Implementation of an artificial intelligence-based peripheral perfusion screening system for early detection of diabetic foot complications
Implementasi sistem skrining perfusi perifer berbasis kecerdasan buatan untuk deteksi dini komplikasi kaki diabetik
DOI:
https://doi.org/10.53713/jcemty.v4i2.741Keywords:
ankle brachial index, artificial intelligence, capillary, peripheral perfusion, screeningAbstract
Peripheral perfusion disorders caused by DM and hypertension synergistically exacerbate lower extremity vascular damage, worsening quality of life. However, limited access to practical, fast, and objective screening instruments at the Foot and Wound Clinic of Universitas Brawijaya Hospital hinders optimal early detection and delays preventive education. This community service program aimed to implement and evaluate an artificial intelligence (AI)-based screening system to facilitate early detection of peripheral perfusion disorders while simultaneously empowering examiners and patients through targeted personalized education. The activities at the RSUB Foot and Wound Clinic during April and May 2026, involving 27 patients using participatory action research (PAR), included: partner problem identification, determining solutions, training 4 examiners, implementing the tool during waiting times, and patient education based on AI output. The developed AI-based screening innovation combines macrovascular and microvascular condition detection. This AI-based screening tool functions not only as an early detection instrument but also as a personalized educational medium for 92.5% of patients unexposed to foot care education, aligning with 18.5% having ulcer histories. Post-implementation, the AI system successfully became a personalized educational medium that visually improved patients' vascular understanding. Additionally, the program effectively increased healthcare workers' screening service capacity without disrupting services. As an evaluation, the system showed acceptable agreement with experts (ABI kappa=0.65; capillary kappa=0.69). In conclusion, this AI system is effective solely as a screening and educational aid, not a standalone diagnostic tool. This innovation was successfully integrated but requires external validation before widespread implementation.
References
Aboyans, V., Bauersachs, R., Mazzolai, L., Brodmann, M., Cacoub, P., De Carlo, M. (2022). Antithrombotic therapies in aortic and peripheral arterial diseases in 2021: A consensus document from the European Society of Cardiology Working Group on Aortic and Peripheral Vascular Diseases. European Heart Journal, 43(9), 779–800 https://doi.org/10.1093/eurheartj/ehab390
Abràmoff, M. D., Tarver, M. E., Loyo-Berrios, N., Trujillo, S., Char, D., Obermeyer, Z. (2023). Considerations for addressing bias in artificial intelligence for health equity. NPJ Digital Medicine, 6(1), 170 https://doi.org/10.1038/s41746-023-00913-9
Arini, M., Hidayah, F. N., & Prakoso, D. A. (2021). Pemberdayaan pasien kelompok prolanis DM melalui edukasi pencegahan dan deteksi dini komorbiditas Tuberculosis-Diabetes Melitus (TB-DM). Jurnal Pengabdian Kepada Masyarakat, 27(4), 339–345 https://doi.org/10.24114/jpkm.v27i4.23377
Bus, S. A., Armstrong, D. G., Crews, R. T., Gooday, C., Jarl, G., Kirketerp-Moller, K. (2024). Guidelines on offloading foot ulcers in persons with diabetes (IWGDF 2023 update). Diabetes/Metabolism Research and Reviews, 40(3), e3647 https://doi.org/10.1002/dmrr.3647
