1
|
Oh TK, Song IA. Deterioration in Quality of Life among COVID-19 Survivors: Population-Based Cohort Study. J Pers Med 2024; 14:569. [PMID: 38929790 PMCID: PMC11204676 DOI: 10.3390/jpm14060569] [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: 04/10/2024] [Revised: 05/16/2024] [Accepted: 05/25/2024] [Indexed: 06/28/2024] Open
Abstract
We aimed to examine the prevalence of, and factors associated with, quality of life (QOL) worsening among coronavirus disease 2019 (COVID-19) survivors. This population-based retrospective cohort study used data from the Korea Disease Control and Prevention Agency and the National Health Insurance Service in South Korea. A total of 325,666 COVID-19 survivors were included in this study. Among them, 106,091 (32.6%) survivors experienced worsening QOL after COVID-19. Specifically, 21,223 (6.5%) participants experienced job loss, 94,556 (29.0%) experienced decreased household income, and 559 (0.2%) acquired new disabilities. In the multivariable logistic regression model, living in rural areas (odds ratio [OR]: 1.02; 95% confidence interval [CI]: 1.01, 1.04; p = 0.009), intensive care unit admission (OR: 1.08, 95% CI: 1.02, 1.15; p = 0.028), and increase in self-payment by 100 USD (OR: 1.02, 95% CI: 1.02, 1.02; p < 0.001) were associated with increased QOL worsening after COVID-19. Old age (OR: 0.99, 95% CI: 0.98, 0.99; p < 0.001), first vaccination (OR: 0.89, 95% CI: 0.86, 0.93; p < 0.001), and second vaccination (OR: 0.95, 95% CI: 0.93, 0.96; p < 0.001) were associated with decreased QOL worsening after COVID-19. Approximately one-third of COVID-19 survivors in South Korea who were admitted to hospitals or monitoring centers experienced QOL worsening.
Collapse
Affiliation(s)
- Tak Kyu Oh
- Department of Anesthesiology and Pain Medicine, Seoul National University Bundang Hospital, Seongnam 13620, Republic of Korea;
- Department of Anesthesiology and Pain Medicine, College of Medicine, Seoul National University, Seoul 01811, Republic of Korea
| | - In-Ae Song
- Department of Anesthesiology and Pain Medicine, Seoul National University Bundang Hospital, Seongnam 13620, Republic of Korea;
- Department of Anesthesiology and Pain Medicine, College of Medicine, Seoul National University, Seoul 01811, Republic of Korea
| |
Collapse
|
2
|
Espinosa-Gonzalez A, Prociuk D, Fiorentino F, Ramtale C, Mi E, Mi E, Glampson B, Neves AL, Okusi C, Husain L, Macartney J, Brown M, Browne B, Warren C, Chowla R, Heaversedge J, Greenhalgh T, de Lusignan S, Mayer E, Delaney BC. Remote COVID-19 Assessment in Primary Care (RECAP) risk prediction tool: derivation and real-world validation studies. Lancet Digit Health 2022; 4:e646-e656. [PMID: 35909058 PMCID: PMC9333950 DOI: 10.1016/s2589-7500(22)00123-6] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/24/2022] [Revised: 05/11/2022] [Accepted: 06/15/2022] [Indexed: 12/13/2022]
Abstract
BACKGROUND Accurate assessment of COVID-19 severity in the community is essential for patient care and requires COVID-19-specific risk prediction scores adequately validated in a community setting. Following a qualitative phase to identify signs, symptoms, and risk factors, we aimed to develop and validate two COVID-19-specific risk prediction scores. Remote COVID-19 Assessment in Primary Care-General Practice score (RECAP-GP; without peripheral oxygen saturation [SpO2]) and RECAP-oxygen saturation score (RECAP-O2; with SpO2). METHODS RECAP was a prospective cohort study that used multivariable logistic regression. Data on signs and symptoms (predictors) of disease were collected from community-based patients with suspected COVID-19 via primary care electronic health records and linked with secondary data on hospital admission (outcome) within 28 days of symptom onset. Data sources for RECAP-GP were Oxford-Royal College of General Practitioners Research and Surveillance Centre (RCGP-RSC) primary care practices (development set), northwest London primary care