Artificial Intelligence and Machine Learning in Cancer Research: A Systematic and Thematic Analysis of the Top 100 Cited Articles Indexed in Scopus Database

To the Editor,

We appreciate the insightful comments. We want to clarify and acknowledge that the missing keyword “cancer” under the “Search Strategy” in the current study was an omission during article writing; however, “cancer” was included as part of our search keywords when we performed the search query. The developed searched query for the study was done using “Cancer” along with other keywords to retrieve all the specific documents using the following terms: Title (Cancer* or Benign neoplasms* or malignancy* or malignant neoplasms* or neoplasia neoplasm* or neoplasms* or benign* or tumors*), and (artificial intelligence* or machine learning* or deep learning* or convolution neural network* or neural network* or random forest* or support vector machine* or fuzzy logic* or computer vision* or automatic programming* or speech understanding* or autonomous robots* or intelligent tutoring* or intelligent agents* or neural network* or voice recognition* or text mining*). ¹

In response to the second issue raised, we performed the search using the “Boolean” search method, a standard procedure for screening and merging keywords. We believe that this approach was succinctly explained in our methodology. Further in the study, the keywords “Benign neoplasms* or malignancy* or malignant neoplasms* or neoplasia neoplasm* or neoplasms* or benign* or tumors*” were reported in the extracted top 100 most cited articles list. ² For example, in the supplementary Table S1, “Benign” appeared in 7% of the articles, followed by malignancy in 4% and malignant in 7%. Moreover, “Cancer” was mentioned in 62% of the articles. Since only top-cited articles were included in our analysis, the non-inclusion of some articles was due to the low citation score.

We also acknowledge the comment regarding the uniqueness of our current study method. To the best of our knowledge, our article is the first to provide a detailed overview of the most cited empirical evidence in AI and ML adoption in cancer research, which could aid in the design of future studies. In addition, we used bibliometric methods, followed by systematic and thematic analysis. Our articles' searched keywords and terms were uniquely designed to capture all previously published articles indexed in the Scopus database within the time frame specified in our manuscript.

Kind regards