Machine learning-based prediction models for home discharge in patients with COVID-19: Development and evaluation using electronic health records.
<h4>Objective</h4>This study aimed to develop and validate predictive models using electronic health records (EHR) data to determine whether hospitalized COVID-19-positive patients would be admitted to alternative medical care or discharged home.<h4>Methods</h4>We conducted a...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2023-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0292888 |
| _version_ | 1797635270056607744 |
|---|---|
| author | Ruben D Zapata Shu Huang Earl Morris Chang Wang Christopher Harle Tanja Magoc Mamoun Mardini Tyler Loftus François Modave |
| author_facet | Ruben D Zapata Shu Huang Earl Morris Chang Wang Christopher Harle Tanja Magoc Mamoun Mardini Tyler Loftus François Modave |
| author_sort | Ruben D Zapata |
| collection | DOAJ |
| description | <h4>Objective</h4>This study aimed to develop and validate predictive models using electronic health records (EHR) data to determine whether hospitalized COVID-19-positive patients would be admitted to alternative medical care or discharged home.<h4>Methods</h4>We conducted a retrospective cohort study using deidentified data from the University of Florida Health Integrated Data Repository. The study included 1,578 adult patients (≥18 years) who tested positive for COVID-19 while hospitalized, comprising 960 (60.8%) female patients with a mean (SD) age of 51.86 (18.49) years and 618 (39.2%) male patients with a mean (SD) age of 54.35 (18.48) years. Machine learning (ML) model training involved cross-validation to assess their performance in predicting patient disposition.<h4>Results</h4>We developed and validated six supervised ML-based prediction models (logistic regression, Gaussian Naïve Bayes, k-nearest neighbors, decision trees, random forest, and support vector machine classifier) to predict patient discharge status. The models were evaluated based on the area under the receiver operating characteristic curve (ROC-AUC), precision, accuracy, F1 score, and Brier score. The random forest classifier exhibited the highest performance, achieving an accuracy of 0.84 and an AUC of 0.72. Logistic regression (accuracy: 0.85, AUC: 0.71), k-nearest neighbor (accuracy: 0.84, AUC: 0.63), decision tree (accuracy: 0.84, AUC: 0.61), Gaussian Naïve Bayes (accuracy: 0.84, AUC: 0.66), and support vector machine classifier (accuracy: 0.84, AUC: 0.67) also demonstrated valuable predictive capabilities.<h4>Significance</h4>This study's findings are crucial for efficiently allocating healthcare resources during pandemics like COVID-19. By harnessing ML techniques and EHR data, we can create predictive tools to identify patients at greater risk of severe symptoms based on their medical histories. The models developed here serve as a foundation for expanding the toolkit available to healthcare professionals and organizations. Additionally, explainable ML methods, such as Shapley Additive Explanations, aid in uncovering underlying data features that inform healthcare decision-making processes. |
| first_indexed | 2024-03-11T12:18:52Z |
| format | Article |
| id | doaj.art-82f15e63a54a4e4398a17e2cc8b7a121 |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-03-11T12:18:52Z |
| publishDate | 2023-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-82f15e63a54a4e4398a17e2cc8b7a1212023-11-07T05:34:15ZengPublic Library of Science (PLoS)PLoS ONE1932-62032023-01-011810e029288810.1371/journal.pone.0292888Machine learning-based prediction models for home discharge in patients with COVID-19: Development and evaluation using electronic health records.Ruben D ZapataShu HuangEarl MorrisChang WangChristopher HarleTanja MagocMamoun MardiniTyler LoftusFrançois Modave<h4>Objective</h4>This study aimed to develop and validate predictive models using electronic health records (EHR) data to determine whether hospitalized COVID-19-positive patients would be admitted to alternative medical care or discharged home.<h4>Methods</h4>We conducted a retrospective cohort study using deidentified data from the University of Florida Health Integrated Data Repository. The study included 1,578 adult patients (≥18 years) who tested positive for COVID-19 while hospitalized, comprising 960 (60.8%) female patients with a mean (SD) age of 51.86 (18.49) years and 618 (39.2%) male patients with a mean (SD) age of 54.35 (18.48) years. Machine learning (ML) model training involved cross-validation to assess their performance in predicting patient disposition.