practices (validation set), and the NHS COVID-19 Clinical Assessment Service (CCAS; validation set). The data source for RECAP-O2 was the Doctaly Assist platform (development set and validation set in subsequent sample). The two probabilistic risk prediction models were built by backwards elimination using the development sets and validated by application to the validation datasets. Estimated sample size per model, including the development and validation sets was 2880 people. FINDINGS Data were available from 8311 individuals. Observations, such as SpO2, were mostly missing in the northwest London, RCGP-RSC, and CCAS data; however, SpO2 was available for 1364 (70·0%) of 1948 patients who used Doctaly. In the final predictive models, RECAP-GP (n=1863) included sex (male and female), age (years), degree of breathlessness (three point scale), temperature symptoms (two point scale), and presence of hypertension (yes or no); the area under the curve was 0·80 (95% CI 0·76-0·85) and on validation the negative predictive value of a low risk designation was 99% (95% CI 98·1-99·2; 1435 of 1453). RECAP-O2 included age (years), degree of breathlessness (two point scale), fatigue (two point scale), and SpO2 at rest (as a percentage); the area under the curve was 0·84 (0·78-0·90) and on validation the negative predictive value of low risk designation was 99% (95% CI 98·9-99·7; 1176 of 1183). INTERPRETATION Both RECAP models are valid tools to assess COVID-19 patients in the community. RECAP-GP can be used initially, without need for observations, to identify patients who require monitoring. If the patient is monitored and SpO2 is available, RECAP-O2 is useful to assess the need for treatment escalation. FUNDING Community Jameel and the Imperial College President's Excellence Fund, the Economic and Social Research Council, UK Research and Innovation, and Health Data Research UK.
Collapse
Affiliation(s)
- Ana Espinosa-Gonzalez
- Institute of Global Health Innovation, Department of Surgery and Cancer, Imperial College London, London, UK
| | - Denys Prociuk
- Institute of Global Health Innovation, Department of Surgery and Cancer, Imperial College London, London, UK
| | - Francesca Fiorentino
- Institute of Global Health Innovation, Department of Surgery and Cancer, Imperial College London, London, UK; Nightingale-Saunders Clinical Trials & Epidemiology Unit, King's Clinical Trials Unit, King's College London, London, UK
| | - Christian Ramtale
- Institute of Global Health Innovation, Department of Surgery and Cancer, Imperial College London, London, UK
| | - Ella Mi
- Institute of Global Health Innovation, Department of Surgery and Cancer, Imperial College London, London, UK
| | - Emma Mi
- Institute of Global Health Innovation, Department of Surgery and Cancer, Imperial College London, London, UK
| | - Ben Glampson
- Department of Surgery and Cancer, Imperial College Healthcare NHS Trust, London, UK
| | - Ana Luisa Neves
- Institute of Global Health Innovation, Department of Surgery and Cancer, Imperial College London, London, UK
| | - Cecilia Okusi
- Nuffield Department of Primary Care, University of Oxford, Oxford, UK
| | - Laiba Husain
- Nuffield Department of Primary Care, University of Oxford, Oxford, UK
| | - Jack Macartney
- Nuffield Department of Primary Care, University of Oxford, Oxford, UK
| | - Martina Brown
- South Central Ambulance Service NHS Trust, Otterboure, UK
| | - Ben Browne
- South Central Ambulance Service NHS Trust, Otterboure, UK
| | | | | | | | - Trisha Greenhalgh
- Nuffield Department of Primary Care, University of Oxford, Oxford, UK
| | - Simon de Lusignan
- Nuffield Department of Primary Care, University of Oxford, Oxford, UK
| | - Erik Mayer
- Institute of Global Health Innovation, Department of Surgery and Cancer, Imperial College London, London, UK
| | - Brendan C Delaney
- Institute of Global Health Innovation, Department of Surgery and Cancer, Imperial College London, London, UK.
