Skip to main content

Table 1 Breakdown of messages exchanged across the data sets according to supervisory category

From: Analysing 3429 digital supervisory interactions between Community Health Workers in Uganda and Kenya: the development, testing and validation of an open access predictive machine learning web app

 

Training data set (n = 437)

Validation data set (n = 1242)

 

Combined human coder categorisation (n (%))

CHWsupervisor App categorisation (n (%))

Combined human coder categorisation (n (%))

CHWsupervisor App categorisation (n (%))

Communication and information messages

308 (70.5%)

286 (65.5%)

565 (45.5%)

498 (40.1%)

Supportive environment messages

77 (17.6%)

114 (26%)

581 (46.8%)

692 (55.7%)

Quality Assurance messages

52 (11.9%)

37 (8.5%)

96 (7.7%)

52 (4.2%)

  1. A breakdown of messages exchanged across the datasets according to their supervisory category