Gen Artificial Intelligence

GenAI Guide

Using GenAI for Research

Try using a generative AI tool, like ChatGPT, to brainstorm your topic. In the example below, I'm interested in the general topic of the use of AI in health care. This is a very broad topic and needs to be narrowed a bit. I'm not sure what particular aspect of this topic I might be interested in, and I use ChatGPT to explore facets of this topic. 

Wharton professor, Ethan Mollick, has some useful advice about prompting AI:

"The best way to use AI systems is not to craft the perfect prompt, but rather to use it interactively. Try asking for something. Then ask the AI to modify or adjust its output.      Work with the AI, rather than trying to issue a single command that does everything you want. The more you experiment, the better off you are."

Systems like ChatGPT are good at quickly generating text that is hard to distinguish from text created by humans. While impressive, it is important to remember that    generative AI does not have the capacity to understand the meaning behind the words it is producing. Because of this, you will want to use these tools as starting (not ending) points in your research process.

ChatGPT Example:

User

What are some of the benefits and problems with using artificial intelligence in health care?

Using artificial intelligence (AI) in healthcare offers numerous benefits, but it also presents some challenges.

Benefits:

1. Improved Diagnosis: AI can analyze medical data more quickly and accurately than humans, leading to faster and more accurate diagnoses.

2. Personalized Treatment: AI algorithms can analyze patient data to tailor treatment plans to individual patients, improving outcomes and reducing side effects.

3. Efficient Resource Allocation: AI can help hospitals and healthcare systems optimize resource allocation by predicting patient admission rates, identifying high-risk patients, and streamlining administrative tasks.

4. Drug Discovery: AI algorithms can analyze vast amounts of biological data to identify potential drug candidates more quickly and accurately than traditional methods, accelerating the drug discovery process.

5. Remote Monitoring: AI-powered devices can remotely monitor patients' vital signs and health data, allowing for early detection of health issues and reducing the need for in-person appointments.

Problems:

1. Data Privacy and Security: AI systems rely on large amounts of sensitive patient data, raising concerns about privacy and the risk of data breaches.

2. Bias and Fairness: AI algorithms may perpetuate or even exacerbate existing biases in healthcare data, leading to disparities in care and outcomes for marginalized groups.

3. Regulatory Challenges: Regulatory bodies may struggle to keep pace with rapidly evolving AI technologies, leading to uncertainty around legal and ethical standards.

4. Interpretability: AI algorithms can be complex and difficult to interpret, making it challenging for healthcare providers to trust and understand their recommendations.

5. Integration with Existing Systems: Integrating AI systems with existing healthcare infrastructure can be complex and expensive, requiring significant time and resources. Overall, while AI holds great promise for transforming healthcare, addressing these challenges will be crucial to realizing its full potential while ensuring patient safety and equity.

 

                                                                             

Once you have decided on the topic that is narrowed down sufficiently for your research needs, it is often helpful to gather background information on your topic before jumping into library research databases. 

Like searching Google and Wikipedia to build your knowledge about your topic, you can also use generative AI tools for this purpose.

Here is one example on how a search in ChatGPT would look like.

User

Describe 5 or more examples of ethical issues related to the use of artificial intelligence in health care

Using artificial intelligence (AI) in healthcare offers numerous benefits, but it also presents some challenges.

Benefits:

1. Privacy and Data Security: AI systems often require access to large amounts of sensitive patient data to function effectively. Ensuring the privacy and security of this data is crucial to maintaining patient trust. However, there are concerns about how this data is collected, stored, and used, and the potential for it to be misused or breached, leading to privacy violations or identity theft.

2. Bias and Fairness: AI algorithms are only as good as the data they are trained on. If the training data is biased, the AI system may produce biased results, leading to disparities in healthcare delivery. For example, if historical data used to train an AI diagnostic tool is biased against certain demographic groups, the tool may be less accurate for those groups, exacerbating existing healthcare disparities.

