biostudies-literatureJones GDNational Institute for Health Research (NIHR)Wellcome Truste185-e193https://www.ebi.ac.uk/biostudies/studies/S-EPMC7618270biostudies-literatureUnknown5(4)<h4>Background</h4>Identification of convulsive epilepsy in sub-Saharan Africa relies on access to resources that are often unavailable. Infrastructure and resource requirements can further complicate case verification. Using machine-learning techniques, we have developed and tested a region-specific questionnaire panel and predictive model to identify people who have had a convulsive seizure. These findings have been implemented into a free app for health-care workers in Kenya, Uganda, Ghana, Tanzania, and South Africa.<h4>Methods</h4>In this retrospective case-control study, we used data from the Studies of the Epidemiology of Epilepsy in Demographic Sites in Kenya, Uganda, Ghana, Tanzania, and South Africa. We randomly split these individuals using a 7:3 ratio into a training dataset anThe Lancet. Digital healthDevelopment and validation of a diagnostic aid for convulsive epilepsy in sub-Saharan Africa: a retrospective case-control study.PMC7618270NIHR200134083744Kakooza AMcDaid DMtai Mwanga DAgbokey FGrassi SDenison TChabi MCollinson MBauni EDoku VAbban HKariuki SMBottomley CSander JSen AO Mageto JMuli DTollman SOdhiambo RKahn KConnor MSylvester IJunior DNYAAkpalu BMathew AWalker RNewton CRAkpalu AMurunga Wekesah FSander JWNgugi AKOtieno PAissaoui LAtieno MKhalayi CWagner RDarkwa ENgugi APeterson SChowdhary NVallentin SKamuyu GThoya YAdjei PKwasa TEgesa IKariuki SMung'ala Odera VMushi VMasanja HCross HCross JHTwine RGomez-Olive FXMahone SKleinschmidt ISottie CJones GDPariyo GBitta MMmbando BMatuja WOdermatt PWaruingi SMwesige AKAsiki GDua TGodi TIddi SManolova GEPInA Study GroupKimambo HAsiamah SChengo EBhwana DAe-Ngibise KOwusu-Agyei SfalseDevelopment and validation of a diagnostic aid for convulsive epilepsy in sub-Saharan Africa: a retrospective case-control study.<h4>Background</h4>Identification of convulsive epilepsy in sub-Saharan Africa relies on access to resources that are often unavailable. Infrastructure and resource requirements can further complicate case verification. Using machine-learning techniques, we have developed and tested a region-specific questionnaire panel and predictive model to identify people who have had a convulsive seizure. These findings have been implemented into a free app for health-care workers in Kenya, Uganda, Ghana, Tanzania, and South Africa.<h4>Methods</h4>In this retrospective case-control study, we used data from the Studies of the Epidemiology of Epilepsy in Demographic Sites in Kenya, Uganda, Ghana, Tanzania, and South Africa. We randomly split these individuals using a 7:3 ratio into a training dataset an2023-01-01T00:00:00Z2023 Apr2026-06-04T15:03:28.093Z2026-06-02T03:08:30.467ZS-EPMC76182703696390810.1016/S2589-7500(22)00255-2