Salahuddin Ahmed (Bangladesh)
Projahnmo Research Foundation
Research
Salahuddin Ahmed is a medical doctor and public health epidemiologist with more than 20 years of experience in designing and managing epidemiological studies, disease surveillance, monitoring and evaluation of public health programs. His research focuses on improving the health and nutritional status of newborns, children, and women in low-resource settings by enhancing the understanding of the major causes of neonatal, child, and maternal morbidity, mortality and malnutrition and by designing and testing cost-effective public health interventions against them. The design and scope of his studies are diverse ranging from formative research to randomized clinical trials. He is the Director of Projahnmo Research Foundation, Bangladesh. He is an associate in the Department of International Health of Johns Hopkins Bloomberg School of Public Health, MD, USA. He is a member of the Integrated Management of Childhood Illness working group in Bangladesh. Dr. Ahmed has published more than 50 scientific articles in peer-reviewed journals and presented his studies in many different international scientific conferences. Email: sahmed@prfbd.org ORCID ID: 0000-0001-6771-0638 ResearchGate: Salahuddin Ahmed (researchgate.net)

Presenter of 1 Presentation

 Conference Calendar

O051 - EVALUATION OF MACHINE LEARNING TO DETECT ADVENTITIOUS LUNG SOUNDS USING DIGITAL AUSCULTATION TO AID CHILDHOOD PNEUMONIA DIAGNOSIS (ID 280)

Session Name
0550 - Parallel Session 08: Diagnosis of Pneumococcal Disease (ID 48)
Session Type
Parallel Session
Date
Tue, 21.06.2022
Session Time
14:50 - 16:20
Room
Birchwood Ballroom
Presenter
Lecture Time
14:55 - 15:05

Abstract

Background

IMCI guidelines for childhood pneumonia diagnosis have high sensitivity but low specificity. A digital stethoscope with an automated machine-learning algorithm for classifying lung sounds may improve diagnostic performance. We aimed to evaluate agreement between digital stethoscope recorded lung sound classifications generated from an automated machine learning algorithm with a paediatrician listening panel from children receiving care at community clinics in rural Bangladesh.

Methods

Government community health workers recorded lung sounds from four chest positions using a novel digital stethoscope in children under-5 with cough and/or difficult breathing at first-level community clinics in Bangladesh from November 2019 to December 2020. A trained paediatrician listening panel classified recorded lung sounds into normal, crackles, wheeze, crackles and wheeze, or uninterpretable. A machine learning algorithm classified recorded sounds into the same categories, which were compared with panel classifications.

Results

Of 2434 children screened, 990 were enrolled. Compared to paediatricians, the sensitivity, specificity, and positive and negative predictive values of detecting abnormal sounds (wheeze and/or crackles) by the machine learning algorithm were 61.8 (95%CI: 55.7, 67.6), 60.7 (56.6, 64.6), 41.8 (36.9, 46.8), and 77.6 (73.6, 81.3) among all enrolled children, and 63.5 (54.5, 71.9), 66.2 (60.1, 73.1), 52.7 (44.4, 60.8), and 75.9 (69.2, 81.8) among children with IMCI defined pneumonia.

Conclusions

This study shows an automated algorithm had moderate sensitivity and specificity for classifying lung sounds as either abnormal or normal when using a paediatric listening panel as the reference. Agreement between the machine learning algorithm and paediatric listening panel modestly increased among children with IMCI-defined pneumonia.

Hide