, BUN AUC 0.99
15 Predictive values of blood Urea nitrogen/creatinine ratio and other routine blood parameters on disease severity and survival of COVID-19 patients [29] Turkey Inpatients 139 Mortality Cox hazard regression BUN/Cr, NLR AUC 0.95
16 Prognostic modelling of COVID-19 using artificial intelligence in a UK population [30] UK Inpatients 398 Mortality Artificial neural network Age, altered mentation, HTN, CLD, collapse, Sex, cough, fever, CKD, DM, CHD, CVA, myalgia, smoking, symptom onset, BMI, diarrhea, vomiting, anosmia, ageusia, cirrhosis, abdominal pain AUC 0.90
17 Redefining cardiac biomarkers in predicting mortality of inpatients with COVID-19 [31] China Inpatients 3219 Mortality Mixed effects cox model Troponin I, CK-MB, BNP, CK, Myoglobin AUC 0.83
18 Risk factors for severe illness in hospitalized Covid-19 patients at a regional hospital [32] USA, Maryland Inpatients 117 Criticality Logistic regression Oxygen requirement, Sputum production, DM, CKD AUC 0.88
19 Scoring systems for predicting mortality for severe patients with COVID-19 [33] China Inpatients 452 Mortality Lasso/regression Age, CHD, D-Dimer, PC, ALC AUC 0.94
20 Simple nomogram based on initial laboratory data for predicting the probability of ICU transfer of COVID-19 patients: Multicenter retrospective study [34] China Inpatients 461 ICU Cox regression Age, HTN, ANC, PC, PT, D-Dimer, ALC, albumin AUC 0.85
21 Clinical characteristics, associated factors, and predicting COVID-19 mortality risk: a retrospective study in Wuhan, China [35] China Inpatients 1633 Mortality Logistic regression Age, Sex, DM, ALC, PC AUC 0.76
22 Combination of four clinical indicators predicts the severe/critical symptom of patients infected COVID-19 [36] China Inpatients 336 Mortality Cox regression Age, GSH, CD3 ratio, total protein AUC 0.98
23 Identification and validation of a novel clinical signature to predict the prognosis in confirmed COVID-19 patients [37] China Inpatients 270 Mortality Cox regression Age, CRP, ALC, ANC, PC AUC 0.95
24 Myocardial injury determination improves risk stratification and predicts mortality in COVID-19 patients [38] Spain Inpatients excluding cardiac primary 707 Mortality Cox regression Age, sex, CRP, myocardial injury, HTN, RAAS inhibitor, hematocrit, Cr, D-Dimer, CCI AUC 0.79
25 Neutrophil-to-lymphocyte ratio and outcomes in Louisiana Covid-19 patients [39] USA, Louisiana Inpatients 125 Mortality Cox Regression NLR (day 2),
NLR (day 5)
AUC 0.78
26 Prediction of the severity of Corona Virus Disease 2019 and its adverse clinical outcomes [40] China Inpatients 88 Mortality Logistic regression Age, ALC, IL 6 AUC 0.97
27 A clinical risk score to identify patients with COVID-19 at high risk of critical care admission or death: An observational cohort study [41] UK Inpatients 1157 Mortality and ICU Lasso/regression Age, sex, Cr, CKD, CLD,
Ethnicity, "index of multiple deprivation", O2 requirement, SAT, respiratory rate, CXR, ALC, ANC, CRP, albumin, cancer, DM, HTN, CHD
AUC 0.76
28 An interpretable mortality prediction model for COVID-19 patients [42] China Inpatients 375 Mortality Decision tree LDH, CRP, ALC/WBC AUC 0.99
29 Clinical prediction model for mortality of adult Diabetes inpatients with COVID-19 in Wuhan, China: a retrospective pilot study [43] China Inpatients with diabetes 78 Mortality Logistic regression PTT, BUN, WBC, LDH AUC 0.84
30 Development and external validation of a prognostic multivariable model on admission for hospitalized patients with COVID-19 [44] China Inpatients 299 Mortality Logistic regression Age, LDH, ALC, SAT AUC 0.98
31 Development and validation of a risk factor-based system to predict short-term survival in adult hospitalized patients with COVID-19: a multicenter, retrospective, cohort study [45] China Inpatients admitted w/o other severe illness 828 Mortality Cox regression Age, LDH, NLR, Direct bilirubin AUC 0.88
