The Future of AI-Assisted Medical Devices in Precision Medicine: A Systematic Review

Background: The integration of Artificial Intelligence (AI) into medical devices has accelerated exponentially between 2020 and 2025, fundamentally altering the landscape of diagnostic medicine. This period is defined by the transition from theoretical algorithms to regulatory-approved, clinically deployed Software as a Medical Device (SaMD), particularly in image-centric specialties.
Objectives: This systematic review aims to (1) quantify and characterize regulatory trends for AI medical devices (AIMDs) in the US and EU; (2) evaluate the clinical efficacy and workflow impact of AI technologies in Ophthalmology, Oncology, and Musculoskeletal (MSK) disorders, with a specific focus on AI-assisted Point-of-Care Ultrasound (POCUS); and (3) assess the role of these technologies in democratizing access to expert-level diagnostics.
Methods: A PRISMA 2020–compliant literature search was conducted across PubMed/MEDLINE, Embase, Cochrane Library, and IEEE Xplore for peer-reviewed studies published between January 1, 2020, and December 31, 2025. Grey literature from FDA and EU regulatory databases was included to capture approval trends. Risk of bias was assessed using QUADAS-AI and ROBIS tools.
Results: The search identified 1,240 records; 67 pivotal studies and systematic reviews were included. Regulatory data reveal >1,000 FDA-authorized AI devices by 2025, with radiology and ophthalmology dominating. In Ophthalmology, autonomous AI for diabetic retinopathy and glaucoma has demonstrated sensitivity comparable to retina specialists (>90%), enabling widespread tele-screening. In Oncology, AI-assisted breast and prostate ultrasound has significantly improved novice diagnostic accuracy (AUC gains >0.10) and reduced unnecessary biopsies through enhanced specificity. In MSK, AI models for fracture detection and real-time POCUS guidance for nerve blocks have standardized procedure quality and reduced inter-operator variability.
Conclusions: AI medical devices have shifted from "assistive" to "autonomous" and "augmentative" roles, effectively democratizing diagnostic capacity. High-quality evidence supports their deployment to bridge workforce gaps, though challenges regarding regulatory harmonization and algorithmic bias persist.

Keywords

Future, AI-Assisted, Medical, Devices

Downloads

PDF JATS XML

References

1. Zhang S, Li Y, Liu W, et al. A decade of review in global regulation and research of artificial intelligence medical devices (2015–2025). Front Med. 2025;12. doi:10.3389/fmed.2025.1630408 [Google Scholar] [Crossref]

2. FDA Approvals Surge for AI-Enabled Medical Devices in 2024 | Insights & Resources | Goodwin. Accessed January 5, 2026. https://www.goodwinlaw.com/en/insights/publications/2024/11/insights-technology-aiml-fda-approvals-of-ai-medical-devices [Google Scholar] [Crossref]

3. Zhang J. Are we ready for AI-augmented generalists? BMJ Evidence-Based Medicine. Published online May 15, 2025. doi:10.1136/bmjebm-2024-113597 [Google Scholar] [Crossref]

4. Kaffas AE, Vo-Phamhi JM, Griffin JF, Hoyt K. Critical Advances for Democratizing Ultrasound Diagnostics in Human and Veterinary Medicine. Annual Review of Biomedical Engineering. 2024;26(Volume 26, 2024):49-65. doi:10.1146/annurev-bioeng-110222-095229 [Google Scholar] [Crossref]

5. Beals D, Simon L, Rogers F, Pogroszewski S. Revolutionizing Diabetic Retinopathy Screening: Integrating AI-Based Retinal Imaging in Primary Care. Journal of CME. 2025;14(1):2437294. doi:10.1080/28338073.2024.2437294 [Google Scholar] [Crossref]

6. Staff TAP. Image-Only AI Model Outperforms Breast Density Assessment for 5-Year Breast Cancer Risk Stratification. Accessed January 5, 2026. https://ascopost.com/news/december-2025/image-only-ai-model-outperforms-breast-density-for-5-year-breast-cancer-risk-stratification/ [Google Scholar] [Crossref]

7. Chiu TM, Li YC, Chi IC, Tseng MH. AI-Driven Enhancement of Skin Cancer Diagnosis: A Two-Stage Voting Ensemble Approach Using Dermoscopic Data. Cancers (Basel). 2025;17(1):137. doi:10.3390/cancers17010137 [Google Scholar] [Crossref]

8. Shariatnia MM, Bagherieh S, Semnani F, et al. Artificial Intelligence Applications in Musculoskeletal Imaging. Curr Rev Musculoskelet Med. 2025;19(1):4. doi:10.1007/s12178-025-09997-0 [Google Scholar] [Crossref]

