Development and Validation of a Machine Learning Model for the Prediction of Bloodstream Infections in Patients with Hematological Malignancies and Febrile Neutropenia
<b>Background/Objectives:</b> The rise of multidrug-resistant (MDR) infections demands personalized antibiotic strategies for febrile neutropenia (FN) in hematological malignancies. This study investigates machine learning (ML) for identifying patient profiles with increased susceptibili...
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Antibiotics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-6382/14/1/13 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589319162822656 |
|---|---|
| author | Antonio Gallardo-Pizarro Christian Teijón-Lumbreras Patricia Monzo-Gallo Tommaso Francesco Aiello Mariana Chumbita Olivier Peyrony Emmanuelle Gras Cristina Pitart Josep Mensa Jordi Esteve Alex Soriano Carolina Garcia-Vidal |
| author_facet | Antonio Gallardo-Pizarro Christian Teijón-Lumbreras Patricia Monzo-Gallo Tommaso Francesco Aiello Mariana Chumbita Olivier Peyrony Emmanuelle Gras Cristina Pitart Josep Mensa Jordi Esteve Alex Soriano Carolina Garcia-Vidal |
| author_sort | Antonio Gallardo-Pizarro |
| collection | DOAJ |
| description | <b>Background/Objectives:</b> The rise of multidrug-resistant (MDR) infections demands personalized antibiotic strategies for febrile neutropenia (FN) in hematological malignancies. This study investigates machine learning (ML) for identifying patient profiles with increased susceptibility to bloodstream infections (BSI) during FN onset, aiming to tailor treatment approaches. <b>Methods:</b> From January 2020 to June 2022, we used the unsupervised ML algorithm KAMILA to analyze data from hospitalized hematological malignancy patients. Eleven features categorized clinical phenotypes and determined BSI and multidrug-resistant Gram-negative bacilli (MDR-GNB) prevalences at FN onset. Model performance was evaluated with a validation cohort from July 2022 to March 2023. <b>Results:</b> Among 462 FN episodes analyzed in the development cohort, 116 (25.1%) had BSIs. KAMILA’s stratification identified three risk clusters: Cluster 1 (low risk), Cluster 2 (intermediate risk), and Cluster 3 (high risk). Cluster 2 (28.4% of episodes) and Cluster 3 (43.7%) exhibited higher BSI rates of 26.7% and 37.6% and GNB BSI rates of 13.4% and 19.3%, respectively. Cluster 3 had a higher incidence of MDR-GNB BSIs, accounting for 75% of all MDR-GNB BSIs. Cluster 1 (27.9% of episodes) showed a lower BSI risk (<1%) with no GNB infections. Validation cohort results were similar: Cluster 3 had a BSI rate of 38.1%, including 78% of all MDR-GNB BSIs, while Cluster 1 had no GNB-related BSIs. <b>Conclusions:</b> Unsupervised ML-based risk stratification enhances evidence-driven decision-making for empiric antibiotic therapies at FN onset, crucial in an era of rising multi-drug resistance. |
| format | Article |
| id | doaj-art-4294d1c9df214beb9b2d01af83a6010a |
| institution | Kabale University |
| issn | 2079-6382 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Antibiotics |
| spelling | doaj-art-4294d1c9df214beb9b2d01af83a6010a2025-01-24T13:18:32ZengMDPI AGAntibiotics2079-63822024-12-011411310.3390/antibiotics14010013Development and Validation of a Machine Learning Model for the Prediction of Bloodstream Infections in Patients with Hematological Malignancies and Febrile NeutropeniaAntonio Gallardo-Pizarro0Christian Teijón-Lumbreras1Patricia Monzo-Gallo2Tommaso Francesco Aiello3Mariana Chumbita4Olivier Peyrony5Emmanuelle Gras6Cristina Pitart7Josep Mensa8Jordi Esteve9Alex Soriano10Carolina Garcia-Vidal11Department of Infectious Diseases, Hospital Clinic of Barcelona-IDIBAPS, 08036 Barcelona, SpainDepartment of Infectious Diseases, Hospital Clinic of Barcelona-IDIBAPS, 08036 Barcelona, SpainDepartment of Infectious Diseases, Hospital Clinic of Barcelona-IDIBAPS, 08036 Barcelona, SpainDepartment of Infectious Diseases, Hospital Clinic of Barcelona-IDIBAPS, 08036 Barcelona, SpainDepartment of Infectious Diseases, Hospital Clinic of Barcelona-IDIBAPS, 08036 Barcelona, SpainDepartment of Infectious Diseases, Hospital Clinic of Barcelona-IDIBAPS, 08036 Barcelona, SpainDepartment of Infectious Diseases, Hospital Clinic of Barcelona-IDIBAPS, 08036 Barcelona, SpainDepartment of Microbiology, Hospital Clinic of Barcelona-IDIBAPS, University of Barcelona, 08036 Barcelona, SpainDepartment of Infectious Diseases, Hospital Clinic of Barcelona-IDIBAPS, 08036 Barcelona, SpainDepartment of Hematology, Hospital Clinic of Barcelona-IDIBAPS, University of Barcelona, 08036 Barcelona, SpainDepartment of Infectious Diseases, Hospital Clinic of Barcelona-IDIBAPS, 08036 Barcelona, SpainDepartment of Infectious Diseases, Hospital Clinic of Barcelona-IDIBAPS, 08036 Barcelona, Spain<b>Background/Objectives:</b> The rise of multidrug-resistant (MDR) infections demands personalized antibiotic strategies for febrile neutropenia (FN) in hematological malignancies. This study investigates machine learning (ML) for identifying patient profiles with increased susceptibility to bloodstream infections (BSI) during FN onset, aiming to tailor treatment approaches. <b>Methods:</b> From January 