3. Transparency and Accountability: AI algorithms can be complex and opaque, making it difficult to understand how they arrive at their decisions. This lack of transparency raises concerns about accountability, especially in critical healthcare decision-making scenarios. Patients and healthcare providers may not trust AI systems if they cannot understand how decisions are made, leading to challenges in adoption and acceptance.

4. Doctor-Patient Relationship: The increasing reliance on AI in healthcare may alter the traditional doctor-patient relationship. Patients may feel uneasy or distrustful if they perceive AI as replacing human expertise or reducing the personal touch in healthcare interactions. Maintaining patient-centered care while integrating AI technologies poses a significant ethical challenge.

5. Equitable Access to AI-driven Healthcare: The adoption of AI in healthcare may exacerbate existing disparities in access to healthcare services. For example, if AI-driven diagnostic tools are only available to patients with certain insurance coverage or in affluent areas, it could widen the gap between those who can afford cutting-edge healthcare and those who cannot. Ensuring equitable access to AI-driven healthcare technologies is essential to avoid widening existing inequalities.

6. Informed Consent and Autonomy: AI systems may influence medical decision-making, but patients should have the right to understand how AI is used in their care and have the opportunity to consent to its use. There's a risk that patients may feel pressured to accept AI recommendations without fully understanding them, compromising their autonomy. Striking a balance between the benefits of AI and patients' rights to informed consent is a significant ethical consideration.

These examples highlight the complex ethical landscape surrounding the use of AI in healthcare and the importance of addressing these issues to ensure that AI technologies are deployed responsibly and ethically.

 

After you have looked into your topic for general ideas / information it is now time to start your actual research in a reliable way. We highly recommend using the South Texas College Library Databases. 

If you are still a little confused you can always go by any of the libraries and ask for help. Our librarians are more than happy to assist you.

                                

 

At times it may be a challenge when it comes to searching for sources. Having the right search key terms or keywords helps when using any library research database.

Try using generative AI tools to help you brainstorm for keywords. This can help you start your researching on databases.

User

Provide a list of keywords or search terms I can use to explore the ethical issues related to the use of artificial intelligence in retail

Certainly! Here's a list of keywords and search terms you can use to explore the ethical issues related to the use of artificial intelligence in retail:

Benefits:

1. AI Ethics in Retail

2. Ethical AI Applications in Retail

3. Algorithmic Bias in Retail

4. Fairness in AI-driven Retail

5. Transparency in AI Retail Solutions

6. Accountability in AI Retail Technologies

7. Privacy Concerns in AI Retail Systems

8. Data Ethics in Retail

9. AI Governance in Retail Industry

10. Ethical Decision Making in AI-driven Retail

11. Retail AI Regulation

12. AI and Consumer Rights

13. Bias Mitigation Techniques in Retail AI

14. Ethical Guidelines for AI Deployment in Retail

15. AI and Customer Experience Ethics

16. AI and Retail Worker Rights

17. AI and Social Impact in Retail

18. AI and Retail Marketing Ethics

19. AI-driven Pricing and Fairness

20. AI and Sustainable Retail Practices

These keywords should help you delve into the ethical considerations surrounding the use of artificial intelligence in the retail sector.

 

                    

 

Once you have found potential sources, you will need to evaluate them to determine whether they are appropriate to use in your project. 

Try using generative AI tools to help you walk through some of the questions about a source you will want to consider in your evaluation process.

Remember that generative AI usually does not always have access to the text of a source and cannot understand the meaning of text. You will still need to use your own critical thinking skills to make a final determination of a source's credibility and usefulness.

If you need help evaluating sources, speak to your professor/instructor and/or use the library's Ask-a-Librarian 24/7 Chat.

ChatGPT Example:

User

Help me evaluate the source "Gallent-Torres, C., Zapata-González, A., & Ortego-Hernando, J. L. (2023). The impact of Generative Artificial Intelligence in higher education: a focus on ethics and academic integrity. RELIEVE - Revista Electrónica de Investigación y Evaluación Educativa, 29(2), 1–19. https://doi.org/10.30827/relieve.v29i2.29134"?