| |
Collapse
|
3
|
Risk stratification of patients with COVID-19 in the community. Lancet Digit Health 2022; 4:e628-e629. [PMID: 35909059 PMCID: PMC9333948 DOI: 10.1016/s2589-7500(22)00146-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/05/2022] [Accepted: 07/11/2022] [Indexed: 11/23/2022]
|
4
|
Meza-Torres B, Delanerolle G, Okusi C, Mayor N, Anand S, Macartney J, Gatenby P, Glampson B, Chapman M, Curcin V, Mayer E, Joy M, Greenhalgh T, Delaney B, de Lusignan S. Differences in Clinical Presentation With Long COVID After Community and Hospital Infection and Associations With All-Cause Mortality: English Sentinel Network Database Study. JMIR Public Health Surveill 2022; 8:e37668. [PMID: 35605170 PMCID: PMC9384859 DOI: 10.2196/37668] [Citation(s) in RCA: 11] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/02/2022] [Revised: 05/06/2022] [Accepted: 05/17/2022] [Indexed: 01/12/2023] Open
Abstract
BACKGROUND Most studies of long COVID (symptoms of COVID-19 infection beyond 4 weeks) have focused on people hospitalized in their initial illness. Long COVID is thought to be underrecorded in UK primary care electronic records. OBJECTIVE We sought to determine which symptoms people present to primary care after COVID-19 infection and whether presentation differs in people who were not hospitalized, as well as post-long COVID mortality rates. METHODS We used routine data from the nationally representative primary care sentinel cohort of the Oxford-Royal College of General Practitioners Research and Surveillance Centre (N=7,396,702), applying a predefined long COVID phenotype and grouped by whether the index infection occurred in hospital or in the community. We included COVID-19 infection cases from March 1, 2020, to April 1, 2021. We conducted a before-and-after analysis of long COVID symptoms prespecified by the Office of National Statistics, comparing symptoms presented between 1 and 6 months after the index infection matched with the same months 1 year previously. We conducted logistic regression analysis, quoting odds ratios (ORs) with 95% CIs. RESULTS In total, 5.63% (416,505/7,396,702) and 1.83% (7623/416,505) of the patients had received a coded diagnosis of COVID-19 infection and diagnosis of, or referral for, long COVID, respectively. People with diagnosis or referral of long COVID had higher odds of presenting the prespecified symptoms after versus before COVID-19 infection (OR 2.66, 95% CI 2.46-2.88, for those with index community infection and OR 2.42, 95% CI 2.03-2.89, for those hospitalized). After an index community infection, patients were more likely to present with nonspecific symptoms (OR 3.44, 95% CI 3.00-3.95; P<.001) compared with after a hospital admission (OR 2.09, 95% CI 1.56-2.80; P<.001). Mental health sequelae were more strongly associated with index hospital infections (OR 2.21, 95% CI 1.64-2.96) than with index community infections (OR 1.36, 95% CI 1.21-1.53; P<.001). People presenting to primary care after hospital infection were more likely to be men (OR 1.43, 95% CI 1.25-1.64; P<.001), more socioeconomically deprived (OR 1.42, 95% CI 1.24-1.63; P<.001), and with higher multimorbidity scores (OR 1.41, 95% CI 1.26-1.57; P<.001) than those presenting after an index community infection. All-cause mortality in people with long COVID was associated with increasing age, male sex (OR 3.32, 95% CI 1.34-9.24; P=.01), and higher multimorbidity score (OR 2.11, 95% CI 1.34-3.29; P<.001). Vaccination was associated with reduced odds of mortality (OR 0.10, 95% CI 0.03-0.35; P<.001). CONCLUSIONS The low percentage of people recorded as having long COVID after COVID-19 infection reflects either low prevalence or underrecording. The characteristics and comorbidities of those presenting with long COVID after a community infection are different from those hospitalized. This study provides insights into the presentation of long COVID in primary care and implications for workload.
Collapse
Affiliation(s)
- Bernardo Meza-Torres
- Nuffield Department of Primary Care Health Sciences, University of Oxford, Oxford, United Kingdom
| | - Gayathri Delanerolle
- Nuffield Department of Primary Care Health Sciences, University of Oxford, Oxford, United Kingdom
| | - Cecilia Okusi
- Nuffield Department of Primary Care Health Sciences, University of Oxford, Oxford, United Kingdom
| | - Nikhil Mayor
- Royal Surrey NHS Foundation Trust, Guildford, United Kingdom
| | - Sneha Anand
- Nuffield Department of Primary Care Health Sciences, University of Oxford, Oxford, United Kingdom
| | - Jack Macartney
- Nuffield Department of Primary Care Health Sciences, University of Oxford, Oxford, United Kingdom
| | - Piers Gatenby
