Bloodstream Infections in Childhood Acute Myeloid Leukemia and Machine Learning Models: A Single-institutional
Taylor L Chappell1, Ellen G Pflaster1, Resty Namata2
1Department of Industrial and Systems Engineering, University of Wisconsin-Madison.
Abstract:
Childhood acute myeloid leukemia (AML) requires intensive chemotherapy, which may result in life-threatening bloodstream infections (BSIs). This study evaluated whether machine learning (ML) could predict BSI using electronic medical records. All children treated for AML at Children's Minnesota between 2005 and 2019 were included. Patients with Down syndrome AML or acute promyelocytic leukemia were excluded. Standard statistics analyzed predictors of BSI, and ML models were trained to predict BSI. Of 95 AML patients, 54.7% had BSI. Of 480 admissions, 19% included BSI. No deaths were related to BSI, and survival of non-Whites was significantly inferior to White patients. Logistic regression revealed that higher cytarabine doses increased the risk of BSI, with an odds ratio (OR) of 1.110 ( P < 0.05). Prophylactic levofloxacin-vancomycin reduced the risk of BSI, with OR of 0.495 ( P < 0.05). The best-performing ML model was regularized logistic regression with an area under the curve (AUC) of 0.748, improved specificity by 37.5% compared with neutropenia, and 2.6% compared with fever. In conclusion, BSI risk was increased by cytarabine and reduced by levofloxacin-vancomycin prophylaxis. ML predicted BSI with improvement over fever or neutropenia. In clinical practice, ML may offer flexibility by controlling sensitivity and specificity by adjusting BSI diagnosis thresholds.
Insights
Machine learning models can predict bloodstream infections (BSIs) in children with acute myeloid leukemia (AML). Predicting BSIs using electronic health records improves upon traditional methods like fever or neutropenia detection.
Area of Science:
- Pediatric Oncology
- Infectious Diseases
- Machine Learning in Healthcare
Background:
- Childhood acute myeloid leukemia (AML) treatment involves intensive chemotherapy, increasing the risk of life-threatening bloodstream infections (BSIs).
- Accurate and early prediction of BSIs is crucial for timely intervention and improved patient outcomes.
Purpose of the Study:
- To evaluate the efficacy of machine learning (ML) models in predicting BSIs in pediatric AML patients using electronic medical records.
- To compare the predictive performance of ML models against traditional clinical indicators such as fever and neutropenia.
Main Methods:
- Retrospective analysis of electronic medical records for pediatric AML patients treated between 2005 and 2019.
- Application of standard statistical methods and various ML models, including regularized logistic regression, to predict BSI.
- Exclusion of patients with Down syndrome AML or acute promyelocytic leukemia.
Main Results:
- The best-performing ML model, regularized logistic regression, achieved an area under the curve (AUC) of 0.748.
- ML models demonstrated improved specificity compared to neutropenia (37.5% increase) and fever (2.6% increase).
- Higher cytarabine doses were associated with increased BSI risk (OR 1.110), while prophylactic levofloxacin-vancomycin reduced BSI risk (OR 0.495).
Conclusions:
- Machine learning models show promise in predicting BSIs in pediatric AML patients, offering improved accuracy over traditional indicators.
- Chemotherapy agents like cytarabine increase BSI risk, whereas prophylactic antibiotics can mitigate this risk.
- ML models provide flexibility in clinical practice by allowing adjustments to sensitivity and specificity thresholds for BSI prediction.
More Related Videos
06:33Author Spotlight: Analyzing Bone Marrow Microenvironment in Murine Hematological Malignancies
Published on: November 10, 2023
09:57Comprehensive Protocol to Sample and Process Bone Marrow for Measuring Measurable Residual Disease and Leukemic Stem Cells in Acute Myeloid Leukemia
Published on: March 5, 2018