Updated April 15th, 2026
In this article, we want to adress a very current but controversial topic: The use of artificial intelligence (AI) language models such as ChatGPT in scientific writing. There are several ways you can utilize ChatGPT while you are doing research or while you are writing a scientific manuscript. In this article we will cover several possibilities on how to use ChatGPT in scientific writing. Please also read how to write a scientific paper before you ask ChatGPT anything about it.
Disclaimer:
#1 Josh from the “future” here: This post is from early 2023 and generative AI has come a long way since there. There are many more (maybe even better) algorithms than the OpenAI-Model, I evalluated while writing this post. For the sake of transparency and just to remind everyone (especially myself) how fast thinks can change, I will not change anything fundamental past this addendum.
#2 As an advanced AI model capable of understanding and generating natural language, ChatGPT can help you in multiple ways. But although the title of this article is “How to use ChatGPT in Scientific Writing”, be aware of the following:
Do not use ChatGPT to write actual text for your scientific manuscript!
ChatGPT may generate wrong and plagiarized content. Although you can check the output of ChatGPT with various tools, you should always be extra careful when copying any parts. Otherwise, you might get your research rejected instantly.

What to Consider Before ChatGPT Can Help You in Scientific Writing
First of all, it is important how you perceive ChatGPT.
It is by no means an automatic typewriter that generates text to be copied and pasted into your manuscript, presentation or other scientific documents. Rather, I suggest that you think of ChatGPT as an assistant that can help you with many things. However, it also has some limitations that you should be aware of before implementing ChatGPT into any of your workflows. In science, ChatGPT may only be of use, if the user (you) has substantial knowledge and experience in her/his field. You need to be able to differenciate meaninful from useless and more important right from wrong information.
It is tempting to give ChatGPT a prompt such as “write me an introduction for a scientific paper with the following title: ‘XYZ'”. I can only recommend everyone to try it – once! The result will make some sense and there might be some valuable information in it but it will most likely not suit your specific topic or thesis. The potential of ChatGPT lies in somewhat more sophisticated approaches.
The Top 6 Applications for ChatGPT in Scientific Writing
Let’s now dive into specific areas and explore how to use ChatGPT for scientific writing. Here we will briefly go through the 5 best ways to use ChatGPT while doing research or writing a scientific manuscript. Each point will be discussed in detail below with example prompts.
- Brainstorming and Finding Arguments
- Summarizing and Concentrating
- Paraphrasing and Simplifying
- Identifying Key Words and Key Points
- Creating Figures and Graphs
- Find Alternative Phrases and Synonyms
But now let us go into details so you can learn how ChatGPT can help you with your scientific research.

