Lars Asker

Lars Asker

Auto-generated profile, based on publicly available information

Lars Asker

Department of Computer and Systems Sciences, Stockholm University, Sweden

Research Focus & Metrics

Academic Career Length

22Years (2005-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 July 2014 in Data Mining and Knowledge Discovery
Verified
Journal Article
Closed access
PDF file
AHAndreas Henelius
Andreas Henelius
KPKai Puolamäki
Kai Puolamäki
HBHenrik Boström
Henrik Boström
LALars Asker
Lars Asker
PPPanagiotis Papapetrou
Panagiotis Papapetrou

1 January 2017 in Journal of Biomedical Informatics
Verified
Journal Article
Open access
JZJing Zhao
Jing Zhao
PPPanagiotis Papapetrou
Panagiotis Papapetrou
LALars Asker
Lars Asker
HBHenrik Boström
Henrik Boström
Electronic health records contain large amounts of longitudinal data that are valuable for biomedical informatics research. The application of machine learning is a promising alternative to manual analysis of such data. However, the complex structure of the data, which includes clinical events that are unevenly distributed over time, poses a challenge for standard learning algorithms. Some approaches to modeling temporal data rely on extracting single values from time series; however, this leads to the loss of potentially valuable sequential information. How to better account for the temporality of clinical data, hence, remains an important research question. In this study, novel representations of temporal data in electronic health records are explored. These representations retain the sequential information, and are directly compatible with standard machine learning algorithms. The explored methods are based on symbolic sequence representations of time series data, which are utilized in a number of different ways. An empirical investigation, using 19 datasets comprising clinical measurements observed over time from a real database of electronic health records, shows that using a distance measure to random subsequences leads to substantial improvements in predictive performance compared to using the original sequences or clustering the sequences. Evidence is moreover provided on the quality of the symbolic sequence representation by comparing it to sequences that are generated using domain knowledge by clinical experts. The proposed method creates representations that better account for the temporality of clinical events, which is often key to prediction tasks in the biomedical domain.

1 January 2009
Verified
Conference Paper
Closed access
PDF file
BGBjörn Gambäck
Björn Gambäck
FOFredrik Olsson
Fredrik Olsson
AAAtelach Alemu Argaw
Atelach Alemu Argaw
LALars Asker
Lars Asker

20 February 2009 in Information Retrieval Journal
Verified
Journal Article
Closed access
PDF file
LALars Asker
Lars Asker
AAAtelach Alemu Argaw
Atelach Alemu Argaw
BGBjörn Gambäck
Björn Gambäck
SASamuel Eyassu Asfeha
Samuel Eyassu Asfeha
LHLemma Nigussie Habte
Lemma Nigussie Habte

3 April 2015
Verified
Book Chapter
Closed access
PDF file
AHAndreas Henelius
Andreas Henelius
KPKai Puolamäki
Kai Puolamäki
ISIsak Samsten
Isak Samsten
JZJing Zhao
Jing Zhao
LALars Asker
Lars Asker
PPPanagiotis Papapetrou
Panagiotis Papapetrou

1 January 2005
Verified
Conference Paper
Closed access
AAAtelach Alemu Argaw
Atelach Alemu Argaw
LALars Asker
Lars Asker