Machine Learning Techniques Used for the Identification of Sociodemographic Factors Associated With Cancer: Systematic Literature Review

Background: Cancer remains one of the foremost causes of mortality globally, with nearly 10 million deaths recorded by 2020. As incidence rates rise, there is growing interest in leveraging machine learning (ML) to enhance prediction, diagnosis, and treatment strategies. Despite these advancements, insufficient attention has been directed towards the integration of sociodemographic variables, which are crucial determinants of health equity, into ML models in oncology. Objective: This review investigates the use of machine learning techniques in the analysis of sociodemographic factors associated with cancer. Specifically, it seeks to map current research endeavors by detailing the types of algorithms employed, sociodemographic variables examined, and validation methodologies utilised. Methods: We conducted a systematic literature review in accordance with the PRISMA guidelines. Searches were executed across seven databases, focusing on primary studies that employed machine learning to investigate the relationship between sociodemographic characteristics and cancer-related outcomes. The search strategy was informed by the PICO framework, and a set of predefined inclusion criteria was used to screen the studies. The methodological quality of each study was assessed. Results: Of the 568 studies examined, 19 satisfied the inclusion criteria. The majority of studies have employed supervised machine learning techniques, with Random Forest and XGBoost being the most commonly utilised. Frequently analysed variables included age, sex, education level, income, and geographic location. Cross-validation is the predominant method for evaluating the model performance. Nevertheless, the integration of clinical and sociodemographic data is limited, and efforts toward external validation are rare. Conclusions: Machine learning (ML) holds significant potential for discerning patterns associated with social determinants of cancer. However, research in this domain remains fragmented and inconsistent. Future investigations should prioritize the integration of contextual factors, enhance model transparency, and bolster external validation. These measures are crucial for the development of more equitable, generalizable, and actionable ML applications for cancer care.