Artificial Intelligence – Its role in health and lymphoedema management

On November 30, 2022, Open AI made ChatGPT publicly accessible, introducing a next-generation artificial intelligence (AI) model tailored for conversational and interactive dialogue.

To assist us with understanding AI ChatGPT was asked some questions.

Click the questions to read the answers

What is AI?

ChatGPT: AI, or Artificial Intelligence, refers to the simulation of human intelligence in machines that are programmed to think and learn like humans. It is a multidisciplinary field of computer science that involves developing algorithms and systems capable of performing tasks that typically require human intelligence. AI encompasses a wide range of techniques and technologies, and it is continuously evolving.

What is the role of AI in healthcare?

ChatGPT:  Some of the key roles of AI in healthcare include:

  • Diagnostic Assistance: AI algorithms can assist in diagnosing diseases and conditions by analyzing medical images, such as X-rays, CT scans, and MRIs. AI can help identify anomalies, patterns, and potential issues more accurately and quickly than human radiologists.
  • Predictive Analytics: AI can be used to analyze patient data to predict disease outbreaks, patient readmissions, or identify individuals at risk of specific health conditions. This enables proactive intervention and resource allocation.
  • Drug Discovery and Development: AI is used to analyze vast datasets to expedite drug discovery and development, identifying potential candidates for new treatments and predicting their effectiveness.
  • Personalized Medicine: AI helps tailor treatment plans based on an individual’s genetic makeup, medical history, and lifestyle, ensuring more effective and targeted healthcare.
  • Telemedicine and Remote Monitoring: AI powers telemedicine applications that enable remote consultations, making healthcare more accessible. It also enables continuous remote monitoring of patients with chronic conditions.
  • Administrative Efficiency: AI automates administrative tasks, such as scheduling, billing, and medical coding, reducing administrative burdens on healthcare providers and improving efficiency.
  • Natural Language Processing (NLP): NLP allows AI to extract insights from electronic health records, clinical notes, and other unstructured data, facilitating research and improving patient care.
  • Robotics and Automation: AI-driven robots and automation assist in surgeries, drug dispensing, and repetitive tasks in healthcare facilities, enhancing precision and efficiency.
  • Virtual Health Assistants: AI-powered virtual assistants provide health information, appointment scheduling, and medication reminders, improving patient engagement and reducing the burden on healthcare staff.
  • Fraud Detection: AI can help identify fraudulent claims and activities in healthcare insurance and billing, saving costs for healthcare organizations.
  • Research and Clinical Trials: AI accelerates the process of identifying potential participants for clinical trials and analyzing research data.
  • Population Health Management: AI can analyze large-scale population health data to identify trends, hotspots, and risk factors, allowing for more effective public health interventions.
  • Chatbots and Mental Health Support: AI-driven chatbots and applications provide mental health support, offering a means for individuals to access guidance and resources.
  • Genomic Analysis: AI can analyze genomic data to predict genetic predispositions to certain diseases and guide personalized healthcare decisions.
  • Security and Privacy: AI is used to enhance the security of healthcare data and protect against data breaches and unauthorized access.

What are the limitations of AI in healthcare?

ChatGPT:  Some of the key limitations of AI in health include:

  • Data Quality and Bias: AI systems heavily rely on the quality of data used for training. In healthcare, data can be inconsistent, incomplete, and biased, leading to AI models that may not be accurate or may perpetuate existing healthcare disparities.
  • Limited Generalizability: AI models trained on specific datasets may perform well in controlled environments but may struggle to generalize to diverse patient populations or real-world clinical settings, where patient characteristics and conditions can vary widely.
  • Lack of Contextual Understanding: AI systems may not fully understand the complex and nuanced medical contexts, such as the emotional and psychological aspects of patient care. This can lead to misunderstandings and potentially incorrect recommendations.
  • Ethical and Legal Concerns: The use of AI in healthcare raises ethical and legal questions, especially in cases where AI systems make critical medical decisions. Issues related to accountability, informed consent, and liability need to be addressed.
  • Limited Creativity and Critical Thinking: AI systems lack the creativity, critical thinking, and intuitive reasoning abilities that healthcare professionals possess. They may struggle to handle unique or unexpected medical cases.
  • Security and Privacy: The use of AI in healthcare raises concerns about the security and privacy of patient data. Data breaches can have serious consequences, particularly when sensitive medical information is involved.
  • Regulatory Hurdles: The healthcare industry is subject to strict regulations and standards. Integrating AI into healthcare practices while complying with these regulations can be challenging.
  • Resistance to Change: Healthcare professionals and institutions may be resistant to adopting AI due to concerns about job security, the perceived depersonalization of healthcare, or unfamiliarity with AI technology.
  • Cost: Developing and implementing AI solutions in healthcare can be expensive, and smaller healthcare providers may face financial barriers to adopting AI.
  • Validation and Certification: Ensuring the safety and effectiveness of AI systems in healthcare requires rigorous validation and certification processes. Developing and adhering to these standards is crucial.
  • Continual Monitoring and Maintenance: AI systems require ongoing monitoring, maintenance, and updates to remain effective. Neglecting this aspect can lead to degraded performance and potential errors.
  • Lack of Real-time Feedback: Many AI systems in healthcare do not provide real-time feedback and explanations to healthcare providers, which can hinder their trust and understanding of AI-driven recommendations.
  • Interoperability: Ensuring that AI systems can seamlessly integrate with existing healthcare systems and electronic health records (EHRs) is a technical challenge.
  • Addressing these limitations requires a collaborative effort among healthcare professionals, AI developers, policymakers, and regulators. Ethical guidelines, regulations, and best practices need to be developed to ensure responsible and effective use of AI in healthcare while addressing its challenges.
  • Lack of Real-time Feedback: Many AI systems in healthcare do not provide real-time feedback and explanations to healthcare providers, which can hinder their trust and understanding of AI-driven recommendations.
  • Interoperability: Ensuring that AI systems can seamlessly integrate with existing healthcare systems and electronic health records (EHRs) is a technical challenge.
  • Addressing these limitations requires a collaborative effort among healthcare professionals, AI developers, policymakers, and regulators. Ethical guidelines, regulations, and best practices need to be developed to ensure responsible and effective use of AI in healthcare while addressing its challenges.

