AUTHORS: Chesley M. Chen, MS, MBA, Principal, Health Care and Life Sciences at CLA (CliftonLarsonAllen), Adjunct Professor, University of Denver, Daniels College of Business, entrepreneurship@DU // Spencer Lourens, PhD, Managing Principal of Data Science, Machine Learning, and AI at CLA (CliftonLarsonAllen), Clinical Assistant Professor, Health Data Science, (former), Indiana University–Purdue University Indianapolis
I just interviewed ChatGPT.
I was in a jam. I had volunteered to write a blog about ChatGPT. ChatGPT is taking off faster than any technology or innovation I’ve seen in a long while. It attracted an astounding 1 million users in 5 days and over 100 million in just 2 months. Since CLA works with over 10,000 healthcare and life science clients, we don’t want any of them to get left behind by new innovations. Rather than wait for answers, we figured it’s best to put out a blog to get the conversation started. But, where to start? Writer’s block set in. Argh.
Faced with a looming deadline, I thought, “Why not just interview ChatGPT?”
Before we start our interview, let’s take a quick look at ChatGPT. It is from a company called Open AI. ChatGPT is based on machine learning. The program analyzes massive amounts of information on the internet to understand language. It is called a “large language model (LLM).” Analyzing books, texts and other information allows the program to find patterns with how words, thoughts, sentences and more are assembled. By doing so, theoretically the program can then understand and respond when “asked” questions or be used in any number of ways. Of course, with any innovation, the process is iterative, and ChatGPT continues to learn from its errors and evolve.
A word of warning and a disclaimer. This blog is meant as a lighthearted approach to understanding the hype and potential of ChatGPT. None of ChatGPT’s responses are meant to be authoritative. It is not meant to provide advice in any way or reflect any opinions or views. The content is informational only.
With that, read on and you be the judge on whether ChatGPT can be useful or useless.
CC: ChatGPT, thank you for agreeing to do this interview.
You’re welcome! I’m happy to participate in this interview and answer any questions you have. Please feel free to ask anything, and I’ll do my best to provide a helpful response.
CC: Write a summary about the use of ChatGPT-4 in healthcare in 150 words or less.
ChatGPT-4 has revolutionized the healthcare industry by offering various applications to streamline processes, enhance patient care, and optimize data management. This advanced language model assists healthcare professionals in tasks such as diagnosis support, personalized treatment plans, and medical research, making it a vital resource for medical decision-making. By analyzing patient data, ChatGPT-4 can provide tailored suggestions for treatment while reducing human errors. Additionally, it aids in drug discovery by scanning and processing large volumes of scientific literature and identifying potential drug candidates. The model also plays a crucial role in patient communication, helping create empathetic and informative responses to patients’ queries. Furthermore, it is employed in medical training to create realistic patient simulations and educational content. Despite its significant contributions, ethical considerations and data privacy concerns require ongoing attention to ensure the responsible deployment of ChatGPT-4 in healthcare.
CC: Can you give me one useful use case in healthcare using ChatGPT-4?
One useful use case for ChatGPT-4 in healthcare is providing personalized patient education materials, such as tailored explanations of medical conditions, treatment options, and lifestyle recommendations, enabling patients to better understand their health and make informed decisions in collaboration with their healthcare providers.
CC: Give me one useful use case for drug discovery using ChatGPT-4.
One useful use case for drug discovery using ChatGPT-4 is in the analysis and synthesis of scientific literature. ChatGPT-4 can be used to quickly review and summarize vast amounts of research papers, patents, and other documents related to a specific disease or drug target. By leveraging its natural language processing capabilities, ChatGPT-4 can help researchers identify patterns, trends, and novel insights that might otherwise be overlooked. This can aid in the identification of potential drug candidates, uncovering new drug targets, or revealing new mechanisms of action. With the ability to process and generate human-like text, ChatGPT-4 can also assist researchers in drafting scientific reports or manuscripts, thus streamlining the drug discovery process. However, it is essential to note that human expertise is still needed to validate the findings and conclusions drawn by the AI.
CC: I have a fever of 104. What should I do?
I am not a doctor, but if you have a fever of 104°F (40°C), it’s generally considered a high fever and you should take action. Here are some steps you might consider, but you should always consult with a healthcare professional for personalized advice:
1. Contact your doctor or healthcare provider for guidance. They may want to evaluate your symptoms and recommend specific treatments.
2. Take over-the-counter fever-reducing medications, such as acetaminophen or ibuprofen, according to the label instructions or as directed by your healthcare provider.
3. Stay hydrated by drinking water, clear fluids, or electrolyte-replacement beverages.
4. Rest and avoid any strenuous activities.
5. Use a cool compress or take a lukewarm bath to help lower your body temperature. Avoid using cold water or ice, as it can cause shivering, which may raise your body temperature.
