Artificial intelligence and multimodal phenotyping of obesity: a path toward personalized molecular medicine

Cover Page

Cite item

Full Text

Open Access Open Access
Restricted Access Access granted
Restricted Access Subscription or Fee Access

Abstract

Introduction. Body mass index remains a convenient screening tool but fails to capture fat distribution, body composition, molecular inflammatory status, psychobehavioral features, or obesity-related end-organ dysfunction.

Objective. To develop and substantiate the methodological architecture of a multimodal obesity phenotyping platform using machine-learning algorithms; to define the analytical toolkit for each clinical-biological domain; and to demonstrate the diagnostic capacity of the platform to discriminate clinically similar but molecularly distinct obesity phenotypes using modelled clinical scenarios.

Material and methods. An analytical, conceptual-modelling study was performed. A systematic review of PubMed/MEDLINE and Scopus publications (2021–2026) was conducted. An eight-domain phenotyping matrix, ML-algorithm stack, and two-tier CDSS architecture were developed in compliance with TRIPOD+AI, DECIDE-AI, CONSORT-AI, and SPIRIT-AI standards. Diagnostic value was demonstrated through two simulation-based clinical scenarios built on published ranges of real clinical parameters.

Results. A hierarchical two-tier system is proposed: an Authors’ Integral Obesity Index as a first-line screening tool (a metabolic modification of previously developed and registered risk-stratification algorithms) and a multimodal AI platform as a second-line precision diagnostic ecosystem. The simulation scenarios confirmed the platform’s ability to discriminate clinically meaningful molecular differences between patients sharing identical BMI values.

Conclusion. Multimodal obesity phenotyping with AI enables a shift from BMI-centric assessment to personalized clinical stratification. Interpretable algorithms implementing CDSS show the highest practical potential. Prospective clinical validation is the next essential step.

About the authors

Vladimir B. Grinevich

S.M. Kirov Military Medical Academy of the Ministry of Defense of the Russian Federation

Author for correspondence.
Email: szgc@ya.ru
ORCID iD: 0000-0002-1095-8787

Head of the 2nd Department (Advanced Therapy Training); Doctor of Medical Sciences, Professor

Russian Federation, Akademika Lebedeva Street, 6, Saint-Petersburg, 194044

Viktor V. Zakrevsky

S.M. Kirov Military Medical Academy of the Ministry of Defense of the Russian Federation

Email: vzakr@list.ru
ORCID iD: 0000-0002-4355-2986

Associate Professor of the 2nd Department (Advanced Therapy Training); Doctor of Medical Sciences

Russian Federation, Akademika Lebedeva Street, 6, Saint-Petersburg, 194044

Yuri A. Kravchuk

S.M. Kirov Military Medical Academy of the Ministry of Defense of the Russian Federation

Email: kravchuk2003@mail.ru
ORCID iD: 0000-0001-8347-0531

Professor of the 2nd Department (Advanced Therapy Training); Doctor of Medical Sciences, Professor

Russian Federation, Akademika Lebedeva Street, 6, Saint-Petersburg, 194044

Pavel V. Seliverstov

S.M. Kirov Military Medical Academy of the Ministry of Defense of the Russian Federation

Email: seliverstov-pv@yandex.ru
ORCID iD: 0000-0001-5623-4226
SPIN-code: 6166-7005

Associate Professor, 2nd Department (Advanced Therapy Training); Candidate of Medical Sciences, Associate Professor

Russian Federation, Akademika Lebedeva Street, 6, Saint-Petersburg, 194044

Anna A. Auzina

The Russian National Research Medical University named after N.I. Pirogov

Email: annaauzina@yandex.ru
ORCID iD: 0009-0002-8400-3382

6th year student

Russian Federation, Ostrovityanova St., 1, Moscow, 117513

Anastasia I. Russkova

The Russian National Research Medical University named after N.I. Pirogov

Email: nastya.russ2003@mail.ru
ORCID iD: 0009-0000-3808-0251

6th year student

Russian Federation, Ostrovityanova St., 1, Moscow, 117513

Ekaterina S. Chernova

The Russian National Research Medical University named after N.I. Pirogov

Email: Katyafresh@bk.ru
ORCID iD: 0009-0004-2142-6753

6th year student

Russian Federation, Ostrovityanova St., 1, Moscow, 117513

Svetlana P. Salikova

S.M. Kirov Military Medical Academy of the Ministry of Defense of the Russian Federation

