Keegan Kosasih1, Udantha Abeyratne2. 1. School of ITEE, The University of Queensland, Sir Fred Schonell Drive, St. Lucia, Brisbane, QLD, 4072, Australia. 2. School of ITEE, The University of Queensland, Sir Fred Schonell Drive, St. Lucia, Brisbane, QLD, 4072, Australia. udantha@itee.uq.edu.au.
Abstract
BACKGROUND: Pneumonia is the leading cause of mortality for children below 5 years of age. The majority of these occur in poor countries with limited access to diagnosis. The World Health Organization (WHO) criterion for pneumonia is the de facto method for diagnosis. It is designed targeting a high sensitivity and uses easy to measure parameters. The WHO criterion has poor specificity. METHODS: We propose a method using common measurements (including the WHO parameters) to diagnose pneumonia at high sensitivity and specificity. Seventeen clinical features obtained from 134 subjects were used to create a series of logistic regression models. We started with one feature at a time, and continued building models with increasing number of features until we exhausted all possible combinations. We used a k-fold cross validation method to measure the performance of the models. RESULTS: The sensitivity of our method was comparable to that of the WHO criterion but the specificity was 84%-655% higher. In the 2-11 month age group, the WHO criteria had a sensitivity and specificity of 92.0%±11.6% and 38.1%±18.5%, respectively. Our best model (using the existence of a runny nose, the number of days with runny nose, breathing rate and temperature) performed at a sensitivity of 91.3%±13.0% and specificity of 70.2%±22.80%. In the 12-60 month age group, the WHO algorithm gave a sensitivity of 95.7%±7.6% at a specificity of 9.8%±13.1%, while our corresponding sensitivity and specificity were 94.0%±12.1% and 74.0%±23.3%, respectively (using fever, number of days with cough, heart rate and chest in-drawing). CONCLUSIONS: The WHO algorithm can be improved through mathematical analysis of clinical observations and measurements routinely made in the field. The method is simple and easy to implement on a mobile phone. Our method allows the freedom to pick the best model in any arbitrary field scenario (e.g., when an oximeter is not available).
BACKGROUND:Pneumonia is the leading cause of mortality for children below 5 years of age. The majority of these occur in poor countries with limited access to diagnosis. The World Health Organization (WHO) criterion for pneumonia is the de facto method for diagnosis. It is designed targeting a high sensitivity and uses easy to measure parameters. The WHO criterion has poor specificity. METHODS: We propose a method using common measurements (including the WHO parameters) to diagnose pneumonia at high sensitivity and specificity. Seventeen clinical features obtained from 134 subjects were used to create a series of logistic regression models. We started with one feature at a time, and continued building models with increasing number of features until we exhausted all possible combinations. We used a k-fold cross validation method to measure the performance of the models. RESULTS: The sensitivity of our method was comparable to that of the WHO criterion but the specificity was 84%-655% higher. In the 2-11 month age group, the WHO criteria had a sensitivity and specificity of 92.0%±11.6% and 38.1%±18.5%, respectively. Our best model (using the existence of a runny nose, the number of days with runny nose, breathing rate and temperature) performed at a sensitivity of 91.3%±13.0% and specificity of 70.2%±22.80%. In the 12-60 month age group, the WHO algorithm gave a sensitivity of 95.7%±7.6% at a specificity of 9.8%±13.1%, while our corresponding sensitivity and specificity were 94.0%±12.1% and 74.0%±23.3%, respectively (using fever, number of days with cough, heart rate and chest in-drawing). CONCLUSIONS: The WHO algorithm can be improved through mathematical analysis of clinical observations and measurements routinely made in the field. The method is simple and easy to implement on a mobile phone. Our method allows the freedom to pick the best model in any arbitrary field scenario (e.g., when an oximeter is not available).
Authors: Shabir A Madhi; Philippe De Wals; Carlos G Grijalva; Keith Grimwood; Ronald Grossman; Naruhiko Ishiwada; Ping-Ing Lee; Cristiana Nascimento-Carvalho; Hanna Nohynek; Katherine L O'Brien; Anne Vergison; Joanne Wolter Journal: Pediatr Infect Dis J Date: 2013-03 Impact factor: 2.129
Authors: Igor Rudan; Shams El Arifeen; Zulfiqar A Bhutta; Robert E Black; Abdullah Brooks; Kit Yee Chan; Mickey Chopra; Trevor Duke; David Marsh; Antonio Pio; Eric A F Simoes; Giorgio Tamburlini; Evropi Theodoratou; Martin W Weber; Cynthia G Whitney; Harry Campbell; Shamim A Qazi Journal: PLoS Med Date: 2011-09-27 Impact factor: 11.069
Authors: Connor A Emdin; Fatima Mir; Shazia Sultana; A M Kazi; Anita K M Zaidi; Michelle C Dimitris; Daniel E Roth Journal: BMC Pediatr Date: 2015-09-30 Impact factor: 2.125
Authors: Amy Sarah Ginsburg; Jaclyn Delarosa; Waylon Brunette; Shahar Levari; Mitch Sundt; Clarice Larson; Charlotte Tawiah Agyemang; Sam Newton; Gaetano Borriello; Richard Anderson Journal: PLoS One Date: 2015-10-16 Impact factor: 3.240
Authors: Li Liu; Shefali Oza; Daniel Hogan; Jamie Perin; Igor Rudan; Joy E Lawn; Simon Cousens; Colin Mathers; Robert E Black Journal: Lancet Date: 2014-09-30 Impact factor: 79.321