Developing a length of stay prediction model for newborns, achieving better accuracy with greater usability.

BACKGROUND: One in ten newborn children is born prematurely. The elongated length of stay (LOS) of these children in the Neonatal Intensive Care Unit (NICU) has important implications on hospital occupancy figures, healthcare and management costs, as well as the psychology of parents. In order to allow accurate planning and resource allocation, this study aims to create a generalizable and robust model to predict the NICU LOS of preterm newborns. METHODS: Data were collected from a large tertiary center NICU between 2011 and 2018 and relates to 5,362 newborns. The selected model was externally validated using a data set of 8,768 newborns from another tertiary center NICU. This report compares several models, such as Random Forest (RF), quantile RF, and other feature selection methods, including LASSO and AIC step-forward selection. In addition, a novel step-forward selection based on False Discovery Rate (FDR) for quantile regression is presented and evaluated. RESULTS: A high-orderquantile regression model for predicting preterm newborns' LOS that uses only four features available at birth had more attractive properties than other richer ones. The model achieved a Mean Absolute Error (MAE) of 6.26 days on the internal validation set (average LOS 27.04) and an MAE of 6.04 days on the external validation set (average LOS 29.32). The suggested model surpassed the accuracy obtained by models in the literature. It is shown empirically that the FDR-based selection has better properties than the AIC-based step-forward selection approach. CONCLUSION: This paper demonstrates a process to create a predictive model for NICU LOS in preterm newborns, where each step is reasoned. We obtain a simple and robust model for NICU LOS prediction, which achieves far better results than the current model used for financing NICUs. Utilizing this model, we have created an easy-to-use online web application to ease parents' worries and to assist NICU management: https://tzviel.shinyapps.io/calcuLOS.

[THE CHALLENGE OF DIAGNOSING RARE LIFE THREATENING SKIN LESIONS].

INTRODUCTION: Skin lesions seen after delivery are frequent and mostly shallow, without the need for special care or diagnosis challenge. In the following case, an infant was born at 35 weeks gestation, presented after the delivery with a well-demarcated, necrotic plaque over the right forearm with neurologic deficit. The differential diagnosis includes life-threatening reasons, therefore, emergent laboratory and imaging tests were held. Treatment was given after consulting a multidisciplinary team of experts, including antibiotic treatment, blood products and anticoagulation and physiotherapy treatment was started. Under this treatment, improvement was noticed but there was still a motor restriction. He was discharged home on his 24th day of life, with the working diagnosis of Congenital Volkmann Ischemic Contracture (CVIC). On his seventh week of life, he arrived to the emergency room with focal seizure resulting from an infarct seen on an MRI. He was diagnosed with cerebral palsy at the age of five months. In conclusion, Congenital Volkmann Ischemic Contracture is a rare diagnosis, however, awareness is of importance since fast treatment is crucial for future prognosis.

[PLATELETS FUNCTION IN A DROP OF BLOOD: FLOW CYTOMETRY ANALYSIS COMPARED TO PLATELET AGGREGATION].

INTRODUCTION: Light transmission aggregometry (LTA) is the most commonly used test for the diagnosis of platelet function disorders, but requires large amounts of blood samples and normal platelet count. OBJECTIVES: To compare flow cytometric (FC) platelet function testing to standard LTA in the general population, in patients treated with anti-platelets drugs and in term and preterm neonates. METHODS: Platelet function was assessed with LTA and FC using PAC1 binding and p-selectin expression, as platelet activation markers, in response to agonist activation. A comparison between LTA and FC was performed in a Clopidogrel treated patient, before and after (24 and 72 hours) loading the drug. The platelet activation markers PAC1 and p-selectin, were compared in umbilical cord blood samples of in-term and preterm neonates. RESULTS: ADP-induced platelet aggregation was comparable to p-selectin expression assayed by FC (r=0.79-0.86) as measured before and after Clopidogrel loading. Both tests showed good response to Clopidogrel in 72 hours but not in 24 hours after its loading. Preterm cord blood platelets showed decreased ADP-induced activation in both activation markers: PAC1 and p-selectin, but only p-selectin reached statistical significance. We identified possible platelet activation markers in response to commonly used agonists' stimulation for FC analysis. CONCLUSIONS: FC analysis of platelet function has added value in the diagnosis of impaired platelet function and anti-platelet drug response. Using FC enables us to test platelet function in minimal blood volume and regardless of platelet count. Identification of the unique activation marker for each agonist is prerequisite for FC analysis of platelet function.

Applying Judgment Analysis Theory and Methods to Obtain an Insight Into Clinical Judgments: Implementation and Findings With a Simulated Neonatal Intensive Care Unit Setup.

INTRODUCTION: Clinicians who provide acute care are required to quickly identify and judge the illness severity of patients who experience deterioration in their clinical state. Accuracy of judgments can only be tested with respect to a valid reference, but in most health care areas, there is no such score. Judgment analysis theory and methods are presented and proposed as a framework to obtain insight into clinical judgments. A study in a simulated neonatal intensive care unit setup is described to demonstrate the applicability of the proposed methodology. METHODS: Sixteen participants from a neonatal intensive care unit department reviewed 31 clips of simulated cases. The participants were directed to use a 5-point scale to rate their personal interpretation regarding the illness severity of the simulated patient. Judgment analysis techniques were used to identify the judgment capabilities of the participants and to determine factors that influence those capabilities. RESULTS: Most participants interpreted the clinical signs information consistently, but interpretation varied remarkably between clinicians, providing possible explanation to the differences between the clinicians' judgments. Significant correlations were found between the doctors' years of medical experience and attributes of their judgments. CONCLUSIONS: Judgment analysis can be used to obtain insight into clinical judgments and to identify and quantify factors that affect clinicians' judgments. Judgment analysis can promote health care by enhancing clinical assessment teaching, by providing objective and personalized feedback to team members about their judgment performance, and by introducing a unified and objective method to study elements that affect clinical judgments.