Which Biomarkers Reveal Neonatal Sepsis?

نویسندگان

  • Kun Wang
  • Vineet Bhandari
  • Sofya Chepustanova
  • Greg Huber
  • Stephen O′Hara
  • Corey S. O′Hern
  • Mark D. Shattuck
  • Michael Kirby
چکیده

We address the identification of optimal biomarkers for the rapid diagnosis of neonatal sepsis. We employ both canonical correlation analysis (CCA) and sparse support vector machine (SSVM) classifiers to select the best subset of biomarkers from a large hematological data set collected from infants with suspected sepsis from Yale-New Haven Hospital's Neonatal Intensive Care Unit (NICU). CCA is used to select sets of biomarkers of increasing size that are most highly correlated with infection. The effectiveness of these biomarkers is then validated by constructing a sparse support vector machine diagnostic classifier. We find that the following set of five biomarkers capture the essential diagnostic information (in order of importance): Bands, Platelets, neutrophil CD64, White Blood Cells, and Segs. Further, the diagnostic performance of the optimal set of biomarkers is significantly higher than that of isolated individual biomarkers. These results suggest an enhanced sepsis scoring system for neonatal sepsis that includes these five biomarkers. We demonstrate the robustness of our analysis by comparing CCA with the Forward Selection method and SSVM with LASSO Logistic Regression.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Diagnostic Role of Serum Haptoglobin level in Early Onset Neonatal Sepsis

Background: Introduction: Searching for an ideal marker for diagnosing neonatal infection is still an important concern in every country. There are many biomarkers reported for neonatal sepsis. Haptoglobin is an acute phase reactants which rise in response to infection and injuries. In this report we discussed the efficacy of serum haptoglobin level in different cut off levels in early onset ne...

متن کامل

Biomarkers in early-Onset Neonatal Sepsis: An Update

Globally, an estimated 500,000 newborns die each year from serious neonatal infections, which account for about 15% of all neonatal deaths. “Suspected sepsis” is one of the most common reasons for admission to the neonatal intensive care unit (NICU). The challenge to the physician has always been trying to differentiate newborns with early onset sepsis from other non-infectious pathology whose ...

متن کامل

1 Which Biomarkers Reveal Neonatal Sepsis ? Supplementary Material

Which Biomarkers Reveal Neonatal Sepsis? Supplementary Material Kun Wang, Vineet Bhandari, Sofya Chepustanova, Greg Huber, Stephen O’Hara, Corey S. O’Hern, Mark D. Shattuck, Michael Kirby 1 Department of Mathematics, Colorado State University, Fort Collins, CO, USA 2 Department of Mechanical Engineering & Materials Science, Yale University, New Haven, CT, USA 3 Division of Perinatal Medicine, D...

متن کامل

Effective Biomarkers for Diagnosis of Neonatal Sepsis.

Infection in neonates continues to be a global problem with significant morbidity and mortality. The diagnosis of neonatal sepsis is complicated by nonspecific clinical symptomatology, a high-false negative rate, and a delay in obtaining blood culture results. An ideal biomarker needs to have a high degree of accuracy in recognizing the presence or absence of definite infection at an early stag...

متن کامل

Significance of Serum Procalcitonin Level in the Early Diagnosis of Neonatal Sepsis

Background: Sepsis in neonates presents itself with non-specific clinical features which makes early diagnosis difficult. However, procalcitonin (PCT) and other inflammatory markers have recently been considered as sensitive markers for the early detection of neonatal sepsis. Therefore, the present study aimed to determine the diagnostic value of PCT in the early detection of neonatal sepsis an...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره 8  شماره 

صفحات  -

تاریخ انتشار 2013