Sökning: id:"swepub:oai:gup.ub.gu.se/318942" >
Neural network trai...
Neural network training with highly incomplete medical datasets
-
- Chang, Yu-Wei (författare)
- University of Gothenburg,Gothenburg University,Göteborgs universitet,Institutionen för fysik (GU),Department of Physics (GU)
-
- Natali, Laura (författare)
- University of Gothenburg,Gothenburg University,Göteborgs universitet,Institutionen för fysik (GU),Department of Physics (GU)
-
- Jamialahmadi, Oveis (författare)
- University of Gothenburg,Gothenburg University,Göteborgs universitet,Institutionen för medicin, avdelningen för molekylär och klinisk medicin,Institute of Medicine, Department of Molecular and Clinical Medicine
-
visa fler...
-
- Romeo, Stefano, 1976 (författare)
- University of Gothenburg,Gothenburg University,Göteborgs universitet,Institutionen för medicin, avdelningen för molekylär och klinisk medicin,Institute of Medicine, Department of Molecular and Clinical Medicine,University Magna Graecia,Sahlgrenska University Hospital
-
- Pereira, Joana B. (författare)
- Karolinska Institutet,Lund University,Lunds universitet,Klinisk minnesforskning,Forskargrupper vid Lunds universitet,Clinical Memory Research,Lund University Research Groups
-
- Volpe, Giovanni, 1979 (författare)
- University of Gothenburg,Gothenburg University,Göteborgs universitet,Institutionen för fysik (GU),Department of Physics (GU)
-
visa färre...
-
(creator_code:org_t)
-
- 2022-07-06
- 2022
- Engelska.
-
Ingår i: Machine Learning-Science and Technology. - : IOP Publishing. - 2632-2153. ; 3:3
- Relaterad länk:
-
http://dx.doi.org/10... (free)
-
visa fler...
-
https://gup.ub.gu.se...
-
https://doi.org/10.1...
-
https://lup.lub.lu.s...
-
http://kipublication...
-
visa färre...
Abstract
Ämnesord
Stäng
- Neural network training and validation rely on the availability of large high-quality datasets. However, in many cases only incomplete datasets are available, particularly in health care applications, where each patient typically undergoes different clinical procedures or can drop out of a study. Since the data to train the neural networks need to be complete, most studies discard the incomplete datapoints, which reduces the size of the training data, or impute the missing features, which can lead to artifacts. Alas, both approaches are inadequate when a large portion of the data is missing. Here, we introduce GapNet, an alternative deep-learning training approach that can use highly incomplete datasets without overfitting or introducing artefacts. First, the dataset is split into subsets of samples containing all values for a certain cluster of features. Then, these subsets are used to train individual neural networks. Finally, this ensemble of neural networks is combined into a single neural network whose training is fine-tuned using all complete datapoints. Using two highly incomplete real-world medical datasets, we show that GapNet improves the identification of patients with underlying Alzheimer's disease pathology and of patients at risk of hospitalization due to Covid-19. Compared to commonly used imputation methods, this improvement suggests that GapNet can become a general tool to handle incomplete medical datasets.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datorteknik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Engineering (hsv//eng)
- NATURVETENSKAP -- Data- och informationsvetenskap -- Bioinformatik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Bioinformatics (hsv//eng)
Nyckelord
- neural networks
- Alzheimer disease
- Covid-19
- incomplete datasets
- missing data
- disease
- biomarkers
- imputation
- Computer Science
- Science & Technology - Other Topics
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
Till lärosätets databas