Modern medicine is often seen as a purely scientific endeavor: precise, objective, and grounded in biological facts. This idea has been remarked in recent years, since it has entered a new era: one driven not just by laboratory discoveries, but by data [1]. But we cannot forget the anthropological perspective that reminds us that medicine is not purely objective or universal, but shaped by social norms, historical contexts, and institutional power [2]. What we define as disease, how symptoms are interpreted, and which treatments are accepted influence research, diagnosis, and patient care in profound ways.

Building on this foundation, the concept of “big data in biomedicine” highlights how massive and diverse datasets are reshaping the life sciences. Diverse datasets include data from genomics and clinical records to imaging and real-world patient data. We have to emphasize both the promise and the difficulty of this transformation: while large-scale data enable more precise diagnostics and the development of personalized medicine, they also introduce major challenges in data integration, storage, and interpretation [1].

Subsequent work in biomedical data science expands this view by stressing that data alone is not sufficient. Value lies in interoperability, standardization, and analytical capacity [3]. Machine learning and deep learning are now central tools for identifying patterns across heterogeneous datasets, improving prediction and clinical decision-making, and accelerating drug discovery. However, these systems depend on data quality and representation. [4]

“Bias, inequality, and data representation remain major challenges in data-driven healthcare.”
Baldi (2018)

Importantly, biomedical data science is a socio-technical system. Data are shaped by institutional practices and cultural assumptions, influencing how knowledge is produced and applied. As automated decision-making becomes more prevalent, questions of transparency, trust, and clinical authority become increasingly relevant. Overall, big data is driving a shift toward predictive and personalized medicine, but its success depends on balancing computational innovation with ethical, social, and cultural awareness. [1]

These developments also intersect with lived experiences of illness. Patients and practitioners often approach disease differently: clinicians may prioritize measurable symptoms and clinical outcomes, while patients navigate illness through personal narratives, emotions, and social relationships. Bridging this gap is essential for more compassionate and effective care.

At a broader level, global inequalities continue to shape access to biomedical innovation. Advanced technologies may exist, but economic, political, and geographic factors determine who benefits from them and who is left behind [3].

Another emerging dimension of biomedicine is the growing role of deep learning and artificial intelligence. These technologies are increasingly used to analyze medical images, predict disease risks, and assist in clinical decision-making. While they promise greater accuracy and efficiency, they also raise important anthropological questions. Who designs these systems, and whose data are they trained on? Biases embedded in datasets can lead to unequal outcomes, reinforcing existing disparities in healthcare [5]. Moreover, the reliance on algorithmic insights can shift the relationship between doctor and patient, introducing new forms of authority and trust. From an anthropological perspective, deep learning is not just a technical innovation—it is a cultural force that reshapes how knowledge, expertise, and care are understood in modern medicine.

“The future of biomedicine lies in combining computational advances with ethical and anthropological awareness.”

Ultimately, an anthropological view of biomedicine challenges us to rethink what we mean by “health” and “healing.” It encourages a more holistic approach—one that values not only scientific knowledge but also cultural understanding and human connection. This perspective does not reject biomedicine; instead, it enriches it by helping build healthcare systems that are not only effective, but also equitable and humane.

References

[1] Costa, F. F. (2013). Big data in biomedicine. Drug Discovery Today, 19(4), 433-440.
(https://doi.org/10.1016/j.drudis.2013.10.012)

[2] Lock, M., & Nguyen, V. (2018). An Anthropology of Biomedicine.
(https://bvbr.bib-bvb.de:443/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=020426555&sequence=000002&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA)

[3] Callahan, T. J., Tripodi, I. J., Pielke-Lombardo, H., & Hunter, L. E. (2020). Knowledge-Based Biomedical Data science. Annual Review Of Biomedical Data Science, 3(1), 23-41. (https://doi.org/10.1146/annurev-biodatasci-010820-091627)

[4] Baldi, P. (2018). Deep Learning in Biomedical Data Science. Annual Review Of Biomedical Data Science, 1(1), 181-205.
(https://doi.org/10.1146/annurev-biodatasci-080917-013343)

[5] Alarcón-Soto, Y., Espasandín-Domínguez, J., Guler, I., Conde-Amboage, M., Gude-Sampedro, F., Langohr, K., Cadarso-Suárez, C., & Gómez-Melis, G. (2019). Data Science in Biomedicine. arXiv (Cornell University).
(https://doi.org/10.48550/arxiv.1909.04486)