9. Page MJ, McKenzie JE, Bossuyt PM, et al. The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. BMJ. 2021;372:n71. doi:10.1136/bmj.n71 [Google Scholar] [Crossref]

10. 510(k) Premarket Notification. Accessed January 5, 2026. [Google Scholar] [Crossref]

11. https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm [Google Scholar] [Crossref]

12. Device Classification Under Section 513(f)(2)(De Novo). Accessed January 5, 2026. https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/denovo.cfm [Google Scholar] [Crossref]

13. Health C for D and R. Breakthrough Devices Program. FDA. Published online August 20, 2025. Accessed January 5, 2026. https://www.fda.gov/medical-devices/how-study-and-market-your-device/breakthrough-devices-program [Google Scholar] [Crossref]

14. Sounderajah V, Ashrafian H, Rose S, et al. A quality assessment tool for artificial intelligence-centered diagnostic test accuracy studies: QUADAS-AI. Nat Med. 2021;27(10):1663-1665. doi:10.1038/s41591-021-01517-0 [Google Scholar] [Crossref]

15. Moher D, Liberati A, Tetzlaff J, Altman DG, PRISMA Group. Preferred reporting items for systematic reviews and meta-analyses: the PRISMA statement. PLoS Med. 2009;6(7):e1000097. doi:10.1371/journal.pmed.1000097 [Google Scholar] [Crossref]

16. AI in medtech is booming. Track new devices here. | MedTech Dive. Accessed January 5, 2026. https://www.medtechdive.com/news/ai-medtech-track-new-devices-fda/748397/ [Google Scholar] [Crossref]

17. Choma A. FDA and AI-enabled medical devices: a few statistics. Graylight Imaging. September 4, 2024. Accessed January 5, 2026. https://wol.graylight-imaging.com/blog/fda-and-ai-enabled-medical-devices-a-few-statistics/ [Google Scholar] [Crossref]

18. FDA approved Artificial Intelligence and Machine Learning (AI/ML)-Enabled Medical Devices: An updated landscape | medRxiv. Accessed January 5, 2026. https://www.medrxiv.org/content/10.1101/2022.12.07.22283216v3 [Google Scholar] [Crossref]

19. Casey B. FDA AI Approvals Surge Past 1k for Radiology. The Imaging Wire. December 11, 2025. Accessed January 5, 2026. https://theimagingwire.com/2025/12/10/ai-enabled-medical-devices-granted-fda-marketing-authorization/ [Google Scholar] [Crossref]

20. The state of artificial intelligence-based FDA-approved medical devices and algorithms: an online database | npj Digital Medicine. Accessed January 5, 2026. https://www.nature.com/articles/s41746-020-00324-0 [Google Scholar] [Crossref]

21. Health C for D and R. Artificial Intelligence-Enabled Medical Devices. FDA. Published online December 5, 2025. Accessed January 5, 2026. https://www.fda.gov/medical-devices/software-medical-device-samd/artificial-intelligence-enabled-medical-devices [Google Scholar] [Crossref]

22. Health C for D and R. Artificial Intelligence-Enabled Medical Devices. FDA. Published online December 5, 2025. Accessed January 5, 2026. https://www.fda.gov/medical-devices/software-medical-device-samd/artificial-intelligence-enabled-medical-devices [Google Scholar] [Crossref]

23. Gupte T, Nitave T, Gobburu J. Regulatory landscape of accelerated approval pathways for medical devices in the United States and the European Union. Front Med Technol. 2025;7. doi:10.3389/fmedt.2025.1586070 [Google Scholar] [Crossref]

24. Medtech regulation outlook in 2023: Faster approvals among priorities as AI moves to fore | MedTech Dive. Accessed January 5, 2026. https://www.medtechdive.com/news/medtech-regulation-FDA-EU-MDR-2023-Outlook/641302/ [Google Scholar] [Crossref]

25. Muralidharan V, Adewale BA, Huang CJ, et al. A scoping review of reporting gaps in FDA-approved AI medical devices. NPJ Digit Med. 2024;7(1):273. doi:10.1038/s41746-024-01270-x [Google Scholar] [Crossref]

26. Gap in FDA’s approval of AI radiology devices: 5 things to know. Accessed January 5, 2026. https://www.beckershospitalreview.com/radiology/gap-in-fdas-approval-of-ai-radiology-devices-5-things-to-know/ [Google Scholar] [Crossref]