Email: salikova.1966@bk.ru
ORCID iD: 0000-0003-4839-9578

Professor of the 2nd Department of Advanced Therapy for Physicians; Doctor of Medical Sciences

Russian Federation, Akademika Lebedeva Street, 6, Saint-Petersburg, 194044

References

  1. Rubino F., Cummings D.E., Eckel R.H. et al. Definition and diagnostic criteria of clinical obesity. Lancet Diabetes Endocrinol. 2025; 13 (3): 221–62. doi: 10.1016/S2213-8587(24)00316-4.
  2. Bray G.A., Kim K.K., Wilding J.P.H. World Obesity Federation. Obesity: a chronic relapsing progressive disease process. Obes Rev. 2017; 18 (7): 715–23. doi: 10.1111/obr.12551.
  3. Watanabe K., Wilmanski T., Diener C. et al. Multiomic signatures of body mass index identify heterogeneous health phenotypes and responses to a lifestyle intervention. Nat Med. 2023; 29 (4): 996–1008. doi: 10.1038/s41591-023-02248-0.
  4. Bays H.E., Fitch A., Cuda S. et al. Artificial intelligence and obesity management: An Obesity Medicine Association Clinical Practice Statement 2023. Obes Pillars. 2023; 6: 100065. doi: 10.1016/j.obpill.2023.100065.
  5. Huang L., Huhulea E.N., Abraham E. et al. The role of artificial intelligence in obesity risk prediction and management. Medicina (Kaunas). 2025; 61 (2): 358. doi: 10.3390/medicina61020358.
  6. Teke J., Msiska M., Adanini O.A. et al. Artificial intelligence for obesity management. Obes Med. 2025; 58: 100657. doi: 10.1016/j.obmed.2025.100657.
  7. Vahid F., Loyola-Leyva A., Tur J. et al. Multimodal (bio)markers and risk of obesity – a comprehensive scoping review. Adv Nutr. 2026; 17 (2): 100579. doi: 10.1016/j.advnut.2025.100579.
  8. Liu X., Batal M., Bifaretti V. et al. Integrating precision medicine and digital health in personalized weight management. Nutrients. 2025; 17 (16): 2695. doi: 10.3390/nu17162695.
  9. Collins G.S., Dhiman P., Andaur Navarro C.L. et al. TRIPOD+AI statement. BMJ. 2024; 385: e078378. doi: 10.1136/bmj-2023-078378.
  10. Vasey B., Nagendran M., Campbell B. et al. DECIDE-AI reporting guideline. Nat Med. 2022; 28 (5): 924–33. doi: 10.1038/s41591-022-01772-9.
  11. Liu X., Rivera S.C., Moher D. et al. CONSORT-AI extension. Nat Med. 2020; 26 (9): 1364–74. doi: 10.1038/s41591-020-1034-x.
  12. Rivera S.C., Liu X., Chan A.W. et al. SPIRIT-AI extension. BMJ. 2020; 370: m3210. doi: 10.1136/bmj.m3210.
  13. Acosta A., Camilleri M., Abu Dayyeh B. et al. Selection of antiobesity medications based on phenotypes. Obesity (Silver Spring). 2021; 29 (4): 662–71. doi: 10.1002/oby.23120.
  14. Sacoto D., Hurtado M.D., Acosta A. Precision medicine and obesity. Handb Exp Pharmacol. 2022; 274: 467–85. doi: 10.1007/164_2021_566.
  15. Anazco D., Acosta A. Precision medicine for obesity. Int. J. Obes (Lond). 2025; 49 (3): 452–63. doi: 10.1038/s41366-024-01599-z.
  16. Tuccinardi D., Masi D., Watanabe M. et al. Precision obesity medicine: a phenotype-guided framework. J. Endocrinol Invest. 2025; 48 (12): 2761–98. doi: 10.1007/s40618-025-02700-7.