What year is AI data based on?

ChatGPT: The AI data on which I was trained and my knowledge is based on information available up to January 2022. I do not have access to real-time data or events that occurred after that date. AI is a rapidly evolving field, and new developments and research continue to emerge, so it’s important to verify information and seek updates from more recent sources if you need the latest information on AI-related topics.

What does the literature say about AI in healthcare

There has been an explosion of research across healthcare about AI. On September 11, 2023, an article was published in CURE which explored artificial intelligence in the world of cancer care. In this article, a software engineer, and cancer survivor, tells how she used the popular AI chatbot ChatGPT to tally up her medical expenses. Another survivor describes how an AI-driven platform helped her connect with a clinical trials.

A number of oncology and technology experts they spoke with also urged caution. AI platforms “are unique in that sense that they have amazing strengths, but they also have pretty important weaknesses, that, if you’re going to be using these things regularly, it’s important to know about,” Dr. Matthew Lungren says. Lungren is an associate clinical professor at the University of California, San Francisco, and chief medical information officer at Nuance Communications, a conversational AI company purchased in 2022 by Microsoft. Always validate and double check information. ChatGPT has been known to make up research papers that don’t actually exist. Remember it’s a tool. However in oncology it may enhance patient-centred communication as it is empathetic.

Stephen Gilbert, professor of medical device regulatory science at the Else Kröner Fresenius Center for Digital Health at Dresden University of Technology in Germany said in a news release “Today there is no way to be certain about the quality, evidence level or consistency of clinical information or supporting evidence for any response. These chatbots are unsafe tools when it comes to medical advice, and it is necessary to develop new frameworks that ensure patient safety,”

Read article in CURE here

Hopkins et al investigated the accuracy of ChatGPT in answering basic fact-based cancer questions to responding to complex clinical questions (Hopkins et al., 2023). They found “ChatGPT demonstrated a remarkable ability to formulate interpretable responses, which appeared to minimize the likelihood of alarm compared with Google’s feature snippet.” However, they stated there is a pressing requirement for regulators and healthcare experts to actively participate in establishing standards for minimal quality and increasing patient awareness regarding the current constraints of emerging artificial intelligence assistants.

Artificial intelligence chatbots will revolutionize how cancer patients access information: ChatGPT represents a paradigm-shift.

Another article by Johnson et al assessed the accuracy and reliability of Chat-GPT (Johnson et al., 2023).


Background: Natural language processing models such as ChatGPT can generate text-based content and are poised to become a major information source in medicine and beyond. The accuracy and completeness of ChatGPT for medical queries is not known.

Methods: Thirty-three physicians across 17 specialties generated 284 medical questions that they subjectively classified as easy, medium, or hard with either binary (yes/no) or descriptive answers. The physicians then graded ChatGPT-generated answers to these questions for accuracy (6-point Likert scale; range 1 – completely incorrect to 6 – completely correct) and completeness (3-point Likert scale; range 1 – incomplete to 3 – complete plus additional context). Scores were summarized with descriptive statistics and compared using Mann-Whitney U or Kruskal-Wallis testing.

Results: Across all questions (n=284), median accuracy score was 5.5 (between almost completely and completely correct) with mean score of 4.8 (between mostly and almost completely correct). Median completeness score was 3 (complete and comprehensive) with mean score of 2.5. For questions rated easy, medium, and hard, median accuracy scores were 6, 5.5, and 5 (mean 5.0, 4.7, and 4.6; p=0.05). Accuracy scores for binary and descriptive questions were similar (median 6 vs. 5; mean 4.9 vs. 4.7; p=0.07). Of 36 questions with scores of 1-2, 34 were re-queried/re-graded 8-17 days later with substantial improvement (median 2 vs. 4; p<0.01). Conclusions: ChatGPT generated largely accurate information to diverse medical queries as judged by academic physician specialists although with important limitations. Further research and model development are needed to correct inaccuracies and for validation.

