<p>Digital holography (DH) has experienced significant advancements in recent years, with improvements in both experimental and algorithmic techniques. This has resulted in an expansion of DH’s applications in biomedicine, as well as other scientific and engineering fields. The introduction of machine learning (ML) and deep learning (DL) has provided a breakthrough in the recognition and prediction of patterns, especially with regards to visual imagery data. This characteristic of ML and DL makes them highly suitable for processing digital holographic data, and they have thus become widely used in digital holography. This review aims to assimilate the research where ML and DL have been employed alongside digital holography in the biomedical field for tasks such as the identification and classification of organelles, diseases, and microbes. The combination of DH and ML/DL has shown significant potential in addressing various challenges in biomedical microscopy, including the identification and classification of cellular and subcellular structures, as well as the detection of pathogenic microbes. This approach has the potential to provide new insights into the dynamics of biological systems, enabling the development of new diagnostic tools and therapies.</p>