Cassidy, B., Yap, M. H., Pappachan, J. M., Ahmad, N., Haycocks, S., O'Shea, C. (2023). Artificial intelligence for automated detection of diabetic foot ulcers: A real-world proof-of-concept clinical evaluation. Diabetes Research and Clinical Practice, 205, 110951 https://doi.org/10.1016/j.diabres.2023.110951
Chuter, V., Schaper, N., Hinchliffe, R., Mills, J., Azuma, N., Behrendt, C. A., Boyko, E. J., Conte, M. S., Humphries, M., Kirksey, L., McGinigle, K. C., Nikol, S., Nordanstig, J., Rowe, V., David, R., van den Berg, J. C., Venermo, M., & Fitridge, R. (2024). Performance of non-invasive bedside vascular testing in the prediction of wound healing or amputation among people with foot ulcers in diabetes: A systematic review. Diabetes/Metabolism Research and Reviews, 40(3), e3701 https://doi.org/10.1002/dmrr.3701
Gallagher, K. A., Mills, J. L., Armstrong, D. G., Conte, M. S., Hiatt, W. R., Humphries, M. D., & American Heart Association Council on Peripheral Vascular Disease. (2024). Current status and principles for the treatment and prevention of diabetic foot ulcers in the cardiovascular patient population: A scientific statement from the American Heart Association. Circulation, 149(4), e256–e268 https://doi.org/10.1161/CIR.0000000000001192
Garces, T. S., Araújo, A. L. de, Sousa, G. J. B., Cestari, V. R. F., Florêncio, R. S., Mattos, S. M., Damasceno, L. L. V., Santiago, J. C. dos S., Pessoa, V. L. M. P., Pereira, M. L. D., & Moreira, T. M. M. (2024). Clinical decision support systems for diabetic foot ulcers: A scoping review. Revista da Escola de Enfermagem da USP, 57, e20230218 https://doi.org/10.1590/1980-220X-REEUSP-2023-0218pt
Khathimah, H., Farahany, S., & Purba, S. H. (2025). Tantangan dan peluang dalam transformasi digital kesehatan di rumah sakit. Abdi Putra: Jurnal Pengabdian Kepada Masyarakat, 5(1), 16–23 https://doi.org/10.52005/abdiputra.v5i1.347
Lekadir, K., Frangi, A. F., Porras, A. R., Glocker, B., Cintas, C., Langlotz, C. P. (2025). FUTURE-AI: International consensus guideline for trustworthy and deployable artificial intelligence in healthcare. BMJ, 388 https://doi.org/10.1136/bmj-2024-081554
Li, Y., Liu, Y., Liu, S., Gao, M., Wang, W., Chen, K. (2023). Diabetic vascular diseases: Molecular mechanisms and therapeutic strategies. Signal Transduction and Targeted Therapy, 8, Article 152 https://doi.org/10.1038/s41392-023-01400-z
Liu, Z., Wei, D., Wang, J., & Gao, L. (2025). Predicting major amputation risk in diabetic foot ulcers using comparative machine learning models for enhanced clinical decision-making. Scientific Reports, 15(1), 28103 https://doi.org/10.1038/s41598-025-13534-x
Mahé, G., Aboyans, V., Cosson, E., Mohammedi, K., Sarlon-Bartoli, G., Lanéelle, D. (2024). Challenges and opportunities in the management of type 2 diabetes in patients with lower extremity peripheral artery disease: A tailored diagnosis and treatment review. Cardiovascular Diabetology, 23, Article 220 https://doi.org/10.1186/s12933-024-02325-9
Nasution, F., Andilala, A., & Siregar, A. A. (2021). Faktor risiko kejadian diabetes mellitus. Jurnal Ilmu Kesehatan, 9(2), 94–102 https://doi.org/10.32831/jik.v9i2.304
Ozturk, L., Laclau, C., Boulon, C., Mangin, M., Braz-Ma, E., Constans, J. (2025). Analysis of nailfold capillaroscopy images with artificial intelligence: Data from literature and performance of machine learning and deep learning from images acquired in the SCLEROCAP study. Microvascular Research, 157, 104753 https://doi.org/10.1016/j.mvr.2024.104753
Pelliccia, A., Sharma, S., Gati, S., Bäck, M., Börjesson, M., Caselli, S. (2021). 2020 ESC Guidelines on sports cardiology and exercise in patients with cardiovascular disease. European Heart Journal, 42(1), 17–96 https://doi.org/10.1093/eurheartj/ehaa605