- Royal Surrey NHS Foundation Trust, Guildford, United Kingdom
| | - Ben Glampson
- Imperial College Healthcare NHS Trust, Imperial Clinical Analytics, Research & Evaluation (iCARE), London, United Kingdom
| | - Martin Chapman
- King's College London, Population Health Sciences, London, United Kingdom
| | - Vasa Curcin
- King's College London, Population Health Sciences, London, United Kingdom
| | - Erik Mayer
- Imperial College Healthcare NHS Trust, Imperial Clinical Analytics, Research & Evaluation (iCARE), London, United Kingdom
| | - Mark Joy
- Nuffield Department of Primary Care Health Sciences, University of Oxford, Oxford, United Kingdom
| | - Trisha Greenhalgh
- Nuffield Department of Primary Care Health Sciences, University of Oxford, Oxford, United Kingdom
| | - Brendan Delaney
- Department of Surgery & Cancer, Institute of Global Health Innovation, Imperial College London, London, United Kingdom
| | - Simon de Lusignan
- Nuffield Department of Primary Care Health Sciences, University of Oxford, Oxford, United Kingdom
| |
Collapse
|
5
|
Mayor N, Meza-Torres B, Okusi C, Delanerolle G, Chapman M, Wang W, Anand S, Feher M, Macartney J, Byford R, Joy M, Gatenby P, Curcin V, Greenhalgh T, Delaney B, de Lusignan S. Developing a Long COVID Phenotype for Postacute COVID-19 in a National Primary Care Sentinel Cohort: Observational Retrospective Database Analysis. JMIR Public Health Surveill 2022; 8:e36989. [PMID: 35861678 PMCID: PMC9374163 DOI: 10.2196/36989] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/03/2022] [Revised: 05/16/2022] [Accepted: 07/19/2022] [Indexed: 11/13/2022] Open
Abstract
BACKGROUND Following COVID-19, up to 40% of people have ongoing health problems, referred to as postacute COVID-19 or long COVID (LC). LC varies from a single persisting symptom to a complex multisystem disease. Research has flagged that this condition is underrecorded in primary care records, and seeks to better define its clinical characteristics and management. Phenotypes provide a standard method for case definition and identification from routine data and are usually machine-processable. An LC phenotype can underpin research into this condition. OBJECTIVE This study aims to develop a phenotype for LC to inform the epidemiology and future research into this condition. We compared clinical symptoms in people with LC before and after their index infection, recorded from March 1, 2020, to April 1, 2021. We also compared people recorded as having acute infection with those with LC who were hospitalized and those who were not. METHODS We used data from the Primary Care Sentinel Cohort (PCSC) of the Oxford Royal College of General Practitioners (RCGP) Research and Surveillance Centre (RSC) database. This network was recruited to be nationally representative of the English population. We developed an LC phenotype using our established 3-step ontological method: (1) ontological step (defining the reasoning process underpinning the phenotype, (2) coding step (exploring what clinical terms are available, and (3) logical extract model (testing performance). We created a version of this phenotype using Protégé in the ontology web language for BioPortal and using PhenoFlow. Next, we used the phenotype to compare people with LC (1) with regard to their symptoms in the year prior to acquiring COVID-19 and (2) with people with acute COVID-19. We also compared hospitalized people with LC with those not hospitalized. We compared sociodemographic details, comorbidities, and Office of National Statistics-defined LC symptoms between groups. We used descriptive statistics and logistic regression. RESULTS The long-COVID phenotype differentiated people hospitalized with LC from people who were not and where no index infection was identified. The PCSC (N=7.4 million) includes 428,479 patients with acute COVID-19 diagnosis confirmed by a laboratory test and 10,772 patients with clinically diagnosed COVID-19. A total of 7471 (1.74%, 95% CI 1.70-1.78) people were coded as having LC, 1009 (13.5%, 95% CI 12.7-14.3) had a hospital admission related to acute COVID-19, and 6462 (86.5%, 95% CI 85.7-87.3) were not hospitalized, of whom 2728 (42.2%) had no COVID-19 index date recorded. In addition, 1009 (13.5%, 95% CI 12.73-14.28) people with LC were hospitalized compared to 17,993 (4.5%, 95% CI 4.48-4.61; P<.001) with uncomplicated COVID-19. CONCLUSIONS Our LC phenotype enables the identification of individuals with the condition in routine data sets, facilitating their comparison with unaffected people through retrospective research. This phenotype and study protocol to explore its face validity contributes to a better understanding of LC.
