Digital twin-enabled personalized nutrition improves metabolic dysfunction-associated fatty liver disease in type 2 diabetes: results of a 1-year randomized controlled study
Open accessAbstract
OBJECTIVE: Postprandial hyperglycemia drives insulin resistance and inflammation, leading to metabolic dysfunction-associated fatty liver disease (MAFLD). Prediction of postprandial glycemic responses by digital twin (DT) technology can fashion a personalized nutrition, activity, and sleep to treat type 2 diabetes (T2D) and MAFLD. This study examines the effects of DT-enabled personalized nutrition, activity, and sleep on glycemic status, surrogate markers of MAFLD, and magnetic resonance imaging-derived proton density fat fraction (MRI-PDFF) in patients with T2D. METHODS: In an open-label randomized trial (2:1), 319 people with T2D were eligible to intervention (DT) or standard care (SC). DT patients followed personalized meal plans with foods suggested by artificial intelligence with least predicted postprandial glycemic response. The primary end point was to compare change in hemoglobin A1c (HbA1c) and medicine reduction between the DT and SC groups. Key secondary end points included remission to compare liver function test scores and visceral adiposity using MRI. RESULTS: was significantly better for DT than for SC (-2.9 [1.8] vs -0.3 [1.2]; P < .001) at 1 year with 72.7% remission of T2D. In patients with abnormal baseline values, significant improvements were seen in DT vs SC patients from baseline to 1 year in nonalcoholic fatty liver disease liver fat score (mean [SD]; -2.5 [2.0] vs -0.1 [1.5]; P < .001) and nonalcoholic fatty liver disease fibrosis score (-1.20 [0.9] vs -0.1 [1.0]; P < .001), respectively. Improvements are seen with DT compared with SC in other liver fat, fibrosis score, and %liver fat by MRI-PDFF. CONCLUSION: At 1 year, DT-enabled personalized treatment significantly improved hyperglycemia and surrogate markers of MAFLD and MRI-PDFF.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
At one year, 73.8% of patients in the DT group achieved a weight loss of ≥5%, and 41.6% achieved a weight loss of ≥10%; mean weight reduction was 7.4 ± 5.9 kg vs. 0.4 ± 3.6 kg, BMI reduction was 2.7 ± 2.3 kg/m2 vs. 0.1 ± 1.8 kg/m2, and waist circumference reduction was 9.5 ± 7.7 cm vs. 1.2 ± 10.8 cm (all P<0.001) compared to the SC group.
“At one year, 73.8% of patients in the DT group achieved a weight loss of ≥5%, and 41.6% achieved a weight loss of ≥10%. Significant differences were observed in mean weight reduction (7.4 ± 5.9 kg vs. 0.4 ± 3.6 kg P<0.001), BMI reduction (2.7 ± 2.3 kg/m² vs. 0.1 ± 1.8 kg/m² P<0.001), and waist circumference reduction (9.5 ± 7.7 cm vs. 1.2 ± 10.8 cm P<0.001) compared to the SC group (18).”
From Personalized nutrition in type 2 diabetes remission: application of digital twin technology for predictive glycemic control (2024) · cites this paper as [18]
Split into 2 atoms — 1 confirmed, 1 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
Experimental — accuracy not yet measuredDT-enabled personalized nutrition significantly lowers HbA1c levels in patients with T2D.
“DT-enabled personalized nutrition significantly lowers A1C levels in patients with T2D.”
From Personalized nutrition in type 2 diabetes remission: application of digital twin technology for predictive glycemic control (2024) · cites this paper as [18]
The DT group showed significant reductions in liver fat percentage by MRI-PDFF (5.5 ± 4.7% vs. 10.9 ± 6.8%, P<.001), with more patients achieving a liver fat content <6% than in the SC group (83.2% vs. 34%).
“The DT group also showed significant reductions in liver fat percentage by Magnetic Resonance Imaging Proton Density Fat Fraction (MRI-PDFF) (5.5 ± 4.7% vs. 10.9 ± 6.8%, P<.001), with more patients achieving a liver fat content <6% than in the SC group (83.2% vs. 34%) (18).”
From Personalized nutrition in type 2 diabetes remission: application of digital twin technology for predictive glycemic control (2024) · cites this paper as [18]
The DT technology's success in managing T2D, MAFLD, hypertension, and complications like diabetic neuropathy and retinopathy is particularly noteworthy.
“The DT technology’s success in managing T2D (18), MAFLD (18), hypertension (19), and complications like diabetic neuropathy (23) and retinopathy (24) is particularly noteworthy.”