<h4>Results</h4>We developed and validated six supervised ML-based prediction models (logistic regression, Gaussian Naïve Bayes, k-nearest neighbors, decision trees, random forest, and support vector machine classifier) to predict patient discharge status. The models were evaluated based on the area under the receiver operating characteristic curve (ROC-AUC), precision, accuracy, F1 score, and Brier score. The random forest classifier exhibited the highest performance, achieving an accuracy of 0.84 and an AUC of 0.72. Logistic regression (accuracy: 0.85, AUC: 0.71), k-nearest neighbor (accuracy: 0.84, AUC: 0.63), decision tree (accuracy: 0.84, AUC: 0.61), Gaussian Naïve Bayes (accuracy: 0.84, AUC: 0.66), and support vector machine classifier (accuracy: 0.84, AUC: 0.67) also demonstrated valuable predictive capabilities.<h4>Significance</h4>This study's findings are crucial for efficiently allocating healthcare resources during pandemics like COVID-19. By harnessing ML techniques and EHR data, we can create predictive tools to identify patients at greater risk of severe symptoms based on their medical histories. The models developed here serve as a foundation for expanding the toolkit available to healthcare professionals and organizations. Additionally, explainable ML methods, such as Shapley Additive Explanations, aid in uncovering underlying data features that inform healthcare decision-making processes.https://doi.org/10.1371/journal.pone.0292888 |
| spellingShingle | Ruben D Zapata Shu Huang Earl Morris Chang Wang Christopher Harle Tanja Magoc Mamoun Mardini Tyler Loftus François Modave Machine learning-based prediction models for home discharge in patients with COVID-19: Development and evaluation using electronic health records. PLoS ONE |
| title | Machine learning-based prediction models for home discharge in patients with COVID-19: Development and evaluation using electronic health records. |
| title_full | Machine learning-based prediction models for home discharge in patients with COVID-19: Development and evaluation using electronic health records. |
| title_fullStr | Machine learning-based prediction models for home discharge in patients with COVID-19: Development and evaluation using electronic health records. |
| title_full_unstemmed | Machine learning-based prediction models for home discharge in patients with COVID-19: Development and evaluation using electronic health records. |
| title_short | Machine learning-based prediction models for home discharge in patients with COVID-19: Development and evaluation using electronic health records. |
| title_sort | machine learning based prediction models for home discharge in patients with covid 19 development and evaluation using electronic health records |
| url | https://doi.org/10.1371/journal.pone.0292888 |
| work_keys_str_mv | AT rubendzapata machinelearningbasedpredictionmodelsforhomedischargeinpatientswithcovid19developmentandevaluationusingelectronichealthrecords AT shuhuang machinelearningbasedpredictionmodelsforhomedischargeinpatientswithcovid19developmentandevaluationusingelectronichealthrecords AT earlmorris machinelearningbasedpredictionmodelsforhomedischargeinpatientswithcovid19developmentandevaluationusingelectronichealthrecords AT changwang machinelearningbasedpredictionmodelsforhomedischargeinpatientswithcovid19developmentandevaluationusingelectronichealthrecords AT christopherharle machinelearningbasedpredictionmodelsforhomedischargeinpatientswithcovid19developmentandevaluationusingelectronichealthrecords AT tanjamagoc machinelearningbasedpredictionmodelsforhomedischargeinpatientswithcovid19developmentandevaluationusingelectronichealthrecords AT mamounmardini machinelearningbasedpredictionmodelsforhomedischargeinpatientswithcovid19developmentandevaluationusingelectronichealthrecords AT tylerloftus machinelearningbasedpredictionmodelsforhomedischargeinpatientswithcovid19developmentandevaluationusingelectronichealthrecords AT francoismodave machinelearningbasedpredictionmodelsforhomedischargeinpatientswithcovid19developmentandevaluationusingelectronichealthrecords |