Collapse
Affiliation(s)
- Nikhil Mayor
- Royal Surrey NHS Foundation Trust, Guildford, United Kingdom
| | - Bernardo Meza-Torres
- Nuffield Department of Primary Care Health Sciences, University of Oxford, Oxford, United Kingdom
- Department of Clinical and Experimental Medicine, University of Surrey, Guildford, United Kingdom
| | - Cecilia Okusi
- Department of Surgery & Cancer, Institute of Global Health Innovation, Imperial College London, London, United Kingdom
| | - Gayathri Delanerolle
- Department of Surgery & Cancer, Institute of Global Health Innovation, Imperial College London, London, United Kingdom
| | - Martin Chapman
- Population Health Sciences, Kings College London, London, United Kingdom
| | - Wenjuan Wang
- Population Health Sciences, Kings College London, London, United Kingdom
| | - Sneha Anand
- Department of Surgery & Cancer, Institute of Global Health Innovation, Imperial College London, London, United Kingdom
| | - Michael Feher
- Nuffield Department of Primary Care Health Sciences, University of Oxford, Oxford, United Kingdom
| | - Jack Macartney
- Nuffield Department of Primary Care Health Sciences, University of Oxford, Oxford, United Kingdom
| | - Rachel Byford
- Nuffield Department of Primary Care Health Sciences, University of Oxford, Oxford, United Kingdom
| | - Mark Joy
- Nuffield Department of Primary Care Health Sciences, University of Oxford, Oxford, United Kingdom
| | - Piers Gatenby
- Royal Surrey NHS Foundation Trust, Guildford, United Kingdom
| | - Vasa Curcin
- Population Health Sciences, Kings College London, London, United Kingdom
| | - Trisha Greenhalgh
- Nuffield Department of Primary Care Health Sciences, University of Oxford, Oxford, United Kingdom
| | - Brendan Delaney
- Department of Surgery & Cancer, Institute of Global Health Innovation, Imperial College London, London, United Kingdom
| | - Simon de Lusignan
- Nuffield Department of Primary Care Health Sciences, University of Oxford, Oxford, United Kingdom
- Royal College of General Practitioners Research and Surveillance Centre, London, United Kingdom
| |
Collapse
|
6
|
Fiorentino F, Prociuk D, Espinosa Gonzalez AB, Neves AL, Husain L, Ramtale SC, Mi E, Mi E, Macartney J, Anand SN, Sherlock J, Saravanakumar K, Mayer E, de Lusignan S, Greenhalgh T, Delaney BC. An Early Warning Risk Prediction Tool (RECAP-V1) for Patients Diagnosed With COVID-19: Protocol for a Statistical Analysis Plan. JMIR Res Protoc 2021; 10:e30083. [PMID: 34468322 PMCID: PMC8494068 DOI: 10.2196/30083] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/05/2021] [Revised: 06/15/2021] [Accepted: 07/05/2021] [Indexed: 12/23/2022] Open
Abstract
BACKGROUND Since the start of the COVID-19 pandemic, efforts have been made to develop early warning risk scores to help clinicians decide which patient is likely to deteriorate and require hospitalization. The RECAP (Remote COVID-19 Assessment in Primary Care) study investigates the predictive risk of hospitalization, deterioration, and death of patients with confirmed COVID-19, based on a set of parameters chosen through a Delphi process performed by clinicians. We aim to use rich data collected remotely through the use of electronic data templates integrated in the electronic health systems of several general practices across the United Kingdom to construct accurate predictive models. The models will be based on preexisting conditions and monitoring data of a patient's clinical parameters (eg, blood oxygen saturation) to make reliable predictions as to the patient's risk of hospital admission, deterioration, and death. OBJECTIVE This statistical analysis plan outlines the statistical methods to build the prediction model to be used in the prioritization of patients in the primary care setting. The statistical analysis plan for the RECAP study includes the development and validation of the RECAP-V1 prediction model as a primary outcome. This prediction model will be adapted as a three-category risk score split into red (high risk), amber (medium risk), and green (low risk) for any patient with suspected COVID-19. The model will predict the risk of deterioration and hospitalization. METHODS After the data have been collected, we will assess the degree of missingness and use a combination of traditional data imputation using multiple imputation by chained equations, as well as more novel machine-learning approaches to impute the missing data for the final analysis. For predictive model development, we will use multiple logistic regression analyses to construct the model. We aim to recruit a minimum of 1317 patients for model development and validation. We will then externally validate the model on an independent dataset of 1400 patients. The model will also be applied for multiple different datasets to assess both its performance in different patient groups and its applicability for different methods of data collection. RESULTS As of May 10, 2021, we have recruited 3732 patients. A further 2088 patients have been recruited through the National Health Service Clinical Assessment Service, and approximately 5000 patients have been recruited through the DoctalyHealth platform. CONCLUSIONS The methodology for the development of the RECAP-V1 prediction model as well as the risk score will provide clinicians with a statistically robust tool to help prioritize COVID-19 patients. TRIAL REGISTRATION ClinicalTrials.gov NCT04435041; https://clinicaltrials.gov/ct2/show/NCT04435041. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID) DERR1-10.2196/30083.
