Progress and current trends in prediction models for the occurrence and prognosis of cancer and cancer-related complications: a bibliometric and visualization analysis

Abstract

Objective: Prediction models, which estimate disease or outcome probabilities, are widely used in cancer research. This study aims to identify hotspots and future directions of cancer-related prediction models using bibliometrics.

Methods: A comprehensive literature search was conducted in the Science Citation Index Expanded (SCIE) from the Web of Science Core Collection (WoSCC) up to November 15, 2024, focusing on cancer-related prediction models research. Co-occurrence analyses of countries, institutions, authors, journals, and keywords were conducted using VOSviewer 1.6.20. Additionally, keyword clustering, timeline visualization, and burst term analysis were performed with CiteSpace 6.3.

Results: A total of 1,661 records were retrieved from the SCIE. After deduplication and eligibility screening, 1,556 publications were included in the analysis. The bibliometric analysis revealed a consistent annual increase in cancer-related prediction model research, with China and the United States emerging as the leading contributors. The United States, England, and the Netherlands had the strongest collaborative networks. The most frequent keywords, excluding "prediction model" and "predictive model", included nomogram (frequency=192), survival (191), risk (121), prognosis (112), breast cancer (103), carcinoma (93), validation (87), surgery (85), diagnosis (83), chemotherapy (80), and machine learning (77). Besides, the timeline view analysis indicated that the "#7 machine learning" cluster was experiencing vigorous growth.

Conclusion: Cancer-related prediction models are rapidly advancing, especially in prognostic models. Emerging modeling techniques, such as neural networks and deep learning algorithms, are likely to play a pivotal role in current and future cancer-related prediction model research. Systematic reviews of cancer-related predictive models, which could help clinicians select the optimal model for specific clinical conditions may emerge as potential research directions in this field.

Keywords: bibliometrics; cancer; hotspots and trends; machine learning; prediction models; visualization analysis.

Figure 1

The process of bibliometric analysis.

Figure 2

Literature screening process.

Figure 3

Distribution of publication types and annual publication volume. (A) Annual publication volume and citations of publications; (B) Distribution of publication types.

Figure 4

Distribution of countries/regions and institutions. (A) A visual mapping of the collaborative networks among countries/regions in relevant publications. Each circle represents a country/region, with the size of the circle proportional to the number of publications; larger circles imply a greater number of publications. (B) A visual mapping of the collaborative networks among institutions. Each circle represents an institution, and the size of the circle proportional to the number of publications; larger circles imply a greater number of publications.

Figure 5

Distribution of authors and journals. (A) Visual mapping of the collaboration networks among authors. Each circle represents an author, and a larger circle indicates more publications. (B) Visual mapping of the journals. Each circle represents a journal, and a larger circle indicates more publications.

Figure 6

Co-occurrence and cluster of keywords. (A) VOSviewer keyword co-occurrence map: Each circle represents a keyword, and a larger circle indicates a higher number of publications associated with that keyword. To ensure readability, only keywords with a frequency of occurrence ≥20 are visually mapped in the VOSviewer keyword co-occurrence map. (B) CiteSpace keyword clustering map: Different colored areas represent different clusters of keywords.

Figure 7

Keyword burst and timeline. (A) CiteSpace burst term map: Burst terms typically represent emerging research directions or shifts in field hotspots. The red segment indicates the burst period of the keyword (i.e., the timeframe when its frequency surged abruptly), while the blue segment corresponds to conventional active periods before or after the burst. Strength refers to the Burst Strength — the higher the value, the more rapidly the attention to the keyword has grown. (B) CiteSpace timeline map: Temporal analysis of keyword clusters, highlighting longitudinal trends, and pivotal milestones. The horizontal axis represents years, while the vertical axis displays keyword clusters. Keywords within the same-color cluster are thematically related. Connecting lines indicate co-occurrence relationships between keywords, and thicker lines signify stronger associations.

Figure 8

Density visualization and timeline of machine learning. (A) VOSviewer keyword density visualization: Each circle represents a keyword, and a brighter circle indicates a higher number of publications associated with that keyword. To ensure readability, only keywords with a frequency of occurrence ≥5 are visually mapped in the density visualization. (B) CiteSpace timeline map: Temporal analysis of keyword clusters, highlighting longitudinal trends, and pivotal milestones. The horizontal axis represents years, while the vertical axis displays keyword clusters. Keywords within the same-color cluster are thematically related. Connecting lines indicate co-occurrence relationships between keywords, and thicker lines signify stronger associations.