{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T09:11:13Z","timestamp":1774516273391,"version":"3.50.1"},"reference-count":36,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,1,25]],"date-time":"2023-01-25T00:00:00Z","timestamp":1674604800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003032","name":"Association Nationale de la Recherche et de la Technologie","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003032","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>This paper presents the use of deep conditional autoencoder to predict the effect of treatments for patients suffering from hemophiliac disorders. Conditional autoencoder is a semi-supervised model that learns an abstract representation of the data and provides conditional reconstruction capabilities. Such models are suited to problems with limited and\/or partially observable data, common situation for data in medicine. Deep conditional autoencoders allow the representation of highly non-linear functions which makes them promising candidates. However, the optimization of parameters and hyperparameters is particularly complex. For parameter optimization, the classical approach of random initialization of weight matrices works well in the case of simple architectures, but is not feasible for deep architectures. For hyperparameter optimization of deep architectures, the classical cross-validation method is costly. In this article, we propose solutions using a conditional pre-training algorithm and incremental optimization strategies. Such solutions reduce the variance of the estimation process and enhances convergence of the learning algorithm. Our proposal is applied for personalized care of hemophiliac patients. Results show better performances than generative adversarial networks (baseline) and highlight the benefits of your contribution to predict the effect of treatments for patients.<\/jats:p>","DOI":"10.3389\/frai.2023.1048010","type":"journal-article","created":{"date-parts":[[2023,1,25]],"date-time":"2023-01-25T08:28:14Z","timestamp":1674635294000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Conditional autoencoder pre-training and optimization algorithms for personalized care of hemophiliac patients"],"prefix":"10.3389","volume":"6","author":[{"given":"C\u00e9dric","family":"Buche","sequence":"first","affiliation":[]},{"given":"Fran\u00e7ois","family":"Lasson","sequence":"additional","affiliation":[]},{"given":"S\u00e9bastien","family":"Kerdelo","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2023,1,25]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1016\/j.neucom.2019.07.106","article-title":"DEVDAN: deep evolving denoising autoencoder","volume":"390","author":"Ashfahani","year":"2020","journal-title":"Neurocomputing"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/2200000006","article-title":"Learning deep architectures for ai","volume":"2","author":"Bengio","year":"2009","journal-title":"Found. Trends Mach. Learn"},{"key":"B3","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/7503.003.0024","article-title":"Greedy layer-wise training of deep networks","volume-title":"Advances in Neural Information Processing Systems 19","author":"Bengio","year":"2007"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.01322","article-title":"Learning with random learning rates","author":"Blier","year":"2018"},{"key":"B5","unstructured":"Why does unsupervised pre-training help deep learning?625660 ErhanD. BengioY. CourvilleA. ManzagolP.-A. VincentP. BengioS. J. Mach. Learn. Res112010"},{"key":"B6","unstructured":"The cascade-correlation learning architecture524532 FahlmanS. E. LebiereC. TouretzkyD. S. Morgan-KaufmannAdvances in Neural Information Processing Systems 21990"},{"key":"B7","doi-asserted-by":"publisher","first-page":"972","DOI":"10.1126\/science.1136800","article-title":"Clustering by passing messages between data points","volume":"315","author":"Frey","year":"2007","journal-title":"Science"},{"key":"B8","unstructured":"G\u00e9ronA. Hors Collection. DunodDeep Learning avec TensorFlow2017"},{"key":"B9","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, volume 9 of Proceedings of Machine Learning Research","author":"Glorot","year":"2010"},{"key":"B10","unstructured":"GoodfellowI. BengioY. CourvilleA. MIT PressDeep Learning2016"},{"key":"B11","doi-asserted-by":"publisher","first-page":"858","DOI":"10.1016\/j.sapharm.2018.11.010","article-title":"Medication administration errors and mortality: Incidents reported in england and wales between 2007\u20132016","volume":"15","author":"Harkanen","year":"2019","journal-title":"Res. Soc. Admin. Pharm"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","article-title":"A fast learning algorithm for deep belief nets","volume":"18","author":"Hinton","year":"2006","journal-title":"Neural Comput"},{"key":"B13","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Reducing the dimensionality of data with neural networks","volume":"313","author":"Hinton","year":"2006","journal-title":"Science"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput"},{"key":"B15","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1136\/bmj.38398.500764.8F","article-title":"Improving