Collapse
Affiliation(s)
- Francesca Fiorentino
- Department of Surgery and Cancer, Imperial College London, London, United Kingdom
- Imperial Clinical Trials Unit, Imperial College London, London, United Kingdom
| | - Denys Prociuk
- Department of Surgery and Cancer, Imperial College London, London, United Kingdom
| | | | - Ana Luisa Neves
- Patient Safety Translational Research Centre, Institute of Global Health Innovation, Imperial College London, London, United Kingdom
| | - Laiba Husain
- Nuffield Department of Primary Care Health Sciences, University of Oxford, Oxford, United Kingdom
| | | | - Emma Mi
- Department of Surgery and Cancer, Imperial College London, London, United Kingdom
| | - Ella Mi
- Department of Surgery and Cancer, Imperial College London, London, United Kingdom
| | - Jack Macartney
- Nuffield Department of Primary Care Health Sciences, University of Oxford, Oxford, United Kingdom
| | - Sneha N Anand
- Nuffield Department of Primary Care Health Sciences, University of Oxford, Oxford, United Kingdom
| | - Julian Sherlock
- Nuffield Department of Primary Care Health Sciences, University of Oxford, Oxford, United Kingdom
| | - Kavitha Saravanakumar
- Whole Systems Integrated Care, North West London Collaboration of Clinical Commissioning Group, London, United Kingdom
| | - Erik Mayer
- Department of Surgery and Cancer, Imperial College London, London, United Kingdom
| | - Simon de Lusignan
- Nuffield Department of Primary Care Health Sciences, University of Oxford, Oxford, United Kingdom
- Royal College of General Practitioners Research and Surveillance Centre, London, United Kingdom
| | - Trisha Greenhalgh
- Nuffield Department of Primary Care Health Sciences, University of Oxford, Oxford, United Kingdom
| | - Brendan C Delaney
- Department of Surgery and Cancer, Imperial College London, London, United Kingdom
| |
Collapse
|
7
|
Campbell TW, Wilson MP, Roder H, MaWhinney S, Georgantas RW, Maguire LK, Roder J, Erlandson KM. Predicting prognosis in COVID-19 patients using machine learning and readily available clinical data. Int J Med Inform 2021; 155:104594. [PMID: 34601240 PMCID: PMC8459591 DOI: 10.1016/j.ijmedinf.2021.104594] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/11/2021] [Revised: 08/30/2021] [Accepted: 09/21/2021] [Indexed: 12/12/2022]
Abstract
Rationale Prognostic tools for aiding in the treatment of hospitalized COVID-19 patients could help improve outcome by identifying patients at higher or lower risk of severe disease. The study objective was to develop models to stratify patients by risk of severe outcomes during COVID-19 hospitalization using readily available information at hospital admission. Methods Hierarchical ensemble classification models were trained on a set of 229 patients hospitalized with COVID-19 to predict severe outcomes, including ICU admission, development of acute respiratory distress syndrome, or intubation, using easily attainable attributes including basic patient characteristics, vital signs at admission, and basic lab results collected at time of presentation. Each test stratifies patients into groups of increasing risk. An additional cohort of 330 patients was used for blinded, independent validation. Shapley value analysis evaluated which attributes contributed most to the models’ predictions of risk. Main results Test performance was assessed using precision (positive predictive value) and recall (sensitivity) of the final risk groups. All test cut-offs were fixed prior to blinded validation. In development and validation, the tests achieved precision in the lowest risk groups near or above 0.9. The proportion of patients with severe outcomes significantly increased across increasing risk groups. While the importance of attributes varied by test and patient, C-reactive protein, lactate dehydrogenase, and D-dimer were often found to be important in the assignment of risk. Conclusions Risk of severe outcomes for patients hospitalized with COVID-19 infection can be assessed using machine learning-based models based on attributes routinely collected at hospital admission.
Collapse
Affiliation(s)
| | - Melissa P Wilson
- Department of Medicine, Division of Personalized Medicine and Bioinformatics, University of Colorado-Anschutz Medical Campus, Aurora, CO, United States
| | | | - Samantha MaWhinney
- Department of Biostatistics and Informatics, University of Colorado, Colorado School of Public Health, United States
| | | | | | | | - Kristine M Erlandson
- Department of Medicine, Division of Infectious Diseases, University of Colorado-Anschutz Medical Campus, Aurora, CO, United States
| |
Collapse
|