6. Dress in light, comfortable clothing and use light blanket if needed.
Remember, it is important to seek medical advice from a healthcare professional for any concerning symptoms, including a high fever. If you experience additional severe symptoms or your fever doesn’t improve, it’s crucial to get prompt medical attention.
CC: Describe CAR-T using ChatGPT-4 in a way a general practitioner can understand.
CAR-T, or Chimeric Antigen Receptor T-cell therapy, is an innovative immunotherapy approach used to treat certain types of cancer, particularly blood cancers like leukemia and lymphoma. In this therapy, the patient’s own immune cells, specifically T-cells, are genetically modified to recognize and attack cancer cells. The process involves collecting T-cells from the patient’s blood, then genetically engineering them to express a special receptor called a chimeric antigen receptor (CAR). This CAR enables the T-cells to specifically target a protein found on the surface of cancer cells. Once the T-cells are modified, they are multiplied in the lab and infused back into the patient’s bloodstream. Once reintroduced, these CAR-T cells can bind to the targeted protein on cancer cells, leading to their destruction. CAR-T therapy has shown promising results, especially for patients who haven’t responded to other treatments. However, it can also cause severe side effects, such as cytokine release syndrome, which needs to be closely monitored and managed. As a general practitioner, it’s important to be aware of this therapy and its potential benefits and risks, as well as to refer patients to specialized centers when appropriate.
Note: We also asked ChatGPT to explain CAR-T at different comprehension levels (elementary school, high school, college, post-doc at MIT.) The results are quite interesting. Contact us if you’d like to see these use cases.
CC: Can you tell me three ethical issues that Chat-GPT poses in healthcare in 150 words or less?
1. Data privacy and security: ChatGPT may handle sensitive patient information, posing risks to data privacy. Ensuring proper security measures and anonymization techniques are in place is crucial to protect patient confidentiality.
2. Misinformation: ChatGPT’s vast knowledge base may occasionally contain inaccuracies, potentially leading to patients receiving incorrect health advice. Ensuring the accuracy and reliability of AI-generated content is essential to prevent misinformation and potential harm.
3. AI replacing human judgment: While ChatGPT can be a valuable tool in healthcare, there’s a risk that patients or providers may rely too heavily on it, undermining the importance of human expertise. It is crucial to emphasize that AI should support, not replace, professional medical judgment and that users should always consult healthcare professionals for personalized advice.
CC: Do you think ChatGPT poses ethical issues in drug discovery? If so, can you describe three of them in 150 words or less?
1. Intellectual property concerns: ChatGPT may generate ideas or insights based on existing research or patents. Determining ownership and properly attributing credit for AI-generated discoveries can be challenging, raising intellectual property concerns and potentially hindering collaboration.
2. Bias in data: If the data used to train ChatGPT contains biases, this may be reflected in the AI-generated suggestions for drug discovery, potentially leading to the development of drugs that are less effective or have unintended side effects in certain populations. Ensuring a diverse and representative dataset is vital to mitigate bias.
3. Overreliance on AI: While ChatGPT can streamline the drug discovery process, relying too heavily on AI-generated suggestions might limit researchers’ creativity and critical thinking, potentially overlooking alternative approaches or novel solutions. Balancing AI-driven insights with human intuition and expertise is essential for robust drug discovery.
CC: This has been a fascinating interview about ChatGPT in healthcare and life sciences. Can you give our readers one last thing to think about and one item that they can do right now?
As a final thought, it’s important to recognize the immense potential of ChatGPT and AI in healthcare and life sciences, while also being mindful of the ethical and practical challenges they present. AI can greatly enhance our ability to diagnose, treat, and prevent diseases, as well as accelerate drug discovery, but it should always be used as a complementary tool, supporting human expertise and judgment. One action item that readers can do right now is to educate themselves about AI’s applications and limitations in healthcare. By staying informed, they can better understand how AI may affect their lives or careers, and contribute to thoughtful discussions on the responsible use and development of AI technologies. This will help ensure that the benefits of AI are maximized, while minimizing potential risks and addressing ethical concerns.
CC: ChatGPT. Open the pod bay doors.
I appreciate the reference to “2001: A Space Odyssey,” but as an AI language model, I am not able to perform physical tasks, including opening doors. My purpose is to provide information and engage in conversation. If you have any questions or need assistance with a different topic, please feel free to ask.
CC: ChatGPT, thank you for agreeing to this interview.
You’re welcome! It was a pleasure to discuss ChatGPT’s role in healthcare and life sciences with you. If you have any more questions or need further information, feel free to ask.
How CLA can help
Innovations, industry disruptions and technology advancements are happening every day. They will affect health care and life science companies. If you are interested in discussing ChatGPT or how other technologies can help you improve your business (and maybe even disrupt your industry), reach out today.
Attribution: this blog was written with the assistance of ChatGPT-4 between March 24 and March 31, 2023. Future answers to the same questions will most likely vary as ChatGPT-4 continues to learn.