Developing and validating a machine learning prognostic model for alerting to imminent deterioration of hospitalized patients with COVID-19
Abstract Our study was aimed at developing and validating a new approach, embodied in a machine learning-based model, for sequentially monitoring hospitalized COVID-19 patients and directing professional attention to patients whose deterioration is imminent. Model development employed real-world pat...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-11-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-23553-7 |
| _version_ | 1798018405518802944 |
|---|---|
| author | Yuri Kogan Ari Robinson Edward Itelman Yeonatan Bar-Nur Daniel Jorge Jakobson Gad Segal Zvia Agur |
| author_facet | Yuri Kogan Ari Robinson Edward Itelman Yeonatan Bar-Nur Daniel Jorge Jakobson Gad Segal Zvia Agur |
| author_sort | Yuri Kogan |
| collection | DOAJ |
| description | Abstract Our study was aimed at developing and validating a new approach, embodied in a machine learning-based model, for sequentially monitoring hospitalized COVID-19 patients and directing professional attention to patients whose deterioration is imminent. Model development employed real-world patient data (598 prediction events for 210 patients), internal validation (315 prediction events for 97 patients), and external validation (1373 prediction events for 307 patients). Results show significant divergence in longitudinal values of eight routinely collected blood parameters appearing several days before deterioration. Our model uses these signals to predict the personal likelihood of transition from non-severe to severe status within well-specified short time windows. Internal validation of the model's prediction accuracy showed ROC AUC of 0.8 and 0.79 for prediction scopes of 48 or 96 h, respectively; external validation showed ROC AUC of 0.7 and 0.73 for the same prediction scopes. Results indicate the feasibility of predicting the forthcoming deterioration of non-severe COVID-19 patients by eight routinely collected blood parameters, including neutrophil, lymphocyte, monocyte, and platelets counts, neutrophil-to-lymphocyte ratio, CRP, LDH, and D-dimer. A prospective clinical study and an impact assessment will allow implementation of this model in the clinic to improve care, streamline resources and ease hospital burden by timely focusing the medical attention on potentially deteriorating patients. |
| first_indexed | 2024-04-11T16:23:34Z |
| format | Article |
| id | doaj.art-9c24c766910e45fabd5dd76acd9a3a40 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-11T16:23:34Z |
| publishDate | 2022-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-9c24c766910e45fabd5dd76acd9a3a402022-12-22T04:14:16ZengNature PortfolioScientific Reports2045-23222022-11-0112111010.1038/s41598-022-23553-7Developing and validating a machine learning prognostic model for alerting to imminent deterioration of hospitalized patients with COVID-19Yuri Kogan0Ari Robinson1Edward Itelman2Yeonatan Bar-Nur3Daniel Jorge Jakobson4Gad Segal5Zvia Agur6Institute for Medical Biomathematics (IMBM)Institute for Medical Biomathematics (IMBM)Department of Internal Medicine I, Chaim Sheba Medical Center, Sackler Faculty of Medicine, Tel Aviv UniversityIntensive Care Unit, Barzilai University Medical CenterIntensive Care Unit, Barzilai University Medical CenterDepartment of Internal Medicine I, Chaim Sheba Medical Center, Sackler Faculty of Medicine, Tel Aviv UniversityInstitute for Medical Biomathematics (IMBM)Abstract Our study was aimed at developing and validating a new approach, embodied in a machine learning-based model, for sequentially monitoring hospitalized COVID-19 patients and directing professional attention to patients whose deterioration is imminent. Model development employed real-world patient data (598 prediction events for 210 patients), internal validation (315 prediction events for 97 patients), and external validation (1373 prediction events for 307 patients). Results show significant divergence in longitudinal values of eight routinely collected blood parameters appearing several days before deterioration. Our model uses these signals to predict the personal likelihood of transition from non-severe to severe status within well-specified short time windows. Internal validation of the model's prediction accuracy showed ROC AUC of 0.8 and 0.79 for prediction scopes of 48 or 96 h, respectively; external validation showed ROC AUC of 0.7 and 0.73 for the same prediction scopes. Results indicate the feasibility of predicting the forthcoming deterioration of non-severe COVID-19 patients by eight routinely collected blood parameters, including neutrophil, lymphocyte, monocyte, and platelets counts, neutrophil-to-lymphocyte ratio, CRP, LDH, and D-dimer. A prospective clinical study and an impact assessment will allow implementation of this model in the clinic to improve care, streamline resources and ease hospital burden by timely focusing the medical attention on potentially deteriorating patients.https://doi.org/10.1038/s41598-022-23553-7 |
| spellingShingle | Yuri Kogan Ari Robinson Edward Itelman Yeonatan Bar-Nur Daniel Jorge Jakobson Gad Segal Zvia Agur Developing and validating a machine learning prognostic model for alerting to imminent deterioration of hospitalized patients with COVID-19 Scientific Reports |
| title | Developing and validating a machine learning prognostic model for alerting to imminent deterioration of hospitalized patients with COVID-19 |
| title_full | Developing and validating a machine learning prognostic model for alerting to imminent deterioration of hospitalized patients with COVID-19 |
| title_fullStr | Developing and validating a machine learning prognostic model for alerting to imminent deterioration of hospitalized patients with COVID-19 |
| title_full_unstemmed | Developing and validating a machine learning prognostic model for alerting to imminent deterioration of hospitalized patients with COVID-19 |
| title_short | Developing and validating a machine learning prognostic model for alerting to imminent deterioration of hospitalized patients with COVID-19 |
| title_sort | developing and validating a machine learning prognostic model for alerting to imminent deterioration of hospitalized patients with covid 19 |
| url | https://doi.org/10.1038/s41598-022-23553-7 |
| work_keys_str_mv | AT yurikogan developingandvalidatingamachinelearningprognosticmodelforalertingtoimminentdeteriorationofhospitalizedpatientswithcovid19 AT arirobinson developingandvalidatingamachinelearningprognosticmodelforalertingtoimminentdeteriorationofhospitalizedpatientswithcovid19 AT edwarditelman developingandvalidatingamachinelearningprognosticmodelforalertingtoimminentdeteriorationofhospitalizedpatientswithcovid19 AT yeonatanbarnur developingandvalidatingamachinelearningprognosticmodelforalertingtoimminentdeteriorationofhospitalizedpatientswithcovid19 AT danieljorgejakobson developingandvalidatingamachinelearningprognosticmodelforalertingtoimminentdeteriorationofhospitalizedpatientswithcovid19 AT gadsegal developingandvalidatingamachinelearningprognosticmodelforalertingtoimminentdeteriorationofhospitalizedpatientswithcovid19 AT zviaagur developingandvalidatingamachinelearningprognosticmodelforalertingtoimminentdeteriorationofhospitalizedpatientswithcovid19 |