What Makes or Breaks a Clinical Trial According to ChatGPT (A.k.a the Industry)

ChatGPT has become incredibly popular not just among AI enthusiasts and content creators but also within our clinical research industry. More than the chat bots we are familiar with, ChatGPT does not simply come back with scripted replies. 

But AI is not God – at least for now it isn’t – so instead of providing answers that are universally and objectively true, it bases its replies on the ‘common wisdom’ a.k.a what people say. So if a huge percentage of people say the Sun rises from the West, that’s what ChatGPT will tell you. In other words, AI inherits human biases. 

This is an important caveat because when we asked ChatGPT what makes or breaks a clinical trial, the answers we got in return were based on the shared knowledge of the whole clinical research industry. Countless experts in planning and running clinical trials believe these to be the most important factors for clinical trial success. 

I decided to share these replies here in full as some of them are very interesting and I’ve heard them repeatedly from feasibility and clinical operations experts. 

Q: Can you analyze what makes or breaks a clinical trial?

A: There are several factors that can make or break a clinical trial. Some of the most important include:

Study design: The study design must be well thought-out and appropriate for the research question being asked. This includes factors such as the sample size, inclusion and exclusion criteria, and endpoint measures.

Recruitment: Recruiting enough participants and ensuring they are representative of the population being studied is crucial for the success of a trial.

Data quality: The data collected during a trial must be accurate, reliable and complete. This includes ensuring that the data is properly collected, recorded, and stored.

Study execution: The trial must be executed in accordance with the study protocol, good clinical practices, and regulatory requirements.

Safety monitoring: Adequate safety monitoring must be in place to identify and address any safety concerns that may arise during the trial.

Data analysis and interpretation: The data must be analyzed and interpreted correctly to draw accurate conclusions from the study.

Funding and resources: Adequate funding and resources are needed to support all aspects of the trial, from design and execution to analysis and dissemination of results.

Q: Can you get deeper into the Study design part? What makes a great study design?

A: A great study design is one that is well thought-out and appropriate for the research question being asked. A well-designed study should have several key features, including:

Clearly defined research question and objectives: The study should have a specific research question that it aims to answer and specific objectives that it aims to achieve.

Sample size calculation: The sample size should be large enough to detect a meaningful difference between the groups being compared, but not so large that it becomes impractical or too costly to conduct the study.

Selection of study population: The population being studied should be clearly defined and appropriate for the research question. The inclusion and exclusion criteria should be clearly specified.

Control group: A control group should be included in the study design to provide a baseline for comparison.

Randomization: Participants should be randomly assigned to the different groups to reduce the risk of bias.

Blinding: To reduce bias, the study should be blinded, meaning that neither the participants nor the researchers know which group the participants are in.

Endpoints: The study should have clearly defined primary and secondary endpoint measures that are appropriate for the research question.

Follow-up: There should be a plan for follow-up to ensure that the participants are safe and to track the long-term effects of the intervention.

Data analysis: The study should have a plan for data analysis that takes into account the specific research question and objectives.

By including these elements in the study design, the study will be able to answer the research question and provide valid conclusions.

Q: Go deeper into point 3 – the selection of the study population. What information do I need in order to make the best selection?

A: The selection of the study population is a crucial step in the design of a clinical trial. The population should be clearly defined and appropriate for the research question. The inclusion and exclusion criteria should be specified in order to select the most appropriate population for the study.

To make the best selection of the study population, you need to consider the following information:

Inclusion criteria: This defines the characteristics that participants must have in order to be eligible for the study. These criteria may include age, gender, diagnosis, and other demographic or clinical characteristics.

Exclusion criteria: This defines the characteristics that would disqualify a participant from the study. These criteria may include other health conditions, medications, or treatments that would interfere with the study.

Target population: This defines the population that the study aims to recruit. This population may be defined by characteristics such as age, gender, or diagnosis.

Feasibility: The population should be large enough and accessible enough to recruit the number of participants required to achieve the study’s objectives.

Representativeness: The population should be representative of the larger population that the study aims to generalize to.

Recruitment plan: The study should have a plan for recruiting participants from the target population.

By considering these factors and selecting the most appropriate population for the study, you will be able to ensure that the study results will be generalizable to the target population and that the study has the power to detect the effects of the intervention.

