Predicting the effectiveness of hydroxyurea in individual sickle cell anemia patients

Homayoun Valafar, Faramarz Valafar, Alan Darvill, Peter Albersheim, Abdullah Kutlar, Kristy F. Woods, John Hardin

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

The study described in this paper was undertaken to develop the ability to predict the response of sickle-cell patients to hydroxyurea (HU) therapy. We analyzed the effect of HU on the values of 23 parameters of 83 patients. A Student's t-test was used to confirm (Rodgers GP, Dover GJ, Noguchi CT, Schechter AN, Nienhuis AW. Hematologic responses of patients with sickle cell disease to treatment with hydroxyurea, N Engl J Med 1990;322;1037-44) at the 0.001 level that treatment with HU increases the proportion of fetal hemoglobin (HbF), and the average corpuscular volume (MCV) of the red blood cells. Correlation analysis failed to establish a statistically significant relationship between any of the 23 parameters and the HbF response. Linear regression analysis also failed to predict a patient's response to HU. On the other hand, artificial neural network (ANN) pattern-recognition analysis of the 23 parameters predicts, with 86.6% accuracy, those patients that respond positively to HU and those that do not. Furthermore, we have found that the values of only 10 of the 23 parameters (listed in the body of this paper) are sufficient to train ANNs to predict which patients will respond to HU. Copyright (C) 2000 Elsevier Science B.V.

Original languageEnglish (US)
Pages (from-to)133-148
Number of pages16
JournalArtificial Intelligence in Medicine
Volume18
Issue number2
DOIs
StatePublished - Feb 1 2000

Fingerprint

Hydroxyurea
Hemoglobin
Sickle Cell Anemia
Linear regression
Regression analysis
Pattern recognition
Blood
Cells
Students
Neural networks
Fetal Hemoglobin
Linear Models
Therapeutics
Erythrocytes
Regression Analysis

Keywords

  • Artificial neural networks
  • Hydrea
  • Hydroxyurea
  • Pattern recognition
  • Sickle cell anemia
  • Variable selection

ASJC Scopus subject areas

  • Artificial Intelligence
  • Medicine(all)

Cite this

Predicting the effectiveness of hydroxyurea in individual sickle cell anemia patients. / Valafar, Homayoun; Valafar, Faramarz; Darvill, Alan; Albersheim, Peter; Kutlar, Abdullah; Woods, Kristy F.; Hardin, John.

In: Artificial Intelligence in Medicine, Vol. 18, No. 2, 01.02.2000, p. 133-148.

Research output: Contribution to journalArticle

Valafar, Homayoun ; Valafar, Faramarz ; Darvill, Alan ; Albersheim, Peter ; Kutlar, Abdullah ; Woods, Kristy F. ; Hardin, John. / Predicting the effectiveness of hydroxyurea in individual sickle cell anemia patients. In: Artificial Intelligence in Medicine. 2000 ; Vol. 18, No. 2. pp. 133-148.
@article{f33fcfa7a1be44498c8f658f3f037497,
title = "Predicting the effectiveness of hydroxyurea in individual sickle cell anemia patients",
abstract = "The study described in this paper was undertaken to develop the ability to predict the response of sickle-cell patients to hydroxyurea (HU) therapy. We analyzed the effect of HU on the values of 23 parameters of 83 patients. A Student's t-test was used to confirm (Rodgers GP, Dover GJ, Noguchi CT, Schechter AN, Nienhuis AW. Hematologic responses of patients with sickle cell disease to treatment with hydroxyurea, N Engl J Med 1990;322;1037-44) at the 0.001 level that treatment with HU increases the proportion of fetal hemoglobin (HbF), and the average corpuscular volume (MCV) of the red blood cells. Correlation analysis failed to establish a statistically significant relationship between any of the 23 parameters and the HbF response. Linear regression analysis also failed to predict a patient's response to HU. On the other hand, artificial neural network (ANN) pattern-recognition analysis of the 23 parameters predicts, with 86.6{\%} accuracy, those patients that respond positively to HU and those that do not. Furthermore, we have found that the values of only 10 of the 23 parameters (listed in the body of this paper) are sufficient to train ANNs to predict which patients will respond to HU. Copyright (C) 2000 Elsevier Science B.V.",
keywords = "Artificial neural networks, Hydrea, Hydroxyurea, Pattern recognition, Sickle cell anemia, Variable selection",
author = "Homayoun Valafar and Faramarz Valafar and Alan Darvill and Peter Albersheim and Abdullah Kutlar and Woods, {Kristy F.} and John Hardin",
year = "2000",
month = "2",
day = "1",
doi = "10.1016/S0933-3657(99)00035-4",
language = "English (US)",
volume = "18",
pages = "133--148",
journal = "Artificial Intelligence in Medicine",
issn = "0933-3657",
publisher = "Elsevier",
number = "2",

