Clinical malaria diagnosis

rule-based classification statistical prototype

Francis Bbosa, Ronald Wesonga, Peter Jehopio

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

In this study, we identified predictors of malaria, developed data mining, statistically enhanced rule-based classification to diagnose malaria and developed an automated system to incorporate the rules and statistical models. The aim of the study was to develop a statistical prototype to perform clinical diagnosis of malaria given its adverse effects on the overall healthcare, yet its treatment remains very expensive for the majority of the patients to afford. Model validation was performed using records from two hospitals (training and predictive datasets) to evaluate system sensitivity, specificity and accuracy. The overall sensitivity of the rule-based classification obtained from the predictive dataset was 70 % [68–74; 95 % CI] with a specificity of 58 % [54–66; 95 % CI]. The values for both sensitivity and specificity varied by age, generally showing better performance for the data mining classification rules for the adult patients. In summary, the proposed system of data mining classification rules provides better performance for persons aged at least 18 years. However, with further modelling, this system of classification rules can provide better sensitivity, specificity and accuracy levels. In conclusion, using the system provides a preliminary test before confirmatory diagnosis is conducted in laboratories.

Original languageEnglish
Article number939
JournalSpringerPlus
Volume5
Issue number1
DOIs
Publication statusPublished - Dec 1 2016

Fingerprint

Malaria
Data Mining
Sensitivity and Specificity
Hospital Records
Statistical Models
Delivery of Health Care
Datasets
Therapeutics

Keywords

  • Malaria diagnosis
  • Rule-based classification
  • Sensitivity
  • Specificity
  • Statistics

ASJC Scopus subject areas

  • General

Cite this

Clinical malaria diagnosis : rule-based classification statistical prototype. / Bbosa, Francis; Wesonga, Ronald; Jehopio, Peter.

In: SpringerPlus, Vol. 5, No. 1, 939, 01.12.2016.

Research output: Contribution to journalArticle

@article{741754c8e27049d691f950da5d10d54c,
title = "Clinical malaria diagnosis: rule-based classification statistical prototype",
abstract = "In this study, we identified predictors of malaria, developed data mining, statistically enhanced rule-based classification to diagnose malaria and developed an automated system to incorporate the rules and statistical models. The aim of the study was to develop a statistical prototype to perform clinical diagnosis of malaria given its adverse effects on the overall healthcare, yet its treatment remains very expensive for the majority of the patients to afford. Model validation was performed using records from two hospitals (training and predictive datasets) to evaluate system sensitivity, specificity and accuracy. The overall sensitivity of the rule-based classification obtained from the predictive dataset was 70 {\%} [68–74; 95 {\%} CI] with a specificity of 58 {\%} [54–66; 95 {\%} CI]. The values for both sensitivity and specificity varied by age, generally showing better performance for the data mining classification rules for the adult patients. In summary, the proposed system of data mining classification rules provides better performance for persons aged at least 18 years. However, with further modelling, this system of classification rules can provide better sensitivity, specificity and accuracy levels. In conclusion, using the system provides a preliminary test before confirmatory diagnosis is conducted in laboratories.",
keywords = "Malaria diagnosis, Rule-based classification, Sensitivity, Specificity, Statistics",
author = "Francis Bbosa and Ronald Wesonga and Peter Jehopio",
year = "2016",
month = "12",
day = "1",
doi = "10.1186/s40064-016-2628-0",
language = "English",
volume = "5",
journal = "SpringerPlus",
issn = "2193-1801",
publisher = "Springer Science and Business Media Deutschland GmbH",
number = "1",

}

TY - JOUR

T1 - Clinical malaria diagnosis

T2 - rule-based classification statistical prototype

AU - Bbosa, Francis

AU - Wesonga, Ronald

AU - Jehopio, Peter

PY - 2016/12/1

Y1 - 2016/12/1

N2 - In this study, we identified predictors of malaria, developed data mining, statistically enhanced rule-based classification to diagnose malaria and developed an automated system to incorporate the rules and statistical models. The aim of the study was to develop a statistical prototype to perform clinical diagnosis of malaria given its adverse effects on the overall healthcare, yet its treatment remains very expensive for the majority of the patients to afford. Model validation was performed using records from two hospitals (training and predictive datasets) to evaluate system sensitivity, specificity and accuracy. The overall sensitivity of the rule-based classification obtained from the predictive dataset was 70 % [68–74; 95 % CI] with a specificity of 58 % [54–66; 95 % CI]. The values for both sensitivity and specificity varied by age, generally showing better performance for the data mining classification rules for the adult patients. In summary, the proposed system of data mining classification rules provides better performance for persons aged at least 18 years. However, with further modelling, this system of classification rules can provide better sensitivity, specificity and accuracy levels. In conclusion, using the system provides a preliminary test before confirmatory diagnosis is conducted in laboratories.

AB - In this study, we identified predictors of malaria, developed data mining, statistically enhanced rule-based classification to diagnose malaria and developed an automated system to incorporate the rules and statistical models. The aim of the study was to develop a statistical prototype to perform clinical diagnosis of malaria given its adverse effects on the overall healthcare, yet its treatment remains very expensive for the majority of the patients to afford. Model validation was performed using records from two hospitals (training and predictive datasets) to evaluate system sensitivity, specificity and accuracy. The overall sensitivity of the rule-based classification obtained from the predictive dataset was 70 % [68–74; 95 % CI] with a specificity of 58 % [54–66; 95 % CI]. The values for both sensitivity and specificity varied by age, generally showing better performance for the data mining classification rules for the adult patients. In summary, the proposed system of data mining classification rules provides better performance for persons aged at least 18 years. However, with further modelling, this system of classification rules can provide better sensitivity, specificity and accuracy levels. In conclusion, using the system provides a preliminary test before confirmatory diagnosis is conducted in laboratories.

KW - Malaria diagnosis

KW - Rule-based classification

KW - Sensitivity

KW - Specificity

KW - Statistics

UR - http://www.scopus.com/inward/record.url?scp=84977090471&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84977090471&partnerID=8YFLogxK

U2 - 10.1186/s40064-016-2628-0

DO - 10.1186/s40064-016-2628-0

M3 - Article

VL - 5

JO - SpringerPlus

JF - SpringerPlus

SN - 2193-1801

IS - 1

M1 - 939

ER -