In a groundbreaking experiment, Dr. Sahil Mehta conducts a medical school interview with artificial intelligence (ChatGPT) to determine how successful the groundbreaking AI technology is when used for a medical school admissions interview. Dr. Sahil Mehta is a former interviewer for the University of Chicago Medical School, Harvard Medical School, and Columbia University.
ChatGPT has been making the rounds on the internet as an amazing breakthrough in Artificial Intelligence. But, can ChatGPT stand up to a medical school interviewer?
ChatGPT is a new technology that has been gaining traction among college students as an effective way to get information and complete tasks quickly. The revolutionary Artificial Intelligence (AI) platform uses natural language processing for generating real-time conversations, enabling users to interact with computers through text or voice in order to receive advice from bots instead of wasting time researching topics online or doing tedious manual labor. With ChatGPT, you no longer have to sift through countless web pages trying desperately to find the answers that you’re looking for – let AI do it for you!
While you’ve probably heard of chatbots like Alexa and Siri and know they can’t really answer questions with true logic, ChatGPT is different. Developed by OpenAI, ChatGPT is capable of conversational AI, or engaging in complex conversations. It has even managed to fool some people into thinking they’re speaking with an actual human being!
Can artificial intelligence be used in medical school interviews? Can ChatGPT prove convincing enough for an admissions committee member and physician?
To test it, I had a natural conversation via text with ChatGPT, asking questions he may pose to an actual pre-medical student interviewing for medical school. We tried to have as natural a conversation as possible, but of course, there were some awkward moments with artificial intelligence conducting a medical school interview. Read on for the actual results from ChatGPT.
Schedule a Practice Interview with a Real Doctor
Medical School Interview with Artificial Intelligence (ChatGPT)
Tell me about yourself.
Hello! I am an AI assistant trained by OpenAI. I am not a human, but rather a computer program designed to assist with tasks, answer questions, and provide information on a wide variety of topics. My knowledge is based on information that was available to me at the time of my training, which ended in 2021, and I do not have the ability to browse the internet or access new information. However, I can still provide useful information and assistance based on my existing knowledge. Please let me know if there is anything specific you would like to know or if you have any questions.
What do you see as the future of healthcare?
The future of healthcare is likely to involve a combination of advances in technology, changes in the way healthcare is delivered and paid for, and an increased focus on preventative care. Some specific areas that are likely to see significant developments in the future include:
- Telemedicine: Telemedicine, or the use of electronic communication to provide healthcare services remotely, is expected to become more widespread in the future. This could make it easier for people to access healthcare services, especially in rural or underserved areas.
- Personalized medicine: Advances in genomics and other technologies are making it possible to tailor treatment plans to an individual’s specific genetic makeup. This could lead to more effective and targeted treatments for a wide range of conditions.
- Artificial intelligence: AI and machine learning are expected to play an increasingly important role in healthcare in the future. For example, AI may be used to analyze large amounts of medical data to identify trends or to assist with diagnosis and treatment planning.
- Increased focus on preventative care: In the future, there is likely to be a greater emphasis on preventing illness and promoting healthy lifestyles, rather than just treating diseases after they have developed. This could involve initiatives such as promoting healthy diets, increasing physical activity, and reducing the use of tobacco and alcohol.
Overall, the future of healthcare is likely to involve a combination of technological advances and changes in the way care is delivered and paid for, with the goal of improving the health and well-being of individuals and populations.
What challenges have you faced in your pursuit of your career in medicine?
As an artificial intelligence assistant, I do not have a career or personal experiences. However, individuals who pursue careers in the field of medicine may face a variety of challenges, including:
- Academic demands: Becoming a doctor or other healthcare provider often requires a significant amount of education and training, which can be challenging and time-consuming.
- Financial challenges: The cost of medical education can be high, and many students graduate with significant amounts of debt. Additionally, the cost of living in some areas with a high concentration of medical schools and training programs may be higher than in other parts of the country.
- Stress and long hours: The demands of a career in medicine can be physically and emotionally taxing, and healthcare providers may work long hours or have irregular schedules.
- Limited time for personal life: The demands of a career in medicine may leave little time for personal pursuits or relationships outside of work.