27. Cuadros J. The Real-World Impact of Artificial Intelligence on Diabetic Retinopathy Screening in Primary Care. J Diabetes Sci Technol. 2021;15(3):664-665. doi:10.1177/1932296820914287 [Google Scholar] [Crossref]

28. Keep an Eye on Clinical Validation Gaps in AI-Enabled Medical Devices | AHA. December 30, 2025. Accessed January 5, 2026. https://www.aha.org/aha-center-health-innovation-market-scan/2025-09-16-keep-eye-clinical-validation-gaps-ai-enabled-medical-devices [Google Scholar] [Crossref]

29. Wang H, Chen X, Miao X, et al. A Deep Learning Model for Detecting Rhegmatogenous Retinal Detachment Using Ophthalmologic Ultrasound Images. Ophthalmologica. 2024;247(1):8-18. doi:10.1159/000535798 [Google Scholar] [Crossref]

30. Wei Q, Chen Q, Zhao C, Jiang R. Performance of automated machine learning in detecting fundus diseases based on ophthalmologic B-scan ultrasound images. BMJ Open Ophthalmol. 2024;9(1):e001873. doi:10.1136/bmjophth-2024-001873 [Google Scholar] [Crossref]

31. Gan F, Chen L, Qin W, et al. OphthUS-GPT: Multimodal AI for Automated Reporting in Ophthalmic B-Scan Ultrasound. medRxiv. Preprint posted online March 4, 2025:2025.03.03.25323237. doi:10.1101/2025.03.03.25323237 [Google Scholar] [Crossref]

32. Yang M, Liu C, Zou P, Wang W. Deep Learning based Optic Nerve Diameter Sheath Characterization and Structure Quantification on Transorbital Ultrasound Images. Front Med. 2025;12. doi:10.3389/fmed.2025.1705459 [Google Scholar] [Crossref]

33. Jalalian A, Mashohor SBT, Mahmud HR, Saripan MIB, Ramli ARB, Karasfi B. Computer-aided detection/diagnosis of breast cancer in mammography and ultrasound: a review. Clin Imaging. 2013;37(3):420-426. doi:10.1016/j.clinimag.2012.09.024 [Google Scholar] [Crossref]

34. Moon WK, Lee YW, Ke HH, Lee SH, Huang CS, Chang RF. Computer-aided diagnosis of breast ultrasound images using ensemble learning from convolutional neural networks. Comput Methods Programs Biomed. 2020;190:105361. doi:10.1016/j.cmpb.2020.105361 [Google Scholar] [Crossref]

35. AI ultrasound tool could reduce unnecessary biopsies by 60%. AuntMinnie. December 5, 2025. Accessed January 5, 2026. https://www.auntminnie.com/clinical-news/ultrasound/article/15773427/ai-ultrasound-tool-could-reduce-unnecessary-biopsies-by-60 [Google Scholar] [Crossref]

36. Li H, Zhao J, Jiang Z. Deep learning-based computer-aided detection of ultrasound in breast cancer diagnosis: A systematic review and meta-analysis. Clin Radiol. 2024;79(11):e1403-e1413. doi:10.1016/j.crad.2024.08.002 [Google Scholar] [Crossref]

37. Ma F, Yu F, Gu X, et al. An interpretable multimodal machine learning model for predicting malignancy of thyroid nodules in low-resource scenarios. BMC Endocr Disord. 2025;25:232. doi:10.1186/s12902-025-02031-x [Google Scholar] [Crossref]

38. Wildman-Tobriner B, Buda M, Hoang JK, et al. Using Artificial Intelligence to Revise ACR TI-RADS Risk Stratification of Thyroid Nodules: Diagnostic Accuracy and Utility. Radiology. 2019;292(1):112-119. doi:10.1148/radiol.2019182128 [Google Scholar] [Crossref]

39. FDA Clears Non-Invasive AI Device for Skin Cancer Detection | CancerNetwork. Accessed January 5, 2026. https://www.cancernetwork.com/view/fda-clears-non-invasive-ai-device-for-skin-cancer-detection [Google Scholar] [Crossref]

40. Jaklitsch E, Thames T, de Campos Silva T, Coll P, Oliviero M, Ferris LK. Clinical Utility of an AI-powered, Handheld Elastic Scattering Spectroscopy Device on the Diagnosis and Management of Skin Cancer by Primary Care Physicians. J Prim Care Community Health. 2023;14:21501319231205979. doi:10.1177/21501319231205979 [Google Scholar] [Crossref]

