Improved feature selection for hematopoietic cell transplantation outcome prediction using rank aggregation

Chandrima Sarkar, Sarah Cooley, Jaideep Srivastava

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

This paper presents a methodology for developing an improved feature selection technique that will help in accurate prediction of outcomes after hematopoietic stem cell transplantation (HSCT) for patients with acute myelogenous leukaemia (AML). Allogeneic HSCT using related or unrelated donors is the standard treatment for many patients with blood related malignancies who are unlikely to be cured by chemotherapy alone, but survival is limited by treatment-related mortality and relapse. Various genetic factors such as tissue type or human leukocyte antigen (HLA) type and immune cell receptors, including the killer-cell immunoglobulin-like receptor (KIR) family can affect the success or failure of HSCT. In this paper we aim to develop a novel, aggregated ranking based feature selection technique using HLA and KIR genotype data, which can efficiently assist in donor selection before BMT and confer significant survival benefit to the patients. In our approach we use a rank aggregation based feature selection technique for selecting suitable donor genotype characteristics. The result obtained is evaluated with classifiers for prediction accuracy. On average, our algorithm improves the prediction accuracy of the results by 3-4% compared to generic analysis without using feature selection or single feature selections algorithms. Most importantly the selected features completely agree with those obtained using traditional statistical approaches, proving the efficiency and robustness of our technique which has great potential in the medical domain.

Original languageEnglish
Title of host publication2012 Federated Conference on Computer Science and Information Systems, FedCSIS 2012
Pages221-226
Number of pages6
Publication statusPublished - 2012
Externally publishedYes
Event2012 Federated Conference on Computer Science and Information Systems, FedCSIS 2012 - Wroclaw
Duration: 9 Sep 201212 Sep 2012

Other

Other2012 Federated Conference on Computer Science and Information Systems, FedCSIS 2012
CityWroclaw
Period9/9/1212/9/12

Fingerprint

Feature extraction
Agglomeration
Stem cells
Antigens
Chemotherapy
Blood
Classifiers
Tissue

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Information Systems

Cite this

Sarkar, C., Cooley, S., & Srivastava, J. (2012). Improved feature selection for hematopoietic cell transplantation outcome prediction using rank aggregation. In 2012 Federated Conference on Computer Science and Information Systems, FedCSIS 2012 (pp. 221-226). [6354439]

Improved feature selection for hematopoietic cell transplantation outcome prediction using rank aggregation. / Sarkar, Chandrima; Cooley, Sarah; Srivastava, Jaideep.

2012 Federated Conference on Computer Science and Information Systems, FedCSIS 2012. 2012. p. 221-226 6354439.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sarkar, C, Cooley, S & Srivastava, J 2012, Improved feature selection for hematopoietic cell transplantation outcome prediction using rank aggregation. in 2012 Federated Conference on Computer Science and Information Systems, FedCSIS 2012., 6354439, pp. 221-226, 2012 Federated Conference on Computer Science and Information Systems, FedCSIS 2012, Wroclaw, 9/9/12.
Sarkar C, Cooley S, Srivastava J. Improved feature selection for hematopoietic cell transplantation outcome prediction using rank aggregation. In 2012 Federated Conference on Computer Science and Information Systems, FedCSIS 2012. 2012. p. 221-226. 6354439
Sarkar, Chandrima ; Cooley, Sarah ; Srivastava, Jaideep. / Improved feature selection for hematopoietic cell transplantation outcome prediction using rank aggregation. 2012 Federated Conference on Computer Science and Information Systems, FedCSIS 2012. 2012. pp. 221-226
@inproceedings{f934a4fdf4e24efba642f9c8721fd2ef,
title = "Improved feature selection for hematopoietic cell transplantation outcome prediction using rank aggregation",
abstract = "This paper presents a methodology for developing an improved feature selection technique that will help in accurate prediction of outcomes after hematopoietic stem cell transplantation (HSCT) for patients with acute myelogenous leukaemia (AML). Allogeneic HSCT using related or unrelated donors is the standard treatment for many patients with blood related malignancies who are unlikely to be cured by chemotherapy alone, but survival is limited by treatment-related mortality and relapse. Various genetic factors such as tissue type or human leukocyte antigen (HLA) type and immune cell receptors, including the killer-cell immunoglobulin-like receptor (KIR) family can affect the success or failure of HSCT. In this paper we aim to develop a novel, aggregated ranking based feature selection technique using HLA and KIR genotype data, which can efficiently assist in donor selection before BMT and confer significant survival benefit to the patients. In our approach we use a rank aggregation based feature selection technique for selecting suitable donor genotype characteristics. The result obtained is evaluated with classifiers for prediction accuracy. On average, our algorithm improves the prediction accuracy of the results by 3-4{\%} compared to generic analysis without using feature selection or single feature selections algorithms. Most importantly the selected features completely agree with those obtained using traditional statistical approaches, proving the efficiency and robustness of our technique which has great potential in the medical domain.",
author = "Chandrima Sarkar and Sarah Cooley and Jaideep Srivastava",
year = "2012",
language = "English",
isbn = "9781467307086",
pages = "221--226",
booktitle = "2012 Federated Conference on Computer Science and Information Systems, FedCSIS 2012",

