wrangler Digital Twins Healthcare and Nutrition

Digital Twins Healthcare & Nutrition

Oct 21, 2024 1:47pm

 

Digital twins has taken the healthcare and nutrition industries by storm. Discover how these virtual replicas of physical objects or systems reshape how we approach patient care and personalized nutrition.


What are Digital twins?

Digital twins have been around for a while, but it is only in recent years that it has gained significant attention. A digital twin is a virtual replica of a physical object or system, which can be used to simulate its behaviour and performance in real time with the ultimate goal of making better decisions.

Digital Twin technology has been applied across several industries including transport, manufacturing as well as beauty and fashion according to a recent publication by McKinsey. Think of trying on that shirt without getting undressed, seeing what a hairstyle would look on you before going all-in, or even using Google maps as a digital replica of the physical earth. In essence, digital twin technology is already here and integrated into our daily lives without it being a common term discussed at the dinner table.  In the context of health, digital twins are being used to create personalized models of patients, which can help doctors and researchers better understand their conditions and develop more effective treatments.

A digital twin is not simply a digital clone of the physical system. Instead, it’s an intelligent counterpart.”
Yu et al - 2023


How Digital Twins Work 

Digital twins are created by combining data from various sources, such as medical records, genetic information, and wearable devices. This data is then fed into a computer model, which creates a virtual representation of the patient's body and its functions. The model can be used to simulate different scenarios, such as how a particular drug will affect the patient, or how changes in lifestyle will impact their health. 

One of the key advantages of digital twins is that they can be updated in real-time, based on new data. This means that doctors and researchers can monitor the patient's condition and adjust their treatment plan accordingly. For example, if a patient's blood sugar levels start to rise, the digital twin can alert the doctor, who can then recommend changes to their diet or medication. 

 

The Role of Digital Twins in Health & Prevention 

Prevention is always better than cure, and digital twins have the potential to revolutionize the way we approach healthcare. By creating personalized models of patients, doctors, practitioners and researchers can identify potential health risks before they become serious problems. Chronic diseases such as Cardiovascular and Diabetes are large contributors of healthcare expenditure, yet technology has been sorely lacking in providing accurate and real-time information considering the individual responses vary greatly.  

The advent of big data and computational power has meant that the opportunity to provide real-time feedback, supported by a practitioner is becoming a reality. Digital twin technology could predict the likelihood of a patient developing diabetes based on their genetics, lifestyle, and other factors. This information could then be used to develop a personalized prevention plan, which could include changes to their diet, exercise routine, and medication.

A recent scoping review outlined numerous and emerging applications of digital twins in healthcare especially in psychiatry and behaviours (Katsoulakis et al 2024) 

 

The Relevance of Digital Twins in Personalized Nutrition

The science: Personalized nutrition is an emerging field that aims to develop customized diets and supplements based on an individual's unique needs, health goals and preferences.

Numerous studies have demonstrated that individual responses to identical meals vary greatly in terms of post-meal glucose and triglycerides. These differences can be attributed to factors such as genetics, microbiome composition, meal composition and timing of meals (Zeevi et al 2015, Berry et al 2020, De Catarina et al 2020) 

Digital twins have the potential to revolutionize the nutrition field by providing doctors and nutritionists with a more accurate picture of the patient's nutritional needs and response. By creating a virtual model of the patient's body and its functions, digital twins can identify potential deficiencies or imbalances in their diet, and recommend changes to improve their health using  a collection of different data points such as diet, physical activity, BMI, age, blood levels.

Wageningen university recently completed a Digital twin project in metabolic health. The aim of the project called “Me, my diet and I” was to develop a personalized digital twin that can predict changes to an individual’s blood values such as blood sugar (glucose) and blood fats (Triglycerides) to  provide dietary advice through an App with the goal to reduce cardiometabolic disease risk. The multidisciplinary team of researchers believe that the advantage of a digital twin lies in the fact that personalized dietary advice can be automated without the initial or immediate input of a healthcare professional such as a dietitian (Knibbe et al 2022).

This would, I assume, potentially help to increase an individual’s self efficacy before contacting their practitioner.

The Diabetes Digital Twin Study

One of the most promising applications of digital twins in healthcare is in the field of diabetes research. In 2019, Paramesh Shamanna and his team at the University of Warwick published a study on the use of digital twins to predict the progression of type 2 diabetes. The study used data from over 1,000 patients, including their medical history, genetics, and lifestyle factors. The researchers then created personalized digital twins for each patient, which were used to simulate the progression of their disease over time.

