NEC analysis            NEC analysis             NEC analysis                                                            STANDFORD COMPUTING

Necrotizing Enterocolitis:       * Bell staging diagnosis        (**) Outcome prediction

Patient --  

Historic factors --  (**)Feeding intolerance?     (**)Apneic/ bradycardic episode?     (**)Oxygen desaturation episode?     (**)Grossly bloody stools?  

physical exam --  (**)Abdominal distentions?     *(**)Capillary refill time (CRT) greater than 2 seconds?     (**)Abdominal wall discoloration?     (**)Abdominal tenderness?  

Medical history --  *(**)Was on a ventilator on the day he/she met the protocol definition of NEC?     Was on CPAP on the day he/she met protocol definition of NEC?     Was ever on vasopressors prior to the day he/she met the protocol definition ofNEC?     (**)Was on vasopressors on the day he/she met protocol definition of NEC?     Did the patient have a diagnosis of PDA confirmed by echocardiogram prior to or on the dayhe/she met the protocol definition of NEC?     Was surgically treated for PDA (includes endovascular coil)?     Was the patient medically treated for PDA?     Was PDA closure documented by an echocardiogram prior to or on the day he/she met theprotocol definition of NEC?     Was the patient given the medication prior to the day he/she met the protocol definition of NEC: Surfactant?     Investigational?     Steroids?     Bicarbonate?     Was the patient receiving antibiotics on the day he/she met the protocol definition of NEC?     Did the patient have a cranial ultrasound confirming intraventricular hemorrhage (IVH) prior to or on the day he/she met the protocol definition of NEC?  

Fluid intake & nutrition --  Did patient receive any IV fluids (bolus or continuous) on the day before he/she met the protocol definition of NEC?     Did patient receive any IV fluids (bolus or continuous) on the day he/she met the protocoldefinition of NEC?     Did the patient ever receive enteral nutrition prior to or on the day he/she met the protocoldefinition of NEC?  

Other findings --  Had any major gastrointestinal anomalies?     Had prior abdominal surgery?  

Radiographic findings --  *(**)Pneumatosis intestinalis?     *(**)Portal venous gas?     (**)Ileus?     *(**)Dilated bowel?     *(**)Pneumoperitoneum?     *(**)Air/fluid levels?     *(**)Thickened bowel walls?     Ascites or peritoneal fluid?     *(**)Free intraperitoneal air?  

Labs --  Were any blood cultures obtained within 5 days prior to or on the day he/she met the protocoldefinition of NEC?     Were there positive results for any blood cultures drawn 6-14 days prior to the day he/she met theprotocol definition of NEC?     (**)WBC (x103/mm3)    (**)Neutrophils (%)     (**)ANC (Neutrophils counts) (x109/L)     *(**)BANDS (%)     Bands count (x109/L)    (**)Platelets (x103/uL)     Hematocrit (%)     C-Reactive Protein (mg/dL)     (**)Bicarbonate (meg/L)     (**)pH value     (**)pH site  



Enter Your Contact Email to Start



Background: Necrotizing enterocolitis (NEC) is a major source of neonatal morbidity and mortality. Since there is no specific diagnostic test or risk of progression model available for NEC, the diagnosis and outcome prediction of NEC is made on clinical grounds. We hypothesized that statistical learning of clinical patterns would lead to an improved algorithm for NEC diagnostic function and prognostic forecasting.
Study design: A six-center consortium of university based pediatric teaching hospitals prospectively collected data on infants under suspicion of having NEC over a 7-year period. A database comprised of 520 infants was utilized to develop the NEC diagnostic and prognostic models by dividing the entire dataset into training and testing cohorts of demographically matched subjects. Developed on the training cohort and validated on the blind testing cohort, our multivariate analyses led to NEC scoring metrics integrating clinical data.
Results: Machine learning using clinical and laboratory results at the time of clinical presentation led to two NEC models: (1) an automated diagnostic classification scheme; (2) a dynamic prognostic method for risk-stratifying patients into low, intermediate and high NEC scores to determine the risk for disease progression. We submit that dynamic risk stratification of infants with NEC will assist clinicians in determining the need for additional diagnostic testing and guide potential therapies in a dynamic manner.

© 2013 Bruce Ling, Ph.D.

For publication, please reference the Stanford NEC diagnostic and prognostic algorithms.

Email Bruce Ling and let him know if you have any suggestions.

Last Modified: 12/11/2013