Abstract

Background: Livestock is a crucial source of livelihood for Ethiopians. However, the sector's contribution to the economy is not as significant as expected. This is mainly due to the prevalence of livestock diseases caused by various pathogens posing a serious threat to local and national food security, reducing income, and impacting the livelihoods of livestock keepers. However, the sector has constraints on improved data management framework for enhanced livestock disease pattern analysis and e-surveillance.

Objective: To control and manage livestock diseases and unlock the full potential of the livestock sector via improved data management, disease pattern analysis, and e-surveillance.

Methods: This study investigates how Electronic Livestock Health Recording Systems (ELHRs) facilitate inclusive data management for uncovering disease patterns. The proposed ELHR framework investigated against various common software quality parameters such as completeness, inclusiveness, functionality, and consistency in livestock disease data management literature and evaluated against existing livestock data management frameworks. A dataset comprising 18,333 samples of livestock disease cases obtained from the ELHRs framework was also used for disease burden analysis.

Results: From the results, the proposed ELHR framework with its holistic focus said to bridge the software quality gaps in previous related specific focus frameworks. From the clustering results, the proposed ELHRs dataset improved disease burden mapping with a silhouette score of 98% compared to another framework which is 68%. Therefore the proposed ELHRs framework's information content manifests improved disease pattern analysis and e-surveillance performance.

Conclusion: ELHRs framework can assist in identifying trends and patterns in livestock disease data, ultimately leading to more effective disease diagnosing and management strategies, therefore the ELHRs framework has the potential to revolutionize livestock disease management, disease pattern analysis, and e-surveillance.

Statistics