Impact of Natural Language Processing on Healthcare Quality: A Review of Clinical and Public Health Applications Urfa Khairatun Hisan M.D. Faculty of Medicine, Universitas Ahmad Dahlan, Indonesia - https://orcid.org/0000-0003-4952-3542 Urfa.hisan@med.uad.ac.id Arij Ben Chaaben Human Genetic lab medical school of tunis Tunisia arijnour56@gmail.com Adeniyi Olarewaju Adeleye Department of Environmental Sciences, Faculty of Science, Federal University Dutse, Jigawa State, Nigeria adeniyi.adeleye@fud.edu.ng Ashish Kaushik Department of Mechanical Engineering, Deenabandhu Chottu Ram University of Science and Technology, Murthal, Sonepat, India ashishkaushik6789@gmail.com Abstract Natural Language Processing (NLP) has a rich history in healthcare, dating back to the 1970s. In the early days, NLP was used primarily to automate the process of medical record transcription. However, as the field of NLP has advanced, its applications in healthcare have become more sophisticated and diverse. This study explores the various applications of Natural Language Processing (NLP) in healthcare and divides them into two broad categories: Clinical Applications and Public Health Applications. The Clinical Applications of NLP in healthcare focus on improving patient care and providing healthcare providers with the necessary tools and information to make informed decisions about patient treatment. These applications include Clinical Documentation, Medical Coding, Clinical Decision Support, and Patient Engagement. Clinical Documentation involves the use of NLP to automate the documentation of patient information, while Medical Coding utilizes NLP to assign appropriate codes to medical procedures and diagnoses. Clinical Decision Support leverages NLP to analyze patient data and provide healthcare providers with recommendations on the best course of treatment, and Patient Engagement employs NLP to enhance patient communication and engagement. On the other hand, Public Health Applications of NLP in healthcare include Sentiment Analysis, Clinical Trials, and Disease Surveillance. Sentiment Analysis uses NLP to analyze social media and other online sources to understand public perceptions and opinions related to health issues. Clinical Trials leverage NLP to identify eligible patients and to analyze trial data. Lastly, Disease Surveillance uses NLP to monitor and track disease JAAHMM Journal of Advanced Analytics in Healthcare Management Submitted 29 June 2021 Accepted 23 October 2021 Published 15 January 2022