Search reports, ask a question, or jump to a page.
The problem
Intervention: Machine learning-based prediction model for hospitalisation within 7 days using clinical features from presentation
Who it was tested with: Children aged 2-59 months presenting with cough and/or difficulty breathing diagnosed with WHO-defined pneumonia in primary care in Malawi.
Children or communities are compared with a group that did not receive the intervention, or followed over years. This is the design that best separates what the intervention did from everything else that changed.
"The training cohort was used to train and validate a machine learning model with a prespecified primary outcome defined as hospitalisation and/or death within 7 days as the outcome. This model was then further evaluated in the testing cohort." The model was developed using one population and validated in an independent external population, meeting experimental design criteria with an objective outcome measure.
Study used hospitalisation and/or death as outcome which may reflect health system factors rather than true disease severity; only one death occurred limiting mortality analysis; comparison models were designed for hospital rather than primary care populations; no clinical impact assessment conducted yet
Across countries and designs
3 studies · 3 countries
