Cancer is the second leading cause of death in developed countries, presenting a significant barrier to global life expectancy improvements. According to the World Health Organization (WHO), in 2023, cancer was one of the top two causes of mortality before the age of 70 in 112 out of 183 countries and ranked third or fourth in 23 other nations [1]. The global incidence of cancer has seen a steady increase over recent decades, with cancer-related deaths rising by over 25 % since the 1990s, and projections indicating more than 23 million new cases annually by 2030 [2], [3].

Cancer arises from both acquired (somatic) and inherited (germline) DNA mutations. While most cancers are attributed to somatic mutations accumulated over a person´s lifetime, 5–10 % of cancers result from germline mutations [4], [5], and approximately 20 % of cancer patients have a familial history of the disease [6]. These figures suggest the existence of hereditary factors that heighten the likelihood of cancer development, potentially affecting multiple family members. Hereditary cancer syndromes (HCS) are typically associated with monogenic, highly penetrant mutations that confer an elevated risk of developing cancer at an early age and often predispose individuals to multiple malignancies [7].

Despite the global significance of hereditary cancer, Latino and other admixed populations remain underrepresented in genetic research. Yadav et al. (2021) advocate for the inclusion of ethnicity in risk management strategies for hereditary cancer [8]. This issue is particularly pertinent to Colombia, where ethnic diversity – stemming from an admixture of Native Americans, Europeans and Sub-Saharian Africans, along with high rates of endogamy in certain regions [9], [10], contributes to a distinct genetic landscape. Such genetic factors increase the occurrence of consanguineous unions and the prevalence of homozygous harmful variants, especially relevant in recessive inheritance patterns [11].

Recent advances in cancer genetics have led to the integration of genetic testing into routine oncological practice. By identifying the 5–10 % of cancer cases that are attributable to inherited mutations, precision medicine can enable more targeted surveillance, prevention, and therapeutic approaches [12]. However, numerous challenges remain in the clinical implementation of genetic testing and its integration with other medical data. Since 2019, the Omic Science Center (Centro de Ciencias Ómicas – CCO, in Spanish) at Sura Colombia, a Healthcare Insurance Company in Colombia and Latin America, has utilized a 30-gene panel aligned with the National Comprehensive Cancer Network ® (NCCN®) guidelines to detect pathogenic variants linked to hereditary cancer syndromes. Until 2022, however, genetic reports were provided in unstructured PDF format, lacking the necessary infrastructure for efficient data processing and analysis.

The absence of standardized reporting and the predominance of unstructured data represent substantial obstacles to population-wide genomic analyses. In this study, we leverage advanced data science techniques to extract and process genetic data from these unstructured reports, integrating them with clinical and sociodemographic information. The objective is to perform a comprehensive genetic and clinical characterization of the Colombian population, with a particular focus on SURA Colombia patients. This article presents the findings of a retrospective analysis of 1377 patients across Colombia, employing data science methodologies to explore hereditary cancer patterns and assess the role of Next-Generation Sequencing (NGS) in precision medicine for hereditary cancer. The study also highlights the potential of integrated data-driven approaches to enhance the understanding of hereditary cancer and inform future clinical decision-making.