以色列Schneider儿童医学中心Moshe Phillip课题组发现，自动人工智能决策可用于青年1型糖尿病患者的胰岛素剂量优化。2020年9月9日，国际知名学术期刊《自然—医学》发表了这一成果。

研究人员测试了基于自动化人工智能的决策支持系统（AI-DSS）指导的频繁胰岛素剂量调整是否与医生指导的控制血糖水平一样有效和安全。ADVICE4U是一项为期六个月、多中心、跨国、平行、随机对照、非劣效性的试验，研究对象是108位年龄在10-21岁之间的1型糖尿病患者，并使用胰岛素泵治疗（ClinicalTrials.gov编号NCT03003806）。

将参与者随机分配为1：1，在AI-DSS（AI-DSS组，n=54）或医师（内科医生，n=54）的指导下，每三周接受一次远程胰岛素剂量调整。AI-DSS组中主要疗效指标的结果：在目标葡萄糖范围内花费的时间百分比（70–180 mg dl^-1（3.9–10.0 mmol l^-1））在统计学上不逊于医师组（分别为50.2±11.1％和51.6±11.3％，P <1×10^-7）。AI-DSS组中读数低于54 mg dl^-1（<3.0 mmol^-1）的百分比在统计学上不逊于医师组（分别为1.3±1.4％和1.0±0.9％，P < 0.0001）。在医师组中报告了与糖尿病相关的三个严重不良事件（两个严重的低血糖、一个糖尿病性酮症酸中毒），而在AI-DSS分支中均未报告。

总之，使用自动决策支持工具来优化胰岛素泵设置并不逊色于专业糖尿病专科中心医师提供的强化胰岛素滴定。

据了解，尽管越来越多地采用胰岛素泵和连续葡萄糖监测设备，但大多数1型糖尿病患者仍未达到其血糖目标。这可能与缺乏专业知识或临床医生分析相关复杂数据的时间不足有关。

附：英文原文

Title: Insulin dose optimization using an automated artificial intelligence-based decision support system in youths with type 1 diabetes

Author: Revital Nimri, Tadej Battelino, Lori M. Laffel, Robert H. Slover, Desmond Schatz, Stuart A. Weinzimer, Klemen Dovc, Thomas Danne, Moshe Phillip

Issue&Volume: 2020-09-09

Abstract: Despite the increasing adoption of insulin pumps and continuous glucose monitoring devices, most people with type 1 diabetes do not achieve their glycemic goals1. This could be related to a lack of expertise or inadequate time for clinicians to analyze complex sensor-augmented pump data. We tested whether frequent insulin dose adjustments guided by an automated artificial intelligence-based decision support system (AI-DSS) is as effective and safe as those guided by physicians in controlling glucose levels. ADVICE4U was a six-month, multicenter, multinational, parallel, randomized controlled, non-inferiority trial in 108 participants with type 1 diabetes, aged 10–21 years and using insulin pump therapy (ClinicalTrials.gov no. NCT03003806). Participants were randomized 1:1 to receive remote insulin dose adjustment every three weeks guided by either an AI-DSS, (AI-DSS arm, n=54) or by physicians (physician arm, n=54). The results for the primary efficacy measure—the percentage of time spent within the target glucose range (70–180mgdl1 (3.9–10.0mmoll1))—in the AI-DSS arm were statistically non-inferior to those in the physician arm (50.2±11.1% versus 51.6±11.3%, respectively, P<1×107). The percentage of readings below 54mgdl1 (<3.0mmoll1) within the AI-DSS arm was statistically non-inferior to that in the physician arm (1.3±1.4% versus 1.0±0.9%, respectively, P<0.0001). Three severe adverse events related to diabetes (two severe hypoglycemia, one diabetic ketoacidosis) were reported in the physician arm and none in the AI-DSS arm. In conclusion, use of an automated decision support tool for optimizing insulin pump settings was non-inferior to intensive insulin titration provided by physicians from specialized academic diabetes centers.

DOI: 10.1038/s41591-020-1045-7

Source: https://www.nature.com/articles/s41591-020-1045-7