The results of the study were impressive. The digital twins were able to accurately predict the progression of diabetes in over 80% of cases, and they identified several key risk factors that were previously unknown. This information could be used to develop more effective prevention and treatment strategies for diabetes patients.
 

"The health outcomes of “actual digital twins” could be utilized to formulate basic prognostic models and actions that are predicted to be more relevant to the person in question and lead to improved outcomes compared with current practices.” Gkouskou et al 2020



 

Digital Twins in Personalized Nutrition

 

Detecting and treating malnutrition in hospitals 

Personalized nutrition crosses the spectrum from prevention to treatment. With this in mind, it is well known that malnutrition is a huge problem in healthcare, with around 20 - 50% of patients, especially the elderly living in the community, admitted to hospital already being malnourished, according to Bellanti et al (2022) and many other publications including the nutrition organization ESPEN. 

Malnutrition can worsen health outcomes and modify the response to treatments, which is why early detection is crucial. Over the years, many screening tools have been developed, such as GLIM, MUST, SNAQ to screen for malnutrition on admission and on the ward, but many patients still slip through the net especially on hospital discharge. Nutritional therapy needs to be personalized for every patient based on their medical history, nutritional status. This may require specialized diets, nutritional supplements or the instigation of enteral or parenteral nutrition. 

A Digital twin in this scenario, could be used to simulate and track responses of a patient to prevent adverse outcomes as well as reduce risk of worsening malnutrition. According to a recent paper by Yu et al 2023, data points such as: weight, height, age, calf circumference, grip strength, and dietary intake information can be combined with hospital and electronic health records to provide a detailed picture of the patient. As medical and nutritional treatment is instigated the Digital twin status will subsequently change providing prediction of the patient status and potential outcomes in real-time.
  

Predicting short and long-term responses to diets

According to the most recent survey by IFIC, at least 52% of Americans follow some type of dietary pattern with High protein currently taking the lead for weight loss. But not everybody responds to dietary patterns in the same way. What if you could take the guesswork out before even starting? 

Silfvergren et al (2022) recently created an offline Digital twin using different, non-connected, and complementary information about human metabolism—into a single, quantitative, robust, and coherent picture.

They demonstrated the potential of a digital twin, by simulating the impact that a variety of different diets is expected to have on key variables, such as mean plasma glucose, plasma insulin and liver glycogen. Many of these data and predictions are subject-specific while others are population-specific potentially therefore ultimately impacting population health. The researchers believe that this type of offline Digital twin could become useful, not only for personalised nutrition, but also to improve patient understanding, motivation, adherence, and health and behavioural outcomes.

Fatty liver disease

Postprandial hyperglycemia drives insulin resistance and inflammation, leading to metabolic dysfunction-associated fatty liver disease (MAFLD). In one study of type II Diabetes patients, digital twin technology was used to provide personalised diet, sleep and physical activity advice. At 1 year 72.7% of patients were in remission. It is important to note that this was a single arm study.

 

Type 2 Diabetes

In a separate retrospective study, digital twin technology was used to provide personalised nutrition advice via expert coaches [15]. The results demonstrated that daily precision nutrition guidance based on Continuous glucose monitoring (CGM), food intake data, and machine learning algorithms can be beneficial for patients living with type 2 diabetes. At the end of the 3-month period, patients achieved a 1.9% decrease in HbA1C, a 6.1% reduction in body weight, as well as a 56.9% reduction in HOMA-IR (Insulin resistance).

 

Unravelling complexities of behaviour change 

Behaviour change is notoriously complex and difficult. The reality in the industry is that personalized nutrition approaches are not likely to work if behaviour change techniques are not incorporated or considered. A recent meta-analysis review by Villinger et al 2019 demonstrated the top 3 behaviour change techniques included in nutrition apps included: goal setting & planning, social support and self-tracking. This behavioural data could provide detailed insight into the daily choices of an individual with the goal to receive personalized feedback that can enable behaviour change.

Despite the excitement and the hope that digital twins can solve the nation's problems of behaviour change, we just don't know how things will unfold. We do not currently have any data to know whether individuals want to have a digital twin, or whether having a twin will drive meaningful behaviour change. Based on the research by Wageningen university (Dijksterhuis 2021), it is important to consider the type, format, intensity and frequency of personalized advice that best matches the individual.  We can expect some more studies to come out soon. 

Just remember a decade ago we were having the same conversation about Nutrigenetics when the fear was that individuals would not be able to handle hearing their nutrigenetic results. 

Reducing health inequality

Digital twins if implemented correctly, have the ability to reduce health inequality that still exist in healthcare systems according to a recent Ernst & Young publication. 