Pratiwi, A. P. H., Umar, H., Mappangara, I., Bakri, S., Rasyid, H., & Zainuddin, A. A. (2025). Prevalence of peripheral arterial disease and peripheral neuropathy in diabetic foot infection in Makassar, Indonesia: A cross-sectional study. Romanian Medical Journal, 72(1) https://doi.org/10.37897/RMJ.2025.1.4
Rodway, A. D., Cheal, D., & Allan, C. (2023). Ankle Doppler for cuffless Ankle Brachial Index estimation and peripheral artery disease diagnosis independent of diabetes. Journal of Clinical Medicine, 12(1), 97 https://doi.org/10.3390/jcm12010097
Rosella, L. C., Shaw, J., Guha, S., Abejirinde, I. O., Gibson, J. L., Lipscombe, L. (2025). A participatory approach to deploy responsible artificial intelligence for diabetes prediction and prevention. Digital Health, 11, 20552076251358541 https://doi.org/10.1177/20552076251358541
Sawami, K., Tanaka, A., & Node, K. (2025). Risk management of cardiovascular disease in older patients with diabetes. Hypertension Research, 48(12), 3179–3186 https://doi.org/10.1038/s41440-025-02424-4
Schaper, N. C., van Netten, J. J., Apelqvist, J., Bus, S. A., Fitridge, R., Game, F. (2024). Practical guidelines on the prevention and management of diabetes-related foot disease (IWGDF 2023 update). Diabetes/Metabolism Research and Reviews, 40(3), e3657 https://doi.org/10.1002/dmrr.3657
Shah, A., Isath, A., & Aronow, W. S. (2022). Cardiovascular complications of diabetes. Expert Review of Endocrinology & Metabolism, 17(5), 383–388 https://doi.org/10.1080/17446651.2022.2099838
Singh, M. V., & Dokun, A. O. (2023). Diabetes mellitus in peripheral artery disease: Beyond a risk factor. Frontiers in Cardiovascular Medicine, 10 https://doi.org/10.3389/fcvm.2023.1148040
Verma, S., Leiter, L. A., Mangla, K. K., Nielsen, N. F., Hansen, Y., & Bonaca, M. P. (2024). Epidemiology and burden of peripheral artery disease in people with type 2 diabetes: A systematic literature review. Diabetes Therapy, 15(9), 1893–1961 https://doi.org/10.1007/s13300-024-01606-6
Watson, E. L., Patel, B., Katsogridakis, E., Pepper, C. J., Messeder, S. J., Saratzis, A. (2022). Selecting portable ankle/toe brachial pressure index systems for a peripheral arterial disease population screening programme: A systematic review, clinical evaluation exercise, and consensus process. European Journal of Vascular and Endovascular Surgery, 64(6), 693–702 https://doi.org/10.1016/j.ejvs.2022.08.008
Wijnand, J. G. J., van Rhijn-Brouwer, F. C. C., Spierings, J., Teraa, M., de Borst, G. J., & Verhaar, M. C. (2022). Nailfold capillaroscopy in patients with peripheral artery disease of the lower limb (CAPAD study). European Journal of Vascular and Endovascular Surgery, 63(6), 900–901 https://doi.org/10.1016/j.ejvs.2022.02.013
Winarsih, B. D., Lestari, D. T., & Prasetyo, E. (2025). Optimalisasi kapasitas kader dalam implementasi integrasi layanan primer untuk mendukung transformasi pelayanan kesehatan di Posyandu. Jurnal Abdimas Indonesia, 7(2), 274–283 https://doi.org/10.26751/jai.v7i2.3160
Yap, M. H., Hachiuma, R., Alavi, A., Brüngel, R., Cassidy, B., Goyal, M. (2021). Deep learning in diabetic foot ulcers detection: A comprehensive evaluation. Computers in Biology and Medicine, 135, 104596 https://doi.org/10.1016/j.compbiomed.2021.104596
You, S., Zheng, D., Wang, Y., Nguyen, T. N., Li, Q., Peters, R. (2025). Healthy lifestyle factors and combined macrovascular and microvascular events in diabetes patients with high cardiovascular risk: Results from ADVANCE. BMC Medicine, 23, Article 87 https://doi.org/10.1186/s12916-025-03932-3
