Journals / Sürdürülebilir Mühendislik Uygulamaları ve Teknolojik Gelişmeler Dergisi / 2025 / Cilt: 8 Sayı: 2

Comparative Analysis of AI-Based Quality Failure Detection in High-Risk Class III Medical Devices

Yüksek Riskli Sınıf III Tıbbi Cihazlarda Yapay Zeka Tabanlı Kalite Hata Analizlerinin Karşılaştırılması

Eylül Eyüpoğlu(KOCAELİ ÜNİVERSİTESİ, TEKNOLOJİ FAKÜLTESİ, BİYOMEDİKAL MÜHENDİSLİĞİ BÖLÜMÜ, BİYOMEDİKAL MÜHENDİSLİĞİ PR.)0009-0003-3108-9888
Faruk Aktaş(KOCAELİ ÜNİVERSİTESİ)0000-0002-6399-5952
Pages
272–287
Publication Date
2025-12-16
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

This study examines quality assurance in Class III medical devices from a holistic perspective, combining conventional quality control methodologies with deep learning-based evaluation techniques.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Quality assurance for medical devices is governed by the Medical Device Regulation (MDR) 2017/745 framework.
📊
Key Findings & Data:Class III medical devices, categorized as the highest risk group, are critical for patient safety and the consistency of device performance.
💡
Conclusion & Impact:This study examines quality assurance in Class III medical devices from a holistic perspective, combining conventional quality control methodologies with deep learning-based evaluation techniques.
🔬Design:Modeling & Simulation
📍Scope:2017 Verileri
⚙️Variables:Kalite Güvence · Derin Öğrenme · Yapay Zeka

Abstract

Quality assurance for medical devices is governed by the Medical Device Regulation (MDR) 2017/745 framework. Under this regulation, medical devices must undergo CE (Community Europe) conformity assessment processes before entering the European market. Class III medical devices, categorized as the highest risk group, are critical for patient safety and the consistency of device performance. The quality and reliability of these devices are established through quality control procedures grounded in standardized test protocols- such as the ISO 10555 series- and product-specific technical standards. However, these protocols are inherently susceptible to operator variability. Consequently, assessment processes relying on operator-dependent procedures and limited sample sizes present constraints regarding objectivity, traceability, and reproducibility. This limitation is particularly pronounced in high-risk devices like coronary balloon angioplasty catheters, which exhibit micro-level manufacturing variations and complex structural characteristics. Failure to detect deviations arising during manufacturing and quality control-regardless of the risk class can lead to clinically significant hazards; the severity of such risks correlates directly with the device's risk classification. Recently, artificial intelligence-assisted quality evaluation approaches, utilizing machine learning and deep learning algorithms, have emerged as effective strategies to overcome these limitations and mitigate associated risks. Specifically, integrating deep learning models with manufacturing data and post-market clinical follow-up (PMCF) outcomes shows significant promise for identifying potential issues before market release and reducing the likelihood of serious adverse events, thereby reinforcing risk management processes. This study examines quality assurance in Class III medical devices from a holistic perspective, combining conventional quality control methodologies with deep learning-based evaluation techniques.

Özet

Tıbbi cihazların kalite güvencesi, Tıbbi Cihazlar Yönetmeliği (Medical Device Regulation- MDR) 2017/745 kapsamında değerlendirilmekte ve tıbbi cihazlar bu yönetmelik kapsamında Avrupa’ya Uygunluk (Community Europe- CE) belgelendirme süreçlerinden geçmektedir. Tıbbi cihaz yönetmeliği kapsamında en yüksek risk grubu altında yer alan Sınıf III cihazlar hasta güvenliği ve cihaz performansının sürekliliği açısından kritik öneme sahiptir. Ürünün kalite ve güvenilirliği, ISO 10555 serisi gibi standart test protokolleri ile ürüne özgü teknik standartlara dayanan ve operatör bağımlılığını içeren kalite kontrol süreçleri tarafından belirlenmektedir. Bu değerlendirmeler, operatörün doğrudan yaptığı süreçlere ve sınırlı örneklem sayılarına dayanması nedeniyle nesnellik, izlenebilirlik ve tekrarlanabilirlik açısından kısıtlı bir güvenilirlik sunmaktadır. Bu durum, mikro düzeyde üretim sapmaları olan ve karmaşık yapısal özellikleri bulunan koroner balon anjiyoplasti kateterleri gibi yüksek risk grubundaki cihazları yakından ilgilendirmektedir. Herhangi bir risk fark etmeksizin tıbbi cihazların üretim ve kalite kontrol süreçlerinde yaşanabilecek sapmaların erken tespit edilememesi klinik açıdan önemli riskler doğurmaktadır. Riskin şiddeti tıbbi cihazın ürün risk grubuyla doğru orantılı olarak artmaktadır. Son yıllarda bu sınırlılıkları aşmak ve bu riskleri ortadan kaldırmak için makine öğrenmesi ve derin öğrenme algoritmalarını içeren yapay zeka destekli ürün kalite değerlendirme yaklaşımları etkili bir araç olarak öne çıkmaktadır. Özellikle Derin öğrenme modelleri kullanılarak üretim verileri ile satış sonrası klinik takip (Post Marketing Clinical Follow- Up- PMCF) çıktılarının bütünleştirilmesinin, ürünün üretim sahasından çıkmadan önce olası sorunların daha erken fark edilmesine ve ciddi olumsuz olayların azaltılmasına katkı sağlayabileceği; bu yolla risk yönetimi süreçlerini güçlendirebileceği değerlendirilmektedir. Bu çalışma, Sınıf III tıbbi cihazlarda kalite güvencesini; geleneksel kalite kontrol yaklaşımları ile derin öğrenme temelli değerlendirme yöntemlerini bütüncül bir bakış açısıyla ele almaktadır.