}

TY - JOUR

T1 - Predicting the effectiveness of hydroxyurea in individual sickle cell anemia patients

AU - Valafar, Homayoun

AU - Valafar, Faramarz

AU - Darvill, Alan

AU - Albersheim, Peter

AU - Kutlar, Abdullah

AU - Woods, Kristy F.

AU - Hardin, John

PY - 2000/2/1

Y1 - 2000/2/1

N2 - The study described in this paper was undertaken to develop the ability to predict the response of sickle-cell patients to hydroxyurea (HU) therapy. We analyzed the effect of HU on the values of 23 parameters of 83 patients. A Student's t-test was used to confirm (Rodgers GP, Dover GJ, Noguchi CT, Schechter AN, Nienhuis AW. Hematologic responses of patients with sickle cell disease to treatment with hydroxyurea, N Engl J Med 1990;322;1037-44) at the 0.001 level that treatment with HU increases the proportion of fetal hemoglobin (HbF), and the average corpuscular volume (MCV) of the red blood cells. Correlation analysis failed to establish a statistically significant relationship between any of the 23 parameters and the HbF response. Linear regression analysis also failed to predict a patient's response to HU. On the other hand, artificial neural network (ANN) pattern-recognition analysis of the 23 parameters predicts, with 86.6% accuracy, those patients that respond positively to HU and those that do not. Furthermore, we have found that the values of only 10 of the 23 parameters (listed in the body of this paper) are sufficient to train ANNs to predict which patients will respond to HU. Copyright (C) 2000 Elsevier Science B.V.

AB - The study described in this paper was undertaken to develop the ability to predict the response of sickle-cell patients to hydroxyurea (HU) therapy. We analyzed the effect of HU on the values of 23 parameters of 83 patients. A Student's t-test was used to confirm (Rodgers GP, Dover GJ, Noguchi CT, Schechter AN, Nienhuis AW. Hematologic responses of patients with sickle cell disease to treatment with hydroxyurea, N Engl J Med 1990;322;1037-44) at the 0.001 level that treatment with HU increases the proportion of fetal hemoglobin (HbF), and the average corpuscular volume (MCV) of the red blood cells. Correlation analysis failed to establish a statistically significant relationship between any of the 23 parameters and the HbF response. Linear regression analysis also failed to predict a patient's response to HU. On the other hand, artificial neural network (ANN) pattern-recognition analysis of the 23 parameters predicts, with 86.6% accuracy, those patients that respond positively to HU and those that do not. Furthermore, we have found that the values of only 10 of the 23 parameters (listed in the body of this paper) are sufficient to train ANNs to predict which patients will respond to HU. Copyright (C) 2000 Elsevier Science B.V.

KW - Artificial neural networks

KW - Hydrea

KW - Hydroxyurea

KW - Pattern recognition

KW - Sickle cell anemia

KW - Variable selection

UR - http://www.scopus.com/inward/record.url?scp=0033966322&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033966322&partnerID=8YFLogxK

U2 - 10.1016/S0933-3657(99)00035-4

DO - 10.1016/S0933-3657(99)00035-4

M3 - Article

C2 - 10648847

AN - SCOPUS:0033966322

VL - 18

SP - 133

EP - 148

JO - Artificial Intelligence in Medicine

JF - Artificial Intelligence in Medicine

SN - 0933-3657

IS - 2

ER -