Despite the rise of Artificial Intelligence (AI) algorithms and their applications in various fields, their utilizations in high-risk fields like healthcare and finance is limited because of the lack of interpretability of their inner workings. Some algorithms are interpretable, but not accurate, whereas some produce accurate results and not decipherable. Research is underway to explore the possibilities to interrogate an AI system, and ask why it makes certain decisions. This paper aims to investigate the decision-making process by AI algorithms in the prediction of sepsis based on patients' clinical records.We were ranked 59 in the PhysioNet/Computing in Cardiology Challenge 2019 and the utility score obtained on the full test set is 0.131, and our team name was ARUL.
Objectives:
Serial C-reactive protein (CRP) monitoring helps to rule out and prognosticate sepsis. Small blood volumes in neonates make it difficult for repeated blood draws for serial CRP monitoring. Hence, the need of the hour is a non-invasive method such as CRP estimation in saliva. This study aims to correlate salivary CRP with serum CRP levels and establish the potential clinical utility of salivary CRP in diagnosing neonatal sepsis.
Materials and Methods:
Twenty-three consecutive neonates diagnosed with clinically suspected sepsis and admitted to the NICU were the study subjects. Demographics such as gestational age and weight at birth, sex and detailed clinical features, and comorbidities were noted. Blood samples for CRP estimation and blood culture were collected as soon as clinical suspicion of sepsis arose. Saliva samples were collected for CRP estimation within 1 h of blood sample collection. The saliva was collected in a 2 mL syringe using low suction. Salivary and serum CRP were estimated by the particle enhanced immunoturbidimetric assay.
Results:
In our study, the CRP levels in saliva correlated moderately well with CRP levels in serum (Spearman correlation coefficient r = 0.582, P = 0.004). The sensitivity and specificity of salivary CRP to predict a serum level of ≥10 mg/L were observed to be 0.75 and 0.93, respectively.
Conclusion:
Our study shows the promise of salivary CRP as a potential clinically meaningful biomarker of neonatal sepsis and warrants the need for larger studies to validate the utility of salivary CRP to serially monitor neonatal sepsis.
The cytological differential diagnoses of gastrointestinal stromal tumours are mesenchymal, neural and neuroendocrine tumours. However, there are potential pitfalls, two of which are presented here.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.