41. Ferris LK, Jaklitsch E, Seiverling EV, et al. DERM-SUCCESS FDA Pivotal Study: A Multi-Reader Multi-Case Evaluation of Primary Care Physicians’ Skin Cancer Detection Using AI-Enabled Elastic Scattering Spectroscopy. J Prim Care Community Health. 2025;16:21501319251342106. doi:10.1177/21501319251342106 [Google Scholar] [Crossref]

42. Jain A, Way D, Gupta V, et al. Development and Assessment of an Artificial Intelligence-Based Tool for Skin Condition Diagnosis by Primary Care Physicians and Nurse Practitioners in Teledermatology Practices. JAMA Netw Open. 2021;4(4):e217249. doi:10.1001/jamanetworkopen.2021.7249 [Google Scholar] [Crossref]

43. Kuo RYL, Harrison C, Curran TA, et al. Artificial Intelligence in Fracture Detection: A Systematic Review and Meta-Analysis. Radiology. 2022;304(1):50-62. doi:10.1148/radiol.211785 [Google Scholar] [Crossref]

44. Guermazi A, Tannoury C, Kompel AJ, et al. Improving Radiographic Fracture Recognition Performance and Efficiency Using Artificial Intelligence. Radiology. 2022;302(3):627-636. doi:10.1148/radiol.210937 [Google Scholar] [Crossref]

45. Lindsey R, Daluiski A, Chopra S, et al. Deep neural network improves fracture detection by clinicians. Proceedings of the National Academy of Sciences. 2018;115(45):11591-11596. doi:10.1073/pnas.1806905115 [Google Scholar] [Crossref]

46. Oettl FC, Zsidai B, Oeding JF, et al. Artificial intelligence-assisted analysis of musculoskeletal imaging-A narrative review of the current state of machine learning models. Knee Surg Sports Traumatol Arthrosc. 2025;33(8):3032-3038. doi:10.1002/ksa.12702 [Google Scholar] [Crossref]

47. Bowness J, El-Boghdadly K, Burckett-St Laurent D. Artificial intelligence for image interpretation in ultrasound-guided regional anaesthesia. Anaesthesia. 2021;76(5):602-607. doi:10.1111/anae.15212 [Google Scholar] [Crossref]

48. Kowa CY, Morecroft M, Macfarlane AJR, et al. Prospective randomized evaluation of the sustained impact of assistive artificial intelligence on anesthetists’ ultrasound scanning for regional anesthesia. BMJ Surg Interv Health Technol. 2024;6(1):e000264. doi:10.1136/bmjsit-2024-000264 [Google Scholar] [Crossref]

49. smart. Nerveblox the Ultrasound AI for Regional Anesthesia Granted FDA Clearance | SmartAlpha. August 17, 2025. Accessed January 5, 2026. https://smartalpha.ai/nerveblox-the-ultrasound-ai-for-regional-anesthesia-granted-fda-clearance/ [Google Scholar] [Crossref]

50. Tang R, Li Z, Jiang L, et al. Development and Clinical Application of Artificial Intelligence Assistant System for Rotator Cuff Ultrasound Scanning. Ultrasound Med Biol. 2024;50(2):251-257. doi:10.1016/j.ultrasmedbio.2023.10.010 [Google Scholar] [Crossref]

51. Li R, Wang X, Li T, et al. Deep learning-based automated measurement of hip key angles and auxiliary diagnosis of developmental dysplasia of the hip. BMC Musculoskelet Disord. 2024;25(1):906. doi:10.1186/s12891-024-08035-3 [Google Scholar] [Crossref]

52. Toward automatic diagnosis of hip dysplasia from 2D ultrasound | Semantic Scholar. Accessed January 5, 2026. https://www.semanticscholar.org/paper/Toward-automatic-diagnosis-of-hip-dysplasia-from-2D-Hareendranathan-Zonoobi/d631b8e1f453d4b0163909c8717daffc72a42ca4 [Google Scholar] [Crossref]

53. Chen M, Cai R, Zhang A, Chi X, Qian J. The diagnostic value of artificial intelligence-assisted imaging for developmental dysplasia of the hip: a systematic review and meta-analysis. J Orthop Surg Res. 2024;19(1):522. doi:10.1186/s13018-024-05003-4 [Google Scholar] [Crossref]

54. AI-powered ultrasound: The future of hip dysplasia screening? - Victorian Hip Dysplasia Registry (VicHip). Accessed January 5, 2026. https://www.vichip.org.au/vichip-blog/family-stories-and-articles/ai-powered-ultrasound-the-future-of-hip-dysplasia-screening/ [Google Scholar] [Crossref]