From Personalized nutrition in type 2 diabetes remission: application of digital twin technology for predictive glycemic control (2024) · cites this paper as [18]
DT technology significantly improves Metabolic Dysfunction-Associated Fatty Liver Disease (MAFLD).
“The DT technology has also demonstrated significant success in improving Metabolic Dysfunction-Associated Fatty Liver Disease (MAFLD).”
From Personalized nutrition in type 2 diabetes remission: application of digital twin technology for predictive glycemic control (2024) · cites this paper as [18]
The proportion of patients with normal Framingham Steatosis Index (FSI) increased from 13.1% to 61.1% in the DT group while remaining stable in the SC group (P=0.0008).
“At one year, the proportion of patients with normal Framingham Steatosis Index (FSI) increased from 13.1% to 61.1% in the DT group while remaining stable in the SC group (P=0.0008) (18).”
From Personalized nutrition in type 2 diabetes remission: application of digital twin technology for predictive glycemic control (2024) · cites this paper as [18]
The proportion of patients with normal NAFLD-LFS increased from 11.8% to 67.4% in the DT group, while it decreased from 16% to 9.9% in the SC group over one year (P<.00001).
“The proportion of patients with normal Nonalcoholic fatty liver disease-Liver Fat Score (NAFLD-LFS) increased from 11.8% to 67.4% in the DT group, whereas it decreased from 16% to 9.9% in the SC group over one year (P<.00001) (18).”
From Personalized nutrition in type 2 diabetes remission: application of digital twin technology for predictive glycemic control (2024) · cites this paper as [18]
At the 1-year follow-up, 37 patients (15.9%) dropped out from the DT group (leaving 196), and 16 patients (18.6%) dropped out from the SC group (leaving 70).
“At the 1-year follow-up, 37 patients (15.9%) dropped out from the DT group (leaving 196), and 16 patients (18.6%) dropped out from the SC group (leaving 70).”
From Personalized nutrition in type 2 diabetes remission: application of digital twin technology for predictive glycemic control (2024) · cites this paper as [18]
After one year, 94% of the DT group discontinued all T2D medications, and 72.7% achieved T2D remission, compared to none in the SC group.
“After one year, 94% of the DT group discontinued all T2D medications, with 72.7% achieving T2D remission, compared to none in the SC group (18).”
From Personalized nutrition in type 2 diabetes remission: application of digital twin technology for predictive glycemic control (2024) · cites this paper as [18]
The proportion of patients with normal fatty liver index (FLI) increased from 13.6% to 54.3% in the DT group, compared to a reduction from 15.9% to 13.4% in the SC group (P=0.0003).
“Similarly, the proportion of patients with normal fatty liver index (FLI) increased from 13.6% to 54.3% in the DT group compared to a reduction from 15.9% to 13.4% in the SC group (P=0.0003) (18).”
From Personalized nutrition in type 2 diabetes remission: application of digital twin technology for predictive glycemic control (2024) · cites this paper as [18]
In the DT group, mean HbA1c improved from 9.0 (±1.9) to 6.1 (±0.7) over one year (P<0.001), while the standard care group changed non-significantly from 8.5 (±1.9) to 8.2 (±1.6) (P=0.051).
“In the DT group, the mean HbA1c improved remarkably from 9.0 (± 1.9) to 6.1 (± 0.7) over one year (P<0.001), whereas the standard care (SC) group using traditional dietary interventions showed a non-significant change from 8.5 (± 1.9) to 8.2 (± 1.6) (P=0.051) (18).”
From Personalized nutrition in type 2 diabetes remission: application of digital twin technology for predictive glycemic control (2024) · cites this paper as [18]
The DT group achieved a significant 2.9% reduction in HbA1c levels compared to a non-significant change in the standard care (SC) group over one year.
“The DT group achieved a significant 2.9% reduction in HbA1c levels compared to a non-significant change in the SC group over one year.”
From Personalized nutrition in type 2 diabetes remission: application of digital twin technology for predictive glycemic control (2024) · cites this paper as [18]
73.8% of patients in the DT group achieved at least 5% weight loss.
“Weight loss was another significant achievement, with 73.8% of patients in the DT group achieving at least 5% weight loss, and 41.6% losing 10% or more.”
From Personalized nutrition in type 2 diabetes remission: application of digital twin technology for predictive glycemic control (2024) · cites this paper as [18]
The proportion of patients with normal Nonalcoholic fatty liver disease Fibrosis Score (NFS) increased from 77.6% to 94.4% in the DT group, compared to an increase from 60.7% to 65.5% in the SC group (P=0.58).
