The　rapid　developments　of　artificial　intelligent　(AI)　is　being　transformed　for　its　extensive　use-cases,　people-centered　intelligent　systems　focusing　on　care　delivery,　research　encounter　complex　problems　related　to　improve　the　overall　infrastructure　and　management　of　intelligent　delivery　service;　for　instance,　bringing　transformation　in　healthcare　sector　for　monitoring　patients　with　chronic　disease.　Most　of　these　systems　are　driven　by　state-of-the-art　learning　algorithms　i.e.,　Convolution　Neural　Network.　The　CNN　algorithm　is　considered　to　be　one　of　the　most　prominent　architectures　of　DL.　Recently,　due　to　enormous　growth　in　the　amount　of　annotated　data　and　the　development　of　CNN　hardware　accelerator,　further,　boost　the　research　on　CNN　and　accomplished　benchmark　enactment　on　different　applications.　This　paper　presents　cutting-edge　applications　of　CNN　for　an　intelligent　healthcare　system.　We　provide　useful　findings　of　different　CNN　features　such　as　optimization,　fast　computation,　design,　activation　function,　and　loss　function.　To　our　knowledge,　this　is　the　first　comprehensive　work　to　address　the　recent　trends　in　the　architecture　of　CNN,　which　offers　insight　to　the　underlying　problems　and　provides　the　potential　solutions　for　any　given　intelligent　healthcare　applications.　©　2021,　Springer　Nature　Switzerland　AG.