Utilizing predictive machine-learning modelling unveils feature-based risk assessment system for hyperinflammatory patterns and infectious outcomes in polytrauma
PurposeEarlier research has identified several potentially predictive features including biomarkers associated with trauma, which can be used to assess the risk for harmful outcomes of polytraumatized patients. These features encompass various aspects such as the nature and severity of the injury, a...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-12-01
|
| Series: | Frontiers in Immunology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fimmu.2023.1281674/full |
| _version_ | 1827587774087168000 |
|---|---|
| author | Melanie Fachet Raghava Vinaykanth Mushunuri Christian B. Bergmann Ingo Marzi Christoph Hoeschen Borna Relja Borna Relja |
| author_facet | Melanie Fachet Raghava Vinaykanth Mushunuri Christian B. Bergmann Ingo Marzi Christoph Hoeschen Borna Relja Borna Relja |
| author_sort | Melanie Fachet |
| collection | DOAJ |
| description | PurposeEarlier research has identified several potentially predictive features including biomarkers associated with trauma, which can be used to assess the risk for harmful outcomes of polytraumatized patients. These features encompass various aspects such as the nature and severity of the injury, accompanying health conditions, immune and inflammatory markers, and blood parameters linked to organ functioning, however their applicability is limited. Numerous indicators relevant to the patients` outcome are routinely gathered in the intensive care unit (ICU) and recorded in electronic medical records, rendering them suitable predictors for risk assessment of polytraumatized patients.Methods317 polytraumatized patients were included, and the influence of 29 clinical and biological features on the complication patterns for systemic inflammatory response syndrome (SIRS), pneumonia and sepsis were analyzed with a machine learning workflow including clustering, classification and explainability using SHapley Additive exPlanations (SHAP) values. The predictive ability of the analyzed features within three days after admission to the hospital were compared based on patient-specific outcomes using receiver-operating characteristics.ResultsA correlation and clustering analysis revealed that distinct patterns of injury and biomarker patterns were observed for the major complication classes. A k-means clustering suggested four different clusters based on the major complications SIRS, pneumonia and sepsis as well as a patient subgroup that developed no complications. For classification of the outcome groups with no complications, pneumonia and sepsis based on boosting ensemble classification, 90% were correctly classified as low-risk group (no complications). For the high-risk groups associated with development of pneumonia and sepsis, 80% of the patients were correctly identified. The explainability analysis with SHAP values identified the top-ranking features that had the largest impact on the development of adverse outcome patterns. For both investigated risk scenarios (infectious complications and long ICU stay) the most important features are SOFA score, Glasgow Coma Scale, lactate, GGT and hemoglobin blood concentration.ConclusionThe machine learning-based identification of prognostic feature patterns in patients with traumatic injuries may improve tailoring personalized treatment modalities to mitigate the adverse outcomes in high-risk patient clusters. |
| first_indexed | 2024-03-09T00:23:50Z |
| format | Article |
| id | doaj.art-f49598e077f244e38957d9c78c69ae37 |
| institution | Directory Open Access Journal |
| issn | 1664-3224 |
| language | English |
| last_indexed | 2024-03-09T00:23:50Z |
| publishDate | 2023-12-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Immunology |
| spelling | doaj.art-f49598e077f244e38957d9c78c69ae372023-12-12T05:20:59ZengFrontiers Media S.A.Frontiers in Immunology1664-32242023-12-011410.3389/fimmu.2023.12816741281674Utilizing predictive machine-learning modelling unveils feature-based risk assessment system for hyperinflammatory patterns and infectious outcomes in polytraumaMelanie Fachet0Raghava Vinaykanth Mushunuri1Christian B. Bergmann2Ingo Marzi3Christoph Hoeschen4Borna Relja5Borna Relja6Institute for Medical Technology, Medical Systems Technology, Faculty of Electrical Engineering and Information Technology, Otto von Guericke University Magdeburg, Magdeburg, GermanyInstitute for Medical Technology, Medical Systems Technology, Faculty of Electrical Engineering and Information Technology, Otto von Guericke University Magdeburg, Magdeburg, GermanyTranslational and Experimental Trauma Research, Department of Trauma, Hand, Plastic and Reconstructive Surgery, Ulm University Medical Center, University Ulm, Ulm, GermanyDepartment of Trauma, Hand and Reconstructive Surgery, Medical Faculty, Goethe University Frankfurt, Frankfurt, GermanyInstitute for Medical Technology, Medical Systems Technology, Faculty of Electrical Engineering and Information Technology, Otto von Guericke University Magdeburg, Magdeburg, GermanyTranslational and Experimental Trauma Research, Department of Trauma, Hand, Plastic and Reconstructive Surgery, Ulm University Medical Center, University Ulm, Ulm, GermanyDepartment of Trauma, Hand and Reconstructive Surgery, Medical Faculty, Goethe University Frankfurt, Frankfurt, GermanyPurposeEarlier research