1. Brainstorming and Finding Arguments
ChatGPT is a great tool to help with generating ideas, finding arguments and general brainstorming. This can be helpful either before you start collecting information or after you already gathered some data in order to check if you maybe missed a relevant point.
How to Brainstorm in Scientific Writing Using ChatGPT
For example, you can ask ChatGPT: “Give me treatment options for hepatocellular carcinoma. Use bullet points.”
It will give you an output that will look something like this:
ChatGPT:
Sure, here are the treatment options for hepatocellular carcinoma in bullet points:
- Surgery (resection or liver transplant)
- Radiofrequency ablation (heat to destroy cancer cells)
- Transarterial chemoembolization (TACE) (chemotherapy drugs injected directly into tumor)
- Systemic chemotherapy (drugs given through the bloodstream)
- Targeted therapy (drugs that target specific proteins or pathways involved in cancer growth)
- Immunotherapy (drugs that help the immune system to fight cancer)
- Radiation therapy (high-energy radiation used to kill cancer cells)
- Palliative care (treatment to relieve symptoms and improve quality of life)
At first sight, this list seems quite complete but depending on your level of expertise you might find that there are things missing (what about radioembolization, microwave ablation etc.). Maybe there will even be obvious mistakes. This is especially important in fields with rapid developments or novel innovations. As ChatGPT has no access to very current data, you need to be able to identify mistakes or gaps in its output.
However, lets say you already made your list and discussed treatment options for hepatocellular carcinoma but somehow missed to include transarterial chemoembolization. In this case, ChatGPT will make you aware of this gap and will allow you to make your text or list more comprehensive. Again, please always be critical about the output and do additional scientiftific research by yourself to fact-check if you are not entirely sure about some things.
How to Use ChatGPT to Compare Things and Find Arguments in Scientific Writing
Given the huge data set that ChatGPT is trained on, it knows a lot about a lot of things. Therefore, you can use it to compare things and find arguments for different items.
For example, you could ask ChatGPT: “Compare radiofrequency and microwave ablation for the treatment of hepatocellular carcinoma“.
In this case, my test output looked like this:
ChatGPT:
Radiofrequency ablation (RFA) and microwave ablation (MWA) are two minimally invasive procedures used to treat hepatocellular carcinoma (HCC). Both techniques aim to destroy cancerous tissue using thermal energy. However, there are some differences between the two methods:
- Mechanism of action: RFA uses high-frequency electrical currents to generate heat, while MWA uses electromagnetic waves to generate heat. MWA can achieve higher temperatures in a shorter amount of time.
- Tumor size: RFA is generally more effective for smaller tumors, typically those less than 3 cm in size. MWA may be better for larger tumors, as it can create a larger ablation zone.
- Procedural time: RFA requires a longer procedural time than MWA. MWA can complete treatment in a shorter time.
- Complications: Both RFA and MWA are generally safe and have few complications. However, there is a slightly higher risk of thermal injury to nearby tissues with MWA.
- Cost: MWA is generally more expensive than RFA.
In summary, RFA and MWA are both effective treatment options for HCC, but the choice between the two may depend on the tumor size and location, as well as the patient’s individual situation and the availability of the techniques in the treatment center.
Again, you need specific knowledge to evaluate this information with regard to the correctness. However, you will get some information of points, where you can get into more detail. For example, maybe you did not include potential differences in procedural time in your discussion. You now can research this point regarding real and authorized information and then add this to your discussion citing the respective references.
Helpful ressources to perform scientific literature research are PubMed and GoogleScholar (among many others).
2. Summarizing and Concentrating
ChatGPT is great in summarizing and modifying text. You can copy and paste any text into the search field and tell it to summarize it into one paragraph or even into single sentences. Or you can even tell it to summarize prior studies for you. Again, there are some things to know beforehand and you are asked to critically evaluate the output.

How to Use ChatGPT for Summarizing Scientific Texts
For example, you can give ChatGPT a scientific text as input. In this test case, I put the first section of the Wikipedia Article of Hepatocellular Carcinoma in the text box and told it to summarize it using just 3 sentences. “TEXT. Summarize this. Three sentences.”
Using this prompt, I received the following output:
ChatGPT:
Hepatocellular carcinoma (HCC) is the most common type of primary liver cancer and is linked to chronic liver injury and inflammation, often caused by chronic viral hepatitis infection or exposure to toxins. HCC has a poor prognosis and treatment varies depending on the specifics of the tumor and overall health of the patient. The incidence of HCC is highest in Asia and sub-Saharan Africa where hepatitis B infection is endemic, but it is also increasing in the United States and other developing countries due to an increase in hepatitis C virus infections.
Again, there might and will be mistakes but this can be a helpful tool to get a short and concise summary of a scientific text or study beyond what is written in the abstract. For example, you can also try to put the DOI/link and title of a study as input. Please be aware, that this will not work for every link, especially if the study is more recent.
How to Use ChatGPT to Concentrate Text in Scientific Writing
Almost everybody, that has published anything in the scientific world or even has presented on a scientific congress has faced ‘word limits‘. Maybe it is the abstract, that can only have 200 words – but your study is soo extensive. Or you want to submit your paper to a journal, that has a word limit of 2400 for the manuscript body – but your manuscript has 3500…
The approach is similar to the one above but now you need to tell ChatGPT that you want to reduce the text to a specific length or “by 10%”. Although this can work quite well, it will sometimes ignore your specifications and write the output significantly longer or shorter.
Furthermore, this approach can have some privacy issues. You can´t know, how the data you put into the text field is collected and processed. I strongly advise not to put sensitive or protected data into the chat box.
3. Paraphrasing and Simplifying
Although summarizing and concentrating text will also result in rephrasing sentences, you can use ChatGPT to adjust the complexity or tone of a text. Maybe you have written a scientific article but you now want to make a presentation for a broader audience. In this case, you might want to reduce scientific terms and implement an easier language.
Lets say you have the following definition for hepatocellular carcinoma:
Hepatocellular carcinoma (HCC) is a neoplastic proliferative disorder of the liver characterized by the malignant transformation and aberrant growth of hepatocytes, which are the primary functional cells of the liver parenchyma, leading to the development of a tumor with the potential for local infiltration, regional metastasis, and systemic dissemination, resulting in significant morbidity and mortality. This pathological condition is thought to arise from a complex interplay of genetic and environmental factors, including but not limited to chronic viral hepatitis, alcohol abuse, non-alcoholic fatty liver disease, and exposure to hepatotoxic agents, which promote the accumulation of genetic mutations, epigenetic alterations, and chromosomal instability within the hepatocyte population, ultimately leading to the dysregulation of multiple signaling pathways involved in cell growth, survival, and differentiation.
You can tell ChatGPT to take the text above as input and “re-write it using shorter sentences and simpler language“. In this case, I got the following output:
ChatGPT:
Hepatocellular carcinoma (HCC) is a type of liver cancer that happens when liver cells grow out of control and form a tumor. This can cause serious health problems and can even be deadly.
Several things can increase the risk of getting HCC, including chronic viral hepatitis, alcohol abuse, and exposure to harmful chemicals. These things can damage the liver and make it more likely for cancer to develop.
This can be especially useful for scientific communications that need to be suitable for a broader audience. I cannot emphasize this enough, please read the output carefully and use it only for orientation and content input.

