How Language Processors Will Change Healthcare in 2023

Authors: Amina H Khalpey, PhD, Brynne Rozell BS, Parker Wilson BS, Ezekiel Mendoza, BS, Zain Khalpey, MD, PhD

In recent years, artificial intelligence (AI) and machine learning (ML) have been making great strides in technological advancement and are rapidly transforming the healthcare industry. ChatGPT, a natural language processing system, is one of the latest developments in AI and ML and is already being used to improve healthcare delivery. This blog post will discuss how ChatGPT is changing healthcare delivery, and provide examples of how it can be used to help patients and healthcare providers.

ChatGPT and Language Processors

ChatGPT can be used to hasten and improve medical diagnosis and decision-making by providing fast, accurate information to clinicians. If given access to patient records, this tool could be used to provide patient information that would otherwise have been missed or misplaced by house staff given the depth and breadth of records. We imagine this a Clinician Assistant integrated into Electronic Medical Records (EMR) that can answer and suggest actions as a clinician navigates patient encounters.

ChatGPT, or another like language processors (LP), can also be used to answer questions from patients, providing detailed explanations about their condition and even provide evidence-based resources for lifestyle improvement. This can help patients better understand their diagnosis, allowing them to make more informed decisions about their care.

An LP could improve patient engagement by providing personalized care plans tailored to the individual patient’s needs and preferences. This would increase patient engagement as the interventions suggested directly apply to them and are not a simple, one-size-fits-all template. This is especially beneficial for patients with chronic conditions, who often require long-term follow-up care and support. Using LPs, healthcare providers can interact with patients in a more personalized and engaging way, helping to keep them engaged and motivated.

LPs could also automate routine tasks and reduce the burden on healthcare staff. By automating routine paperwork and repetitive tasks, LPs can help healthcare staff focus on more important tasks, freeing up time to spend on more value-adding activities and be more directly involved in patient care. LPs could reduce errors in healthcare data, as it can detect and correct errors in medical records and other data sources. Reducing the risk of medical errors will improve healthcare outcomes and make healthcare spending more efficient. It is estimated that 15-30% of all healthcare dollars are spent on billing and financial services (Jiwani et al 2014). If many of these tasks involving paperwork could be automated, hospitals would save money and improve billing efficiency. There is a potential for healthcare dollars to be saved en masse with the use of LPs along with generative AI.

LPs can also improve communication between healthcare providers and patients. By providing regular updates on patient care, LPs can help healthcare providers and patients remain informed to provide better care. It will help healthcare providers build trust and better understand the needs of their patients.

In conclusion, LPs are already beginning to revolutionize healthcare delivery, and their potential to improve healthcare outcomes and patient engagement is only just beginning to be realized. We at Khalpey AI Lab are working to further develop and improve LPs to seamlessly integrate them into a functional AI-based EMR. We believe this has the potential to completely change the way healthcare is delivered, providing more thorough record processing, improved decision-making, personalized care plans, and improved communication between healthcare providers and patients. We are pushing healthcare into the future with the help of AI.


Jiwani, A., Himmelstein, D., Woolhandler, S. et al. Billing and insurance-related administrative costs in United States’ health care: synthesis of micro-costing evidence. BMC Health Serv Res 14, 556 (2014).