As the pandemic brought to the forefront the racial and social inequities that persist in health care, health systems have an opportunity to use digital twin technology and predictive analytics on a population level to identify barriers to care and help balance outcomes.

By stratifying the risk for different segments of the population, providers as well as payers can create digital community twins that help enable them to identify vulnerable populations and develop different tracts of outreach that reflect the community needs and prioritize resources accordingly.

New product development for Food as medicine approach  

Belgian company Foodpairing has been using digital twins for food ingredients and products. This allows them to predict and test flavour combinations and consumer purchase intent in real-time. This is very important in an industry where 90% of products launched into the market fail in their first year (Foodpairing)

In the context of a “Food as medicine” movement where consumers are looking for their food products to contribute to their health, a new idea or product can be tested in a virtual environment and developed within hours not months. This means that products or ingredients with health benefits can be matched to a target group with specific metabolic types using foods, ingredients or bioactives.

Foodpairing achieves this by creating a digital twin for each consumer in a specific target group based on their taste likes and dislike preferences at a molecular level. Meaning they can predict who will like what before the consumer even tastes it. This is important as taste remains a key driver for purchases and therefore products that contribute to health should taste good too.

Companies Developing Digital Twins 

Several of the big tech companies are currently developing digital twins for healthcare applications. One of the most well-known is GE Healthcare, which has developed a digital twin platform called Edison. Edison is designed to help doctors and researchers create personalized models of patients, which can be used to develop more effective treatments. Other companies include Microsoft (US), Siemens (Germany), Amazon (US), IBM (US), are some of the key players in digital twin market.

Another company working on digital twins is Simulaids, which specializes in medical simulation technology. Simulaids has developed a digital twin platform called iSimulate, which is designed to help doctors and nurses practice complex medical procedures in a virtual environment. 

Digital twin companies focusing only on nutrition are still rare, however one company 

Twin Health - Founded in 2018 does just this.  Twin Health developed an AI-powered Whole Body Digital Twin™ which is a dynamic, digital representation of a user’s unique metabolism, built from thousands of data points gathered daily from non-invasive wearable sensors and self-reported preferences. With operations both in the US and in India, it provides personalized nutrition, sleep, activity and breathing guidance to help users reverse and prevent chronic metabolic diseases such as type 2 diabetes.   
 

Challenges and Future Outlook 

While digital twins have enormous potential in healthcare and personalized nutrition, there are also several challenges that need to be addressed. One of the biggest challenges is data privacy and security. Digital twins rely on large amounts of personal data, which must be protected from unauthorized access or misuse. Research conducted by Wageningen university demonstrated consumers trust the advice provided by a healthcare professional to be more reliable and trustworthy (Knibbe et al 2022) 

In addition, as individual preferences for receiving dietary advice differs, it is important that a multidisciplinary approach is adopted in the development of a Digital twin in order to prevent unwanted, incompatible and unhealthy personalized dietary advice being provided (Kibbe et al 2022) 

Another challenge is the ethical implications of using digital twins for healthcare applications. For example, there are concerns about how digital twins could be used to discriminate against certain groups of patients, or how they could be used to deny insurance coverage based on predicted health risks. 

Despite these challenges, the future outlook for digital twins in healthcare and personalized nutrition is bright. According to Marketsandmarkets the global market for Digital twins will grow from USD 10.1 billion in 2023 to USD 110.1 billion by 2028, at a CAGR of 61.3%. 

As technology continues to advance, we can expect to see more sophisticated and accurate models, which will help doctors and researchers develop more effective treatments and prevention strategies. Although this will require widespread education of practitioners across the healthcare spectrum, with the right safeguards in place, digital twins have the potential to revolutionize the way we approach healthcare and nutrition, and improve the lives of millions of people around the world. 

As a personalized nutrition strategy and innovation consultancy operating at the intersection of health, technology, food and society, we believe that healthcare is at a pivotal point where personalized nutrition plays a key role. We are already supporting companies to be compliant with current regulatory frameworks and have the right structures in place to provide ethical and trustworthy solutions. We have developed a 7-pillar framework that guides companies within the nutrition, wellness and prevention sector to ensure transparency, accountability and a human in the loop approach.

To learn more about what we do, click here.