Q: What do I need for a great feasibility assessment?

A: Feasibility assessment is an important step in the design of a clinical trial that helps to determine whether the proposed trial is practical and achievable. A great feasibility assessment should include the following elements:

Recruitment plan: The feasibility assessment should include a detailed plan for recruiting participants from the target population. This plan should include information on how participants will be identified and contacted, as well as the expected response rate.

Sample size calculation: The feasibility assessment should include a sample size calculation to determine the number of participants needed to achieve the study’s objectives. This calculation should take into account the expected response rate and the desired level of precision for the study results.

Resources: The feasibility assessment should include an assessment of the resources needed to conduct the trial. This includes financial resources, personnel, equipment, and facilities.

Timeline: The feasibility assessment should include a timeline for the trial, including the expected duration of the study, the recruitment period, and the follow-up period.

Ethical considerations: The feasibility assessment should include an assessment of the ethical considerations of the trial, including informed consent, participant safety, and data protection.

Operational considerations: The feasibility assessment should include an assessment of the operational considerations of the trial, including the availability of investigational product, logistics, regulatory requirements, and data management.

By including these elements in the feasibility assessment, you can ensure that the trial is practical and achievable, and that the resources and time required to conduct the trial are appropriate for the research question and objectives.

Q: Can you dig deeper into the recruitment plan and its details?

A: A recruitment plan is an essential component of a clinical trial’s feasibility assessment. It outlines the methods and strategies that will be used to identify and enroll participants in the study. A great recruitment plan should include the following elements:

Target population: The recruitment plan should clearly define the target population for the study. This includes the inclusion and exclusion criteria for participants, as well as the expected size of the population.

Recruitment sites: The recruitment plan should identify the locations where participants will be recruited, such as hospitals, clinics, or community centers. It should also consider the feasibility of recruiting participants from these sites.

Recruitment strategies: The recruitment plan should outline the strategies that will be used to identify and contact potential participants. This includes methods such as mailings, phone calls, social media, and advertisements in newspapers or on websites.

Screening procedures: The recruitment plan should describe the screening procedures that will be used to determine whether potential participants meet the inclusion and exclusion criteria for the study.

Consent process: The recruitment plan should describe the process for obtaining informed consent from participants. This should include the information that will be provided to participants, as well as the process for obtaining and documenting consent.

Retention strategies: The recruitment plan should include strategies for keeping participants in the study for the duration of the trial. This may include regular follow-up calls or visits, as well as incentives for participation.

Tracking system: The recruitment plan should include a system for tracking the number of participants recruited, the number of participants who have withdrawn, and the reasons for withdrawal.

By including these elements in the recruitment plan, you can ensure that the study will be able to recruit the number of participants needed to achieve its objectives, while also ensuring that the participants are representative of the target population and that the study is conducted in an ethical manner.

Q: What are the different ways to assess the expected size of the population?

A: There are several ways to assess the expected size of the population for a clinical trial, including:

Literature review: A review of the existing literature on the condition or disease being studied can provide information on the prevalence and incidence of the condition in the population.

Database searches: Searching databases such as the National Health Service Central Register or the National Cancer Institute’s Surveillance, Epidemiology, and End Results (SEER) program can provide information on the number of people with a specific condition.

Surveys: Surveys can be conducted to gather information on the prevalence and incidence of a condition in a specific population.

Hospital or clinic records: Reviewing records from hospitals or clinics can provide information on the number of people with a specific condition who have been treated at those facilities.

Expert opinion: Experts in the field can provide an estimate of the number of people with a specific condition based on their experience and knowledge.

The main factors that affect the expected size of the population for a clinical trial include:

Prevalence and incidence: The prevalence and incidence of the condition or disease being studied will affect the number of people eligible for the trial.

Inclusion and exclusion criteria: The inclusion and exclusion criteria for the trial will affect the number of people eligible to participate.

Recruitment sites: The number of potential participants will depend on the location of the recruitment sites, as well as the accessibility of those sites to the target population.

Time frame: The expected size of the population will depend on the time frame of the trial, as the number of people with a condition may change over time.

Other factors: Other factors such as availability of treatments, patient’s willingness to participate, and cultural or socioeconomic factors may affect the expected size of the population.

