Predicting appropriateness of antibiotic treatment among ICU patients with hospital-acquired infection
Abstract Antimicrobial resistance is a rising global health threat, leading to ineffective treatments, increased mortality and rising healthcare costs. In ICUs, inappropriate empiric antibiotic therapy is often given due to treatment urgency, causing poor outcomes. This study developed a machine lea...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-024-01426-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823861580674105344 |
|---|---|
| author | Ella Goldschmidt Ella Rannon Daniel Bernstein Asaf Wasserman Michael Roimi Anat Shrot Dan Coster Ron Shamir |
| author_facet | Ella Goldschmidt Ella Rannon Daniel Bernstein Asaf Wasserman Michael Roimi Anat Shrot Dan Coster Ron Shamir |
| author_sort | Ella Goldschmidt |
| collection | DOAJ |
| description | Abstract Antimicrobial resistance is a rising global health threat, leading to ineffective treatments, increased mortality and rising healthcare costs. In ICUs, inappropriate empiric antibiotic therapy is often given due to treatment urgency, causing poor outcomes. This study developed a machine learning model to predict the appropriateness of empiric antibiotics for ICU-acquired bloodstream infections, using data from the MIMIC-III database. To address missing values and dataset imbalances, novel computational methods were introduced. The model achieved an AUROC of 77.3% and AUPRC of 40.4% on validation, with similar results on external datasets from MIMIC-IV and Rambam Hospital. The model also predicted mortality risk, identifying a 30% mortality rate in high-risk patients versus 16.8% in low-risk groups. External validation on the eICU database showed a comparable gap, with mortality rates at 24% for high-risk and 7.7% for low-risk groups. Our study demonstrates the potential of machine learning models to predict inappropriate empiric antibiotic treatment. |
| format | Article |
| id | doaj-art-9f614089539f48aa91a015e76e63ace5 |
| institution | Kabale University |
| issn | 2398-6352 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj-art-9f614089539f48aa91a015e76e63ace52025-02-09T12:55:36ZengNature Portfolionpj Digital Medicine2398-63522025-02-018111610.1038/s41746-024-01426-9Predicting appropriateness of antibiotic treatment among ICU patients with hospital-acquired infectionElla Goldschmidt0Ella Rannon1Daniel Bernstein2Asaf Wasserman3Michael Roimi4Anat Shrot5Dan Coster6Ron Shamir7Blavatnik School of Computer Science, Tel-Aviv UniversityThe Shmunis School of Biomedicine and Cancer Research, Tel-Aviv UniversityDepartment of Internal Medicine “E”, Tel-Aviv Sourasky Medical CenterDepartment of Internal Medicine “E”, Tel-Aviv Sourasky Medical CenterIntensive Care Unit, Rambam Health Care CampusIndependent researcherBlavatnik School of Computer Science, Tel-Aviv UniversityBlavatnik School of Computer Science, Tel-Aviv UniversityAbstract Antimicrobial resistance is a rising global health threat, leading to ineffective treatments, increased mortality and rising healthcare costs. In ICUs, inappropriate empiric antibiotic therapy is often given due to treatment urgency, causing poor outcomes. This study developed a machine learning model to predict the appropriateness of empiric antibiotics for ICU-acquired bloodstream infections, using data from the MIMIC-III database. To address missing values and dataset imbalances, novel computational methods were introduced. The model achieved an AUROC of 77.3% and AUPRC of 40.4% on validation, with similar results on external datasets from MIMIC-IV and Rambam Hospital. The model also predicted mortality risk, identifying a 30% mortality rate in high-risk patients versus 16.8% in low-risk groups. External validation on the eICU database showed a comparable gap, with mortality rates at 24% for high-risk and 7.7% for low-risk groups. Our study demonstrates the potential of machine learning models to predict inappropriate empiric antibiotic treatment.https://doi.org/10.1038/s41746-024-01426-9 |
| spellingShingle | Ella Goldschmidt Ella Rannon Daniel Bernstein Asaf Wasserman Michael Roimi Anat Shrot Dan Coster Ron Shamir Predicting appropriateness of antibiotic treatment among ICU patients with hospital-acquired infection npj Digital Medicine |
| title | Predicting appropriateness of antibiotic treatment among ICU patients with hospital-acquired infection |
| title_full | Predicting appropriateness of antibiotic treatment among ICU patients with hospital-acquired infection |
| title_fullStr | Predicting appropriateness of antibiotic treatment among ICU patients with hospital-acquired infection |
| title_full_unstemmed | Predicting appropriateness of antibiotic treatment among ICU patients with hospital-acquired infection |
| title_short | Predicting appropriateness of antibiotic treatment among ICU patients with hospital-acquired infection |
| title_sort | predicting appropriateness of antibiotic treatment among icu patients with hospital acquired infection |
| url | https://doi.org/10.1038/s41746-024-01426-9 |
| work_keys_str_mv | AT ellagoldschmidt predictingappropriatenessofantibiotictreatmentamongicupatientswithhospitalacquiredinfection AT ellarannon predictingappropriatenessofantibiotictreatmentamongicupatientswithhospitalacquiredinfection AT danielbernstein predictingappropriatenessofantibiotictreatmentamongicupatientswithhospitalacquiredinfection AT asafwasserman predictingappropriatenessofantibiotictreatmentamongicupatientswithhospitalacquiredinfection AT michaelroimi predictingappropriatenessofantibiotictreatmentamongicupatientswithhospitalacquiredinfection AT anatshrot predictingappropriatenessofantibiotictreatmentamongicupatientswithhospitalacquiredinfection AT dancoster predictingappropriatenessofantibiotictreatmentamongicupatientswithhospitalacquiredinfection AT ronshamir predictingappropriatenessofantibiotictreatmentamongicupatientswithhospitalacquiredinfection |