🔖

Cite This Article

Eyüpoğlu, E., Aktaş, F. (2025). Comparative Analysis of AI-Based Quality Failure Detection in High-Risk Class III Medical Devices. Sürdürülebilir Mühendislik Uygulamaları ve Teknolojik Gelişmeler Dergisi, Cilt: 8 Sayı: 2, 272–287. https://doi.org/10.51764/smutgd.1831873

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (28)

  1. Barla, P. C., & Karthikeyan, L. (2024). “Harnessing Artificial Intelligence For Real Time Quality Assurance In Medical Device Manufacturing.” The American Journals of Medical Technology, 6(06), 24-31. https://doi.org/10.37547/tajet/Volume06Issue06-04
  2. Bevins, N. B., Silosky, M. S., Badano, A., Marsh, R. M., Flynn, M. J., & Walz-Flannigan, A. I. (2020). Practical application of AAPM Report 270 in display quality assurance: A report of Task Group 270. Medical physics, 47(9), e920–e928. https://doi.org/10.1002/mp.14227
  3. Bonatti, R., Soloperto, C., Baiocco, L., Colombo, I., Scaglione, S., & Metta, G. (2024). Expert system for online defect detection in medical devices produced by electron beam melting using layer-by-layer optical images. 3D Printing and Additive Manufacturing. https://doi.org/10.1089/3dp.2023.0222
  4. Bonatti, A. F., Vozzi, G., & De Maria, C. (2024). Enhancing quality control in bioprinting through machine learning. Biofabrication, 16(2), 10.1088/1758-5090/ad2189. https://doi.org/10.1088/1758-5090/ad2189 Bozsik, B. (2023, October 19). How to classify Medical Devices for certification? SGS. https://www.sgs.com/en-ca/news/2023/10/how-to-classify-medical-devices-for-certification
  5. Brilakis, E. S., Banerjee, S., Karmpaliotis, D., Lombardi, W. L., Tsai, T. T., Shunk, K. A., Kennedy, K. F., Spertus, J. A., Holmes, D. R., Jr, & Grantham, J. A. (2015). Procedural outcomes of chronic total occlusion percutaneous coronary intervention: a report from the NCDR (National Cardiovascular Data Registry). JACC. Cardiovascular interventions, 8(2), 245–253. https://doi.org/10.1016/j.jcin.2014.08.014
  6. Chan, H. P., Hadjiiski, L. M., & Samala, R. K. (2020). Computer-aided diagnosis in the era of deep learning. Medical physics, 47(5), e218–e227. https://doi.org/10.1002/mp.13764
  7. Commission, European (2017). Regulation (EU) 2017/745 of the European Parliament and of the Council of 5 April 2017 on medical devices, amending Directive 2001/83/EC, Regulation (EC) No 178/2002 and Regulation (EC) No 1223/2009 and repealing Council Directives 90/385/EEC and 93/42/EEC (Text with EEA relevance.). Official Journal of the European Union, OJ L 117, 5.5.2017, pp. 1–175 (BG, ES, CS, DA, DE, ET, EL, EN, FR, GA, HR, IT, LV, LT, HU, MT, NL, PL, PT, RO, SK, SL, FI, SV).
  8. Dengler, S., Lahriri, S., Trunzer, E., & Vogel- Heuser, B. (2021). Applied machine learning for a zero defect tolerance system in the automated assembly of pharmaceutical devices. Decision Support System, 146, 113540.
  9. FDA U.S. Food & Drag (2025, May 12). Artificial Intelligence-Enabled Medical Devices? FDA. https://www.fda.gov/medical-devices/software-medical-device-samd/artificial-intelligence-enabled-medical-devices.
  10. Fişne, A., Kalay, A. & Eken, S. Fast and efficient computing for deep learning-based defect detection models in lightweight devices. Journal of Intelligent Manufacturing, 36, 5035–5050 (2025).
  11. Flöck, A., Tu, N. C., Rüland, A., Holzgreve, W., Gembruch, U., & Geipel, A. (2017). Non-invasive prenatal testing (NIPT): Europe's first multicenter post-market clinical follow-up study validating the quality in clinical routine. Archives of gynecology and obstetrics, 296(5), 923–928. https://doi.org/10.1007/s00404-017-4517-3
  12. Helou, B., Bel-Brunon, A., Dupont, C., Ye, W., Silvestro, C., Rochette, M., Lucas, A., Kaladji, A., & Haigron, P. (2021). Influence of balloon design, plaque material composition, and balloon sizing on acute post angioplasty outcomes: An implicit finite element analysis. International journal for numerical methods in biomedical engineering, 37(8), e3499. https://doi.org/10.1002/cnm.3499