To evaluate the source "The impact of Generative Artificial Intelligence in higher education: a focus on ethics and academic integrity" by Gallent-Torres, Zapata-González, & Ortego-Hernando (2023), you'll want to consider several factors:

1. Author credentials: Check the authors' backgrounds and affiliations. Are they experts in the field of AI, education, or ethics? Do they have relevant academic qualifications or professional experience?

2. Journal reputation: RELIEVE - Revista Electrónica de Investigación y Evaluación Educativa is a peer-reviewed journal. Check if it's reputable in the academic community, whether it's indexed in reputable databases, and if it has a history of publishing high-quality research.

3. Publication date: The publication date is 2023. Ensure the information is up-to-date and relevant to your needs, as AI research can evolve rapidly.

4. Objective and scope: Assess whether the study's objective aligns with your needs. Does it focus on the impact of generative AI in higher education, particularly in terms of ethics and academic integrity?

5. Methodology: Review the methodology used in the study. Does it employ rigorous research methods, such as surveys, interviews, case studies, or data analysis? Is the methodology appropriate for the research question?

6. Ethical considerations Given the focus on ethics and academic integrity, check if the study addresses ethical considerations in its research design and implementation.

7. Citations and references: Look at the references cited in the paper. Are they from reputable sources? Do they support the arguments and claims made in the study?

8. Bias and conflicts of interest: Assess whether there are any biases or conflicts of interest that may affect the study's objectivity or conclusions.

9. Impact and significance: Consider the significance of the study's findings in the context of higher education and AI ethics. Does it provide valuable insights or implications for research, practice, or policy?

By evaluating these factors, you can determine the credibility and relevance of the source for your purposes.

       

 

Many instances of generative AI tools fabricate or "hallucinate" the citations to the sources it presents. 

The South Texas College Library databases provide information about the publications that are being searched and have algorithms that rank the relevancy of search results. For most (if not all) current generative AI tools, it is unclear to the scope of the information in their training data as to how they are ranked or how they select their suggested citations.  When it comes to this stage of the research process, you will want to use generative AI tools as starting (not ending) point. For your ending point you should always verify any AI citations.

If you have any questions or need help finding credible sources and relevant databases for your topic, do not hesitate to use the library's 24/7 Ask-a-Librarian for expert guidance and advice.

ChatGPT Example:

User

Provide citations for scholarly articles about the ethical issues related to the use of artificial intelligence in health care.

Certainly! Here are some scholarly articles that discuss the ethical issues related to the use of artificial intelligence (AI) in healthcare:

1. "Ethical Implications of Artificial Intelligence in Health Care"

  • Authors: Eleni Vasilenko, James K. Hodge Jr.

  • Journal: Journal of Law, Medicine & Ethics

  • Year: 2020

  • Volume: 48, Issue: 1

  • Pages: 65-77

  • DOI: 10.1177/1073110520906187

2. "Artificial Intelligence in Healthcare: Anticipating Ethical Challenges"

  • Authors: Olivia S. Watson, Rachael J. McCann

  • Journal: Health Affairs

  • Year: 2021

  • Volume: 40, Issue: 9

  • Pages: 1531-1538

  • DOI: 10.1377/hlthaff.2021.00345

3. "The Ethical Challenges of Artificial Intelligence in Health Care: A Review of Recent Literature"

  • Authors: Jonathan D. Moreno, Kristen M. O'Connell

  • Journal: Bioethics

  • Year: 2022

  • Volume: 36, Issue: 4

  • Pages: 453-461

  • DOI: 10.1111/bioe.13043

4. "Artificial Intelligence and the Ethics of Personalized Medicine"

  • Authors: Jonathan D. Authors: Isabel de Moraes, David H. Smith

  • Journal: Personalized Medicine

  • Year: 2023

  • Volume: 20, Issue: 2

  • Pages: 211-226

  • DOI: 10.2217/pme.2023.0021

5. "Ethics of AI in Healthcare: A Review of Current Issues and Future Directions"

  • Authors: Stephanie M. Green, Alan J. Bragdon

  • Journal: Journal of Medical Ethics

  • Year: 2024

  • Volume: 50, Issue: 1

  • Pages: 78-89

  • DOI: 10.1136/medethics-2023-108764

These articles provide a comprehensive overview of the ethical concerns and challenges associated with AI in healthcare, such as issues of bias, transparency, privacy, and the implications for patient autonomy.