32 Early prediction of mortality risk among severe COVID-19 patients using machine learning [46] China Inpatients 183 Mortality Logistic regression Age, CRP, D Dimer, ALC AUC 0.88
33 Estimation of risk factors for COVID-19 mortality—preliminary results [47] China Unclear N/A Mortality Logistic regression Age, CHD, CLD, Sex Not reported
34 Evaluation and Improvement of the National Early Warning Score (NEWS2) for COVID-19: a multi-hospital study [48] UK Inpatients 439 Criticality Lasso/regression Age, BUN, SAT, CRP, eGFR, ANC, NLR, NEWS2, O2 requirement AUC 0.74
35 Host susceptibility to severe COVID-19 and establishment of a host risk score: findings of 487 cases outside Wuhan [49] China Inpatients 487 Mortality and "severe cases" Logistic regression Age, sex, HTN Not reported
36 Prognostic factors for COVID-19 pneumonia progression to severe symptom based on the earlier clinical features: a retrospective analysis [50] China Inpatients 125 "Severe" pneumonia Logistic regression Underlying disease, respiratory rate, CRP, LDH AUC 0.98
37 Risk prediction for poor outcome and death in hospital in-patients with COVID19: derivation in Wuhan, China and external validation in London, UK [51] China Inpatients 775 Mortality Logistic regression Age, sex, ALC, ANC, platelets, CRP, Cr AUC 0.91
38 Predicting severe COVID-19 at presentation, introducing the COVID Severity Score [52] Netherlands Inpatients 261 Respiratory failure Logistic regression Age, CRP, ALC, NLR, BUN, LDH, RDW, SAT AUC 0.79
39 Comorbidity and prognostic factors on admission of a covid-19 cohort in a general hospital [53] Spain Inpatients 96 Mortality Regression Age, LDH, Cardiomyopathy Not reported
40 Epidemiology, risk factors and clinical course of SARS-CoV-2 infected patients in a Swiss university hospital: an observational retrospective study [54] Switzerland Inpatients 200 Ventilation Regression Sex, qSOFA score, CXR, CRP Not reported
41 Comparison of deep learning with regression analysis in creating predictive models for SARS-CoV-2 outcomes [55] UK Inpatients 398 Mortality Artificial neural network Confusion, collapse, dyspnea, cough, CKD, heart failure, CVA, fever, sex, CHD, HTN AUC 0.93
  1. ADL, activities of daily living; ALC, absolute lymphocyte count; ANC, absolute neutrophil count; ALT, alanine aminotransferase; AST, aspartate transaminase; BUN, blood urea nitrogen; CCI, Charlson comorbidity index; CD, cluster of differentiation; CHD, coronary heart disease; CK, creatinine kinase; CK-MB, creatinine kinase-MB; CKD, chronic kidney disease; Cr, creatinine; CRP, C reactive peptide; CLD, chronic lung disease; CXR, chest Xray; CVA, cerebrovascular accident; DM, diabetes mellitus; eGFR, estimated glomerular filtration rate; FiO2, fraction of inspired oxygen; GSH, glutathione reductase; HTN, hypertension; IL,6 interleukin 6; LDH, lactate dehydrogenase; NEWS2, national early warning score 2; [48] NLR, neutrophil to lymphocyte ratio; O2, oxygen; PC, procalcitonin; PT, prothrombin time; PTT, partial thromboplastin time; qSOFA, quick sequential organ failure assessment; RAAS, renin–angiotensin–aldosterone system; RDW, red blood cell distribution width; SAT, oxygen saturation; WBC, white blood cell count
  2. aMany studies used multiple methods to help select variables or as trials. The method listed corresponds to the method used to produce the final performance listed
  3. bWhen available the area under the curve (AUC) or c-statistic is shown, if multiple, best is shown. Although other measures may have been performed, they are not shown
  4. c “Criticality” is mortality or ICU stay or ventilation