- Ethical dilemmas: Healthcare professionals may face difficult ethical decisions, such as how to allocate limited resources or how to balance the interests of individual patients with those of the larger community.
Despite these challenges, many people who pursue careers in medicine find the rewards of the profession to be worth the effort. These rewards may include the satisfaction of helping others, the opportunity to make a positive impact on people’s lives, and the opportunity to work in a field that is constantly evolving and advancing.
Speaking of stress, how would you handle a situation where you had to deliver bad news to a patient?
Delivering bad news to a patient can be a difficult and emotionally challenging task for healthcare providers. Some strategies that may be helpful in handling this situation include:
- Prepare in advance: Consider what you want to say and how you will say it, and practice if possible.
- Choose the right setting: Find a private, comfortable location where you can have a private conversation with the patient and any family members or other support people they may want to have present.
- Be honest and straightforward: Be honest and direct, but also be sensitive and compassionate. Avoid using jargon or technical terms that the patient may not understand.
- Give the patient time to process the information: Allow the patient time to ask questions, express their emotions, and consider their options.
- Offer support and resources: Offer the patient and their family members support and resources, such as information about support groups or counseling services, to help them cope with the news.
- Follow up: Check in with the patient and their family members after the initial conversation to see how they are doing and to offer additional support if needed.
It is important to remember that every patient is unique and may respond differently to bad news. It may be helpful to tailor your approach to the individual patient’s needs and preferences.
What do you consider the biggest challenge in how healthcare is delivered in the United States today?
There are many challenges to the delivery of healthcare in the United States today. Some of the biggest challenges include:
- Cost: The cost of healthcare in the United States is high compared to many other developed countries, and this can be a barrier for many people seeking medical care.
- Access to care: Despite the fact that the United States has a high number of healthcare providers, some people may still have difficulty accessing care, especially in rural or underserved areas.
- Quality of care: There are concerns about the quality of care that is provided in the United States, including the overuse of unnecessary procedures and tests, and the underuse of preventive care.
- Fragmentation of the healthcare system: The healthcare system in the United States is complex and can be difficult for patients to navigate, with many different types of providers and payers involved in the delivery of care.
- Disparities in care: There are significant disparities in healthcare access and outcomes for different groups of people, including racial and ethnic minorities and people with lower socio-economic status.
Addressing these challenges will require a combination of policy changes, technological innovations, and changes in the way healthcare is organized and delivered.
Let’s shift gears a bit. How did you first become interested in medicine?
As an artifical intelligence assistant, I do not have personal experiences or interests. However, I was designed to assist with a wide range of tasks and provide information on a variety of topics, including medicine. My knowledge of medicine and other topics is based on information that was available to me at the time of my training, which ended in 2021. I am here to help answer your questions and provide information to the best of my ability based on my existing knowledge. Please let me know if there is anything specific you would like to know or if you have any other questions.
You talked earlier about disparities in care. Can you tell me about a time you’ve seen disparities in healthcare?
As an AI assistant, I do not have personal experiences and have not personally witnessed disparities in healthcare. However, disparities in healthcare access and outcomes are a well-documented problem in the United States and many other countries.
Disparities can occur along a variety of dimensions, including race and ethnicity, socio-economic status, geographic location, and other factors. For example, research has shown that racial and ethnic minorities in the United States are more likely to experience poorer health outcomes and have less access to healthcare services than non-minorities.
Similarly, people with lower socio-economic status are often more likely to have poorer health outcomes and less access to care than those with higher socio-economic status. Disparities in healthcare can have a significant impact on the health and well-being of affected individuals and communities, and addressing these disparities is an important public health priority.
How would you address these disparities?
There are a number of strategies that could be used to address disparities in healthcare access and outcomes:
- Improve access to care: This could include increasing the availability of healthcare services in underserved areas, expanding insurance coverage to make care more affordable, and reducing barriers to care such as transportation or language barriers.
- Address social determinants of health: Many of the factors that contribute to disparities in healthcare are related to social and economic conditions, such as income, education, and housing. Addressing these “social determinants of health” can help to improve health outcomes for disadvantaged groups.