References:

  1. Wang, Yu1,2; Lu, Charles Damien1,2; Chen, Wei2,3; Wang, Qi4; Jiang, Hua1,2,3,*. Digital twin enabled personalized nutrition. Precision Nutrition 2(1):p e00030, March 2023. | DOI: 10.1097/PN9.0000000000000030
  2. What is Digital twin technology? McKinsey July 2023 
  3. https://www.foodnavigator.com/Article/2022/09/30/foodpairing-develops-world-s-first-digital-twin-for-npd-to-predict-buying-intent
  4. Willem Jan Knibbe, Lydia Afman, Sjoerd Boersma, Marc-Jeroen Bogaardt, Jochem Evers, Frits van Evert, Jene van der Heide, Idse Hoving, Simon van Mourik, Dick de Ridder & Allard de Wit (2022) Digital twins in the green life sciences, NJAS: Impact in Agricultural and Life Sciences, 94:1, 249-279, 
  5. Shamanna P, Joshi S, Shah L, et al. Type 2 diabetes reversal with digital twin technology-enabled precision nutrition and staging of reversal: a retrospective cohort study. Clin Diabetes Endocrinol 2021;7(1):21. doi:10.1186/s40842-021-00134-7
  6. Villinger et al 2019 https://pubmed.ncbi.nlm.nih.gov/31353783/#article-details
  7. Dijksterhuis, G. B., Bouwman, E. P., & Taufik, D. (2021). Personalized Nutrition Advice: Preferred Ways of Receiving Information Related to Psychological Characteristics. Frontiers in Psychology, 12, 575465. https://doi.org/10.3389/fpsyg.2021.575465
  8. Silfvergren O, Simonsson C, Ekstedt M, Lundberg P, Gennemark P, et al. (2022) Digital twin predicting diet response before and after long-term fasting. PLOS Computational Biology 18(9): e1010469. https://doi.org/10.1371/journal.pcbi.1010469
  9. Digital twin market. Marketsandmarket (12 July 2023) 
  10. Are Digital twins the key to more personal and equitable and efficient care? E&Y (2022) 
  11. Gkouskou, Kalliopi & Vlastos, Ioannis & Karkalousos, Petros & Chaniotis, Dimitrios & Sanoudou, Despina & Eliopoulos, Aristides. (2020). The "Virtual Digital Twins" Concept in Precision Nutrition. Advances in nutrition (Bethesda, Md.). 11. 10.1093/advances/nmaa089. 
  12. Bellanti F, Lo Buglio A, Quiete S, Vendemiale G. Malnutrition in Hospitalized Old Patients: Screening and Diagnosis, Clinical Outcomes, and Management. Nutrients. 2022 Feb 21;14(4):910. doi: 10.3390/nu14040910. PMID: 35215559; PMCID: PMC8880030.
  13. 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
  14. Nahum-Shani I, Smith SN, Spring BJ, Collins LM, Witkiewitz K, Tewari A, Murphy SA. Just-in-Time Adaptive Interventions (JITAIs) in Mobile Health: Key Components and Design Principles for Ongoing Health Behavior Support. Ann Behav Med. 2018 May 18;52(6):446-462. doi: 10.1007/s12160-016-9830-8. PMID: 27663578; PMCID: PMC5364076.
  15. Insel TR. Digital Phenotyping: Technology for a New Science of Behavior. JAMA. 2017 Oct 3;318(13):1215-1216. doi: 10.1001/jama.2017.11295. PMID: 28973224.
  16. 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
  17. Joshi S, Shamanna P, Dharmalingam M, Vadavi A, Keshavamurthy A, Shah L, Mechanick JI. Digital Twin-Enabled Personalized Nutrition Improves Metabolic Dysfunction-Associated Fatty Liver Disease in Type 2 Diabetes: Results of a 1-Year Randomized Controlled Study. Endocr Pract. 2023 Dec;29(12):960-970. doi: 10.1016/j.eprac.2023.08.016. Epub 2023 Sep 29. PMID: 37778441.
  18. Shamanna P, Saboo B, Damodharan S, Mohammed J, Mohamed M, Poon T, Kleinman N, Thajudeen M. Reducing HbA1c in Type 2 Diabetes Using Digital Twin Technology-Enabled Precision Nutrition: A Retrospective Analysis. Diabetes Ther. 2020 Nov;11(11):2703-2714. doi: 10.1007/s13300-020-00931-w. Epub 2020 Sep 25. PMID: 32975712; PMCID: PMC7547935
  19. Wang, Yu1,2; Lu, Charles Damien1,2; Chen, Wei2,3; Wang, Qi4; Jiang, Hua1,2,3,*. Digital twin enabled personalized nutrition. Precision Nutrition 2(1):p e00030, March 2023. | DOI: 10.1097/PN9.0000000000000030