1
|
Datta D, Ray S, Martinez L, Newman D, Dalmida SG, Hashemi J, Sareli C, Eckardt P. Feature Identification Using Interpretability Machine Learning Predicting Risk Factors for Disease Severity of In-Patients with COVID-19 in South Florida. Diagnostics (Basel) 2024; 14:1866. [PMID: 39272651 PMCID: PMC11394003 DOI: 10.3390/diagnostics14171866] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/12/2024] [Revised: 08/16/2024] [Accepted: 08/21/2024] [Indexed: 09/15/2024] Open
Abstract
Objective: The objective of the study was to establish an AI-driven decision support system by identifying the most important features in the severity of disease for Intensive Care Unit (ICU) with Mechanical Ventilation (MV) requirement, ICU, and InterMediate Care Unit (IMCU) admission for hospitalized patients with COVID-19 in South Florida. The features implicated in the risk factors identified by the model interpretability can be used to forecast treatment plans faster before critical conditions exacerbate. Methods: We analyzed eHR data from 5371 patients diagnosed with COVID-19 from South Florida Memorial Healthcare Systems admitted between March 2020 and January 2021 to predict the need for ICU with MV, ICU, and IMCU admission. A Random Forest classifier was trained on patients' data augmented by SMOTE, collected at hospital admission. We then compared the importance of features utilizing different model interpretability analyses, such as SHAP, MDI, and Permutation Importance. Results: The models for ICU with MV, ICU, and IMCU admission identified the following factors overlapping as the most important predictors among the three outcomes: age, race, sex, BMI, diarrhea, diabetes, hypertension, early stages of kidney disease, and pneumonia. It was observed that individuals over 65 years ('older adults'), males, current smokers, and BMI classified as 'overweight' and 'obese' were at greater risk of severity of illness. The severity was intensified by the co-occurrence of two interacting features (e.g., diarrhea and diabetes). Conclusions: The top features identified by the models' interpretability were from the 'sociodemographic characteristics', 'pre-hospital comorbidities', and 'medications' categories. However, 'pre-hospital comorbidities' played a vital role in different critical conditions. In addition to individual feature importance, the feature interactions also provide crucial information for predicting the most likely outcome of patients' conditions when urgent treatment plans are needed during the surge of patients during the pandemic.
Collapse
Affiliation(s)
- Debarshi Datta
- Christine E. Lynn College of Nursing, Florida Atlantic University, Boca Raton, FL 33431, USA
| | - Subhosit Ray
- Christine E. Lynn College of Nursing, Florida Atlantic University, Boca Raton, FL 33431, USA
| | - Laurie Martinez
- Christine E. Lynn College of Nursing, Florida Atlantic University, Boca Raton, FL 33431, USA
| | - David Newman
- Christine E. Lynn College of Nursing, Florida Atlantic University, Boca Raton, FL 33431, USA
| | - Safiya George Dalmida
- Christine E. Lynn College of Nursing, Florida Atlantic University, Boca Raton, FL 33431, USA
| | - Javad Hashemi
- College of Engineering & Computer Science, Florida Atlantic University, Boca Raton, FL 33431, USA
| | | | - Paula Eckardt
- Memorial Healthcare System, Hollywood, FL 33021, USA
| |
Collapse
|
2
|
Rosychuk RJ, Khangura JK, Ortiz SS, Cheng I, Bielska IA, Yan J, Morrison LJ, Hayward J, Grant L, Hohl CM. Characteristics and outcomes of patients with COVID-19 who return to the emergency department: a multicentre observational study by the Canadian COVID-19 Emergency Department Rapid Response Network (CCEDRRN). Emerg Med J 2024; 41:210-217. [PMID: 38365437 DOI: 10.1136/emermed-2023-213277] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/11/2023] [Accepted: 02/05/2024] [Indexed: 02/18/2024]
Abstract
OBJECTIVE Unplanned return emergency department (ED) visits can reflect clinical deterioration or unmet need from the original visit. We determined the characteristics and outcomes of patients with COVID-19 who return to the ED for COVID-19-related revisits. METHODS This retrospective observational study used data for all adult patients visiting 47 Canadian EDs with COVID-19 between 1 March 2020 and 31 March 2022. Multivariable logistic regression assessed the characteristics associated with having a no return visit (SV=single visit group) versus at least one return visit (MV=return visit group) after being discharged alive at the first ED visit. RESULTS 39 809 patients with COVID-19 had 44 862 COVID-19-related ED visits: 35 468 patients (89%) had one visit (SV group) and 4341 (11%) returned to the ED (MV group) within 30 days (mean 2.2, SD=0.5 ED visit). 40% of SV patients and 16% of MV patients were admitted at their first visit, and 41% of MV patients not admitted at their first ED visit were admitted on their second visit. In the MV group, the median time to return was 4 days, 49% returned within 72 hours. In multivariable modelling, a repeat visit was associated with a variety of factors including older age (OR=1.25 per 10 years, 95% CI (1.22 to 1.28)), pregnancy (1.86 (1.46 to 2.36)) and presence of comorbidities (eg, 1.72 (1.40 to 2.10) for cancer, 2.01 (1.52 to 2.66) for obesity, 2.18 (1.42 to 3.36) for organ transplant), current/prior substance use, higher temperature or WHO severe disease (1.41 (1.29 to 1.54)). Return was less likely for females (0.82 (0.77 to 0.88)) and those boosted or fully vaccinated (0.48 (0.34 to 0.70)). CONCLUSIONS Return ED visits by patients with COVID-19 within 30 days were common during the first two pandemic years and were associated with multiple factors, many of which reflect known risk for worse outcomes. Future studies should assess reasons for revisit and opportunities to improve ED care and reduce resource use. TRIAL REGISTRATION NUMBER ClinicalTrials.gov, NCT04702945.