4. Identifying Key Words and Key Points
Another helpful application can be the identification of key words and key points for your study. Lets talk about how to use ChatGPT to identify key words and key points in scientific writing:
Many scientific jounals require you to provide key words in addition to the abstract. Furthermore, key points can be helpful to communicate your key findings and they might also be required by some journals.
Lets say, you wrote a manuscript for the following study: “In-patient care trends in peripheral artery disease in the German healthcare system over the past decade“
You already wrote your manuscript but now you also need some key words and key points. In this case, the journal also requires your key words to be compatible with the MeSH (Medical Subject Headings) database.
Example on How to Use ChatGPT for Generating MeSH Key Words
You could paste your abstract to ChatGPT as input and ask something like this: “I have this abstract: [paste abstract]. Please give me 5 key words and 3 key points. Make the key words MeSH compatible.“
Here I got this output:
ChatGPT:
Sure, here are five potential keywords that are compatible with the PubMed MeSH (Medical Subject Headings) database:
- Peripheral Arterial Disease
- Hospitalization/trends
- Comorbidity
- Revascularization
- Health Care Costs
Please note that these MeSH terms may have subheadings that can be used to refine the search further. Additionally, there may be other MeSH terms that are relevant to your study that are not included in this list.
Here are three potential key points for your study:
- Hospitalizations due to peripheral artery disease have increased over the past decade, with a notable rise in comorbid patients.
- The average cost per hospitalization has increased over time, reflecting the growing burden of peripheral artery disease on healthcare systems.
- Endovascular approaches, such as percutaneous transluminal angioplasty, are becoming more common for treating peripheral artery disease, particularly in smaller vessels below the knee.
As you are the expert of your study, you might find some key words more suitable and some key points not fitting. However, this approach can be a good start and facilitate your progress in scientific writing.
5. Creating Figures and Graphs
ChatGPT can be a good ressource and assistance during the generation of figures and graphs for your scientific study. In this paragraph we want to talk about how to use ChatGPT to create figures and graphs in scientific writing. Starting from getting ideas to the actual generation of figures, there are several steps where you can utilize ChatGPT.
How to Use ChatGPT to Get Ideas for Graphs in Scientific Writing
Let´s start with which graphs to use. If you have enough information for your study, you can ask ChatGPT for ideas for graphs. For example, given the information (abstract) of the prompt before, you could ask: “What would be great graphs for the study mentioned above?“
ChatGPT:
Based on the information provided in the abstract, here are a few graphs that could be useful for this study:
- Line graph showing trends in the number of hospitalizations for peripheral artery disease over time (2009-2018). This graph could highlight the increase in hospitalizations over the decade.
- Bar graph comparing the frequency of different comorbidities among patients hospitalized for peripheral artery disease. This graph could help identify the most common comorbidities associated with the disease.
- Stacked bar graph comparing the frequency of different revascularization procedures performed for peripheral artery disease, such as percutaneous transluminal angioplasty, bypasses, and endarterectomies. This graph could show the shift from surgical to endovascular approaches over the decade.
- Scatter plot showing the relationship between hospitalization costs and patient comorbidities or severity of peripheral artery disease. This graph could help identify factors that contribute to higher hospitalization costs.
- Box plot showing the distribution of the linear van Walraven score among patients hospitalized for peripheral artery disease over time. This graph could highlight the increasing severity of cases over the decade.
These are just a few ideas for potential graphs based on the information provided in the abstract. The most appropriate types of graphs may depend on the specific research questions and data available for the study.
You will probably already have some ideas that you want to illustrate in your paper, but using this prompt will give you some concrete suggestions in no time. Since we tend to use similar approaches (and similar numbers) in our studies, this can also be a good source of new ideas to help broaden your horizons.

