Predicting Extubation Readiness in Preterm Infants Utilizing Machine Learning: A Diagnostic Utility Study.

OBJECTIVE: The objective of this study was to predict extubation readiness in preterm infants using machine learning analysis of bedside pulse oximeter and ventilator data. STUDY DESIGN: This is an observational study with prospective recordings of oxygen saturation (SpO2) and ventilator data from infants <30 weeks of gestation age. Research pulse oximeters collected SpO2 (1 Hz sampling rate) to quantify intermittent hypoxemia (IH). Continuous ventilator metrics were collected (4-5-minute sampling) from bedside ventilators. Data modeling was completed using unbiased machine learning algorithms. Three model sets were created using the following data source combinations: (1) IH and ventilator (IH + SIMV), (2) IH, and (3) ventilator (SIMV). Infants were also analyzed separated by postnatal age (infants <2 or ≥2 weeks of age). Models were compared by area under the receiver operating characteristic curve (AUC). RESULTS: A total of 110 extubation events from 110 preterm infants were analyzed. Infants had a median gestation age and birth weight of 26 weeks and 825 g, respectively. Of the 3 models presented, the IH + SIMV model achieved the highest AUC of 0.77 for all infants. Separating infants by postnatal age increased accuracy further achieving AUC of 0.94 for <2 weeks of age group and AUC of 0.83 for ≥2 weeks group. CONCLUSIONS: Machine learning analysis has the potential to enhance prediction accuracy of extubation readiness in preterm infants while utilizing readily available data streams from bedside pulse oximeters and ventilators.

Spatial association of homicide rate with violence, sociodemographic, and public security factors: global burden of disease study 2018 for municipalities in Brazil.

OBJECTIVES: To analyse spatial-temporal changes and spatial association of homicide rates with violence, sociodemographic, public security and human rights indicators in Brazilian municipalities. STUDY DESIGN: An ecological study using homicide estimates from the Global Burden of Disease and population from the Brazilian Ministry of Health, 2000 to 2018. The explanatory variables come from the systems of mortality, notifications of violence and security, and the Brazilian Institute of Geography and Statistics. METHODS: Moran indices and maps identified clusters of high and low risk for homicides in three trienniums (p < 0.05). Multivariate linear and spatial regressions estimated explanatory factors' contributions for the last triennium. RESULTS: Municipalities with high rates of homicides (>34/100,000) doubled, reaching 21.5 %. Those rates were concentrated in big cities, and increased in smaller municipalities. Increases in critical areas were found in the Northeast and North regions: more than 40 % in the states of Sergipe, Bahia, Ceará, Rio Grande do Norte and Roraima. Decreases occurred in the Southeast and Midwest regions: more than 35 % in São Paulo and Rio de Janeiro states. The spatial model, with an 18.9 % higher R2 (0.706), showed a positive association for records of violence, Blacks, low-level education, municipalities >50,000 inhabitants and municipalities with homicide and municipal police. CONCLUSIONS: An increase in and the interiorisation of homicide risk areas in Brazil was observed, with displacement among regions (from the Southeast to the North/Northeast). The level of violence was the main explanatory factor for homicides. Territorial space proved to be important to understand and prevent lethal crime.