Development of a data-driven COVID-19 prognostication tool to inform triage and step-down care for hospitalised patients in Hong Kong: a population-based cohort study
Abstract Background This is the first study on prognostication in an entire cohort of laboratory-confirmed COVID-19 patients in the city of Hong Kong. Prognostic tool is essential in the contingency response for the next wave of outbreak. This study aims to develop prognostic models to predict COVID...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2020-12-01
|
| Series: | BMC Medical Informatics and Decision Making |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12911-020-01338-0 |
| _version_ | 1818352910596046848 |
|---|---|
| author | Eva L. H. Tsui Carrie S. M. Lui Pauline P. S. Woo Alan T. L. Cheung Peggo K. W. Lam Van T. W. Tang C. F. Yiu C. H. Wan Libby H. Y. Lee |
| author_facet | Eva L. H. Tsui Carrie S. M. Lui Pauline P. S. Woo Alan T. L. Cheung Peggo K. W. Lam Van T. W. Tang C. F. Yiu C. H. Wan Libby H. Y. Lee |
| author_sort | Eva L. H. Tsui |
| collection | DOAJ |
| description | Abstract Background This is the first study on prognostication in an entire cohort of laboratory-confirmed COVID-19 patients in the city of Hong Kong. Prognostic tool is essential in the contingency response for the next wave of outbreak. This study aims to develop prognostic models to predict COVID-19 patients’ clinical outcome on day 1 and day 5 of hospital admission. Methods We did a retrospective analysis of a complete cohort of 1037 COVID-19 laboratory-confirmed patients in Hong Kong as of 30 April 2020, who were admitted to 16 public hospitals with their data sourced from an integrated electronic health records system. It covered demographic information, chronic disease(s) history, presenting symptoms as well as the worst clinical condition status, biomarkers’ readings and Ct value of PCR tests on Day-1 and Day-5 of admission. The study subjects were randomly split into training and testing datasets in a 8:2 ratio. Extreme Gradient Boosting (XGBoost) model was used to classify the training data into three disease severity groups on Day-1 and Day-5. Results The 1037 patients had a mean age of 37.8 (SD ± 17.8), 53.8% of them were male. They were grouped under three disease outcome: 4.8% critical/serious, 46.8% stable and 48.4% satisfactory. Under the full models, 30 indicators on Day-1 and Day-5 were used to predict the patients’ disease outcome and achieved an accuracy rate of 92.3% and 99.5%. With a trade-off between practical application and predictive accuracy, the full models were reduced into simpler models with seven common specific predictors, including the worst clinical condition status (4-level), age group, and five biomarkers, namely, CRP, LDH, platelet, neutrophil/lymphocyte ratio and albumin/globulin ratio. Day-1 model’s accuracy rate, macro-/micro-averaged sensitivity and specificity were 91.3%, 84.9%/91.3% and 96.0%/95.7% respectively, as compared to 94.2%, 95.9%/94.2% and 97.8%/97.1% under Day-5 model. Conclusions Both Day-1 and Day-5 models can accurately predict the disease severity. Relevant clinical management could be planned according to the predicted patients’ outcome. The model is transformed into a simple online calculator to provide convenient clinical reference tools at the point of care, with an aim to inform clinical decision on triage and step-down care. |
| first_indexed | 2024-12-13T19:01:08Z |
| format | Article |
| id | doaj.art-95034ad1641346b8b5158e1681ecf538 |
| institution | Directory Open Access Journal |
| issn | 1472-6947 |
| language | English |
| last_indexed | 2024-12-13T19:01:08Z |
| publishDate | 2020-12-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Informatics and Decision Making |
| spelling | doaj.art-95034ad1641346b8b5158e1681ecf5382022-12-21T23:34:41ZengBMCBMC Medical Informatics and Decision Making1472-69472020-12-0120111910.1186/s12911-020-01338-0Development of a data-driven COVID-19 prognostication tool to inform triage and step-down care for hospitalised patients in Hong Kong: a population-based cohort studyEva L. H. Tsui0Carrie S. M. Lui1Pauline P. S. Woo2Alan T. L. Cheung3Peggo K. W. Lam4Van T. W. Tang5C. F. Yiu6C. H. Wan7Libby H. Y. Lee8Statistics and Data Science Department, Hospital AuthorityStatistics and Data Science Department, Hospital AuthorityStatistics and Data Science Department, Hospital AuthorityStatistics and Data Science Department, Hospital AuthorityStatistics and Data Science Department, Hospital AuthorityStatistics and Data Science Department, Hospital AuthorityStatistics and Data Science Department, Hospital AuthorityStatistics and Data Science Department, Hospital AuthorityStrategy and Planning Division, Hospital AuthorityAbstract Background This is the first study on prognostication in an entire cohort of laboratory-confirmed COVID-19 patients in the city of Hong Kong. Prognostic tool is essential in the contingency response for the next wave of outbreak. This study aims to develop prognostic models to predict COVID-19 patients’ clinical outcome on day 1 and day 5 of hospital admission. Methods We