Reducing neonatal mortality is a critical global health objective,especially in resource-constrained developing countries.This study employs machine learning(ML)techniques to predict fetal health status based on cardi...Reducing neonatal mortality is a critical global health objective,especially in resource-constrained developing countries.This study employs machine learning(ML)techniques to predict fetal health status based on cardiotocography(CTG)examination findings,utilizing a dataset from the Kaggle repository due to the limited comprehensive healthcare data available in developing nations.Features such as baseline fetal heart rate,uterine contractions,and waveform characteristics were extracted using the RFE wrapper feature engineering technique and scaled with a standard scaler.Six ML models—Logistic Regression(LR),Decision Tree(DT),Random Forest(RF),Gradient Boosting(GB),Categorical Boosting(CB),and Extended Gradient Boosting(XGB)—are trained via cross-validation and evaluated using performance metrics.The developed models were trained via cross-validation and evaluated using ML performance metrics.Eight out of the 21 features selected by GB returned their maximum Matthews Correlation Coefficient(MCC)score of 0.6255,while CB,with 20 of the 21 features,returned the maximum and highest MCC score of 0.6321.The study demonstrated the ability of ML models to predict fetal health conditions from CTG exam results,facilitating early identification of high-risk pregnancies and enabling prompt treatment to prevent severe neonatal outcomes.展开更多
Background: The outcome of neonatal surgery depends on safe anaesthesia, competent surgery and good nursing care. The University of Uyo Teaching Hospital, Uyo, Nigeria, established in February 2008, has specialist ana...Background: The outcome of neonatal surgery depends on safe anaesthesia, competent surgery and good nursing care. The University of Uyo Teaching Hospital, Uyo, Nigeria, established in February 2008, has specialist anaesthetic and surgical manpower. The aim of the study was to determine the outcome and contributing factors to mortality in neonatal surgical emergencies at this new tertiary health institution. Method: It was a retrospective descriptive study of neonates that underwent emergency surgery at the University of Uyo Teaching Hospital between June 2008 and May 2011. Data was obtained from the anaesthetic register, ward admission and discharged register, nurses report books and patient case files. Results: Forty-five neonates were operated upon during the three year period. There were 28 males and 17 females with a male to female ratio of 1.7:1. Forty-four (97.8%) of the neonates were referred to the University of Uyo Teaching Hospital. The mean age and body weight at presentation were 47.5 ± 44.4 hours and 2.65 ± 0.61 kg respectively. The mean interval between admission and surgical intervention was 4.9 ± 6.2 days. Malformations of the gut (40%) and anterior abdominal wall (26.7%) were the major pathologies. The overall mortality following surgery was 62.2%. Case fatality rates ranged from 0% for Hirschprung’s disease to 100% for tracheoesophageal fistula. The immediate causes of death among these neonates were peritonitis from gangrenous gut, hypovolaemia and repeat surgery. Contributing factors to mortality were delivery in unorthodox health facilities, delay in presentation as well as surgical intervention and inefficient postoperative monitoring. Conclusion: Emergency neonatal surgeries at the UUTH are associated with unacceptable high mortality. Reduction in such mortality would require campaign for early presentation, a lot more timely surgical interventions and upgrading of monitoring facili- ties to help in improving perioperative monitoring and care.展开更多
文摘Reducing neonatal mortality is a critical global health objective,especially in resource-constrained developing countries.This study employs machine learning(ML)techniques to predict fetal health status based on cardiotocography(CTG)examination findings,utilizing a dataset from the Kaggle repository due to the limited comprehensive healthcare data available in developing nations.Features such as baseline fetal heart rate,uterine contractions,and waveform characteristics were extracted using the RFE wrapper feature engineering technique and scaled with a standard scaler.Six ML models—Logistic Regression(LR),Decision Tree(DT),Random Forest(RF),Gradient Boosting(GB),Categorical Boosting(CB),and Extended Gradient Boosting(XGB)—are trained via cross-validation and evaluated using performance metrics.The developed models were trained via cross-validation and evaluated using ML performance metrics.Eight out of the 21 features selected by GB returned their maximum Matthews Correlation Coefficient(MCC)score of 0.6255,while CB,with 20 of the 21 features,returned the maximum and highest MCC score of 0.6321.The study demonstrated the ability of ML models to predict fetal health conditions from CTG exam results,facilitating early identification of high-risk pregnancies and enabling prompt treatment to prevent severe neonatal outcomes.
文摘Background: The outcome of neonatal surgery depends on safe anaesthesia, competent surgery and good nursing care. The University of Uyo Teaching Hospital, Uyo, Nigeria, established in February 2008, has specialist anaesthetic and surgical manpower. The aim of the study was to determine the outcome and contributing factors to mortality in neonatal surgical emergencies at this new tertiary health institution. Method: It was a retrospective descriptive study of neonates that underwent emergency surgery at the University of Uyo Teaching Hospital between June 2008 and May 2011. Data was obtained from the anaesthetic register, ward admission and discharged register, nurses report books and patient case files. Results: Forty-five neonates were operated upon during the three year period. There were 28 males and 17 females with a male to female ratio of 1.7:1. Forty-four (97.8%) of the neonates were referred to the University of Uyo Teaching Hospital. The mean age and body weight at presentation were 47.5 ± 44.4 hours and 2.65 ± 0.61 kg respectively. The mean interval between admission and surgical intervention was 4.9 ± 6.2 days. Malformations of the gut (40%) and anterior abdominal wall (26.7%) were the major pathologies. The overall mortality following surgery was 62.2%. Case fatality rates ranged from 0% for Hirschprung’s disease to 100% for tracheoesophageal fistula. The immediate causes of death among these neonates were peritonitis from gangrenous gut, hypovolaemia and repeat surgery. Contributing factors to mortality were delivery in unorthodox health facilities, delay in presentation as well as surgical intervention and inefficient postoperative monitoring. Conclusion: Emergency neonatal surgeries at the UUTH are associated with unacceptable high mortality. Reduction in such mortality would require campaign for early presentation, a lot more timely surgical interventions and upgrading of monitoring facili- ties to help in improving perioperative monitoring and care.