“Liver fibrosis scores also improved, with the proportion of patients with normal Nonalcoholic fatty liver disease Fibrosis Score (NFS) increasing from 77.6% to 94.4% in the DT group compared to an increase from 60.7% to 65.5% in the SC group (P=0.58) (18).”
From Personalized nutrition in type 2 diabetes remission: application of digital twin technology for predictive glycemic control (2024) · cites this paper as [18]
41.6% of patients in the DT group lost 10% or more weight.
“Weight loss was another significant achievement, with 73.8% of patients in the DT group achieving at least 5% weight loss, and 41.6% losing 10% or more.”
From Personalized nutrition in type 2 diabetes remission: application of digital twin technology for predictive glycemic control (2024) · cites this paper as [18]
DT technology led to notable improvements in MAFLD, with the proportion of patients with normal NAFLD-LFS increasing from 11.8% to 67.4% in the DT group while decreasing in the SC group.
“DT technology also led to notable improvements in MAFLD, with the proportion of patients with normal NAFLD-LFS increasing from 11.8% to 67.4% in the DT group while decreasing in the SC group.”
From Personalized nutrition in type 2 diabetes remission: application of digital twin technology for predictive glycemic control (2024) · cites this paper as [18]
After one year, 72.7% of the DT group achieved remission.
“After one year, 94% of the DT group discontinued T2D medications, with 72.7% achieving remission.”
From Personalized nutrition in type 2 diabetes remission: application of digital twin technology for predictive glycemic control (2024) · cites this paper as [18]
There were significant improvements in FLI and liver fat percentage in the DT group.
“Additionally, there were significant improvements in FLI and liver fat percentage, further demonstrating the DT’s positive impact on liver health (18).”
From Personalized nutrition in type 2 diabetes remission: application of digital twin technology for predictive glycemic control (2024) · cites this paper as [18]
After one year, 94% of the DT group discontinued T2D medications.
“After one year, 94% of the DT group discontinued T2D medications, with 72.7% achieving remission.”
From Personalized nutrition in type 2 diabetes remission: application of digital twin technology for predictive glycemic control (2024) · cites this paper as [18]
There were notable reductions in BMI and waist circumference in the DT group, far exceeding those seen in the SC group.
“There were also notable reductions in BMI and waist circumference, far exceeding those seen in the SC group (18).”
From Personalized nutrition in type 2 diabetes remission: application of digital twin technology for predictive glycemic control (2024) · cites this paper as [18]
The DT technology's broader benefits in cardiovascular health, liver function, and weight management indicate its potential as a comprehensive solution for managing metabolic syndrome.
“Additionally, the DT technology’s broader benefits in cardiovascular health (21), liver function (18), and weight management (18) indicate its potential as a comprehensive solution for managing the complex challenges of metabolic syndrome.”
From Personalized nutrition in type 2 diabetes remission: application of digital twin technology for predictive glycemic control (2024) · cites this paper as [18]
The DT technology has the ability to significantly lower HbA1c levels and achieve high remission rates in T2D patients.
“One of the most striking implications is the DT technology’s ability to significantly lower HbA1c levels and achieve high remission rates in T2D patients (18).”
From Personalized nutrition in type 2 diabetes remission: application of digital twin technology for predictive glycemic control (2024) · cites this paper as [18]
DT technology has a positive impact on liver health.
“Additionally, there were significant improvements in FLI and liver fat percentage, further demonstrating the DT’s positive impact on liver health (18).”
From Personalized nutrition in type 2 diabetes remission: application of digital twin technology for predictive glycemic control (2024) · cites this paper as [18]
The DT technology provides superior glycemic control compared to standard care.
“This highlights the superior glycemic control provided by the DT technology (18).”
