Background Prediction of neonatal deaths in NICUs is important for benchmarking and evaluating healthcare services in NICUs. Application of machine learning techniques can improve physicians’ ability to predict the neonatal deaths. The aim of this study was to present a neonatal death risk prediction model using machine learning techniques. Methods This study was conducted in Tehran, Iran in two phases. Initially, important risk factors in neonatal death were identified and then several machine learning models including Artificial Neural Network (ANN), decision tree (Random Forest (RF), C5.0 and CHART tree), Support Vector Machine (SVM), Bayesian Network and Ensemble models were developed. Finally, we prospectively applied these models to predict neonatal death in a NICU and followed up the neonates to compare the outcomes of these neonates with real outcomes. Results 17 factors were considered important in neonatal mortality prediction. The highest Area Under the Curve (AUC) was achieved for the SVM and Ensemble models with 0.98. The best precision and specificity were 0.98 and 0.94, respectively for the RF model. The highest accuracy, sensitivity and F-score were achieved for the SVM model with 0.94, 0.95 and 0.96, respectively. The best performance of models in prospective evaluation was for the ANN, C5.0 and CHAID tree models. Conclusion Using the developed machine learning models can help physicians predict the neonatal deaths in NICUs.
This study assesses the impact of religiosity on delirium severity and patient outcomes among Shi'a Muslim intensive care unit (ICU) patients. We conducted a prospective observational cohort study in 21 ICUs from 6 Iranian academic medical centers. Delirium was assessed using the Confusion Assessment Method for the ICU (CAM-ICU) tool. Eligible patients were intubated, receiving mechanical ventilation (MV) for ≥ 48 h. Illness severity was assessed using Acute Physiology and Chronic Health Evaluation II (APACHE II) scores. A total of 4200 patients were enrolled. Patient religiosity was categorized as more (40.6%), moderate (42.3%), or less (17.1%) based on responses to patient and surrogate questionnaires. The findings suggest that lower pre-illness religiosity may be associated with greater delirium severity, MV duration, and ICU and hospital LOS. The lower mortality in the less religiosity group may be related in part to a greater proportion of female patients, but it remains unclear whether and to what extent greater religiosity impacted treatment decisions by patients and families. Further investigation is needed to validate and clarify the mechanism of the mortality findings.
Background: Parents of preterm neonates are exposed to stress leading to post traumatic stress disorders (PTSD). Objectives: In the present study we compared the prevalence of PTSD in parents of hospitalized preterm and term neonates. Methods: A descriptive-comparative study was undertaken in 2 Iranian Hospitals during 2016 and 2017. Parents of NICU hospitalized preterm neonates as well as those of hospitalized term newborns entered the study. Parents were invited for interview at day 3 -5 after neonate's birth. Questionnaires for acute stress disorder (ASD) were filled out and scored for both mother and father. After a month, parents were asked for a second interview. Prenatal post traumatic stress questionnaires (PPQ) for all mothers and posttraumatic stress disorder checklist (PCL) for all fathers were completed. All recorded data were analyzed to compare the prevalence of PTSD among parents of term and preterm infants. P values less than 0.05 were considered statistically significant. Results: Parents of 80 NICU hospitalized preterm neonates and parents of 80 term hospitalized neonates entered the study. Both the mean ASD and PPQ scores among mothers of preterm infants were significantly higher than those of mothers of term infants (53.77 ± 13.58 vs. 49.27 ± 12.55; P = 0.032 and 31.67 ± 11.85 vs. 28.08 ± 8.80; P = 0.032). The mean PCL score among fathers of preterm infants was significantly higher than their counterparts in other group (31.5 ± 14.9 vs. 21.37 ± 5.4; P < 0.0001). A significant correlation was observed between mother's PPQ and father's PCL scores (P < 0.0001). Mothers with higher ASD scores also showed higher PPQ scores (P < 0.001). Conclusions: Although hospitalization of a neonate is a stressful event for parent, neonate's condition related age at birth was the main subject for parents' psychological complication and PTSD. Moreover, we found that, of parents, mothers were more vulnerable for PTSD but fathers indicated delayed onset of PTSD symptoms.
