Dataset Information

Quantitative Preterm EEG Analysis: The Need for Caution in Using Modern Data Science Techniques.

ABSTRACT: Hemodynamic changes during neonatal transition increase the vulnerability of the preterm brain to injury. Real-time monitoring of brain function during this period would help identify the immediate impact of these changes on the brain. Neonatal EEG provides detailed real-time information about newborn brain function but can be difficult to interpret for non-experts; preterm neonatal EEG poses even greater challenges. An objective quantitative measure of preterm brain health would be invaluable during neonatal transition to help guide supportive care and ultimately protect the brain. Appropriate quantitative measures of preterm EEG must be calculated and care needs to be taken when applying the many techniques available for this task in the era of modern data science. This review provides valuable information about the factors that influence quantitative EEG analysis and describes the common pitfalls. Careful feature selection is required and attention must be paid to behavioral state given the variations encountered in newborn EEG during different states. Finally, the detrimental influence of artifacts on quantitative EEG analysis is illustrated.

SUBMITTER: O'Toole JM

PROVIDER: S-EPMC6509809 | biostudies-other | 2019

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Quantitative Preterm EEG Analysis: The Need for Caution in Using Modern Data Science Techniques.

O'Toole John M JM Boylan Geraldine B GB

Frontiers in pediatrics 20190503

Hemodynamic changes during neonatal transition increase the vulnerability of the preterm brain to injury. Real-time monitoring of brain function during this period would help identify the immediate impact of these changes on the brain. Neonatal EEG provides detailed real-time information about newborn brain function but can be difficult to interpret for non-experts; preterm neonatal EEG poses even greater challenges. An objective quantitative measure of preterm brain health would be invaluable d ...[more]

PMID: 31131267

Similar Datasets

Project description:BackgroundModern modelling techniques may potentially provide more accurate predictions of binary outcomes than classical techniques. We aimed to study the predictive performance of different modelling techniques in relation to the effective sample size ("data hungriness").MethodsWe performed simulation studies based on three clinical cohorts: 1282 patients with head and neck cancer (with 46.9% 5 year survival), 1731 patients with traumatic brain injury (22.3% 6 month mortality) and 3181 patients with minor head injury (7.6% with CT scan abnormalities). We compared three relatively modern modelling techniques: support vector machines (SVM), neural nets (NN), and random forests (RF) and two classical techniques: logistic regression (LR) and classification and regression trees (CART). We created three large artificial databases with 20 fold, 10 fold and 6 fold replication of subjects, where we generated dichotomous outcomes according to different underlying models. We applied each modelling technique to increasingly larger development parts (100 repetitions). The area under the ROC-curve (AUC) indicated the performance of each model in the development part and in an independent validation part. Data hungriness was defined by plateauing of AUC and small optimism (difference between the mean apparent AUC and the mean validated AUC <0.01).ResultsWe found that a stable AUC was reached by LR at approximately 20 to 50 events per variable, followed by CART, SVM, NN and RF models. Optimism decreased with increasing sample sizes and the same ranking of techniques. The RF, SVM and NN models showed instability and a high optimism even with >200 events per variable.ConclusionsModern modelling techniques such as SVM, NN and RF may need over 10 times as many events per variable to achieve a stable AUC and a small optimism than classical modelling techniques such as LR. This implies that such modern techniques should only be used in medical prediction problems if very large data sets are available.

Project description:With a realistic threat against biodiversity in rain forests and in the sea, a sustainable use of natural products is becoming more and more important. Basic research directed against different organisms in Nature could reveal unexpected insights into fundamental biological mechanisms but also new pharmaceutical or biotechnological possibilities of more immediate use. Many different strategies have been used prospecting the biodiversity of Earth in the search for novel structure-activity relationships, which has resulted in important discoveries in drug development. However, we believe that the development of multidisciplinary incentives will be necessary for a future successful exploration of Nature. With this aim, one way would be a modernization and renewal of a venerable proven interdisciplinary science, Pharmacognosy, which represents an integrated way of studying biological systems. This has been demonstrated based on an explanatory model where the different parts of the model are explained by our ongoing research. Anti-inflammatory natural products have been discovered based on ethnopharmacological observations, marine sponges in cold water have resulted in substances with ecological impact, combinatory strategy of ecology and chemistry has revealed new insights into the biodiversity of fungi, in depth studies of cyclic peptides (cyclotides) has created new possibilities for engineering of bioactive peptides, development of new strategies using phylogeny and chemography has resulted in new possibilities for navigating chemical and biological space, and using bioinformatic tools for understanding of lateral gene transfer could provide potential drug targets. A multidisciplinary subject like Pharmacognosy, one of several scientific disciplines bridging biology and chemistry with medicine, has a strategic position for studies of complex scientific questions based on observations in Nature. Furthermore, natural product research based on intriguing scientific questions in Nature can be of value to increase the attraction for young students in modern life science.

Dataset Information

Quantitative Preterm EEG Analysis: The Need for Caution in Using Modern Data Science Techniques.

Publications

Quantitative Preterm EEG Analysis: The Need for Caution in Using Modern Data Science Techniques.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets