I have to confess I am very Trekkie. In general I am a SCIFI fan but Star Trek is the apple of my eyes. So I was so very happy when some years ago I was given by my lovely husband a fascinating book for my birthday called “Treknology: The Science of Star Trek from Tricorders to Warp Drive” (1). It is amazing how many of the “treknology” has come to be real and useful. I would so, dedicate this section of the blog to technology, some of them would have little to do with Star Trek by it is OK. By the way here a link to the Journal of Applied Treknology (2).
And I want to beging talking about Digital Twins, a concept constantly present in Star Trek from the simulation of battles or the holodek to the medical simulations.
Several years ago already, I found this fascinating concept: Digital Twins. As in planning for example a building and programing a “digital” building exactly the same as the one planned, except for the fact that it was not real but in a digital context. But the programing included all the necesary variables to make it useful to test the twin in diferent situations, a twister, an earthquake, etc. Thus you could, at least in theory, have a good idea of what would happen to the bulding in the real world.
Obviously one of the most amazing uses would be construct digital twins of our patients and check out treatments or interventions first on them. Complex, I know, but lets play with this idea for a moment.
What striked me the most is how physical the perspective was in defining the Digital Twins. Therefore, I was missing the Social Determinants of Health which have an incredible influence in survival and in quality of life. I am a specialist in Preventive Medicine, Public Health and Healthcare Management so my viewpoint is very public health-driven.
Undoubtely, the omic sciences are paramount in precision medicine, however if we obviate the social determinants we will be preparing our twins to fail.
Another amazing thing is the unexistence of a clear consensus in a framework of social determinants of health and how to measure them. Do not misunderstand me, there is a lot of literature about SdoH but we do not agree most of the time among each other to define what to include or not in a sistematic analisis of SdoH. Perhaps this is the main handicap for the inclusion of SdoH in most of our innovative thinking. Or perhaps that even if they were inequivocally described and proven in 1974 in the Lalonde’s report (3) we still, as community, do not really believe in their influence in health, at least in rich countries. I leave a link of a review of the Lalonde’s report (4).
Could be dificult to grasp but the postal code can determine the patients commintment to the treatment plan. Education, age, culture, sex, gender, economic status, legal situation, etc may determine if the patient will or will not follow treatment adquately. Moreover, it could signal other problems on the treatment impacto on health. As an example, a body well cared for, with healthy food, exercise, and intellectual stimuli would react differently to lots of treatments, and curious enough the food we choose to eat is never enterely our decision. So, there are people that will be eating unhealthy food because they can no afford another kind, or they do not understand de difference.
Do not misunderstand me, there are several iniciatives on this issue. I have tracked some of them. Funny enough the first step is knowing how to introduce the variables in the system. Thus, there is the need to know which variable should be included and how technically can we do that.
The World Health Organization (WHO) among other international institutions (5), are identifying and stablishing an standardized taxonomy of the social determinants of health. On the other hand, initiatives such as the Gravity Project (6) that develop data standards to represent individual-level SDOH information in digital platforms. On the other, hand, the project relies on the international standards, the FHIR (Fast Healthcare Interoperability Resources), where the variables are structured as Observation (such as housing or food data) and Condition (such as the social risks) helping on the operability of the data (7). While designing a digital twin this will allow to translate their social determinants into code, hopefully in real time.
But there is a need middle man that help extracting the variables from the sources, such as the Electronic Health Records (8).
However, there is a need for a specific framework on a holistic “human-in-environment” model. That is, not only translate a biological entity into a digital twin but also its contex and habitat. Therefore, the need to stablish a consensual, if posible, Social Digital Twins Framework. Curiously enough in the works about Smart Cities and City Digital Twin it has been as well detected de need to include social determinants to increase the accuracy of the twin (9).
An international multistakeholder framework to integrate SdoH in clinical practice and in digital twins will target the engineering pipeline directly to address algorithmic bias. Will provide rules for programmers to build mathematical «fairness constraints» into machine learning code, preventing biased digital twin simulations from making harmful clinical assumptions or recommendations. Taking into account if a patient suffers from lower digital literacy, a lack of adequate biometric wearable coverage, social networks, postal code, sex and gender, socioeconomic status, etc.
In 2024 scoping review (10) was published analysing some of these aspects.
So, nowaday the key point continous to be, how do we include SDoH in digital twins programming to have a real twin of our patient, with an accuracy decent enough to make trustable predictions? Or are we setlling for a more or less prediction when our patient’s health is at stake. What do tyou think?
We shall talk about ethical issues and equity of digital twins in another post if you like. Have a great day.
-
Siegel E, [author] Ransom CR [editor] Treknology: The Science of Star Trek from Tricorders to Warp Drive. Dallas (TX): BenBella Books; 2017.
-
Journal of Applied Treknology. Journal of Applied Treknology [Internet]. Disponible en: https://www.treknology.org/
-
Lalonde, M. (1974). A new perspective on the health of Canadians. Ottawa, ON: Minister of Supply and Services Canada. Retrieved from Public Health Agency of Canada website: http://www.phac-aspc.gc.ca/ph-sp/pdf/perspect-eng.pdf
-
Frohlich KL. From the Lalonde Report to the structural determinants of health. Can J Public Health. 2025 Sep;116(Suppl 2):56-58. doi: 10.17269/s41997-025-01070-0. Epub 2026 Jan 5. PMID: 41490956; PMCID: PMC12770164. https://pmc.ncbi.nlm.nih.gov/articles/PMC12770164/pdf/41997_2025_Article_1070.pdf
-
World Health Organization. Global research agenda on social determinants of health [Internet]. Geneva: WHO; 2024. Disponible en: https://www.who.int/publications/i/item/9789240088320
-
The Gravity Project. Overview [Internet]. Washington (DC): The Gravity Project. Disponible en: https://thegravityproject.net/overview/
-
HL7 International. FHIR Implementation Guide: SDOH Clinical Care [Internet]. Disponible en: https://build.fhir.org/ig/HL7/fhir-sdoh-clinicalcare/en/
-
Patel SB, Nguyen NT. Creation of a Mapped, Machine-Readable Taxonomy to Facilitate Extraction of Social Determinants of Health Data from Electronic Health Records. AMIA Annu Symp Proc. 2022 Feb 21;2021:959-968. PMID: 35308929; PMCID: PMC8861691 https://pmc.ncbi.nlm.nih.gov/articles/PMC8861691/) )
-
Yossef Ravid, B. and Aharon-Gutman, M. (2022). The Social Digital Twin:The Social Turn in the Field of Smart Cities. Environment and Planning B: Urban Analytics and City Science, 50, 1455 – 1470. https://journals.sagepub.com/doi/10.1177/23998083221137079
-
Katsoulakis, E., Wang, Q., Wu, H. et al. Digital twins for health: a scoping review. npj Digit. Med. 7, 77 (2024). https://doi.org/10.1038/s41746-024-01073-0 https://www.nature.com/articles/s41746-024-01073-0
0 comentarios