Cardiovascular　disease　is　one　of　the　leading　causes　of　death　worldwide,　especially　in　middle　-　and　low-income　countries.　The　prevention　of　cardiovascular　diseases　is　very　important　to　reduce　medical　costs　and　maintain　social　stability.　The　logistic　regression　model　can　establish　a　reliable　cardiovascular　disease　prediction　model　based　on　daily　indicators,　which　has　the　advantages　of　being　simple　and　efficient,　strong　interpretability,　and　wide　applicability　in　cardiovascular　disease　prediction.　The　accuracy　of　the　model　needs　to　be　improved,　so　this　paper　summarizes　the　possible　methods　to　improve　the　logistic　regression　model,　including　feature　selection,　regularization　technology,　hyperparameter　optimization,　and　other　strategies　to　further　improve　the　prediction　performance.　This　study　suggests　that　indicators　of　daily　living　are　associated　with　cardiovascular　disease　and　have　implications　for　the　diagnosis　of　cardiovascular　disease.　At　the　same　time,　the　establishment　of　a　logistic　regression　model　provides　reliable　decision　support　for　cardiovascular　diseases.　Future　research　can　focus　on　improving　and　optimizing　the　model　to　provide　more　reliable　decision　support　for　clinical　practice　and　patient　needs.　This　study　aims　to　provide　potential　patients　and　physicians　with　important　information　about　cardiovascular　disease　through　logistic　regression　models,　thereby　improving　prevention　accuracy　and　efficiency　and　reducing　the　incidence　and　associated　health　burden　of　cardiovascular　disease.　©　2024　American　Institute　of　Physics　Inc..　All　rights　reserved.