Collapse
Affiliation(s)
- Rhonda J Rosychuk
- Department of Pediatrics, University of Alberta, Edmonton, Alberta, Canada
| | - Jaspreet K Khangura
- Department of Emergency Medicine, University of Alberta, Edmonton, Alberta, Canada
| | - Sylvia S Ortiz
- Department of Pediatrics, University of Alberta, Edmonton, Alberta, Canada
| | - Ivy Cheng
- Sunnybrook Research Institute, Toronto, Ontario, Canada
- Division of Emergency/Department of Medicine, University of Toronto, Toronto, Ontario, Canada
| | - Iwona A Bielska
- Department of Health Research Methods, Evidence, and Impact, McMaster University, Hamilton, Ontario, Canada
- Institute of Public Health, Jagiellonian University, Krakow, Poland
| | - Justin Yan
- Division of Emergency Medicine, Department of Medicine, London Health Sciences Centre, London, Ontario, Canada
- Schulich School of Medicine and Dentistry, Western University, London, Ontario, Canada
| | - Laurie J Morrison
- Department of Emergency Services, Sunnybrook Health Sciences Centre, Toronto, Ontario, Canada
- Division of Emergency Medicine, University of Toronto, Toronto, Ontario, Canada
| | - Jake Hayward
- Department of Emergency Medicine, University of Alberta, Edmonton, Alberta, Canada
| | - Lars Grant
- Department of Emergency Medicine, McGill University, Montreal, Quebec, Canada
- Lady Davis Institute for Medical Research, Montreal, Québec, Canada
| | - Corinne M Hohl
- Department of Emergency Medicine, The University of British Columbia, Vancouver, British Columbia, Canada
- Emergency Department, Vancouver General Hospital, Vancouver, British Columbia, Canada
| |
Collapse
|
3
|
Brooks SC, Rosychuk RJ, Perry JJ, Morrison LJ, Wiemer H, Fok P, Rowe BH, Daoust R, Vatanpour S, Turner J, Landes M, Ohle R, Hayward J, Scheuermeyer F, Welsford M, Hohl C. Derivation and validation of a clinical decision rule to risk-stratify COVID-19 patients discharged from the emergency department: The CCEDRRN COVID discharge score. J Am Coll Emerg Physicians Open 2022; 3:e12868. [PMID: 36579029 PMCID: PMC9780419 DOI: 10.1002/emp2.12868] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/15/2022] [Revised: 11/10/2022] [Accepted: 11/17/2022] [Indexed: 12/24/2022] Open
Abstract
Objective To risk-stratify COVID-19 patients being considered for discharge from the emergency department (ED). Methods We conducted an observational study to derive and validate a clinical decision rule to identify COVID-19 patients at risk for hospital admission or death within 72 hours of ED discharge. We used data from 49 sites in the Canadian COVID-19 Emergency Department Rapid Response Network (CCEDRRN) between March 1, 2020, and September 8, 2021. We randomly assigned hospitals to derivation or validation and prespecified clinical variables as candidate predictors. We used logistic regression to develop the score in a derivation cohort and examined its performance in predicting short-term adverse outcomes in a validation cohort. Results Of 15,305 eligible patient visits, 535 (3.6%) experienced the outcome. The score included age, sex, pregnancy status, temperature, arrival mode, respiratory rate, and respiratory distress. The area under the curve was 0.70 (95% confidence interval [CI] 0.68-0.73) in derivation and 0.71 (95% CI 0.68-0.73) in combined derivation and validation cohorts. Among those with a score of 3 or less, the risk for the primary outcome was 1.9% or less, and the sensitivity of using 3 as a rule-out score was 89.3% (95% CI 82.7-94.0). Among those with a score of ≥9, the risk for the primary outcome was as high as 12.2% and the specificity of using 9 as a rule-in score was 95.6% (95% CI 94.9-96.2). Conclusion The CCEDRRN COVID discharge score can identify patients at risk of short-term adverse outcomes after ED discharge with variables that are readily available on patient arrival.