From Personalized nutrition in type 2 diabetes remission: application of digital twin technology for predictive glycemic control (2024) · cites this paper as [18]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Digital twin: Enabling technologies, challenges and open research
Fuller, A., Fan, Z., Day, C., & Barlow, C. (2020) · IEEE Access · doi:10.1109/access.2020.2998358 · Cited by 2,965 · see citing works
Personalized nutrition by prediction of glycemic responses
Zeevi, D., Korem, T., Zmora, N., Israeli, D., Rothschild, D., Weinberger, A., Ben-Yacov, O., Lador, D., Avnit-Sagi, T., Lotan-Pompan, M., et al. (2015) · Cell · doi:10.1016/j.cell.2015.11.001 · Cited by 2,929 · see citing works
Monnier, L., Mas, E., Ginet, C., Michel, F., Villon, L., Cristol, J.-P., & Colette, C. (2006) · JAMA · doi:10.1001/jama.295.14.1681 · Cited by 2,444 · see citing works
Human postprandial responses to food and potential for precision nutrition
Berry, S. E., Valdes, A. M., Drew, D. A., Asnicar, F., Mazidi, M., Wolf, J., Capdevila, J., Hadjigeorgiou, G., Davies, R., Al Khatib, H., et al. (2020) · Nature Medicine · doi:10.1038/s41591-020-0934-0 · Cited by 932 · see citing works
A global review of food-based dietary guidelines
Herforth, A., Arimond, M., Álvarez-Sánchez, C., Coates, J., Christianson, K., & Muehlhoff, E. (2019) · Advances in Nutrition · doi:10.1093/advances/nmy130 · Cited by 848 · see citing works
Kuchay, M. S., Krishan, S., Mishra, S. K., Farooqui, K. J., Singh, M. K., Wasir, J. S., Bansal, B., Kaur, P., Jevalikar, G., Gill, H. K., et al. (2018) · Diabetes Care · doi:10.2337/dc18-0165 · Cited by 662 · see citing works
Standards of Medical Care in Diabetes—2020 Abridged for Primary Care Providers
Riddle, M., & Holl, R. (2019) · Clinical Diabetes · doi:10.2337/cd20-as01 · Cited by 616 · see citing works
O’Keefe, J. H., & Bell, D. S. H. (2007) · The American Journal of Cardiology · doi:10.1016/j.amjcard.2007.03.107 · Cited by 538 · see citing works
Celis-Morales, C., Livingstone, K. M., Marsaux, C. F. M., Macready, A. L., Fallaize, R., O’Donovan, C. B., Woolhead, C., Forster, H., Walsh, M. C., Navas-Carretero, S., et al. (2016) · International Journal of Epidemiology · doi:10.1093/ije/dyw186 · Cited by 399 · see citing works
Lazo, M., Solga, S. F., Horska, A., Bonekamp, S., Diehl, A. M., Brancati, F. L., Wagenknecht, L. E., Pi-Sunyer, F. X., Kahn, S. E., Clark, J. M., et al. (2010) · Diabetes Care · doi:10.2337/dc10-0856 · Cited by 367 · see citing works
Inflammation as a potential link between nonalcoholic fatty liver disease and insulin resistance
Asrih, M., & Jornayvaz, F. R. (2013) · Journal of Endocrinology · doi:10.1530/joe-13-0201 · Cited by 284 · see citing works
The role of nutrition in non‐alcoholic fatty liver disease: Pathophysiology and management
Berná, G., & Romero‐Gómez, M. (2020) · Liver International · doi:10.1111/liv.14360 · Cited by 235 · see citing works
Mendes-Soares, H., Raveh-Sadka, T., Azulay, S., Edens, K., Ben-Shlomo, Y., Cohen, Y., Ofek, T., Bachrach, D., Stevens, J., Colibaseanu, D., et al. (2019) · JAMA Network Open · doi:10.1001/jamanetworkopen.2018.8102 · Cited by 212 · see citing works
Snetselaar, L. G., Jesus, J. M. D., DeSilva, D. M., & Stoody, E. E. (2021) · PubMed Central · doi:10.1097/nt.0000000000000512 · Cited by 154 · see citing works
Mazzotti, A., Caletti, M. T., Brodosi, L., Domizio, S. D., Forchielli, M. L., Petta, S., Bugianesi, E., Bianchi, G. P., & Marchesini, G. (2018) · Journal of Hepatology · doi:10.1016/j.jhep.2018.07.013 · Cited by 117 · see citing works
Shamanna, P., Saboo, B., Damodharan, S., Mohammed, J., Mohamed, M., Poon, T., Kleinman, N. L., & Thajudeen, M. (2020) · Diabetes Therapy · doi:10.1007/s13300-020-00931-w · Cited by 113 · see citing works
Self-citationLim, S. L., Johal, J., Ong, K. W., Han, C. Y., Chan, Y. H., Lee, Y. M., & Loo, W. M. (2020) · JMIR mhealth and uhealth · doi:10.2196/14802 · Cited by 79 · see citing works