has identified several potentially predictive features including biomarkers associated with trauma, which can be used to assess the risk for harmful outcomes of polytraumatized patients. These features encompass various aspects such as the nature and severity of the injury, accompanying health conditions, immune and inflammatory markers, and blood parameters linked to organ functioning, however their applicability is limited. Numerous indicators relevant to the patients` outcome are routinely gathered in the intensive care unit (ICU) and recorded in electronic medical records, rendering them suitable predictors for risk assessment of polytraumatized patients.Methods317 polytraumatized patients were included, and the influence of 29 clinical and biological features on the complication patterns for systemic inflammatory response syndrome (SIRS), pneumonia and sepsis were analyzed with a machine learning workflow including clustering, classification and explainability using SHapley Additive exPlanations (SHAP) values. The predictive ability of the analyzed features within three days after admission to the hospital were compared based on patient-specific outcomes using receiver-operating characteristics.ResultsA correlation and clustering analysis revealed that distinct patterns of injury and biomarker patterns were observed for the major complication classes. A k-means clustering suggested four different clusters based on the major complications SIRS, pneumonia and sepsis as well as a patient subgroup that developed no complications. For classification of the outcome groups with no complications, pneumonia and sepsis based on boosting ensemble classification, 90% were correctly classified as low-risk group (no complications). For the high-risk groups associated with development of pneumonia and sepsis, 80% of the patients were correctly identified. The explainability analysis with SHAP values identified the top-ranking features that had the largest impact on the development of adverse outcome patterns. For both investigated risk scenarios (infectious complications and long ICU stay) the most important features are SOFA score, Glasgow Coma Scale, lactate, GGT and hemoglobin blood concentration.ConclusionThe machine learning-based identification of prognostic feature patterns in patients with traumatic injuries may improve tailoring personalized treatment modalities to mitigate the adverse outcomes in high-risk patient clusters.https://www.frontiersin.org/articles/10.3389/fimmu.2023.1281674/fullrisk assessmentclinical decision makingclassificationexplainabilitySHAP valuesblood |
| spellingShingle | Melanie Fachet Raghava Vinaykanth Mushunuri Christian B. Bergmann Ingo Marzi Christoph Hoeschen Borna Relja Borna Relja Utilizing predictive machine-learning modelling unveils feature-based risk assessment system for hyperinflammatory patterns and infectious outcomes in polytrauma Frontiers in Immunology risk assessment clinical decision making classification explainability SHAP values blood |
| title | Utilizing predictive machine-learning modelling unveils feature-based risk assessment system for hyperinflammatory patterns and infectious outcomes in polytrauma |
| title_full | Utilizing predictive machine-learning modelling unveils feature-based risk assessment system for hyperinflammatory patterns and infectious outcomes in polytrauma |
| title_fullStr | Utilizing predictive machine-learning modelling unveils feature-based risk assessment system for hyperinflammatory patterns and infectious outcomes in polytrauma |
| title_full_unstemmed | Utilizing predictive machine-learning modelling unveils feature-based risk assessment system for hyperinflammatory patterns and infectious outcomes in polytrauma |
| title_short | Utilizing predictive machine-learning modelling unveils feature-based risk assessment system for hyperinflammatory patterns and infectious outcomes in polytrauma |
| title_sort | utilizing predictive machine learning modelling unveils feature based risk assessment system for hyperinflammatory patterns and infectious outcomes in polytrauma |
| topic | risk assessment clinical decision making classification explainability SHAP values blood |
| url | https://www.frontiersin.org/articles/10.3389/fimmu.2023.1281674/full |
| work_keys_str_mv | AT melaniefachet utilizingpredictivemachinelearningmodellingunveilsfeaturebasedriskassessmentsystemforhyperinflammatorypatternsandinfectiousoutcomesinpolytrauma AT raghavavinaykanthmushunuri utilizingpredictivemachinelearningmodellingunveilsfeaturebasedriskassessmentsystemforhyperinflammatorypatternsandinfectiousoutcomesinpolytrauma AT christianbbergmann utilizingpredictivemachinelearningmodellingunveilsfeaturebasedriskassessmentsystemforhyperinflammatorypatternsandinfectiousoutcomesinpolytrauma AT ingomarzi utilizingpredictivemachinelearningmodellingunveilsfeaturebasedriskassessmentsystemforhyperinflammatorypatternsandinfectiousoutcomesinpolytrauma AT christophhoeschen utilizingpredictivemachinelearningmodellingunveilsfeaturebasedriskassessmentsystemforhyperinflammatorypatternsandinfectiousoutcomesinpolytrauma AT bornarelja utilizingpredictivemachinelearningmodellingunveilsfeaturebasedriskassessmentsystemforhyperinflammatorypatternsandinfectiousoutcomesinpolytrauma AT bornarelja utilizingpredictivemachinelearningmodellingunveilsfeaturebasedriskassessmentsystemforhyperinflammatorypatternsandinfectiousoutcomesinpolytrauma |