Predicting Huntington’s Disease: Extreme Learning Machine with Missing Values

Emil Eirola; Anton Akusok; Kaj-Mikael Björk; Hans  Johnson; Amaury Lendasse

doi:10.1007/978-3-319-57421-9_16

Predicting Huntington’s Disease: Extreme Learning Machine with Missing Values

Emil Eirola, Anton Akusok, Kaj-Mikael Björk, Hans Johnson, Amaury Lendasse

Finance, Helsinki

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

Abstract

Problems with incomplete data and missing values are common and important in real-world machine learning scenarios, yet often underrepresented in the research field. Particularly data related to healthcare tends to feature missing values which must be handled properly, and ignoring any incomplete samples is not an acceptable solution. The Extreme Learning Machine has demonstrated excellent performance in a variety of machine learning tasks, including situations with missing values. In this paper, we present an application to predict the onset of Huntington’s disease several years in advance based on data from MRI brain scans. Experimental results show that such prediction is indeed realistic with reasonable accuracy, provided the missing values are handled with care. In particular, Multiple Imputation ELM achieves exceptional prediction accuracy.

Original language	English
Title of host publication	Proceedings of ELM-2016
Number of pages	12
Place of Publication	Cham
Publisher	Springer
Publication date	26.05.2017
Pages	195-206
ISBN (Print)	978-3-319-57420-2
ISBN (Electronic)	978-3-319-57421-9
DOIs	https://doi.org/10.1007/978-3-319-57421-9_16
Publication status	Published - 26.05.2017
MoE publication type	A4 Article in conference proceedings
Event	2016 the 7th International Conference on Extreme Learning Machines (ELM) - Marina Bay Sands, Singapore Duration: 13.12.2016 → 15.12.2016

Publication series

Name	Proceedings in Adaptation, Learning and Optimization (PALO)
Volume	9

Keywords

512 Business and Management
Extreme learning machine
Missing values
Multiple imputation
Huntington’s disease
Prediction

Access to Document

10.1007/978-3-319-57421-9_16

OpenUrl availability

Full text

Cite this

@inproceedings{46440c085e8d479294d784b503144f75,

title = "Predicting Huntington{\textquoteright}s Disease: Extreme Learning Machine with Missing Values",

abstract = "Problems with incomplete data and missing values are common and important in real-world machine learning scenarios, yet often underrepresented in the research field. Particularly data related to healthcare tends to feature missing values which must be handled properly, and ignoring any incomplete samples is not an acceptable solution. The Extreme Learning Machine has demonstrated excellent performance in a variety of machine learning tasks, including situations with missing values. In this paper, we present an application to predict the onset of Huntington{\textquoteright}s disease several years in advance based on data from MRI brain scans. Experimental results show that such prediction is indeed realistic with reasonable accuracy, provided the missing values are handled with care. In particular, Multiple Imputation ELM achieves exceptional prediction accuracy.",

keywords = "512 Business and Management, Extreme learning machine, Missing values, Multiple imputation, Huntington{\textquoteright}s disease, Prediction",

author = "Emil Eirola and Anton Akusok and Kaj-Mikael Bj{\"o}rk and Hans Johnson and Amaury Lendasse",

year = "2017",

month = may,

day = "26",

doi = "10.1007/978-3-319-57421-9_16",

language = "English",

isbn = "978-3-319-57420-2",

series = " Proceedings in Adaptation, Learning and Optimization (PALO)",

publisher = "Springer",

pages = "195--206 ",

booktitle = "Proceedings of ELM-2016",

address = "International",

note = "2016 the 7th International Conference on Extreme Learning Machines (ELM) ; Conference date: 13-12-2016 Through 15-12-2016",

}

Eirola, E, Akusok, A, Björk, K-M, Johnson, H & Lendasse, A 2017, Predicting Huntington’s Disease: Extreme Learning Machine with Missing Values. in Proceedings of ELM-2016. Proceedings in Adaptation, Learning and Optimization (PALO), vol. 9, Springer, Cham, pp. 195-206 , 2016 the 7th International Conference on Extreme Learning Machines (ELM) , Marina Bay Sands, Singapore, 13.12.2016. https://doi.org/10.1007/978-3-319-57421-9_16

Predicting Huntington’s Disease: Extreme Learning Machine with Missing Values. / Eirola, Emil; Akusok, Anton; Björk, Kaj-Mikael et al.

Proceedings of ELM-2016. Cham : Springer, 2017. p. 195-206 ( Proceedings in Adaptation, Learning and Optimization (PALO); Vol. 9).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Predicting Huntington’s Disease: Extreme Learning Machine with Missing Values

AU - Eirola, Emil

AU - Akusok, Anton

AU - Björk, Kaj-Mikael

AU - Johnson, Hans

AU - Lendasse, Amaury

PY - 2017/5/26

Y1 - 2017/5/26

N2 - Problems with incomplete data and missing values are common and important in real-world machine learning scenarios, yet often underrepresented in the research field. Particularly data related to healthcare tends to feature missing values which must be handled properly, and ignoring any incomplete samples is not an acceptable solution. The Extreme Learning Machine has demonstrated excellent performance in a variety of machine learning tasks, including situations with missing values. In this paper, we present an application to predict the onset of Huntington’s disease several years in advance based on data from MRI brain scans. Experimental results show that such prediction is indeed realistic with reasonable accuracy, provided the missing values are handled with care. In particular, Multiple Imputation ELM achieves exceptional prediction accuracy.

AB - Problems with incomplete data and missing values are common and important in real-world machine learning scenarios, yet often underrepresented in the research field. Particularly data related to healthcare tends to feature missing values which must be handled properly, and ignoring any incomplete samples is not an acceptable solution. The Extreme Learning Machine has demonstrated excellent performance in a variety of machine learning tasks, including situations with missing values. In this paper, we present an application to predict the onset of Huntington’s disease several years in advance based on data from MRI brain scans. Experimental results show that such prediction is indeed realistic with reasonable accuracy, provided the missing values are handled with care. In particular, Multiple Imputation ELM achieves exceptional prediction accuracy.

KW - 512 Business and Management

KW - Extreme learning machine

KW - Missing values

KW - Multiple imputation

KW - Huntington’s disease

KW - Prediction

U2 - 10.1007/978-3-319-57421-9_16

DO - 10.1007/978-3-319-57421-9_16

M3 - Conference contribution

SN - 978-3-319-57420-2

T3 - Proceedings in Adaptation, Learning and Optimization (PALO)

SP - 195

EP - 206

BT - Proceedings of ELM-2016

PB - Springer

CY - Cham

T2 - 2016 the 7th International Conference on Extreme Learning Machines (ELM)

Y2 - 13 December 2016 through 15 December 2016

ER -

Predicting Huntington’s Disease: Extreme Learning Machine with Missing Values

Abstract

Publication series

Keywords

Access to Document

OpenUrl availability

Fingerprint

Cite this