Nigam, P., Bhatt, S. P., Misra, A., Vaidya, M., Dasgupta, J., & Chadha, D. S. (2013) · PLoS ONE · doi:10.1371/journal.pone.0049286 · Cited by 75 · see citing works
Hashiba, M., Ono, M., Hyogo, H., Ikeda, Y., Masuda, K., Yoshioka, R., Ishikawa, Y., Nagata, Y., Munekage, K., Ochi, T., et al. (2013) · PLoS ONE · doi:10.1371/journal.pone.0076161 · Cited by 59 · see citing works
Vilar-Gomez, E., Athinarayanan, S. J., Adams, R. N., Hallberg, S. J., Bhanpuri, N. H., McKenzie, A. L., Campbell, W. W., McCarter, J. P., Phinney, S. D., Volek, J. S., et al. (2019) · BMJ Open · doi:10.1136/bmjopen-2018-023597 · Cited by 50 · see citing works
Impact of benign sample size on binary classification accuracy
Mimura, M. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.118630 · Cited by 18 · see citing works
Chang, X., Bian, H., Xia, M., Zhu, X., Sun, X., Yang, X., Gao, J., Lin, H., Yan, H., & Gao, X. (2022) · Diabetes & Metabolism · doi:10.1016/j.diabet.2022.101377 · Cited by 9 · see citing works
Shamanna, P., Joshi, S., Shah, L., et al. (2022) · European Heart Journal · doi:10.1093/eurheartj/ehab849.177 · Cited by 3 · see citing works
Self-citationShamanna, P., Joshi, S., Shah, L., et al. (2022) · Journal of Hypertension · doi:10.1097/01.hjh.0000835932.52938.30 · Cited by 3 · see citing works
Self-citationJoshi, S., SHAH, L., MOHAMED, M., MOHAMMED, J., Poon, T., DHARMALINGAM, M., Vadavi, A., SABOO, B., Damodharan, S., Keshavamurthy, A., et al. (2022) · Diabetes · doi:10.2337/db22-26-or · Cited by 3 · see citing works
Self-citationShamanna, P., SHAH, L., MOHAMMED, J., MOHAMED, M., Poon, T., DHARMALINGAM, M., SABOO, B., Damodharan, S., Vadavi, A., Thajudeen, M., et al. (2022) · Diabetes · doi:10.2337/db22-4-lb · Cited by 2 · see citing works
Self-citationJoshi, S., Dharmalingam, M., Keshavamurthy, A., et al. (2023) · Endocrine Practice · doi:10.1016/j.eprac.2023.03.067 · Cited by 1 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Shamanna, P., Joshi, S., Thajudeen, M., Shah, L., Poon, T., Mohamed, M., & Mohammed, J. (2024) · Frontiers in Endocrinology · doi:10.3389/fendo.2024.1485464 · Cited by 56 · see citing works
Self-citationShamanna, P., Maheshwari, A., Keshavamurthy, A., Bhat, S., Kulkarni, A., R, S., K, K., Gupta, M., Thajudeen, M., Kulkarni, R., et al. (2025) · AACE Clinical Case Reports · doi:10.1016/j.aace.2024.11.004 · Cited by 10 · see citing works
Self-citation
- Authors
- Joshi, S., Shamanna, P., Dharmalingam, M., Vadavi, A., Keshavamurthy, A., Shah, L., & Mechanick, J. I.
- Affiliations
- Lilavati Hospital & Research Centre (IN)
- Bangalore Diabetes Centre (IN)
- M.S. Ramaiah Medical College (IN)
- Icahn School of Medicine at Mount Sinai (US)
- Corresponding author
- Shamanna, Paramesh
- Vadavi, Arun
- Keshavamurthy, Ashok
- Shah, Lisa
- Mechanick, Jeffrey I.
- Venue
- Endocrine Practice
- Publisher
- Elsevier BV
- Published
- 2023-12
- Volume
- 29
- Issue
- 12
- Pages
- 960-970
- ISSN
- 1530-891X (ISSN-L)
- OpenAlex
- W4387165744
- Cited by
- 81
- References
- 27
- Citations by year
- 2026: 35 · 2025: 27 · 2024: 19
- FWCI
- 13.30
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Endocrine Practice (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Genetics › Nutrition, Genetics, and Disease
- Health Sciences › Medicine › Endocrinology, Diabetes and Metabolism › Diabetes Management and Research
- Health Sciences › Medicine › Endocrinology, Diabetes and Metabolism › Diabetes Treatment and Management
- Keywords
- digital twin, personalized nutrition, non-alcoholic fatty liver disease, type 2 diabetes, postprandial hyperglycemia, insulin resistance, HbA1c, diabetes remission, liver fat fraction, liver fibrosis, visceral fat
- MeSH terms
- Artificial Intelligence, Diabetes Mellitus, Type 2, Fibrosis, Glycated Hemoglobin, Humans, Liver, Magnetic Resonance Imaging, Biomarkers, Non-alcoholic Fatty Liver Disease
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
