大数据时代的革新：利用机器学习和人工智能推动腹壁力学研究

doi:10.16139/j.1007-9610.2024.04.05

摘要/Abstract

摘要：

随着机器学习和人工智能技术的快速发展，腹壁力学研究正逐步克服传统评估方法的限制。通过应用深度学习算法和大数据分析，建立精确的力学和预测模型，分析腹壁肌肉在不同条件下的应力分布，制定个性化的治疗方案。这不仅有助于优化疝修补手术方案，降低复发风险，还有望改善病人的预后情况。展望未来，将继续整合多维度数据，进一步推动腹壁力学领域的系统性研究及其临床应用。

关键词: 机器学习, 人工智能, 腹壁力学, 诊断

Abstract:

Research in abdominal wall mechanics is progressively overcoming the limitations of traditional assessment methods with the application of machine learning and artificial intelligence technologies. By leveraging deep learning algorithms and big data analytics, precise mechanical and predictive models are being established to analyze the stress distribution in abdominal wall muscles under various conditions, facilitating the development of personalized treatment strategies. This approach not only aids in optimizing hernia repair strategies and reducing recurrence risks, but also has the potential to improve patient outcomes. Looking ahead, the continued integration of multidimensional data will further drive systematic research and clinical application in the field of abdominal wall mechanics.

Key words: Machine learning, Artificial intelligence, Abdominal wall mechanics, Diagnosis

中图分类号:

R656.3

毛明焕, 杨槟泽, 彭雪强, 李航宇. 大数据时代的革新：利用机器学习和人工智能推动腹壁力学研究[J]. 外科理论与实践, 2024, 29(04): 300-303.

MAO Minghuan, YANG Binze, PENG Xueqiang, LI Hangyu. Innovation in the era of big data: advancing abdominal wall mechanics research through machine learning and artificial intelligence[J]. Journal of Surgery Concepts & Practice, 2024, 29(04): 300-303.

参考文献 18

[1]	ALIOTTA R E, GATHERWRIGHT J, KRPATA D, et al. Complex abdominal wall reconstruction, harnessing the power of a specialized multidisciplinary team to improve pain and quality of life[J]. Hernia, 2019, 23(2):205-215. doi: 10.1007/s10029-019-01916-w pmid: 30798398
[2]	BATISTA G A, BELTRÁN S P, PASSOS M H P D, et al. Comparison of the electromyography activity during exercises with stable and unstable surfaces: a systematic review and meta-analysis[J]. Sports (Basel), 2024, 12(4):111.
[3]	DEERENBERG E B, HENRIKSEN N A, ANTONIOU G A, et al. Updated guideline for closure of abdominal wall incisions from the European and American hernia socie-ties[J]. Br J Surg, 2022, 109(12):1239-1250.
[4]	GUNNARSSON U, JOHANSSON M, STRIGÅRD K. Assessment of abdominal muscle function using the Biodex System-4. validity and reliability in healthy volunteers and patients with giant ventral hernia[J]. Hernia, 2011, 15(4):417-421. doi: 10.1007/s10029-011-0805-1 pmid: 21380564
[5]	STARK B, EMANUELSSON P, GUNNARSSON U, et al. Validation of Biodex system 4 for measuring the strength of muscles in patients with rectus diastasis[J]. J Plast Surg Hand Surg, 2012, 46(2):102-105. doi: 10.3109/2000656X.2011.644707 pmid: 22471258
[6]	GUEROULT P, JOPPIN V, CHAUMOITRE K, et al. Linea alba 3D morphometric variability by CT scan exploration[J]. Hernia, 2024, 28(2):485-494. doi: 10.1007/s10029-023-02939-0 pmid: 38177404
[7]	CUI P, ZHAO S, CHEN W. Identification of the vas de-ferens in laparoscopic inguinal hernia repair surgery using the convolutional neural network[J]. J Healthc Eng, 2021,2021:5578089.
[8]	JOURDAN A, DHUME R, GUÉRIN E, et al. Numerical investigation of a finite element abdominal wall model during breathing and muscular contraction[J]. Comput Methods Programs Biomed, 2024,244:107985.
[9]	ZHANG Q, CHEN Z, PENG Y, et al. The novel magnesium-titanium hybrid cannulated screws for the treatment of vertical femoral neck fractures: biomechanical evaluation[J]. J Orthop Translat, 2023,42:127-136.
[10]	CHARVÁTOVÁ H, EAST B, PROCHÁZKA A, et al. Computational analysis and classification of hernia repairs[J]. Appl Sci, 2024, 14(8):3236.
[11]	RELLE J J, VOß S, RASCHIDI R, et al. HEDI: first-time clinical application and results of a biomechanical evaluation and visualisation tool for incisional hernia repair[J]. ArXiv.org,2023:2307.01502.
[12]	OKORJI L M, GIRI O, LUQUE-SANCHEZ K, et al. Computed tomography measurements to predict need for robotic transversus abdominis release: a single institution analysis[J]. Hernia, 2024, 28(5):1649-1655.
[13]	KARAMI M, ZOHOOR H, CALVO B, et al. A 3D multi-scale skeletal muscle model to predict active and passive responses. Application to intra-abdominal pressure prediction[J]. Comput Methods Appl Mech Eng, 2023,415:116222.
[14]	LESCH C, NESSEL R, ADOLF D, et al. STRONGHOLD first-year results of biomechanically calculated abdominal wall repair: a propensity score matching[J]. Hernia, 2024, 28(1):63-73.
[15]	ELHAGE S A, DEERENBERG E B, AYUSO S A, et al. Development and validation of image-based deep learning models to predict surgical complexity and complications in abdominal wall reconstruction[J]. JAMA Surg, 2021, 156(10):933-940. doi: 10.1001/jamasurg.2021.3012 pmid: 34232255
[16]	TUSET L, LÓPEZ-CANO M, FORTUNY G, et al. A virtual simulation approach to assess the effect of trocar-site placement and scar characteristics on the abdominal wall biomechanics[J]. Sci Rep, 2024, 14(1):3583.
[17]	TUSET L, LÓPEZ-CANO M, FORTUNY G, et al. Virtual simulation of the biomechanics of the abdominal wall with different stoma locations[J]. Sci Rep, 2022, 12(1):3545. doi: 10.1038/s41598-022-07555-z pmid: 35241748
[18]	EMMERZAAL J, DE BRABANDERE A, VAN DER STRAATEN R, et al. Can the output of a learned classification model monitor a person’s functional recovery status post-total knee arthroplasty?[J]. Sensors (Basel), 2022, 22(10):3698.