No abstract

No abstract

is an Education Engineer for SparkFun Electronics, a cutting edge open-source hardware and electronics education company. Brian started his career in engineering with wireless transport technologies for ADC Telecommunications in Minneapolis, MN. While working at ADC, Brian volunteered at the Science Museum of Minnesota and quickly discovered a passion for teaching and working with students -especially in an environment that fostered and supported the "wow" factor associated with inquiry and discovery. In 2007, Brian left the world of engineering to pursue a career in education. For the past 5 years, Brian has taught various levels of high school physics, mathematics, applied technology, and robotics.Brian joined Sparkfun Electronics to help integrate "tinkering," electronics, and computational thinking into the classroom. One of his goals is to help teachers to de-mystify how household consumer electronics work. With a few simple tools, classrooms can excite and encourage students to explore the possibilities of microcontrollers, electronics, and physical computing.

Introduction:Early diagnosis and antibiotic administration are essential for reducing sepsis morbidity and mortality; however, diagnosis remains difficult due to complex pathogenesis and presentation. We created a machine learning model for bacterial sepsis identification in the neonatal intensive care unit (NICU) using hematological analyzer data.Methods: Hematological analyzer data were gathered from NICU patients up to 48 hours prior to clinical evaluation for bacterial sepsis. Five models, Support Vector Machine, K-nearest-neighbors, Logistic Regression, Random Forest (RF), and Extreme Gradient boosting (XGBoost), were trained on 60 hematological and nine clinical variables for 2357 cases (1692 control, 665 septic). Clinical feature only models (nine variables) were additionally trained and compared with models including hematological variables. Feature importance was used to assess relative contributions of parameters to performance. Results: The three best performing models were RF, Logistic Regression, and XGBoost. RF achieved an average accuracy of 0.74, AUC-ROC of 0.73, Sensitivity of 0.38, and Specificity of 0.88. Logistic Regression achieved an average accuracy of 0.70, AUC-ROC of 0.74, Sensitivity of 0.62, and Specificity of 0.73. XGBoost achieved an average accuracy of 0.72, AUC-ROC of 0.71, Sensitivity of 0.40, and Specificity of 0.85. All models with hematological variables had significantly stronger performance than models trained on only clinical features. Neutrophil parameters had the highest average feature importance. Conclusions: Machine learning models using hematological analyzer data can classify NICU patients as sepsis positive or negative with stronger performance compared to clinical feature only models. Hematological analyzer variables could augment current sepsis classification machine learning algorithms.

is an Education Engineer for SparkFun Electronics, a cutting edge open-source hardware and electronics education company. Brian started his career in engineering with wireless transport technologies for ADC Telecommunications in Minneapolis, MN. While working at ADC, Brian volunteered at the Science Museum of Minnesota and quickly discovered a passion for teaching and working with students -especially in an environment that fostered and supported the "wow" factor associated with inquiry and discovery. In 2007, Brian left the world of engineering to pursue a career in education. For the past 5 years, Brian has taught various levels of high school physics, mathematics, applied technology, and robotics.Brian joined Sparkfun Electronics to help integrate "tinkering," electronics, and computational thinking into the classroom. One of his goals is to help teachers to de-mystify how household consumer electronics work. With a few simple tools, classrooms can excite and encourage students to explore the possibilities of microcontrollers, electronics, and physical computing.