Archive \ Volume.17 2026 Issue 3

Does Artificial Intelligence Change Medication-Taking or Merely Predict It? A Systematic Review and Meta-Analysis of Adherence Interventions

Laura Keller*✉ , Thomas Lehmann , Simon Brunner , Christoph Meier , David Thompson
  1. Department of AI Adherence Interventions, Faculty of Pharmacy, ETH Zurich, Zurich, Switzerland.
  2. Department of Medication-Taking Behavior and AI, Faculty of Pharmacy, EPFL Lausanne, Lausanne, Switzerland.

  3. Department of Predictive vs. Interventional AI, Faculty of Pharmacy, University of Bern, Bern, Switzerland.

  4. Department of Meta-Analysis and Pharmacy AI, Faculty of Pharmacy, University of Basel, Basel, Switzerland.

Abstract

Artificial intelligence is increasingly used to identify medication nonadherence and deliver digital support, but predictive accuracy does not establish that medication-taking changes. Objective: To determine whether artificial-intelligence-enabled adherence interventions improve medication-taking, examine clinical and utilization outcomes, and evaluate heterogeneity, robustness, and certainty. We conducted a protocol-driven systematic review and random-effects meta-analysis aligned with PRISMA 2020. Comparative studies published from 2017 through July 15, 2026 were eligible when an artificial-intelligence component selected, personalized, adapted, verified, escalated, or delivered support intended to change medication-taking. Prediction-only models, static reminders, simulations, protocols, and uncontrolled studies were excluded from effect synthesis. Two reviewers independently screened records, extracted data, appraised risk of bias, and assessed certainty. Searches identified 2,587 records; 703 duplicates were removed, 1,884 records were screened, and 102 full texts were assessed. Eleven reports representing 10 studies were included. Seven studies involving 934 participants entered the primary meta-analysis. Artificial-intelligence-enabled interventions improved adherence relative to eligible comparators (Hedges g=0.41, 95% confidence interval 0.17–0.65; I²=58%). The 95% prediction interval was −0.22 to 1.04. Effects attenuated after exclusion of high-risk studies and studies with unequal adherence measurement. Clinical and utilization outcomes did not establish clear downstream benefit. Certainty was low for adherence and very low for clinical, utilization, safety, and acceptability outcomes. Artificial-intelligence-enabled interventions may improve selected adherence measures, but prediction performance should not be interpreted as intervention effectiveness. Stronger comparative studies using equivalent measurement, longer follow-up, and patient-important outcomes are required. Independent replication across medicines, populations, and care settings therefore remains necessary.


Downloads: 29
Views: 73

How to cite:
Vancouver
Keller L, Lehmann T, Brunner S, Meier C, Thompson D. Does Artificial Intelligence Change Medication-Taking or Merely Predict It? A Systematic Review and Meta-Analysis of Adherence Interventions. Arch Pharm Pract. 2026;17(3):56-65. https://doi.org/10.51847/CviyBD7V1l
APA
Keller, L., Lehmann, T., Brunner, S., Meier, C., & Thompson, D. (2026). Does Artificial Intelligence Change Medication-Taking or Merely Predict It? A Systematic Review and Meta-Analysis of Adherence Interventions. Archives of Pharmacy Practice, 17(3), 56-65. https://doi.org/10.51847/CviyBD7V1l