By considering these factors, you can make an informed estimate of the expected size of the population for your clinical trial, which will help you to determine the appropriate sample size for the study.

Q: Please tell me more about the so called “Other factors” that you listed. What are they and how important are they?

A: The “other factors” that I mentioned in my previous response refer to any additional factors that may affect the expected size of the population for a clinical trial. These can include:

Availability of treatments: If there are already treatments available for the condition or disease being studied, this may affect the number of people who are willing to participate in the trial or who meet the inclusion criteria.

Patient’s willingness to participate: Patients may be more or less willing to participate in a trial depending on factors such as the nature of the condition, the potential risks and benefits of the treatment being studied, and the patient’s overall health status.

Cultural or socioeconomic factors: Cultural or socioeconomic factors may affect the number of people who are eligible or willing to participate in a trial. For example, a trial that requires frequent visits to a clinic or hospital may be less accessible to people living in rural areas or who have limited transportation.

Privacy and data protection concerns: Participants may be less willing to participate in a trial if they are concerned about the privacy and security of their personal information.

Trust in the healthcare system: Trust in the healthcare system can also affect the willingness of participants to participate in a clinical trial, for example if there is a history of exploitation in medical research in a certain population.

All these factors can have a significant impact on the feasibility and success of a clinical trial, and should be taken into account when assessing the expected size of the population and developing the recruitment plan. It is also important to consider these factors when designing the trial to ensure that the trial is accessible and inclusive to all populations.

Q: How can I check the availability of treatments?

A: There are several ways to check the availability of treatments for a specific condition or disease:

Literature review: Reviewing the existing literature on the condition or disease can provide information on the treatments that are currently available. This includes searching databases such as PubMed, Embase, and the Cochrane Library.

Clinical practice guidelines: Clinical practice guidelines, such as those from the National Institute for Health and Care Excellence (NICE) or the American College of Physicians (ACP), provide information on the recommended treatments for a specific condition.

Government websites: Government websites, such as those of the US Food and Drug Administration (FDA) or the European Medicines Agency (EMA), provide information on the treatments that are currently approved for use.

Professional societies: Professional societies, such as the American Medical Association (AMA) or the European Society of Cardiology (ESC), often have information on the treatments that are currently available for a specific condition.

Consultation with experts: Consultation with experts in the field, such as physicians or researchers, can provide information on the treatments that are currently available and their effectiveness.

It is important to take into account the availability of treatments when designing a clinical trial, as this will affect the number of people who are eligible to participate and the comparability of the study groups. For example, if a treatment is already available and considered standard of care, it will be difficult to find participants who are not receiving it, and the trial design will have to account for this.

NB! You don’t actually have to do all of that. TrialHub’s Standard of Care module completely automates the process. In fact, we are the first platform to link reimbursed drugs to indications (and sub-populations) with 98% accuracy. Standard of Care helps you identify where your eligible patients are and at which step of their journey they become eligible.

Q: What about the patient’s willingness to participate, how do I measure it?

A: Measuring a patient’s willingness to participate in a clinical trial can be challenging, but there are several methods that can be used to assess this:

Surveys: Surveys can be used to gather information from potential participants about their willingness to participate in a trial. This can include questions about the potential risks and benefits of the treatment being studied, as well as the participant’s overall health status.

Focus groups: Focus groups can be used to gather information from potential participants about their perceptions of the trial, including their willingness to participate. This can provide valuable insights into the concerns and motivations of potential participants.

Interviews: Interviews with potential participants can provide detailed information about their willingness to participate in a trial, as well as any concerns or reservations they may have.

Review of existing data: Reviewing existing data, such as hospital or clinic records, can provide information about patient’s willingness to participate.

Pilot studies: Conducting a pilot study with a small group of potential participants can provide valuable information about patient’s willingness to participate in a trial, as well as any issues or concerns that may arise during the recruitment process.

It is important to take into account the patient’s willingness to participate in a clinical trial, as this will affect the number of people who are eligible to participate and the feasibility of the trial.

It is also important to take this into account when designing the trial, as a trial that is not well received by the potential participants, may not have enough participants to be completed, or the participants may not be representative of the population being studied.


How accurate do you find ChatGPT’s replies? Would you add or elaborate on something? I’d love to hear your thoughts in the comments.

Scroll to Top