  13. Hendel, R. C., Patel, M. R., Allen, J. M., Min, J. K., Shaw, L. J., Wolk, M. J., Douglas, P. S., Kramer, C. M., Stainback, R. F., Bailey, S. R., Doherty, J. U., & Brindis, R. G. (2013). Appropriate use of cardiovascular technology: 2013 ACCF appropriate use criteria methodology update: a report of the American College of Cardiology Foundation appropriate use criteria task force. Journal of the American College of Cardiology, 61(12), 1305–1317. https://doi.org/10.1016/j.jacc.2013.01.025
  14. Guha, B., Moore, S. & Huyghe, J.M. Application and validation of machine vision inspection for efficient in-process monitoring of complex biomechanical device manufacturing. Journal of Engineering and Applied Science. 70, 72 (2023). https://doi.org/10.1186/s44147-023-00242-4
  15. International Organization for Standardization. (2013). Intravascular catheters- Sterile and single-use catheters. Part 3: Central venous catheters. ISO.
  16. International Organization for Standardization. (2016). ISO 13485:2016 Medical devices- Quality management systems- Requirements for regulatory purposes. ISO.
  17. International Organization for Standardization. (2019). ISO 14971:2019 Medical devices- Application of risk management to medical devices. ISO.
  18. International Organization for Standardization. (2023). ISO 10555-1: Intravascular catheters- Sterile and single-use catheters- Part 1: General requirements. ISO.
  19. International Organization for Standardization. (2020). ISO/TR 24971:2020 Medical devices- Guidance on the application of ISO 14971. ISO.
  20. Korkmaz, M., & Barstuğan, M. (2020). A Deep Learning-Based Quality Control Application. Avrupa Bilim Ve Teknoloji Dergisi, 332-336. https://doi.org/10.31590/ejosat.804744
  21. Krittanawong, C., Rogers, A. J., Johnson, K. W., Wang, Z., Turakhia, M. P., Halperin, J. L., & Narayan, S. M. (2021). Integration of novel monitoring devices with machine learning technology for scalable cardiovascular management. Nature reviews. Cardiology, 18(2), 75–91. https://doi.org/10.1038/s41569-020-00445-9
  22. Mao, W.-L., Wang, C.-C., Chou, P.-H., & Liu, Y.-T. (2024). Automated defect detection for mass-produced electronic components based on YOLO object detection models. IEEE Sensors Journal, 24(16), 26877–26888. https://doi.org/10.1109/JSEN.2024.3418618
  23. Mercolli, L., Rominger, A., & Shi, K. (2024). Towards quality management of artificial intelligence systems for medical applications. Zeitschrift fur medizinische Physik, 34(2), 343–352. https://doi.org/10.1016/j.zemedi.2024.02.001
  24. Muehlematter, U. J., Daniore, P., & Vokinger, K. N. (2021). Approval of artificial intelligence and machine learning-based medical devices in the USA and Europe (2015-20): a comparative analysis. The Lancet. Digital health, 3(3), e195–e203. https://doi.org/10.1016/S2589-7500(20)30292-2
  25. Roman, M., Biancari, F., Ahmed, A. B., Agarwal, S., Hadjinikolaou, L., Al-Sarraf, A., Tsang, G., Oo, A. Y., Field, M., Santini, F., & Mariscalco, G. (2019). Prothrombin Complex Concentrate in Cardiac Surgery: A Systematic
  26. Review and Meta-Analysis. The Annals of thoracic surgery, 107(4), 1275–1283. https://doi.org/10.1016/j.athoracsur.2018.10.013
  27. Shimony, A., Eisenberg, M. J., Filion, K. B., & Amit, G. (2012). Beneficial effects of right ventricular non-apical vs. apical pacing: a systematic review and meta-analysis of randomized-controlled trials. Europace: European pacing, arrhythmias, and cardiac electrophysiology: journal of the working groups on cardiac pacing, arrhythmias, and cardiac cellular electrophysiology of the European Society of Cardiology, 14(1), 81–91. https://doi.org/10.1093/europace/eur240
  28. Shimony, A., Eisenberg, M. J., Filion, K. B., & Amit, G. (2012). Beneficial effects of right ventricular non-apical vs. apical pacing: a systematic review and meta-analysis of randomized-controlled trials. Europace: European pacing, arrhythmias, and cardiac electrophysiology: journal of the working groups on cardiac pacing, arrhythmias, and cardiac cellular electrophysiology of the European Society of Cardiology, 14(1), 81–91. https://doi.org/10.1093/europace/eur240