How to Use ChatGPT to Create Graphs in Scientific Writing
If you have ever written a scientific paper, you have probably been at the point where you wanted to illustrate your data with a graph or plot. There are several options and software out there to create high quality graphs and this will not be a step-by-step guide on how to use different software. From Excel to SPSS to Python (Matplotlib) and R (ggplot2), many tools can be used and will most likely produce acceptable graphs. However, both Matplotlib (Python) and gglplot2 (R) are very powerful and able to generate excellent and extremely versatile visualizations of your data. The downside is that you now have to learn how to program in those languages.
Now what does that have to do with ChatGPT you might ask? If you ever worked with Python or R, you will have come to the point where you wanted or needed to tweak your plot in some way. To do this, you read through guides, forum posts and stack overflow and ultimately found the line of code that did just what you wanted.
However, you may have never used Python or R before and feel overwhelmed by the thought of learning a programming language just to create some plots. Whether you are a beginner of this approach or you already found yourself struggeling while trying to adjust some of your figures, ChatGPT is here to help.
Example on How To Use ChatGPT to Create a Scientific Graph
As a novice, you can ask ChatGPT on how to generate a graph in any programming language. For example:
“How to generate a scatter plot in R using ggplot2?“
In this case, you will get specific instructions with annotations and even readily written code to use to generate your high-quality figure.
ChatGPT:
library(ggplot2)# create a data framedf <- data.frame(x = c(1, 2, 3, 4, 5), y = c(2, 4, 5, 7, 9))# initialize the plotggplot(data = df, aes(x = x, y = y)) + # add a layer for the scatter plot geom_point() + # add a title and axis labels labs(title = "Scatter Plot", x = "X Axis", y = "Y Axis") + # set the x and y axis limits xlim(0, 6) + ylim(0, 10) + # customize the theme theme_classic()

Naturally, you need some knowledge on how to install and use R. However, with just basic knowledge you can kickstart the creation of your first high-end scientific graphs. And be aware that you can just ask for any modification.
Maybe you want to add a regression line to your plot: “How to add a regression line to this graph?“
ChatGPT:
library(ggplot2)# create a data framedf <- data.frame(x = c(1, 2, 3, 4, 5), y = c(2, 4, 5, 7, 9))# initialize the plotggplot(data = df, aes(x = x, y = y)) + # add a layer for the scatter plot geom_point() + # add a title and axis labels labs(title = "Scatter Plot", x = "X Axis", y = "Y Axis") + # set the x and y axis limits xlim(0, 6) + ylim(0, 10) + # customize the theme theme_classic() + # add a linear regression line geom_smooth(method = "lm")

The detailed descriptions in the output of ChatGPT will help you to modify your code yourself. Before you know it, you will be able to create beautiful and expressive plots on your own, and you will use ChatGPT for more advanced questions.
Of course, you will need to learn how to import your data, install packages, manage data frames, and much more. But with the help of ChatGPT, the learning curve of any programming language can be significantly flattened enabling everybody to create lovely scientific graphs and plots.
6. Alternative Phrases and Synonyms
If you´re writing about a certain topic, you may find yourself using the same phrases over and over again. Not only does this create a somewhat monotonous aspect, but it also limits how your manuscript can be perceived. For example, if you´re always using the term “patients with oncologic diseases” in your paper that analyzes something about oncology patients, you are missing something out. Same thing is true if you´re writing a rebuttal letter and you start your comments to the reviewers always the same way.
Try asking ChatGPT for alternative phrases or synonyms. This will not only spice up your text, but also broaden your horizons for future scientific writing.
Just paste your overused phrase into ChatGPT and ask for (lets say 5) alternative phrases or synonyms. In no time you will have a good basis to use in your manuscript.
Happy writing!
Some links on this site are affiliate links (*). If you choose to buy a product using these links, I might get a commision for this purchase. For you, this does not change the price.