Download Citation
References
  1. De Geest S, Zullig LL, Dunbar-Jacob J, Helmy R, Hughes DA, Wilson IB, et al. ESPACOMP Medication Adherence Reporting Guideline (EMERGE). Ann Intern Med. 2018;169(1):30-5. doi:10.7326/M18-0543
  2. Stewart SJF, Moon Z, Horne R. Medication nonadherence: health impact, prevalence, correlates and interventions. Psychol Health. 2023;38(6):726-65. doi:10.1080/08870446.2022.2144923
  3. Babel A, Taneja R, Mondello Malvestiti F, Monaco A, Donde S. Artificial intelligence solutions to increase medication adherence in patients with non-communicable diseases. Front Digit Health. 2021;3:669869. doi:10.3389/fdgth.2021.669869
  4. Reis ZSN, Pereira GMV, Dias CDS, Lage EM, de Oliveira IJR, Pagano AS. Artificial intelligence-based tools for patient support to enhance medication adherence: a focused review. Front Digit Health. 2025;7:1523070. doi:10.3389/fdgth.2025.1523070
  5. Page MJ, McKenzie JE, Bossuyt PM, Boutron I, Hoffmann TC, Mulrow CD, et al. The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. BMJ. 2021;372:n71. doi:10.1136/bmj.n71
  6. Rethlefsen ML, Kirtley S, Waffenschmidt S, Ayala AP, Moher D, Page MJ, et al. PRISMA-S: an extension to the PRISMA Statement for reporting literature searches in systematic reviews. Syst Rev. 2021;10(1):39. doi:10.1186/s13643-020-01542-z
  7. Page MJ, Moher D, Bossuyt PM, Boutron I, Hoffmann TC, Mulrow CD, et al. PRISMA 2020 explanation and elaboration: updated guidance and exemplars for reporting systematic reviews. BMJ. 2021;372:n160. doi:10.1136/bmj.n160
  8. Rethlefsen ML, Page MJ. PRISMA 2020 and PRISMA-S: common questions on tracking records and the flow diagram. J Med Libr Assoc. 2022;110(2):253-7. doi:10.5195/jmla.2022.1449
  9. Sterne JAC, Savović J, Page MJ, Elbers RG, Blencowe NS, Boutron I, et al. RoB 2: a revised tool for assessing risk of bias in randomised trials. BMJ. 2019;366:l4898. doi:10.1136/bmj.l4898
  10. Jackson D, Law M, Rücker G, Schwarzer G. The Hartung-Knapp modification for random-effects meta-analysis: a useful refinement but are there any residual concerns? Stat Med. 2017;36(25):3923-34. doi:10.1002/sim.7411
  11. Langan D, Higgins JPT, Jackson D, Bowden J, Veroniki AA, Kontopantelis E, et al. A comparison of heterogeneity variance estimators in simulated random-effects meta-analyses. Res Synth Methods. 2019;10(1):83-98. doi:10.1002/jrsm.1316
  12. Petropoulou M, Mavridis D. A comparison of 20 heterogeneity variance estimators in statistical synthesis of results from studies: a simulation study. Stat Med. 2017;36(27):4266-80. doi:10.1002/sim.7431
  13. Lin L, Chu H. Quantifying publication bias in meta-analysis. Biometrics. 2018;74(3):785-94. doi:10.1111/biom.12817
  14. Guyatt GH, Ebrahim S, Alonso-Coello P, Johnston BC, Mathioudakis AG, Briel M, et al. GRADE guidelines 17: assessing the risk of bias associated with missing participant outcome data in a body of evidence. J Clin Epidemiol. 2017;87:14-22. doi:10.1016/j.jclinepi.2017.05.005
  15. Campbell M, McKenzie JE, Sowden A, Katikireddi SV, Brennan SE, Ellis S, et al. Synthesis without meta-analysis (SWiM) in systematic reviews: reporting guideline. BMJ. 2020;368:l6890. doi:10.1136/bmj.l6890
  16. Bohlmann A, Mostafa J, Kumar M. Machine learning and medication adherence: scoping review. JMIRx Med. 2021;2(4):e26993. doi:10.2196/26993
  17. Labovitz DL, Shafner L, Reyes Gil M, Virmani D, Hanina A. Using artificial intelligence to reduce the risk of nonadherence in patients on anticoagulation therapy. Stroke. 2017;48(5):1416-9. doi:10.1161/STROKEAHA.116.016281
  18. Bain EE, Shafner L, Walling DP, Othman AA, Chuang-Stein C, Hinkle J, et al. Use of a novel artificial intelligence platform on mobile devices to assess dosing compliance in a phase 2 clinical trial in subjects with schizophrenia. JMIR Mhealth Uhealth. 2017;5(2):e18. doi:10.2196/mhealth.7030
  19. Horne BD, Muhlestein JB, Lappé DL, May HT, Le VT, Bair TL, et al. Behavioral nudges as patient decision support for medication adherence: the ENCOURAGE randomized controlled trial. Am Heart J. 2022;244:125-134. doi:10.1016/j.ahj.2021.11.001
  20. Nayak A, Vakili S, Nayak K, Nikolov M, Chiu M, Sosseinheimer P, et al. Use of voice-based conversational artificial intelligence for basal insulin prescription management among patients with type 2 diabetes: a randomized clinical trial. JAMA Netw Open. 2023;6(12):e2340232. doi:10.1001/jamanetworkopen.2023.40232