2020 to June 2022, we used the unsupervised ML algorithm KAMILA to analyze data from hospitalized hematological malignancy patients. Eleven features categorized clinical phenotypes and determined BSI and multidrug-resistant Gram-negative bacilli (MDR-GNB) prevalences at FN onset. Model performance was evaluated with a validation cohort from July 2022 to March 2023. <b>Results:</b> Among 462 FN episodes analyzed in the development cohort, 116 (25.1%) had BSIs. KAMILA’s stratification identified three risk clusters: Cluster 1 (low risk), Cluster 2 (intermediate risk), and Cluster 3 (high risk). Cluster 2 (28.4% of episodes) and Cluster 3 (43.7%) exhibited higher BSI rates of 26.7% and 37.6% and GNB BSI rates of 13.4% and 19.3%, respectively. Cluster 3 had a higher incidence of MDR-GNB BSIs, accounting for 75% of all MDR-GNB BSIs. Cluster 1 (27.9% of episodes) showed a lower BSI risk (<1%) with no GNB infections. Validation cohort results were similar: Cluster 3 had a BSI rate of 38.1%, including 78% of all MDR-GNB BSIs, while Cluster 1 had no GNB-related BSIs. <b>Conclusions:</b> Unsupervised ML-based risk stratification enhances evidence-driven decision-making for empiric antibiotic therapies at FN onset, crucial in an era of rising multi-drug resistance.https://www.mdpi.com/2079-6382/14/1/13febrile neutropeniabloodstream infectionshematological malignanciesmachine learningKAMILA |
| spellingShingle | Antonio Gallardo-Pizarro Christian Teijón-Lumbreras Patricia Monzo-Gallo Tommaso Francesco Aiello Mariana Chumbita Olivier Peyrony Emmanuelle Gras Cristina Pitart Josep Mensa Jordi Esteve Alex Soriano Carolina Garcia-Vidal Development and Validation of a Machine Learning Model for the Prediction of Bloodstream Infections in Patients with Hematological Malignancies and Febrile Neutropenia Antibiotics febrile neutropenia bloodstream infections hematological malignancies machine learning KAMILA |
| title | Development and Validation of a Machine Learning Model for the Prediction of Bloodstream Infections in Patients with Hematological Malignancies and Febrile Neutropenia |
| title_full | Development and Validation of a Machine Learning Model for the Prediction of Bloodstream Infections in Patients with Hematological Malignancies and Febrile Neutropenia |
| title_fullStr | Development and Validation of a Machine Learning Model for the Prediction of Bloodstream Infections in Patients with Hematological Malignancies and Febrile Neutropenia |
| title_full_unstemmed | Development and Validation of a Machine Learning Model for the Prediction of Bloodstream Infections in Patients with Hematological Malignancies and Febrile Neutropenia |
| title_short | Development and Validation of a Machine Learning Model for the Prediction of Bloodstream Infections in Patients with Hematological Malignancies and Febrile Neutropenia |
| title_sort | development and validation of a machine learning model for the prediction of bloodstream infections in patients with hematological malignancies and febrile neutropenia |
| topic | febrile neutropenia bloodstream infections hematological malignancies machine learning KAMILA |
| url | https://www.mdpi.com/2079-6382/14/1/13 |
| work_keys_str_mv | AT antoniogallardopizarro developmentandvalidationofamachinelearningmodelforthepredictionofbloodstreaminfectionsinpatientswithhematologicalmalignanciesandfebrileneutropenia AT christianteijonlumbreras developmentandvalidationofamachinelearningmodelforthepredictionofbloodstreaminfectionsinpatientswithhematologicalmalignanciesandfebrileneutropenia AT patriciamonzogallo developmentandvalidationofamachinelearningmodelforthepredictionofbloodstreaminfectionsinpatientswithhematologicalmalignanciesandfebrileneutropenia AT tommasofrancescoaiello developmentandvalidationofamachinelearningmodelforthepredictionofbloodstreaminfectionsinpatientswithhematologicalmalignanciesandfebrileneutropenia AT marianachumbita developmentandvalidationofamachinelearningmodelforthepredictionofbloodstreaminfectionsinpatientswithhematologicalmalignanciesandfebrileneutropenia AT olivierpeyrony developmentandvalidationofamachinelearningmodelforthepredictionofbloodstreaminfectionsinpatientswithhematologicalmalignanciesandfebrileneutropenia AT emmanuellegras developmentandvalidationofamachinelearningmodelforthepredictionofbloodstreaminfectionsinpatientswithhematologicalmalignanciesandfebrileneutropenia AT cristinapitart developmentandvalidationofamachinelearningmodelforthepredictionofbloodstreaminfectionsinpatientswithhematologicalmalignanciesandfebrileneutropenia AT josepmensa developmentandvalidationofamachinelearningmodelforthepredictionofbloodstreaminfectionsinpatientswithhematologicalmalignanciesandfebrileneutropenia AT jordiesteve developmentandvalidationofamachinelearningmodelforthepredictionofbloodstreaminfectionsinpatientswithhematologicalmalignanciesandfebrileneutropenia AT alexsoriano developmentandvalidationofamachinelearningmodelforthepredictionofbloodstreaminfectionsinpatientswithhematologicalmalignanciesandfebrileneutropenia AT carolinagarciavidal developmentandvalidationofamachinelearningmodelforthepredictionofbloodstreaminfectionsinpatientswithhematologicalmalignanciesandfebrileneutropenia |