NICU. Has the future arrived? Anirudha Das MD Neonatologist Asst - PowerPoint PPT Presentation

Artificial intelligence in the NICU…. Has the future arrived? Anirudha Das MD Neonatologist Asst Professor of Pediatrics and Neonatology Cleveland Clinic Foundation Cleveland, Ohio, United States

Research interest in Artificial Intelligence?

Definition Decision Support System (DSS): computer-based application that collects, organizes and analyzes data to facilitate/assist healthcare professionals make clinical decisions. Knowledge Based Data driven aims to capture the knowledge of Processing large amounts of data to human experts to support abstract patterns utilized for predictions, decision-making or emulate human behavior in similar conditions in the past (Malak et al. , 2019) (Montani and Striani, 2019)

Decision support systems Knowledge based: Data driven: • Top down approach • Bottoms up • Lack of knowledge in many areas • Recent surge in capability of or lack of management collecting large amounts of data consensus • Transparency and explainability • Lack of transparency and is present explainability (Montani and Striani, 2019)

Decision Support Systems Clinical Decision Support System (CDSS): computer- based application that collects, organizes and analyzes data to facilitate/assist healthcare professionals make clinical decisions. Resource utilization Prognosis Cost estimation Diagnosis Treatment Outcomes (Malak et al. , 2019)

Parameters: demographics/characteristics • Maternal factors: Age, race, diagnosis, complications, GBS, previous still birth, magnesium therapy, antenatal steroids, antepartum hemorrhage etc. • Infant: Birth weight, gestation, sex, physiological scores (SNAPPE) (CRIB II), weight gain • Labs: Glucose, sodium, potassium, chloride, blood parameters, cultures • Management: Number of ventilated/oxygenated days, fluids, lipids, dextrose, calorie intake including carbohydrates, proteins and fats (Shillan et al. , 2019)

Parameters: Vitals aEEG Pulse oximeter TCO2 Heart Rate NIRS RR, BP and Temp

Data • About 20,000 terabytes of data is being produced in the United states each year • Healthcare professionals have access to this data because they are managing the patient • There are limitations of organizing, processing and analyzing this data • AI can help with this data! • When models are built on the basis of quantitative data, objective measures can be provided and cut-offs for patient management established (SCCM, 2018)

Types of Artificial Intelligence • Support vector machines • Artificial neural networks • Decision tree • K-nearest newborns • Gaussian mixture model • Regression • Rule based • Fuzzy logic • Multi agent-based approaches • Biosensors

NICU Diagnosis Seizures Jaundice HIE Plus ROP Sepsis/NEC

NICU Diagnosis Seizures Jaundice HIE Plus ROP Sepsis (Temko et al. , 2011)

NICU Diagnosis Seizures Jaundice HIE Plus ROP Sepsis/NEC (Peter Campbell et al. , 2016)

NICU Diagnosis Seizures Jaundice HIE Plus ROP Sepsis (Lake, Fairchild and Moorman, 2014)

NICU Diagnosis Seizures Jaundice HIE Plus ROP Sepsis (Joshi et al. , 2019)

NICU Diagnosis Seizures Jaundice HIE Plus ROP Sepsis/NEC (Irles et al. , 2018)

NICU Prognosis Discharge Mortality

NICU Prognosis Discharge Mortality (Frize et al. , 2005)

NICU Prognosis Discharge Mortality (Podda et al. , 2018)

NICU Prognosis Discharge Mortality (Chaves and Nascimento, 2014)

NICU Monitoring Apnea monitoring Mechanical Ventilation Brain maturity Pain (Morton, 2017)

NICU Monitoring Apnea monitoring Mechanical Ventilation Brain maturity Pain (Morton, 2017)

Our project:

Data captor Data captor server application Beachwood Hillcrest Data converted to HL-7 format EMR Interface Engine Main Campus Repository Fairview

Beachwood