  17. Mundt C., Yusufoğlu B., Kudenko D., Esatbeyoglu T. AI-driven personalized nutrition. Mol. Nutr Food Res. 2025; 69: e2500431.
  18. Rouskas K. et al. The influence of an AI-driven personalized nutrition program on the human gut microbiome. Nutrients. 2025; 17 (7): 1260. doi: 10.3390/nu17071260.
  19. Motevalli M., Boaventura B.C.B., Stanford F.C. ChatGPT for obesity management. Lancet Digit Health. 2026. doi: 10.1016/j.landig.2026.100980.
  20. Loft A., Emont M.P., Weinstock A. et al. Towards a consensus atlas of human and mouse adipose tissue. Nat Metab. 2025; 7 (5): 875–94. doi: 10.1038/s42255-025-01296-9.
  21. Hinte L.C., Castellano-Castillo D., Yang Y.H. et al. Adipose tissue retains an epigenetic memory of obesity after weight loss. Nature. 2024; 636 (8042): 457–65. doi: 10.1038/s41586-024-08165-7.
  22. Fox C.K., Molitor S., Vock D.M. et al. Appetitive and psychological phenotypes of pediatric patients with obesity. Pediatr Obes. 2024; 19 (4): e13101. doi: 10.1111/ijpo.13101.
  23. Collet T.H., Schwitzgebel V.M. Precision medicine in rare genetic obesity disorders. Front Nutr. 2024; 11: 1509994. doi: 10.3389/fnut.2024.1509994.
  24. Zuccaro M.V., LeDuc C.A., Lustig R.H., Chung W.K. Updates on rare genetic variants and gene therapy in obesity. Curr Obes Rep. 2024; 13 (3): 626–41. doi: 10.1007/s13679-024-00567-y.
  25. Wood C.T., Khalsa A.S. Overview of BMI and other ways of measuring obesity. Pediatr Clin North Am. 2024; 71 (5): 781–96. doi: 10.1016/j.pcl.2024.07.002.
  26. Селиверстов П.В. Медицинская методология дистанционного анкетного скрининга факторов риска ХНИЗ у лиц молодого возраста. Врач. 2026; 5. doi: 10.29296/25877305-2026-First-Online-02. [Seliverstov P.V. Meditsinskaya metodologiya distantsionnogo anketnogo skrininga faktorov riska KhNIZ u lits molodogo vozrasta. Vrach. 2026; 5. doi: 10.29296/25877305-2026-First-Online-02 (in Russian)].
  27. Селиверстов П.В. Клинико-цифровая стратификация риска ХНИЗ. Врач. 2026; 5. doi: 10.29296/25877305-2026-First-Online-01. [Seliverstov P.V. Kliniko-tsifrovaya stratifikatsiya riska KhNIZ: metodologiya integratsii dannykh distantsionnogo skrininga i laboratorno-instrumentalnykh issledovaniy. Vrach. 2026; 5. doi: 10.29296/25877305-2026-First-Online-01 (in Russian)].
  28. Селиверстов П.В., Крюков Е.В., Гриневич В.Б. Практическая реализация технологии искусственного интеллекта при проведении профилактического медицинского осмотра. Медицинский совет. 2025; 19 (13): 282–8. [Seliverstov P.V., Kryukov E.V., Grinevich V.B. Prakticheskaya realizatsiya tekhnologiy iskusstvennogo intellekta pri provedenii profilakticheskogo meditsinskogo osmotra. Meditsinskiy Sovet. 2025; 19 (13): 282–8. doi: 10.21518/ms2025-322 (in Russian)].
