Back to Search
Start Over
Generation and application of a convolutional neural networks algorithm in evaluating stool consistency in diapers.
- Source :
-
Acta Paediatrica . Jun2023, Vol. 112 Issue 6, p1333-1340. 8p. - Publication Year :
- 2023
-
Abstract
- Aim: The aim of the study was to develop a deep convolutional neural networks (CNNs) algorithm for automated assessment of stool consistency from diaper photographs and test its performance under real‐world conditions. Methods: Diaper photographs were enrolled via a mobile phone application. The stool consistency was assessed independently according to the Brussels Infant and Toddler Stool Scale (BITSS) by paediatricians. These images were randomised into a training data set and a test data set. After training and testing, the new algorithm was used under real‐world conditions by parents. Results: There was an overall agreement of 92.9% between paediatricians and the CNN‐generated algorithm. Post hoc classification into the validated 4 categories of the BITSS yielded an agreement of 95.4%. Spearman correlation analysis across the ranking of 7 BITSS photographs and validated 4 categories showed a significant correlation of rho = 0.93 (95% CI, 0.92, 0.94; p < 0.001) and rho = 0.92 (95% CI, 0.90, 0.93; p < 0.001), respectively. The real‐world application yielded further insights into changes in stool consistency between age categories and mode of feeding. Conclusion: The new CNN‐based algorithm is able to reliably identify stool consistency from diaper photographs and may support the communication between parents and paediatricians. [ABSTRACT FROM AUTHOR]
- Subjects :
- *CONVOLUTIONAL neural networks
*DIAPERS
*ALGORITHMS
*RANK correlation (Statistics)
Subjects
Details
- Language :
- English
- ISSN :
- 08035253
- Volume :
- 112
- Issue :
- 6
- Database :
- Academic Search Index
- Journal :
- Acta Paediatrica
- Publication Type :
- Academic Journal
- Accession number :
- 163588485
- Full Text :
- https://doi.org/10.1111/apa.16731