Editorial: Artificial Intelligence Bioinformatics: Development and Application of Tools for Omics and Inter-Omics Studies

Chicco, Davide; Heider, Dominik; Facchiano, Angelo

doi:10.3389/fgene.2020.00309

Cited by 9 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a result, ten experiments were conducted, one for each number of nodes considered. For each experiment, a model with the following characteristics was created: Learning rate: 0.001; Loss Function: Binary cross-entropy; Optimization algorithm: Stochastic Gradient Descent; Trigger function for hidden layer: ReLU; Trigger function for the output layer: sigmoids; Number of nodes in the hidden layer: x

[ 5 , 15 ]. …”

Section: Resultsmentioning

confidence: 99%

“…In fact, it was further partitioned, according to an 80:20 ratio, into an additional training set and a validation set. A grid search was performed on these two in a search space, understood as the number of nodes, equal to the interval [ 5 , 15 ]. For the search of the best optimization algorithm, the first training set was used, on which a k-fold cross-validation with k = 9 was applied, with experiments repeated 11 times.…”

Section: Methodsmentioning

confidence: 99%

“…Artificial intelligence (AI) applies computer science and technology to problem-solving based on large data sets. It is a fast-growing field, which found many applications in biology and medicine research, as demonstrated in a large body of scientific literature [ 4 , 5 , 6 , 7 ], and also in studies on diabetes, not only in the therapeutic monitoring but also in the prediction of new-onset diabetes, and of future complications related to this pathology, and it is estimated that this methodology will help in bringing down the diabetes global prevalence of 8.8% [ 8 ].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Machine Learning as a Support for the Diagnosis of Type 2 Diabetes

Agliata

Giordano

Bardozzo

et al. 2023

IJMS

Self Cite

View full text Add to dashboard Cite

Diabetes is a chronic, metabolic disease characterized by high blood sugar levels. Among the main types of diabetes, type 2 is the most common. Early diagnosis and treatment can prevent or delay the onset of complications. Previous studies examined the application of machine learning techniques for prediction of the pathology, and here an artificial neural network shows very promising results as a possible valuable aid in the management and prevention of diabetes. Additionally, its superior ability for long-term predictions makes it an ideal choice for this field of study. We utilized machine learning methods to uncover previously undiscovered associations between an individual’s health status and the development of type 2 diabetes, with the goal of accurately predicting its onset or determining the individual’s risk level. Our study employed a binary classifier, trained on scratch, to identify potential nonlinear relationships between the onset of type 2 diabetes and a set of parameters obtained from patient measurements. Three datasets were utilized, i.e., the National Center for Health Statistics’ (NHANES) biennial survey, MIMIC-III and MIMIC-IV. These datasets were then combined to create a single dataset with the same number of individuals with and without type 2 diabetes. Since the dataset was balanced, the primary evaluation metric for the model was accuracy. The outcomes of this study were encouraging, with the model achieving accuracy levels of up to 86% and a ROC AUC value of 0.934. Further investigation is needed to improve the reliability of the model by considering multiple measurements from the same patient over time.

show abstract

[ 5 , 15 ]. …”

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning as a Support for the Diagnosis of Type 2 Diabetes

Agliata

Giordano

Bardozzo

et al. 2023

IJMS

Self Cite

View full text Add to dashboard Cite

show abstract

“…Following up on a Research Topic already carried out in past years ( Chicco et al, 2020 ), we introduce a new Research Topic of articles to present Artificial Intelligence and new bioinformatics applications and computational approaches for analyzing omics data, or the application of existing tools, toward a more complete interpretation of biological phenomena, with applications in personalized medicine and biotechnology.…”

Section: Introductionmentioning

confidence: 99%

Editorial: Artificial intelligence and bioinformatics applications for omics and multi-omics studies

Facchiano,

Heider,

Mutarelli

2024

Front. Genet.

Self Cite

View full text Add to dashboard Cite

“…Following the NETTAB/BBCC2019 Conference (http://www.igst.it/nettab/2019/), this Research Topic has been aimed to collect articles that describe development of novel tools for the analysis of proteomics data and their integration with omics data from genomics level in studies that add knowledge into the complexity of biology using inter-omics approaches. The Conference has been organized as a joint meeting of two annual events, NETTAB (http://www.nettab.org) and BBCC (http://www.bbcc-meetings.it), both followed by the publication of article collections in specialized journals (Armano et al, 2007;Romano et al, 2011Romano et al, , 2017Romano et al, , 2019Marabotti et al, 2018;Chicco et al, 2020;Facchiano, 2020). The Conference has been attended by about 80 researchers, hosted a special session on "Computational Proteomics" and a panel discussion entitled "Community efforts for computational proteomics", co-chaired by the leaders of the ELIXIR Proteomics Community, Oliver Kohlbacher (University of Tübingen), Lennart Martens (VIB-UGent Center for Medical Biotechnology) and Juan Antonio Vizcaíno (EBI).…”

mentioning

confidence: 99%