高级检索

人工智能肠鸣音监测对优化重度颅脑损伤患者早期肠内营养支持时机的价值

Value of artificial intelligence in monitoring bowel sound in optimizing timing of early enteral nutrition support for patients with severe craniocerebral injury

    摘要
  • 摘要:
    目的 探讨基于人工智能的肠鸣音(BS)监测对优化重度颅脑损伤(sTBI)早期肠内营养(EEN)支持时机的价值。
    方法 选取sTBI患者166例作为研究对象，并采用随机数字法分为对照组(n=83)和观察组(n=83)。对照组采用人工评估判定肠内营养支持时机; 观察组采用基于人工智能的BS监测判定肠内营养支持时机。观察2组患者的肠内营养喂养耐受度、喂养量、营养支持相关指标、营养指标和并发症发生情况。
    结果 对照组营养支持第1、3、7天的肠内营养耐受评估量表评分和喂养不耐受(FI)发生率高于观察组，差异有统计学意义(P < 0.05)。观察组营养支持前3 d、>3~7 d和>7~14 d平均每日喂养量高于对照组，差异有统计学意义(P < 0.05)。观察组达到目标量70%的时间为(78.25±12.08) h, 短于对照组的(90.94±15.31) h, 差异有统计学意义(P < 0.05)。营养支持第1、3、7天的胃残余容积量(GRV)少于对照组，差异有统计学意义(P < 0.05)。营养支持4周后，观察组的白蛋白(ALB)、前白蛋白(PA)和小腿围(CC)高于对照组，差异有统计学意义(P < 0.05)。观察组发生并发症患者占比为37.35%, 低于对照组的60.24%, 差异有统计学意义(P < 0.05)。
    结论 基于人工智能的BS监测可缩短sTBI患者达到肠内营养目标喂养量的时间，降低FI发生风险，并为sTBI患者EEN的启动时机提供关键临床决策支持。

     

    Abstract:
    Objective To explore the value of artificial intelligence-based bowel sound (BS) monitoring in optimizing the timing of early enteral nutrition (EEN) support in patients with severe traumatic brain injury (sTBI).
    Methods A total of 166 sTBI patients were selected as the study subjects, and randomly divided into control group (n=83) and observation group (n=83) using the random number method. In the control group, the timing of enteral nutrition support was determined by manual assessment, while in the observation group, it was determined by artificial intelligence-based BS monitoring. The enteral nutrition feeding tolerance, feeding volume, nutrition support-related indicators, nutritional indicators and the occurrence of complications were observed in both groups.
    Results On the 1st, 3rd and 7th days of nutrition support, the scores on the enteral nutrition tolerance assessment scale and the incidence of feeding intolerance (FI) in the control group were significantly higher than those in the observation group (P < 0.05). The average feeding volumes in the observation group during the first 3 days, >3 to 7 days, and >7 to 14 days of nutrition support were significantly higher than those in the control group (P < 0.05). The time to reach 70% of the target volume in the observation group was (78.25±12.08) h, which was significantly shorter than (90.94±15.31) h in the control group (P < 0.05). The gastric residual volumes (GRV) on the 1st, 3rd and 7th day of nutrition support were significantly lower in the observation group than those in the control group (P < 0.05). After 4 weeks of nutrition support, the albumin (ALB), prealbumin (PA) and calf circumference (CC) in the observation group were significantly higher than those in the control group (P < 0.05). The overall complication rate in the observation group was 37.35%, which was lower than 60.24% in the control group, with a statistically significant difference (P < 0.05).
    Conclusion Artificial intelligence-based BS monitoring can shorten the time for sTBI patients to reach the target enteral nutrition feeding volume, reduce the risk of FI, and provide crucial clinical decision support for determining the initiation timing of EEN in sTBI patients.

     

    • HTML全文
    • 参考文献(25)
    • 相关文章
    • 施引文献
  • 资源附件(0)

/

返回文章
返回