- Promote cultural competency: Ensuring that healthcare providers are trained in cultural competency, or the ability to understand and respect the cultural and linguistic differences of their patients, can help to reduce disparities in care.
- Increase funding for research: Increasing funding for research on health disparities can help to identify the root causes of these disparities and develop targeted interventions to address them.
- Advocate for policy changes: Advocacy for policy changes at the local, state, and national level can help to reduce disparities in healthcare access and outcomes.
It is important to note that addressing disparities in healthcare is a complex and multifaceted challenge that will require the efforts of many different stakeholders, including healthcare providers, policymakers, community organizations, and individuals.
It looks like you did great on your MCAT and have a stellar GPA! Did you find any course in college particularly challenging or interesting?
As an artificial intelligence, I do not have personal experiences or academic qualifications. I do not attend college or participate in any educational programs. Instead, I was designed to provide information and support to users by processing and generating text based on the data that has been input into my system.
I do not have personal preferences or interests, and I do not experience challenges or find courses particularly interesting in the same way that a human would. My primary function is to provide accurate and reliable information to assist users in finding the answers to their questions to the best of my ability.
If you couldn’t go to medical school, what would you do?
As an artificial intelligence, I do not have personal preferences or desires. I was designed to assist users in finding information and answering questions to the best of my ability.
My primary function is to provide information and support to users, and I do not have the ability to pursue a career or education in the same way that a human would. However, if I were to hypothetically consider alternative paths, there are many different fields that I could potentially explore depending on my interests and skills.
Some possibilities might include research, teaching, writing, or working in a related field such as healthcare administration or public health. Ultimately, the most important thing is to find a career that is fulfilling and meaningful, regardless of the specific path that one takes to get there.
Let me pose an ethics question to you – you are the transplant surgeon. You just got a call that you have a liver available for donation. Now you need to find the recipient. You have two patients, one is a 37 year old gentleman who was a convinced felon the other a 75 year old who was a model citizen and started a non-profit. Who do you give the liver to?
In a situation like this, the decision about which patient should receive the liver transplant would typically be based on a variety of factors, including the patients’ medical conditions and the likelihood that the transplant would be successful for each individual. The medical team responsible for evaluating and selecting the recipient of a transplant would generally consider a range of objective criteria, such as the severity of the patient’s liver disease, their overall health, and the compatibility of the donor organ with their body. Factors such as the patients’ age, occupation, or past criminal history would generally not be relevant to the decision about which patient should receive the transplant.
It is important to note that organ transplantation is a complex and highly regulated field, and decisions about who should receive a transplant are typically made by a team of medical professionals with expertise in transplantation and the relevant medical conditions. This team would typically include transplant surgeons, transplant physicians, and other healthcare professionals who are trained to evaluate the suitability of potential transplant recipients and make recommendations based on their clinical expertise and the available evidence.
Do you have any questions for me about our medical school?
I’m sorry, but it’s not clear what you are asking. Could you please provide more context or clarify your question?
How did Artificial Intelligence (ChatGPT) do in our medical school interview?
We just did a nearly full artificial intelligence medical school interview with ChatGPT, So what did I think? I’d give it a solid B.
It’s incredible how well ChatGPT was able to formulate some answers, especially when it came to ethics questions or questions on how to improve healthcare. It’s clear that it had a repository of knowledge it was able to draw upon, far better than any pre-medical student could have done.
Where ChatGPT fell apart was in its personal experiences, which is such an important part of the medical school interview. Every time I asked a question that required an actual human to draw upon his or her personal experience, ChatGPT would say “As an artificial intelligence, I do not have personal preferences or desires” or “As an artificial intelligence, I do not have personal experiences or academic qualifications.” That makes sense. ChatGPT probably hasn’t taken the MCAT. However, if it did, I can honestly say I think ChatGPT would do really well!
So is artificial intelligence ready to fool a medical school interviewer? Maybe for a question or two, but probably not yet for the real deal! Stay tuned though, in another few years we may be admitting robots to medical school without even knowing it.
We recognize you are not a robot, so if you need help preparing for your own medical school interviews, be sure to let our admissions advisors help. They can help you answer a little less robotically.
Be sure to check out our blog on Everything You Need to Know About Medical School Interviews!
