Back

Prediction Analysis of Preterm Neonates Mortality using Machine Learning Algorithms via Python Programming

Monfared, V.; Hashemi, A.

2023-01-21 bioinformatics
10.1101/2023.01.20.524905 bioRxiv
Show abstract

Prediction analysis of preterm neonate mortality is necessary and significant for benchmarking and evaluating healthcare services in Hospitals and other medical centers. Application of artificial intelligence and machine learning models, which is a hot topic in medicine/healthcare and engineering, may improve physicians skill to predict the preterm neonatal deaths. The main purpose of this research article is to introduce a preterm neonatal mortality risk prediction by means of machine learning/ML predictive models to survive infants using supervised ML models if possible. Moreover, this paper presents some effective parameters and features which affect to survive the infants directly. It means, the obtained model has an accuracy of about 91.5% to predict the status of infant after delivery. After recognizing the critical status for an infant, physicians and other healthcare personnel can help to infant for possible surviving using special medical NICU cares. It has been tried to get some suitable models with high accuracy and comparing the results. In a word, a survival prediction analysis of preterm neonate mortality has been carried out using machine learning methods via Python programming (possible surviving infants after delivery in the hospital).

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.