  21. Chen HH, Hsu HT, Lin PC, Chen CY, Hsieh HF, Ko CH. Efficacy of a smartphone app in enhancing medication adherence and accuracy in individuals with schizophrenia during the COVID-19 pandemic: randomized controlled trial. JMIR Ment Health. 2023;10:e50806. doi:10.2196/50806
  22. Lauffenburger JC, Yom-Tov E, Keller PA, McDonnell ME, Crum KL, Bhatkhande G, et al. The impact of using reinforcement learning to personalize communication on medication adherence: findings from the REINFORCE trial. NPJ Digit Med. 2024;7(1):39. doi:10.1038/s41746-024-01028-5
  23. Worrall C, Shirley D, Bullard J, Dao A, Morrisette T. Impact of a clinical pharmacist-led, artificial intelligence-supported medication adherence program on medication adherence performance, chronic disease control measures, and cost savings. J Am Pharm Assoc. 2025;65(1):102271. doi:10.1016/j.japh.2024.102271
  24. Arshed M, Mahmud A, Minhat HS, Lim PY, Zakar R. Effectiveness of a multifaceted mobile health intervention (Multi-Aid-Package) in medication adherence and treatment outcomes among patients with hypertension in a low- to middle-income country: randomized controlled trial. JMIR Mhealth Uhealth. 2024;12:e50248. doi:10.2196/50248
  25. Ho PM, Glorioso TJ, Allen LA, Blankenhorn R, Glasgow RE, Grunwald GK, et al. Personalized patient data and behavioral nudges to improve adherence to chronic cardiovascular medications: a randomized pragmatic trial. JAMA. 2025;333(1):49-59. doi:10.1001/jama.2024.21739
  26. Lau-Min KS, Marini J, Shah NK, Pucci D, Blauch AN, Cambareri C, et al. Pilot study of a mobile phone chatbot for medication adherence and toxicity management among patients with GI cancers on capecitabine. JCO Oncol Pract. 2024;20(4):483-90. doi:10.1200/OP.23.00365
  27. Bebarta NK, Prabhakaran A, Bhat A, Upadya PS, Shashikiran U, Poojari S, et al. Artificial intelligence-based approaches for monitoring medication adherence among cardiovascular disease patients: a scoping review. BMC Med Inform Decis Mak. 2026;26(1):132. doi:10.1186/s12911-026-03422-3
  28. Chen S, Fang Y, Ding L, Mo PKH, Wang Z. Artificial intelligence-based chatbots to enhance medication adherence among patients with non-communicable chronic diseases: systematic review and meta-analysis. PLOS Digit Health. 2026;5(7):e0001507. doi:10.1371/journal.pdig.0001507
  29. Kurniawan MH, Handiyani H, Nuraini T, Hariyati RTS, Sutrisno S. A systematic review of artificial intelligence-powered chatbot intervention for managing chronic illness. Ann Med. 2024;56(1):2302980. doi:10.1080/07853890.2024.2302980
  30. Hultcrantz M, Rind D, Akl EA, Treweek S, Mustafa RA, Iorio A, et al. The GRADE Working Group clarifies the construct of certainty of evidence. J Clin Epidemiol. 2017;87:4-13. doi:10.1016/j.jclinepi.2017.05.006
  31. Murad MH, Mustafa RA, Schünemann HJ, Sultan S, Santesso N. Rating the certainty in evidence in the absence of a single estimate of effect. Evid Based Med. 2017;22(3):85-7. doi:10.1136/ebmed-2017-110668
  32. Zhang Y, Coello PA, Brożek J, Wiercioch W, Etxeandia-Ikobaltzeta I, Akl EA, et al. Using systematic reviews in guideline development: the GRADE approach. Res Synth Methods. 2019;10(3):312-29. doi:10.1002/jrsm.1313
  33. Longoni C, Bonezzi A, Morewedge CK. Resistance to medical artificial intelligence. J Consum Res. 2019;46(4):629-50. doi:10.1093/jcr/ucz013
  34. Gaube S, Suresh H, Raue M, Merritt A, Berkowitz SJ, Lermer E, et al. Do as AI say: susceptibility in deployment of clinical decision-aids. NPJ Digit Med. 2021;4(1):31. doi:10.1038/s41746-021-00385-9
  35. Kiani A, Uyumazturk B, Rajpurkar P, Wang A, Gao R, Jones E, et al. Impact of a deep learning assistant on the histopathologic classification of liver cancer. NPJ Digit Med. 2020;3:23. doi:10.1038/s41746-020-0232-8
  36. Richardson JP, Smith C, Curtis S, Watson S, Zhu X, Barry B, et al. Patient apprehensions about the use of artificial intelligence in healthcare. NPJ Digit Med. 2021;4(1):140. doi:10.1038/s41746-021-00509-1
  37. Wiens J, Saria S, Sendak M, Ghassemi M, Liu VX, Doshi-Velez F, et al. Do no harm: a roadmap for responsible machine learning for health care. Nat Med. 2019;25(9):1337-40. doi:10.1038/s41591-019-0548-6
  38. Vasey B, Nagendran M, Campbell B, Clifton DA, Collins GS, Denaxas S, et al. Reporting guideline for the early-stage clinical evaluation of decision support systems driven by artificial intelligence: DECIDE-AI. Nat Med. 2022;28(5):924-33. doi:10.1038/s41591-022-01772-9

 

 


Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.