Login / Signup

Algorithm for diagnosis of early Schistosoma haematobium using prodromal signs and symptoms in pre-school age children in an endemic district in Zimbabwe.

Tariro L Mduluza-JokonyaArthur VengesaiHerald MidziMaritha KasambalaLuxwell JokonyaThajasvarie NaickerTakafira Mduluza
Published in: PLoS neglected tropical diseases (2021)
This study demonstrates for the first time prodromal signs and symptoms associated with early S. haematobium infection in pre-school age children. These prodromal signs and symptoms pave way for early intervention and management, thus decreasing the harm of late diagnosis. Our algorithm has the potential to assist in risk-stratifying pre-school age children for early S. haematobium infection. Independent validation of the algorithm on another cohort is needed to assess the utility further.
Keyphrases
  • machine learning
  • young adults
  • parkinson disease
  • deep learning
  • randomized controlled trial
  • sleep quality
  • neural network
  • physical activity
  • hiv infected