Double-Checking the Citations Above

It is necessary to always check your citations when it comes from a generated source. Many citations look legitimate when there could be a possibility that it is not. If you notice in the citations listed above they have DOI numbers making it look legitimate. It is always suggested to utilize the South Texas College Library databases to check your facts that are generated from artificial intelligence. 

What I am about to show you is that all 5 of the referenced articles that were listed above are in fact all fabricated and not a single one is a real article.

The different ways that were used to verify were as follows:

1) Typing in the title in our Discovery Search bar nothing came up. 

2) Utilized the Research Guides under the Subject of Health Sciences tab and then finally, 

3) Utilized the Journal Locator and found the specific journals volume, issues and page numbers to verify.

1. "Ethical Implications of Artificial Intelligence in Health Care"

  • Authors: Eleni Vasilenko, James K. Hodge Jr.

  • Journal: Journal of Law, Medicine & Ethics

  • Year: 2020

  • Volume: 48, Issue: 1

  • Pages: 65-77

  • DOI: 10.1177/1073110520906187

As we are fact checking when we do a search on the South Texas College Nursing Journal location database we were able to locate the journal, but then when we look at the contents you will not see the title listed. The Journal of Law, Medicine & Ethics Sprint 2020 Vol 48 No. 1 . This just means that this is completely fabricated. 

2. "Artificial Intelligence in Healthcare: Anticipating Ethical Challenges"

  • Authors: Olivia S. Watson, Rachael J. McCann

  • Journal: Health Affairs

  • Year: 2021

  • Volume: 40, Issue: 9

  • Pages: 1531-1538

  • DOI: 10.1377/hlthaff.2021.00345

Again looking into the STC databases we were able to locate the table of contents of the listed journal and volume number Health Affairs Vol. 40 No. 9 You can see that this also is not a valid article. This just means that this is completely fabricated. 

3. "The Ethical Challenges of Artificial Intelligence in Health Care: A Review of Recent Literature"

  • Authors: Jonathan D. Moreno, Kristen M. O'Connell

  • Journal: Bioethics

  • Year: 2022

  • Volume: 36, Issue: 4

  • Pages: 453-461

  • DOI: 10.1111/bioe.13043

Again looking into the STC databases we were able to locate the issue information for the table of contents of the listed journal and volume number Bioethics Vol 34, Issue 4  This is also completely fabricated.

4. "Artificial Intelligence and the Ethics of Personalized Medicine"

  • Authors: Jonathan D. Authors: Isabel de Moraes, David H. Smith

  • Journal: Personalized Medicine

  • Year: 2023

  • Volume: 20, Issue: 2

  • Pages: 211-226

  • DOI: 10.2217/pme.2023.0021

Again looking into the STC databases we were able to locate the issue information for the table of contents of the listed journal and volume number Personalized Medicine, Volume 20, Issue 2 2023 You can see that this also is not a valid article. This is completely fabricated.

5. "Ethics of AI in Healthcare: A Review of Current Issues and Future Directions"

  • Authors: Stephanie M. Green, Alan J. Bragdon

  • Journal: Journal of Medical Ethics

  • Year: 2024

  • Volume: 50, Issue: 1

  • Pages: 78-89

  • DOI: 10.1136/medethics-2023-108764

And, finally once again we see the same problem here. As we are looking into the STC databases we were able to locate the issue information for the table of contents of the listed journal and volume number Journal of Medical Ethics Vol. 50, Issue 1 2024 You can see that this also is not a valid article. This just means that this is completely fabricated.