GPT, or Generative Pre-trained Transformer, is a type of artificial intelligence that has the unremarkable ability to generate human-like text. The program is free to use during the “research preview” time. GPT gained 1 million users in under a week of being released. Keep in mind that this technology is currently in the beta testing phase.
It is important to note the limitations. The quality of the responses depends on the quality of the prompts the user enters in GPT. The answers are not always correct. The answers are to be created to “feel correct to humans.” If the user does not know the area in question, then the answer might be incorrect, and the user may not be aware that it is incorrect. Other limitations are based on the data that GPT has used to be trained. If the data entered is biased, then the data expressed by GPT can be biased. In this example, the “medicine data” in certain fields may be limited. As a result, GPT may not be able to answer. Another limitation is the data is accurate until the year 2021. Any events after that GPT will not have in its database. Keep in mind that GPT does not use the internet. Let’s evaluate the potential of this technology. I believe it can revolutionize the field of medicine and health care and has already been used in several applications.
One example of how GPT can be used in medicine is the creation of virtual assistants for patients. These assistants can provide personalized recommendations and advice to patients based on their medical history, current symptoms, and other relevant factors. For example, a virtual assistant could suggest over-the-counter medications or home remedies for a patient experiencing a cold or flu or provide information on managing a chronic condition such as diabetes. These virtual assistants can be accessed through a variety of platforms, such as websites, mobile apps, or even voice assistants like Amazon’s Alexa or Google Assistant. This can be especially useful for patients who live in rural areas or have difficulty accessing health care, as they can get personalized recommendations and advice without having to physically visit a health care provider.
Another potential use of GPT in health care is in the creation of personalized treatment plans for patients. By analyzing a patient’s medical history, current symptoms, and other factors, a GPT-powered system could generate a customized treatment plan that considers the patient’s specific needs and preferences. This could be especially useful for patients with complex or rare conditions that require specialized care. For example, a GPT system could be used to recommend a specific combination of medications or therapies that are most likely to be effective for a particular patient based on their medical history and other factors. This could help reduce the risk of adverse reactions or other complications and ensure that patients receive the most appropriate care for their needs.
GPT could also help health care professionals with daily tasks, such as transcribing medical records or generating reports. By using GPT to automate these tasks, health care professionals could save time and focus on more important tasks, such as caring for patients. For example, a GPT system could be trained to transcribe patient medical records accurately and efficiently, freeing up health care professionals to spend more time interacting with patients and providing care. This could also help to reduce the risk of errors in medical records, which can have serious consequences for patients.
One potential challenge with using GPT in health care is the need for accurate and up-to-date data. For GPT to provide reliable recommendations and treatment plans, it must have access to accurate and current medical information. This could be achieved by regularly updating the data that GPT uses, as well as ensuring that the data is sourced from reputable sources. Additionally, it will be important to consider privacy and security concerns when using GPT in health care, as sensitive medical information will be involved. Measures such as encryption and secure data storage will be necessary to protect patient privacy and ensure medical data security.
Physicians are already using this technology. I have seen physicians posting that they have used this to help them create Physician order sets. The most popular example that went viral is on December 13, 2023, Dr. Clifford Stermer posted on TikTok on using “Chat GPT to save time with insurance denials. Get you the care they need.” In the video, he asked Chat GPT to write a letter to United Health asking them to approve an Echocardiogram on a patient with systemic sclerosis. Make references to supporting scientific literature and list the appropriate articles. Here is a sample letter that Chat GPT created from a physician.
Dear United Health,
I am writing to request approval for an echocardiogram for my patient with systemic sclerosis. Systemic sclerosis, also known as scleroderma, is a chronic autoimmune disorder that can lead to damage and dysfunction in various organs and tissues, including the heart. Studies have shown that individuals with systemic sclerosis are at increased risk for cardiovascular complications, including hypertension, pulmonary arterial hypertension, and myocardial fibrosis.
Echocardiography is a non-invasive imaging technique that uses sound waves to visualize the heart and assess its function. It is a valuable tool for monitoring and diagnosing cardiovascular abnormalities in individuals with systemic sclerosis.
Supporting scientific literature suggests that echocardiography should be routinely performed in individuals with systemic sclerosis to detect early cardiac involvement and guide appropriate management. In a review of the literature, Riemekasten et al. (2013) found that echocardiography was useful for identifying myocardial fibrosis, left ventricular dysfunction, and diastolic dysfunction in individuals with systemic sclerosis. Similarly, a study by Guevara et al. (2010) found that echocardiography was useful for identifying early cardiac involvement and predicting prognosis in individuals with systemic sclerosis.
I believe that an echocardiogram is necessary for the proper management of my patient with systemic sclerosis and request that it be approved by United Health. Thank you for your consideration.
Sincerely, [Your Name]
References:
Guevara JP, Park H, Therneau T, et al. (2010). Echocardiography and cardiac involvement in systemic sclerosis: a population-based study. Arthritis Care & Research, 62(6), 767-774.
Riemekasten G, Distler O, Rhyner C, et al. (2013). Cardiac involvement in systemic sclerosis: current concepts and future directions. Autoimmunity Reviews, 12(8), 924-933.
It is important to note that he later posted a video telling health care providers to check the references that GPT yields. He notes that it is better to cite your own known reference to use with GPT.
Overall, GPT has the potential to greatly improve the efficiency and effectiveness of health care by providing personalized recommendations and treatment plans to patients and helping health care professionals with their daily tasks. While there are challenges to overcome, such as the need for accurate and up-to-date data and concerns about privacy and security, the use of GPT in health care holds great promise for the future.
Some possible future applications of GPT in health care could include using GPT-powered chatbots to provide mental health support to patients or using GPT to generate personalized exercise and nutrition plans for patients based on their individual needs and goals. GPT could also be used to help health care providers with tasks such as scheduling appointments or managing patient records, making the health care system more efficient and effective overall. The potential for GPT in health care is vast, and it will be interesting to see how it is used in the coming years to improve patient care and the overall efficiency of the health care system.
Harvey Castro is a physician, health care consultant, and serial entrepreneur with extensive experience in the health care industry. He can be reached on his website, harveycastromd.info, Twitter @HarveycastroMD, Facebook, Instagram, and YouTube. He is the author of ChatGPT and Healthcare: The Key To The New Future of Medicine, ChatGPT and Healthcare: Unlocking The Potential Of Patient Empowerment, Revolutionize Your Health and Fitness with ChatGPT’s Modern Weight Loss Hacks, and Success Reinvention.