Exploration of Clinical Application of AI System Incorporating LSTM Algorithm for Management of Anesthetic Dose in Cancer Surgery

Zepeng Shen; Yong Wang; Ke Hu; Zhiyuan  Wang; Sifang Lin

Authors

Zepeng Shen China-Britain Artificial Intelligence Association, Oxford, United Kingdom
Yong Wang Information Technology, University of Aberdeen, Aberdeen, United Kingdom
Ke Hu Mechanical Design, Manufacturing and Automation, Heilongjiang Institute of Technology, Heilongjiang, China
Zhiyuan Wang Logistics and Supply Chain Management, Cranfield University, United Kingdom
Sifang Lin Anesthesiology, Peking Union Medical College, Beijing, China

Keywords:

LSTM algorithm, Artificial intelligence system, Anesthesia, Dosage management for cancer surgery, Exploration of clinical application

Abstract

The purpose of this study is to explore the clinical application of artificial intelligence system based on LSTM (Long and Short Time Memory Network) algorithm in the management of anesthetic dose for cancer surgery. The complexity of cancer surgery and the diversity of patient physiological characteristics put forward extremely high requirements for the precision and real-time of anesthetic dosage. Traditional anesthesia management methods rely on pharmacokinetic / pharmacodynamic models and the experience of anesthesiologists, but have limitations in handling dynamic physiological data and individual differences. To this end, this study constructed an intelligent anesthetic dose management system incorporating the LSTM algorithm to predict the anesthetic requirements and dynamically adjust the drug dose by analyzing real-time physiological data during the operation. The main methods include data collection, training and optimization of LSTM model, and system development and testing. In the experiment, intraoperative physiological data of 100 cancer surgery patients were selected for modeling combined with LSTM algorithm and compared with traditional anesthesia management methods. The results showed that the LSTM-based system is significantly better than the traditional methods in the accuracy and real-time performance of the anesthetic dose prediction, which can effectively reduce the incidence of anesthesia-related complications and improve the safety and success rate of surgery. The significance of this study is to provide an intelligent and personalized anesthetic dosage management scheme for cancer surgery, and to improve the precision of anesthetic management. Pasiacity and efficiency are of great clinical value. At the same time, the successful application of this system provides a reference for the further promotion of artificial intelligence technology in the medical field, and has a broad practical application prospect.

References

Sun Xin, Liu Yanchao, Zheng Heng. Clinical application and development progress of anticancer peptides [J]. Pharmacy Advances, 2024, 48(12):951-960. DOI:10.20053/j.issn1001-5094.2024.12.007.

Silver Caixia, Lun, Li Yicong, etc. Experience of anesthesia management in domestic remote 5G robotic urology surgery [J/OL]. Journal of Minimally Invasive Urology, 2024, (05): 299-302 [2025-01-24]. https://doi.org/10.19558/j.cnki.10-1020/r.2024.05.002.

Ji Muhuo, Hu Xiaoyi, Yang Jianjun. Perioperative anesthesia management in patients with coexisting multimorbidity: Challenges and Opportunities [J]. Journal of Clinical Anesthesiology, 2024,40 (11): 1125-1129.

Silver Caixia, Lun, Li Yicong, etc. Experience of anesthesia management in domestic remote 5G robot urology surgery [J]. Journal of Minimally Invasive Urology, 2024,13(05):299-302.DOI:10.19558/j.cnki.10-1020/r. 2024.05. 002.

Shimada K, Inokuchi R, Ohigashi T, et al.Artificial intelligence-assisted interventions for perioperative anesthetic management: a systematic review and meta-analysis[J].BMC Anesthesiology,2024,24(1):306-306.

Obimba C D, Esteva C, Tsicheu N N E, et al.Effectiveness of Artificial Intelligence Technologies in Cancer Treatment for Older Adults: A Systematic Review[J].Journal of Clinical Medicine,2024,13(17):4979-4979.

Hoang T D, Dinstag G, Shulman D E, et al.A deep-learning framework to predict cancer treatment response from histopathology images through imputed transcriptomics.[J].Nature cancer,2024,5(9):1305-1317.

Hu Xiaoyi, Wang Di, Ji Muhuo, et al. Prospect of machine learning in the field of anesthesiology [J]. Journal of Clinical Anesthesiology, 2024,40 (06): 634-638.

Fijten R R, Hasannejadasl H, Offermann J C, et al.1782: Patients perspectives on AI and decision making in cancer care[J].Radiotherapy and Oncology,2024,194(S1):S2931-S2933.

Correction to: Artificial intelligence electrocardiogram as a novel screening tool to detect a newly abnormal left ventricular ejection fraction after anthracycline-based cancer therapy[J]. European journal of preventive cardiology,2024,31(5):640-640.

Huang Jiangyuan, Wang Jingjing, Zhang Liangqing. Progress in the application of AI machine learning in thoracic anesthesia [J]. Chinese Pharma, 2024,19 (02): 308-311.

Shahzad K, Zanona A M, Elzaghmouri M B, et al. Using Artificial Intelligence And Machine Learning Approaches To Enhance Cancer Therapy And Drug Discovery: A Narrative Review[J]. Journal of Ayub Medical College, Abbottabad : JAMC,2024,36(1):183-189.

Derbal Y. Adaptive Cancer Therapy in the Age of Generative Artificial Intelligence[J].Cancer control : journal of the Moffitt Cancer Center, 2024,3110732748241264704-10732748241264704.

Pajuelo A. A Perspective Review of Cancer Therapy (Part II): Adoptive Cell Transfer, Metabolic Therapy, and Artificial Intelligence[J].Science Insights, 2023,43(6):

Geza H, Pietro M, Raffaella M. Artificial intelligence-assisted electrocardiography: a new and easily accessible approach for diagnosing cancer therapy-related cardiac dysfunction.[J].European journal of preventive cardiology,2023,

Shan C, H B K, B M F, et al.Use of Artificial Intelligence Chatbots for Cancer Treatment Information.[J].JAMA oncology,2023,

Zhu Mingzhu, Tao Lei, Zhang Fujun, et al. Advances in perioperative difficult airway management [J]. Shanghai Medicine, 2023, 46(05):318-323. DOI:10.19842/j.cnki.issn. 0253-9934.2023.05.012.

Dipesh U, Dongxiao Z, Jack H W. ChatGPT-A promising generative AI tool and its implications for cancer care[J]. Cancer, 2023, 129(15).

Andreas C, Nikolina D. Big Data, Machine Learning, and Artificial Intelligence to Advance Cancer Care: Opportunities and Challenges[J].Seminars in oncology nursing,2023,39(3):151429-151429.

Y. L S, Gift E, Krishna D, et al. Commentary: “Multimodality advanced cardiovascular and molecular imaging for early detection and monitoring of cancer therapy-associated cardiotoxicity and the role of artificial intelligence and big data”[J]. Frontiers in Cardiovascular Medicine,2023,10982028-982028.