Assessing the Accuracy and Reliability of AI-Generated Medical Responses: An Evaluation of the Chat-GPT Mode

AI and lymphoedema

If we want to consider AI as a possible source for educating our clients, it’s important to check its accuracy. Let’s do this by testing ChatGPT and its accuracy in the area of lymphoedema. What do you think?

Click the questions to read the answers

What is lymphoedema?

ChatGPT: Lymphoedema, also spelled as lymphedema, is a condition characterized by the abnormal accumulation of lymphatic fluid in tissues, leading to swelling and fluid retention in various parts of the body, typically in an arm or a leg. This condition occurs when the lymphatic system, responsible for draining excess fluid from the body’s tissues and supporting the immune system, is impaired or damaged. Lymphoedema can be a result of various factors, including surgery, radiation therapy, injury, infection, or congenital abnormalities that affect the lymphatic vessels. It can lead to discomfort, limited mobility, and an increased risk of infection if left untreated. Management and treatment often involve compression garments, manual lymphatic drainage, exercise, and other therapeutic approaches to reduce swelling and improve the quality of life for individuals with lymphoedema.

What are the risk factors for developing lymphoedema after breast cancer management?

ChatGPT: The risk factors for developing lymphoedema after breast cancer management can include:

  1. Surgery: Lymphoedema risk is higher after breast cancer surgeries that involve the removal of lymph nodes (sentinel or axillary lymph node dissection) as it can disrupt the normal lymphatic drainage.
  2. Radiation therapy: Radiation therapy to the lymph nodes in the underarm area can damage lymphatic vessels, increasing the risk of lymphoedema.
  3. The extent of surgery: More extensive surgeries, such as mastectomy (removal of the entire breast), may have a higher risk compared to lumpectomy (partial breast removal).
  4. Obesity: Being overweight or obese can put additional stress on the lymphatic system and increase the risk of lymphoedema.
  5. Infection or injury: Any injury or infection to the arm or axillary region on the side of the breast cancer treatment can contribute to lymphoedema.
  6. Age: Older individuals may be at a higher risk of developing lymphoedema.
  7. Genetics: Some people may have a genetic predisposition to lymphatic system issues, which can increase their risk.
  8. Previous history of lymphoedema: If a person has had lymphoedema in the past, they may be at a higher risk of developing it again.

It’s important to note that the risk of developing lymphoedema can vary from person to person, and not everyone who undergoes breast cancer management will develop this condition. To reduce the risk and manage lymphoedema, it’s crucial to follow recommended guidelines, including proper care of the affected limb, maintaining a healthy lifestyle, and monitoring for early signs of lymphoedema. Consultation with a healthcare provider experienced in lymphoedema management is also essential.

I had lymph nodes removed in my groin because of cancer and now my leg is aching. What is the reason?

ChatGPT: I’m not a doctor, but I can provide some general information that might help you understand why your leg is aching after having lymph nodes removed in the groin due to cancer. Aching in the leg following lymph node removal in the groin could be attributed to several factors, including:

  1. Lymphoedema: Lymphoedema is a common condition that can occur after lymph node removal. It may cause swelling, discomfort, and aching in the affected limb, such as the leg. This is due to a disruption in the normal flow of lymphatic fluid.
  2. Scar tissue formation: Surgical procedures can lead to the formation of scar tissue, which might press on nerves or blood vessels, causing pain or discomfort.
  3. Nerve damage: During surgery, nerves in the groin area can be affected, leading to pain or discomfort in the leg.
  4. Infection or inflammation: Infections or inflammation in the surgical site or surrounding tissues can cause pain and discomfort.
  5. Poor circulation: Reduced blood flow or poor circulation in the leg may result in aching or discomfort.

It’s important to consult with your healthcare provider about your symptoms. They can provide a thorough evaluation, diagnose the cause of your leg pain, and recommend appropriate treatment or interventions. They may also be able to provide guidance on managing lymphoedema if that is the cause of your discomfort. Always seek medical advice for a proper assessment and personalized recommendations based on your specific situation.

Take home message

Artificial intelligence has a part to play in lymphoedema education, but it remains crucial for consumers to verify such information with a lymphoedema practitioner, a healthcare expert, or through other reputable sources.

Hopkins, A. M., Logan, J. M., Kichenadasse, G., & Sorich, M. J. (2023). Artificial intelligence chatbots will revolutionize how cancer patients access information: ChatGPT represents a paradigm-shift. JNCI Cancer Spectrum, 7(2), pkad010.

Johnson, D., Goodman, R., Patrinely, J., Stone, C., Zimmerman, E., Donald, R., Chang, S., Berkowitz, S., Finn, A., & Jahangir, E. (2023). Assessing the accuracy and reliability of AI-generated medical responses: an evaluation of the Chat-GPT model. Research square.