Identifying the need for infection-related consultations in intensive care patients using machine learning models
Abstract Infection-related consultations on intensive care units (ICU) have a positive impact on quality of care and clinical outcome. However, timing of these consultations is essential and to date they are typically event-triggered and reactive. Here, we investigate a proactive approach to identif...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-01-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-024-52741-w |
| _version_ | 1827301135659040768 |
|---|---|
| author | Leslie R. Zwerwer Christian F. Luz Dimitrios Soudis Nicoletta Giudice Maarten W. N. Nijsten Corinna Glasner Maurits H. Renes Bhanu Sinha |
| author_facet | Leslie R. Zwerwer Christian F. Luz Dimitrios Soudis Nicoletta Giudice Maarten W. N. Nijsten Corinna Glasner Maurits H. Renes Bhanu Sinha |
| author_sort | Leslie R. Zwerwer |
| collection | DOAJ |
| description | Abstract Infection-related consultations on intensive care units (ICU) have a positive impact on quality of care and clinical outcome. However, timing of these consultations is essential and to date they are typically event-triggered and reactive. Here, we investigate a proactive approach to identify patients in need for infection-related consultations by machine learning models using routine electronic health records. Data was retrieved from a mixed ICU at a large academic tertiary care hospital including 9684 admissions. Infection-related consultations were predicted using logistic regression, random forest, gradient boosting machines, and long short-term memory neural networks (LSTM). Overall, 7.8% of admitted patients received an infection-related consultation. Time-sensitive modelling approaches performed better than static approaches. Using LSTM resulted in the prediction of infection-related consultations in the next clinical shift (up to eight hours in advance) with an area under the receiver operating curve (AUROC) of 0.921 and an area under the precision recall curve (AUPRC) of 0.541. The successful prediction of infection-related consultations for ICU patients was done without the use of classical triggers, such as (interim) microbiology reports. Predicting this key event can potentially streamline ICU and consultant workflows and improve care as well as outcome for critically ill patients with (suspected) infections. |
| first_indexed | 2024-03-07T15:29:59Z |
| format | Article |
| id | doaj.art-b181b45a98044d98a21a2be8128ed56f |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-24T16:17:56Z |
| publishDate | 2024-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-b181b45a98044d98a21a2be8128ed56f2024-03-31T11:21:32ZengNature PortfolioScientific Reports2045-23222024-01-0114111310.1038/s41598-024-52741-wIdentifying the need for infection-related consultations in intensive care patients using machine learning modelsLeslie R. Zwerwer0Christian F. Luz1Dimitrios Soudis2Nicoletta Giudice3Maarten W. N. Nijsten4Corinna Glasner5Maurits H. Renes6Bhanu Sinha7Department of Health Sciences, University Medical Center Groningen, University of GroningenDepartment of Medical Microbiology and Infection Prevention, University Medical Center Groningen, University of GroningenCenter for Information Technology, University of GroningenCenter for Information Technology, University of GroningenDepartment of Critical Care, University Medical Center Groningen, University of GroningenDepartment of Medical Microbiology and Infection Prevention, University Medical Center Groningen, University of GroningenDepartment of Critical Care, University Medical Center Groningen, University of GroningenDepartment of Medical Microbiology and Infection Prevention, University Medical Center Groningen, University of GroningenAbstract Infection-related consultations on intensive care units (ICU) have a positive impact on quality of care and clinical outcome. However, timing of these consultations is essential and to date they are typically event-triggered and reactive. Here, we investigate a proactive approach to identify patients in need for infection-related consultations by machine learning models using routine electronic health records. Data was retrieved from a mixed ICU at a large academic tertiary care hospital including 9684 admissions. Infection-related consultations were predicted using logistic regression, random forest, gradient boosting machines, and long short-term memory neural networks (LSTM). Overall, 7.8% of admitted patients received an infection-related consultation. Time-sensitive modelling approaches performed better than static approaches. Using LSTM resulted in the prediction of infection-related consultations in the next clinical shift (up to eight hours in advance) with an area under the receiver operating curve (AUROC) of 0.921 and an area under the precision recall curve (AUPRC) of 0.541. The successful prediction of infection-related consultations for ICU patients was done without the use of classical triggers, such as (interim) microbiology reports. Predicting this key event can potentially streamline ICU and consultant workflows and improve care as well as outcome for critically ill patients with (suspected) infections.https://doi.org/10.1038/s41598-024-52741-w |
| spellingShingle | Leslie R. Zwerwer Christian F. Luz Dimitrios Soudis Nicoletta Giudice Maarten W. N. Nijsten Corinna Glasner Maurits H. Renes Bhanu Sinha Identifying the need for infection-related consultations in intensive care patients using machine learning models Scientific Reports |
| title | Identifying the need for infection-related consultations in intensive care patients using machine learning models |
| title_full | Identifying the need for infection-related consultations in intensive care patients using machine learning models |
| title_fullStr | Identifying the need for infection-related consultations in intensive care patients using machine learning models |
| title_full_unstemmed | Identifying the need for infection-related consultations in intensive care patients using machine learning models |
| title_short | Identifying the need for infection-related consultations in intensive care patients using machine learning models |
| title_sort | identifying the need for infection related consultations in intensive care patients using machine learning models |
| url | https://doi.org/10.1038/s41598-024-52741-w |
| work_keys_str_mv | AT leslierzwerwer identifyingtheneedforinfectionrelatedconsultationsinintensivecarepatientsusingmachinelearningmodels AT christianfluz identifyingtheneedforinfectionrelatedconsultationsinintensivecarepatientsusingmachinelearningmodels AT dimitriossoudis identifyingtheneedforinfectionrelatedconsultationsinintensivecarepatientsusingmachinelearningmodels AT nicolettagiudice identifyingtheneedforinfectionrelatedconsultationsinintensivecarepatientsusingmachinelearningmodels AT maartenwnnijsten identifyingtheneedforinfectionrelatedconsultationsinintensivecarepatientsusingmachinelearningmodels AT corinnaglasner identifyingtheneedforinfectionrelatedconsultationsinintensivecarepatientsusingmachinelearningmodels AT mauritshrenes identifyingtheneedforinfectionrelatedconsultationsinintensivecarepatientsusingmachinelearningmodels AT bhanusinha identifyingtheneedforinfectionrelatedconsultationsinintensivecarepatientsusingmachinelearningmodels |