  29. Селиверстов П.В. Разработка медицинской методики телемедицинского скрининга здоровья взрослого населения. Медицинский совет. 2022; 23: 366–72. [Seliverstov P.V. Razrabotka meditsinskoy metodologii telemedicinskogo skrininga zdorovya vzroslogo naseleniya. Meditsinskiy Sovet. 2022; 23: 366–72. doi: 10.21518/2079-701X-2022-16-23-366-372 (in Russian)].
  30. Гриневич В.Б., Закревский В.В., Кравчук Ю.А., Селиверстов П.В. и др. Холистическая многопрофильная модель кардиометаболического риска. Молекулярная Медицина. 2026. [Grinevich V.B., Zakrevsky V.V., Kravchuk Yu.A., Seliverstov P.V. et al. Kholisticheskaya mnogoprofilnaya model kardiometabolicheskogo riska. Molekulyarnaya Meditsina. 2026 (in Russian)].
  31. Kain J., Uauy R., Lera L. et al. Waist-to-height ratio as a global cardiometabolic risk indicator. Am. J. Clin. Nutr. 2024; 119 (5): 1272–80. doi: 10.1093/ajcn/nqae059.
  32. Tchernof A., Despres J.P. Pathophysiology of human visceral obesity. Physiol Rev. 2013; 93 (1): 359–404. doi: 10.1152/physrev.00033.2011.
  33. Kullberg J., Johansson L., Ahlstrom H. Body composition and fat distribution by MRI – emerging role in precision medicine. Int. J. Obes. 2024; 48: 1024–33. doi: 10.1038/s41366-024-01551-1.
  34. Stefan N., Birkenfeld A.L., Schulze M.B., Ludwig D.S. Obesity and impaired metabolic health in patients with COVID-19. Nat Rev Endocrinol. 2020; 16 (7): 341–2. doi: 10.1038/s41574-020-0364-6.
  35. Yudkin J.S., Kumari M., Humphries S.E., Mohamed-Ali V. Inflammation, obesity, stress and coronary heart disease: is interleukin-6 the link? Atherosclerosis. 2000; 148 (2): 209–14. doi: 10.1016/S0021-9150(99)00463-3.
  36. Bluher M. Obesity: global epidemiology and pathogenesis. Nat Rev Endocrinol. 2019; 15 (5): 288–98. doi: 10.1038/s41574-019-0176-8.
  37. Lim S., Meigs J.B. Links between ectopic fat and cardiometabolic profile. Clin. Chem. 2014; 60 (1): 98–108. doi: 10.1373/clinchem.2013.202929.
  38. Qian J., Ng H., Zhu X. et al. Deep learning for wearable-based sleep staging. NPJ Digit Med. 2024; 7: 78. doi: 10.1038/s41746-024-01075-4.
  39. Lean M.E.J., Astrup A., Roberts S.B. Making progress on the global crisis of obesity and weight management. BMJ. 2018; 361: k2538. doi: 10.1136/bmj.k2538.
  40. Caballero B. The Global Epidemic of Obesity: An Overview. Epidemiol Rev. 2007; 29: 1–5. doi: 10.1093/epirev/mxm012.
  41. Dhurandhar N.V., Thomas D. The link between dietary sugar intake and obesity. Curr Opin Clin Nutr Metab Care. 2015; 18 (4): 354–8. doi: 10.1097/MCO.0000000000000167.
  42. Koliaki C., Liatis S., Kokkinos A. Obesity and cardiovascular disease: revisiting an old relationship. Metabolism. 2019; 92: 98–107. doi: 10.1016/j.metabol.2018.10.011.
  43. Couzin-Frankel J. The obesity field struggles with its new drugs – and its image. Science. 2023; 381: 118–9. doi: 10.1126/science.adj5040.
  44. Ryan DH, Yockey SR. Weight loss and improvement in comorbidity. J. Obes. 2017:5685094. doi: 10.1155/2017/5685094.

Supplementary files

Supplementary Files
Action
1. JATS XML
Download

Copyright (c) 2026 Russkiy Vrach Publishing House