Collapse
Affiliation(s)
- Steven C. Brooks
- Departments of Emergency Medicine and Public Health SciencesQueen's UniversityKingstonOntarioCanada
| | | | - Jeffrey J. Perry
- Department of Emergency MedicineUniversity of OttawaOttawaOntarioCanada
| | - Laurie J. Morrison
- Department of Emergency Services, Sunnybrook Health Sciences Centre, Department of Medicine, Division of Emergency MedicineUniversity of TorontoTorontoOntarioCanada
| | - Hana Wiemer
- Department of Emergency MedicineDalhousie UniversityHalifaxNova ScotiaCanada
| | - Patrick Fok
- Department of Emergency MedicineDalhousie UniversityHalifaxNova ScotiaCanada
| | - Brian H. Rowe
- Department of Emergency MedicineUniversity of AlbertaEdmontonAlbertaCanada
| | - Raoul Daoust
- Departement de Médecine de Famille et Médecine d'urgenceUniversité de MontréalMontréalQuébecCanada
| | - Shabnam Vatanpour
- Department of Emergency MedicineUniversity of CalgaryCalgaryAlbertaCanada
| | - Joel Turner
- Department of Emergency MedicineMcGill UniversityMontréalQuébecCanada
| | - Megan Landes
- Department of Family and Community MedicineDivision of Emergency MedicineUniversity of TorontoTorontoOntarioCanada
| | - Robert Ohle
- Department of Emergency Medicine, Health Science North Research InstituteNorthern Ontario School of MedicineSudburyOntarioCanada
| | - Jake Hayward
- Department of Emergency MedicineUniversity of AlbertaEdmontonAlbertaCanada
| | - Frank Scheuermeyer
- Department of Emergency MedicineUniversity of British ColumbiaVancouverBritish ColumbiaCanada
| | - Michelle Welsford
- Department of Medicine, Division of Emergency MedicineMcMaster UniversityHamiltonOntarioCanada
| | - Corinne Hohl
- Department of Emergency MedicineUniversity of British ColumbiaVancouverBritish ColumbiaCanada
| | | |
Collapse
|
4
|
Zhao X, Lai JW, Wah Ho AF, Liu N, Hock Ong ME, Cheong KH. Predicting hospital emergency department visits with deep learning approaches. Biocybern Biomed Eng 2022. [DOI: 10.1016/j.bbe.2022.07.008] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
|
5
|
Bayly BL, Kercheval JB, Cranford JA, Girgla T, Adapa AR, Busschots GV, Li KY, Perry M, Fung CM, Greineder CF, Losman ED. The MedConnect Program: Symptomatology, Return Visits, and Hospitalization of COVID-19 Outpatients Following Discharge From the Emergency Department. Cureus 2022; 14:e26771. [PMID: 35967167 PMCID: PMC9366921 DOI: 10.7759/cureus.26771] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 07/12/2022] [Indexed: 11/27/2022] Open
Abstract
Background and objective Although hospitalization is required for only a minority of those infected with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the high rates of morbidity and mortality among these patients have led researchers to focus on the predictors of admission and adverse outcomes in the inpatient population. However, there is scarce data on the clinical trajectory of individuals symptomatic enough to present for emergency care, but not sick enough to be admitted. In light of this, we aimed to examine the symptomatology, emergency department (ED) revisits, and hospitalization of coronavirus disease 2019 (COVID-19) outpatients after discharge from the ED. Methods Adult patients with COVID-19 infection were prospectively enrolled after discharge from the ED between May and December 2020. Patients were followed up longitudinally for 14 days via phone interviews designed to provide support and information and to track symptomatology, ED revisits, and hospitalization. Results A volunteer, medical student-run program enrolled 199 COVID-19 patients discharged from the ED during the first nine months of the pandemic. Of the 176 patients (88.4%) who completed the 14-day protocol, 29 (16.5%) had a second ED visit and 17 (9.6%) were admitted, 16 (9%) for worsening COVID-19 symptoms. Age, male sex, comorbid illnesses, and self-reported dyspnea, diarrhea, chills, and fever were associated with hospital admission for patients with a subsequent ED visit. For those who did not require admission, symptoms generally improved following ED discharge. Age >65 years and a history of cardiovascular disease (CVD) were associated with a longer duration of cough, but generally, patient characteristics and comorbidities did not significantly affect the overall number or duration of symptoms. Conclusions Nearly one in five patients discharged from the ED with COVID-19 infection had a second ED evaluation during a 14-day follow-up period, despite regular phone interactions aimed at providing support and information. More than half of them required admission for worsening COVID-19 symptoms. Established risk factors for severe disease and self-reported persistence of certain symptoms were associated with hospital admission, while those who did not require hospitalization had a steady improvement in symptoms over the 14-day period.
Collapse
|