clinical practice using clinical decision support systems: a systematic review of trials to identify features critical to success","volume":"330","author":"Kawamoto","year":"2005","journal-title":"BMJ"},{"key":"B16","unstructured":"Semi-supervised learning with deep generative models35813589 KingmaD. P. RezendeD. J. MohammedS. WellingM. GhahramaniZ. WellingM. CortesC. LawrenceN. D. WeinbergerK. Q. 29989965Curran AssociatesAdvances in Neural Information Processing Systems 272014"},{"key":"B17","unstructured":"LassonF. ENIBInt\u00e9r\u00eats des Auto-Encodeurs profonds pour les syst\u00e8mes d'ide \u00e0 l'individualisation de th\u00e9rapies2020"},{"key":"B18","first-page":"109","article-title":"A clinical decision support system to help the interpretation of laboratory results and to elaborate a clinical diagnosis in blood coagulation domain","volume-title":"International Work-Conference on Artificial Neural Networks (IWANN)","author":"Lasson","year":"2019"},{"key":"B19","first-page":"80","article-title":"Temporal deep belief network for online human motion recognition","volume-title":"30th International Florida Artificial Intelligence Research Society Conference (FLAIRS)","author":"Lasson","year":"2017"},{"key":"B20","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"B21","first-page":"598","article-title":"Optimal brain damage","volume-title":"Advances in Neural Information Processing Systems 2","author":"Lecun","year":"1990"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1804","DOI":"10.3406\/intel.1987.1804","article-title":"Modeles connexionnistes de l'apprentissage","volume":"2","author":"Lecun","year":"1987","journal-title":"Intellectica"},{"key":"B23","doi-asserted-by":"publisher","first-page":"i2139","DOI":"10.1136\/bmj.i2139","article-title":"Medical error \u2013 the third leading cause of death in the us","volume":"353","author":"Makary","year":"2016","journal-title":"BMJ"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1511.05644","article-title":"Adversarial autoencoders","author":"Makhzani","year":"2016","journal-title":"arXiv"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1411.1784","article-title":"Conditional generative adversarial nets","author":"Mirza","year":"2014","journal-title":"arXiv"},{"key":"B26","volume-title":"Lecture notes. CS 294a: Sparse autoencoder","author":"Ng","year":"2017"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1809.09081","article-title":"Autonomous deep learning: Incremental learning of denoising autoencoder for evolving data streams","author":"Pratama","year":"2018","journal-title":"arXiv"},{"key":"B28","first-page":"55","article-title":"Early stopping-but when?","volume-title":"Neural Networks: Tricks of the Trade","author":"Prechelt","year":"1996"},{"key":"B29","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1109\/72.248452","article-title":"Pruning algorithms-a survey","volume":"4","author":"Reed","year":"1993","journal-title":"IEEE Trans. Neural Netw"},{"key":"B30","first-page":"833","article-title":"Contractive auto-encoders: Explicit invariance during feature extraction","volume-title":"Proceedings of the 28th International Conference on International Conference on Machine Learning","author":"Rifai","year":"2011"},{"key":"B31","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"Rumelhart","year":"1986","journal-title":"Nature"},{"key":"B32","doi-asserted-by":"publisher","first-page":"546","DOI":"10.2471\/BLT.17.198002","article-title":"The third global patient safety challenge: tackling medication-related harm","volume":"95","author":"Sheikh","year":"2017","journal-title":"Bull. World Health Organ"},{"key":"B33","unstructured":"Learning structured output representation using deep conditional generative models34833491 SohnK. YanX. LeeH. Montreal, QCMIT PressProceedings of the 28th International Conference on Neural Information Processing Systems2015"},{"key":"B34","doi-asserted-by":"crossref","DOI":"10.1145\/1390156.1390294","article-title":"Extracting and composing robust features with denoising autoencoders","author":"Vincent","year":"2008","journal-title":"International Conference on Machine Learning Proceedings"},{"key":"B35","first-page":"1453","article-title":"Online incremental feature learning with denoising autoencoders","volume-title":"Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, volume 22 of Proceedings of Machine Learning Research","author":"Zhou","year":""},{"key":"B36","unstructured":"Supplementary material: Online incremental feature learning with denoising autoencoders14531461 ZhouG. SohnK. LeeH. J. Mach. Learn. Res22"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2023.1048010\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T15:28:48Z","timestamp":1701790128000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2023.1048010\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,25]]},"references-count":36,"alternative-id":["10.3389\/frai.2023.1048010"],"URL":"https:\/\/doi.org\/10.3389\/frai.2023.1048010","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,25]]},"article-number":"1048010"}}