did a retrospective analysis of a complete cohort of 1037 COVID-19 laboratory-confirmed patients in Hong Kong as of 30 April 2020, who were admitted to 16 public hospitals with their data sourced from an integrated electronic health records system. It covered demographic information, chronic disease(s) history, presenting symptoms as well as the worst clinical condition status, biomarkers’ readings and Ct value of PCR tests on Day-1 and Day-5 of admission. The study subjects were randomly split into training and testing datasets in a 8:2 ratio. Extreme Gradient Boosting (XGBoost) model was used to classify the training data into three disease severity groups on Day-1 and Day-5. Results The 1037 patients had a mean age of 37.8 (SD ± 17.8), 53.8% of them were male. They were grouped under three disease outcome: 4.8% critical/serious, 46.8% stable and 48.4% satisfactory. Under the full models, 30 indicators on Day-1 and Day-5 were used to predict the patients’ disease outcome and achieved an accuracy rate of 92.3% and 99.5%. With a trade-off between practical application and predictive accuracy, the full models were reduced into simpler models with seven common specific predictors, including the worst clinical condition status (4-level), age group, and five biomarkers, namely, CRP, LDH, platelet, neutrophil/lymphocyte ratio and albumin/globulin ratio. Day-1 model’s accuracy rate, macro-/micro-averaged sensitivity and specificity were 91.3%, 84.9%/91.3% and 96.0%/95.7% respectively, as compared to 94.2%, 95.9%/94.2% and 97.8%/97.1% under Day-5 model. Conclusions Both Day-1 and Day-5 models can accurately predict the disease severity. Relevant clinical management could be planned according to the predicted patients’ outcome. The model is transformed into a simple online calculator to provide convenient clinical reference tools at the point of care, with an aim to inform clinical decision on triage and step-down care.https://doi.org/10.1186/s12911-020-01338-0COVID-19PrognosticPredictionClinical outcomeDisease severityTriage |
| spellingShingle | Eva L. H. Tsui Carrie S. M. Lui Pauline P. S. Woo Alan T. L. Cheung Peggo K. W. Lam Van T. W. Tang C. F. Yiu C. H. Wan Libby H. Y. Lee Development of a data-driven COVID-19 prognostication tool to inform triage and step-down care for hospitalised patients in Hong Kong: a population-based cohort study BMC Medical Informatics and Decision Making COVID-19 Prognostic Prediction Clinical outcome Disease severity Triage |
| title | Development of a data-driven COVID-19 prognostication tool to inform triage and step-down care for hospitalised patients in Hong Kong: a population-based cohort study |
| title_full | Development of a data-driven COVID-19 prognostication tool to inform triage and step-down care for hospitalised patients in Hong Kong: a population-based cohort study |
| title_fullStr | Development of a data-driven COVID-19 prognostication tool to inform triage and step-down care for hospitalised patients in Hong Kong: a population-based cohort study |
| title_full_unstemmed | Development of a data-driven COVID-19 prognostication tool to inform triage and step-down care for hospitalised patients in Hong Kong: a population-based cohort study |
| title_short | Development of a data-driven COVID-19 prognostication tool to inform triage and step-down care for hospitalised patients in Hong Kong: a population-based cohort study |
| title_sort | development of a data driven covid 19 prognostication tool to inform triage and step down care for hospitalised patients in hong kong a population based cohort study |
| topic | COVID-19 Prognostic Prediction Clinical outcome Disease severity Triage |
| url | https://doi.org/10.1186/s12911-020-01338-0 |
| work_keys_str_mv | AT evalhtsui developmentofadatadrivencovid19prognosticationtooltoinformtriageandstepdowncareforhospitalisedpatientsinhongkongapopulationbasedcohortstudy AT carriesmlui developmentofadatadrivencovid19prognosticationtooltoinformtriageandstepdowncareforhospitalisedpatientsinhongkongapopulationbasedcohortstudy AT paulinepswoo developmentofadatadrivencovid19prognosticationtooltoinformtriageandstepdowncareforhospitalisedpatientsinhongkongapopulationbasedcohortstudy AT alantlcheung developmentofadatadrivencovid19prognosticationtooltoinformtriageandstepdowncareforhospitalisedpatientsinhongkongapopulationbasedcohortstudy AT peggokwlam developmentofadatadrivencovid19prognosticationtooltoinformtriageandstepdowncareforhospitalisedpatientsinhongkongapopulationbasedcohortstudy AT vantwtang developmentofadatadrivencovid19prognosticationtooltoinformtriageandstepdowncareforhospitalisedpatientsinhongkongapopulationbasedcohortstudy AT cfyiu developmentofadatadrivencovid19prognosticationtooltoinformtriageandstepdowncareforhospitalisedpatientsinhongkongapopulationbasedcohortstudy AT chwan developmentofadatadrivencovid19prognosticationtooltoinformtriageandstepdowncareforhospitalisedpatientsinhongkongapopulationbasedcohortstudy AT libbyhylee developmentofadatadrivencovid19prognosticationtooltoinformtriageandstepdowncareforhospitalisedpatientsinhongkongapopulationbasedcohortstudy |