V Sunila, Kurian Jais, Mariam Mathew Liny, Mathew Pratheesh, John Dary, Joseph Jeena
Research Department of Statistics, Nehru Arts and Science College Kanhangad, Kanhangad, IND.
Department of Mathematics, St Stephen's College Uzhavoor, Uzhavoor, IND.
Cureus. 2024 Sep 9;16(9):e69033. doi: 10.7759/cureus.69033. eCollection 2024 Sep.
Stochastic models play a pivotal role in disease prediction by accounting for randomness and uncertainty in biological systems. This study offers a visualization of trends in the application of stochastic models for disease prediction from 1990 to 2024, based on a bibliometric analysis of Scopus data. Key findings reveal a significant growth in research post-2014, largely driven by global health challenges like COVID-19. Despite these advancements, gaps remain in applying these models to non-communicable diseases and low-resource settings. By integrating computational techniques like machine learning, stochastic models hold promise for improving predictive accuracy. This study highlights the need for further international collaboration and interdisciplinary research, offering practical insights for researchers and public health professionals aiming to enhance disease prediction and intervention strategies.
随机模型通过考虑生物系统中的随机性和不确定性，在疾病预测中发挥着关键作用。本研究基于对Scopus数据的文献计量分析，对1990年至2024年随机模型在疾病预测中的应用趋势进行了可视化展示。主要研究结果表明，2014年之后研究显著增长，这主要是由COVID-19等全球卫生挑战推动的。尽管取得了这些进展，但在将这些模型应用于非传染性疾病和资源匮乏地区方面仍存在差距。通过整合机器学习等计算技术，随机模型有望提高预测准确性。本研究强调了进一步开展国际合作和跨学科研究的必要性，为旨在加强疾病预测和干预策略的研究人员和公共卫生专业人员提供了实用见解。