Background Although the use of a peripherally inserted central catheter (PICC) has many advantages for the treatment of neonates, catheter malposition may result in serious complications that could be life-threatening. We report the case of a 10-day-old neonate with cardiac tamponade secondary to a PICC line who was successfully treated by pericardiocentesis. Case presentation An Iranian (Asian) preterm male neonate was born by Cesarean section with a birth weight of 1190 g and a first-minute Apgar score of 7. Based on an increased respiratory distress syndrome (RDS) score from 4 to 7, resuscitation measures and intubation were performed at the neonatal intensive care unit (NICU). On day 3 after birth, a PICC line was inserted for parenteral therapy. A chest X-ray confirmed that the tip of the PICC line was in the appropriate position. Mechanical ventilation was discontinued 72 h post-NICU admission because of the improved respiratory condition. On the day 10 post-NICU admission, he suddenly developed hypotonia, apnea, hypoxia, hypotension, and bradycardia. Resuscitation and ventilation support were immediately started, and inotropic drugs were also given. Emergency echocardiography showed a severe pericardial effusion with tamponade. The PICC line was removed, and urgent pericardiocentesis was carried out. The respiratory situation gradually improved, the O2 saturation increased to 95%, and vital signs remained stable. Conclusions Dramatic improvement of the neonate's clinical responses after pericardial drainage and PICC removal were suggestive of PICC displacement, pericardial perforation, and cardiac tamponade.
Background: Coronavirus disease 2019 caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has spread worldwide, causing a significant public health disaster. Objectives: The present study aimed to evaluate the clinical features and laboratory data of neonates born to mothers with COVID-19. Methods: A retrospective multicenter cohort study was conducted from March 20 to September 5, 2020, on all neonates born to mothers with positive real-time reverse transcriptase-polymerase chain reaction for SARS-CoV-2 or clinically suspected COVID-19. Neonates enrolled in this study were from five different hospitals affiliated with the Tehran University of Medical Sciences. All the newborns were tested for SARS-CoV-2 using nasopharyngeal swabs during the first 24 - 48 hours of life, and a second-time swabbing was performed as indicated at subsequent visits. All categorical data were manifested as frequency (%), and continuous data were shown as mean ± SD. Results: Forty-four neonates born to 39 infected mothers were evaluated during the study period. Nineteen women had complications during pregnancy, including hypertensive disorders, gestational diabetes, preterm labor, etc. Besides, 54.5% of the neonates were born preterm. The mean gestational age and birth weight were 35.11 ± 4.01 weeks and 2,567 ± 898 g, respectively. Fifteen (34.1%) neonates were symptomatic at birth, and during the observation, more neonates became symptomatic. Finally, 27/44 (61.3%) neonates became symptomatic, and 17/44 remained asymptomatic. The most common clinical manifestations were respiratory distress (77.7%), followed by fever or hypothermia (18.5%), gastrointestinal problems (14.8%), and neurologic findings (3.7%). Also, the most common clinical feature of eight neonates with positive RT-PCR was respiratory distress, followed by neurologic symptoms, temperature instability, and gastrointestinal disorder, in sequence. Few abnormalities were seen in laboratory findings. Chest X-rays were abnormal in 22.2% of the neonates. Conclusions: The SARS-CoV-2 infection during pregnancy may cause severe maternal and neonatal morbidities. Neonates with positive SARS-CoV-2 may demonstrate a spectrum of clinical features. The most common feature of neonates born to mothers with COVID-19 was respiratory distress.
Background Previous studies have indicated that the majority of cases with “failed” results related to transient evoked otoacoustic emissions (OAE) test have the normal hearing. The present study aimed to assess the possible relationships between perinatal factors and the false-positive OAE results. Methods A case-control study was carried out in an Iranian Hospital in 2020. Based on the OAE results on the first day of life, newborns were divided into 2 groups; Control group included subjects with “Pass” OAE results. Every neonate with “Fail” OAE result was referred for auditory brainstem response (ABR). Neonates with bilateral fail OAE but normal ABR results (false-positive OAE) were considered as the case group. All recorded data were analyzed to assess the possible correlations between maternal/neonatal factors and the false-positive OAE results. Results One hundred and eighty-one neonates entered the study. Of all included neonates, 87 (48.1%) cases showed bilateral fail OAE and 94 (51.9%) subjects passed the OAE test. Normal ABR results (false-positive OAE) were observed in all cases with bilateral fail OAE. Comparisons of variables affecting the OAE results showed that of all perinatal factors, neonate’s sex (p = 0.046) and cesarean section (p = 0.003) were the only influencing factors that increased the risk of false-positive OAE results. Conclusion Based on the results, the cesarean section delivery and neonate’s male sex increased the risk of false-positive results related to OAE test. Implementing other screening tests such as ABR or Automated ABR as the initial screening test could be suggested for such cases.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.