The power of data mining in diagnosis of childhood pneumonia.
| Thursday, 4th of August 2016 |
 |
 |
J R Soc Interface. 2016 Jul;13(120). pii: 20160266. doi: 10.1098/rsif.2016.0266.
The power of data mining in diagnosis of childhood pneumonia.
Naydenova E1, Tsanas A2, Howie S3, Casals-Pascual C4, De Vos M2.
- 1Department of Engineering Science, Institute of Biomedical Engineering, University of Oxford, Oxford, UK elina.naydenova@eng.ox.ac.uk.
- 2Department of Engineering Science, Institute of Biomedical Engineering, University of Oxford, Oxford, UK.
- 3Child Survival Theme, Medical Research Council Unit, Serrekunda, The Gambia.
- 4Nuffield Department of Medicine, Wellcome Trust Centre for Human Genetics, University of Oxford, Oxford, UK.
Abstract below; full text is at http://rsif.royalsocietypublishing.org/content/13/120/20160266.long
Childhood pneumonia is the leading cause of death of children under the age of 5 years globally. Diagnostic information on the presence of infection, severity and aetiology (bacterial versus viral) is crucial for appropriate treatment. However, the derivation of such information requires advanced equipment (such as X-rays) and clinical expertise to correctly assess observational clinical signs (such as chest indrawing); both of these are often unavailable in resource-constrained settings. In this study, these challenges were addressed through the development of a suite of data mining tools, facilitating automated diagnosis through quantifiable features. Findings were validated on a large dataset comprising 780 children diagnosed with pneumonia and 801 age-matched healthy controls. Pneumonia was identified via four quantifiable vital signs (98.2% sensitivity and 97.6% specificity). Moreover, it was shown that severity can be determined through a combination of three vital signs and two lung sounds (72.4% sensitivity and 82.2% specificity); addition of a conventional biomarker (C-reactive protein) further improved severity predictions (89.1% sensitivity and 81.3% specificity). Finally, we demonstrated that aetiology can be determined using three vital signs and a newly proposed biomarker (lipocalin-2) (81.8% sensitivity and 90.6% specificity). These results suggest that a suite of carefully designed machine learning tools can be used to support multi-faceted diagnosis of childhood pneumonia in resource-constrained settings, compensating for the shortage of expensive equipment and highly trained clinicians.
© 2016 The Authors.
Similar articles
- Review Clinical symptoms and signs for the diagnosis of Mycoplasma pneumoniae in children and adolescents with community-acquired pneumonia.[Cochrane Database Syst Rev. 2012]
- The validity of clinical criteria in predicting pneumonia among children under five years of age.[J Family Community Med. 2004]
- Wavelet augmented cough analysis for rapid childhood pneumonia diagnosis.[IEEE Trans Biomed Eng. 2015]
- Mothers perceptions of severe pneumonia in their own children: a controlled study in Pakistan.[Soc Sci Med. 1994]
- Review Pneumonia in severely malnourished children in developing countries - mortality risk, aetiology and validity of WHO clinical signs: a systematic review.[Trop Med Int Health. 2009]
| Are three drugs for malaria better than two?
Friday, 24th of April 2020 |
| Public health Interventions and epidemic intensity during the 1918 influenza pandemic
Thursday, 16th of April 2020 |
| Chloroquine and hydroxychloroquine as available weapons to fight COVID-19
Tuesday, 17th of March 2020 |
| Using models to shape measles control and elimination strategies in low- and middle-income countries: A review of recent applications
Monday, 17th of February 2020 |
| Immunization Agenda 2030
Tuesday, 11th of February 2020 |
 |
40977443 |
| www.measlesinitiative.org www.technet21.org www.polioeradication.org www.globalhealthlearning.org www.who.int/bulletin allianceformalariaprevention.com www.malariaworld.org http://www.panafrican-med-journal.com/ |