}

TY - GEN

T1 - Improved feature selection for hematopoietic cell transplantation outcome prediction using rank aggregation

AU - Sarkar, Chandrima

AU - Cooley, Sarah

AU - Srivastava, Jaideep

PY - 2012

Y1 - 2012

N2 - This paper presents a methodology for developing an improved feature selection technique that will help in accurate prediction of outcomes after hematopoietic stem cell transplantation (HSCT) for patients with acute myelogenous leukaemia (AML). Allogeneic HSCT using related or unrelated donors is the standard treatment for many patients with blood related malignancies who are unlikely to be cured by chemotherapy alone, but survival is limited by treatment-related mortality and relapse. Various genetic factors such as tissue type or human leukocyte antigen (HLA) type and immune cell receptors, including the killer-cell immunoglobulin-like receptor (KIR) family can affect the success or failure of HSCT. In this paper we aim to develop a novel, aggregated ranking based feature selection technique using HLA and KIR genotype data, which can efficiently assist in donor selection before BMT and confer significant survival benefit to the patients. In our approach we use a rank aggregation based feature selection technique for selecting suitable donor genotype characteristics. The result obtained is evaluated with classifiers for prediction accuracy. On average, our algorithm improves the prediction accuracy of the results by 3-4% compared to generic analysis without using feature selection or single feature selections algorithms. Most importantly the selected features completely agree with those obtained using traditional statistical approaches, proving the efficiency and robustness of our technique which has great potential in the medical domain.

AB - This paper presents a methodology for developing an improved feature selection technique that will help in accurate prediction of outcomes after hematopoietic stem cell transplantation (HSCT) for patients with acute myelogenous leukaemia (AML). Allogeneic HSCT using related or unrelated donors is the standard treatment for many patients with blood related malignancies who are unlikely to be cured by chemotherapy alone, but survival is limited by treatment-related mortality and relapse. Various genetic factors such as tissue type or human leukocyte antigen (HLA) type and immune cell receptors, including the killer-cell immunoglobulin-like receptor (KIR) family can affect the success or failure of HSCT. In this paper we aim to develop a novel, aggregated ranking based feature selection technique using HLA and KIR genotype data, which can efficiently assist in donor selection before BMT and confer significant survival benefit to the patients. In our approach we use a rank aggregation based feature selection technique for selecting suitable donor genotype characteristics. The result obtained is evaluated with classifiers for prediction accuracy. On average, our algorithm improves the prediction accuracy of the results by 3-4% compared to generic analysis without using feature selection or single feature selections algorithms. Most importantly the selected features completely agree with those obtained using traditional statistical approaches, proving the efficiency and robustness of our technique which has great potential in the medical domain.

UR - http://www.scopus.com/inward/record.url?scp=84872556902&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84872556902&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781467307086

SP - 221

EP - 226

BT - 2012 Federated Conference on Computer Science and Information Systems, FedCSIS 2012

ER -