The study develops machine-learning algorithms based on nuclear morphology features to accurately predict cellular senescence induced by various stressors in different cell types and tissues. These classifiers, which require less computational power than image-based deep neural networks, can be adapted for use with open-source image analysis software, making them accessible to a broader scientific community. The algorithms were validated using A549 human lung adenocarcinoma cells treated with etoposide, and their performance was compared with traditional senescence markers such as SA-β-Galactosidase activity and p16^INK4a^. The classifiers were also tested on co-cultures of senescent and non-senescent cells, quiescent cells, and cells undergoing DNA damage, demonstrating their ability to distinguish senescent cells from other cell states. Additionally, the classifiers were used to identify drugs that selectively induce senescence in cancer cells and to monitor senescence in mouse models of liver cancer initiation, aging, and fibrosis, as well as in patients with fatty liver disease. The study concludes that these senescence classifiers can help elucidate the pathophysiological roles of senescence and assist in the discovery and validation of senotherapies.The study develops machine-learning algorithms based on nuclear morphology features to accurately predict cellular senescence induced by various stressors in different cell types and tissues. These classifiers, which require less computational power than image-based deep neural networks, can be adapted for use with open-source image analysis software, making them accessible to a broader scientific community. The algorithms were validated using A549 human lung adenocarcinoma cells treated with etoposide, and their performance was compared with traditional senescence markers such as SA-β-Galactosidase activity and p16^INK4a^. The classifiers were also tested on co-cultures of senescent and non-senescent cells, quiescent cells, and cells undergoing DNA damage, demonstrating their ability to distinguish senescent cells from other cell states. Additionally, the classifiers were used to identify drugs that selectively induce senescence in cancer cells and to monitor senescence in mouse models of liver cancer initiation, aging, and fibrosis, as well as in patients with fatty liver disease. The study concludes that these senescence classifiers can help elucidate the pathophysiological roles of senescence and assist in the discovery and validation of senotherapies.