55. Deep Medicine: How Artificial Intelligence Can Make Healthcare Human Again. Published online January 7, 2019. Accessed January 5, 2026. https://psnet.ahrq.gov/issue/deep-medicine-how-artificial-intelligence-can-make-healthcare-human-again [Google Scholar] [Crossref]

56. Frija G, Salama DH, Kawooya MG, Allen B. A paradigm shift in point-of-care imaging in low-income and middle-income countries. eClinicalMedicine. 2023;62. doi:10.1016/j.eclinm.2023.102114 [Google Scholar] [Crossref]

57. A New Era for Point-of-Care Ultrasound: 2025 Marks the Turning Point. Medical Product Outsourcing. January 9, 2025. Accessed January 5, 2026. https://www.mpo-mag.com/exclusives/a-new-era-for-point-of-care-ultrasound-2025-marks-the-turning-point/ [Google Scholar] [Crossref]

58. Narang A, Bae R, Hong H, et al. Utility of a Deep-Learning Algorithm to Guide Novices to Acquire Echocardiograms for Limited Diagnostic Use. JAMA Cardiol. 2021;6(6):624-632. doi:10.1001/jamacardio.2021.0185 [Google Scholar] [Crossref]

59. Pokaprakarn T, Prieto JC, Price JT, et al. AI Estimation of Gestational Age from Blind Ultrasound Sweeps in Low-Resource Settings. NEJM Evidence. 2022;1(5):EVIDoa2100058. doi:10.1056/EVIDoa2100058 [Google Scholar] [Crossref]

60. Viswanathan AV, Pokaprakarn T, Kasaro MP, et al. Deep learning to estimate gestational age from fly-to cineloop videos: A novel approach to ultrasound quality control. Int J Gynaecol Obstet. 2024;165(3):1013-1021. doi:10.1002/ijgo.15321 [Google Scholar] [Crossref]

61. Kim S, Fischetti C, Guy M, Hsu E, Fox J, Young SD. Artificial Intelligence (AI) Applications for Point of Care Ultrasound (POCUS) in Low-Resource Settings: A Scoping Review. Diagnostics (Basel). 2024;14(15):1669. doi:10.3390/diagnostics14151669 [Google Scholar] [Crossref]

62. Health C for D and R. Artificial Intelligence-Enabled Medical Devices. FDA. Published online December 5, 2025. Accessed January 6, 2026. https://www.fda.gov/medical-devices/software-medical-device-samd/artificial-intelligence-enabled-medical-devices [Google Scholar] [Crossref]

63. MedTech Europe 2024 Regulatory Survey: key findings and insights. MedTech Europe. Accessed January 5, 2026. https://www.medtecheurope.org/resource-library/medtech-europe-2024-regulatory-survey-key-findings-and-insights/ [Google Scholar] [Crossref]

64. MDR certification bottleneck | ICON plc. Accessed January 5, 2026. https://www.iconplc.com/insights/blog/2022/11/30/mdr-certification-bottleneck [Google Scholar] [Crossref]

65. The EU AI Act and Medical Devices: Navigating High-Risk Compliance. June 27, 2025. Accessed January 5, 2026. https://www.reedsmith.com/our-insights/blogs/viewpoints/102kq35/the-eu-ai-act-and-medical-devices-navigating-high-risk-compliance/ [Google Scholar] [Crossref]

66. Kelly CJ, Karthikesalingam A, Suleyman M, Corrado G, King D. Key challenges for delivering clinical impact with artificial intelligence. BMC Med. 2019;17(1):195. doi:10.1186/s12916-019-1426-2 [Google Scholar] [Crossref]

67. AI devices with no clinical validation tied to more recalls, study finds | MedTech Dive. Accessed January 5, 2026. https://www.medtechdive.com/news/ai-medical-devices-no-validation-more-recalls-jama/758991/ [Google Scholar] [Crossref]

68. Will AI Be Your New Doctor? Probably Not, Thanks to Recent Trends in State Regulation // Cooley // Global Law Firm. Accessed January 5, 2026. https://www.cooley.com/news/insight/2025/2025-08-06-will-ai-be-your-new-doctor-probably-not-thanks-to-recent-trends-in-state-regulation [Google Scholar] [Crossref]

69. Augmented intelligence in medicine. American Medical Association. October 21, 2025. Accessed January 5, 2026. [Google Scholar] [Crossref]

70. https://www.ama-assn.org/practice-management/digital-health/augmented-intelligence-medicine [Google Scholar] [Crossref]

The Future of AI-Assisted Medical Devices in Precision Medicine: A Systematic Review

Authors

Article Information

Publication Timeline

Abstract

Keywords

Downloads

References

Metrics

Views & Downloads

Similar Articles