Department of Computer Science and Applied Mathematics, Weizmann Institute of Science, Rehovot, Israel.
Department of Molecular Cell Biology, Weizmann Institute of Science, Rehovot, Israel.
Diabetes Care. 2021 Sep;44(9):1980-1991. doi: 10.2337/dc21-0162. Epub 2021 Jul 23.
To compare the clinical effects of a personalized postprandial-targeting (PPT) diet versus a Mediterranean (MED) diet on glycemic control and metabolic health in prediabetes.
We randomly assigned adults with prediabetes ( = 225) to follow a MED diet or a PPT diet for a 6-month dietary intervention and additional 6-month follow-up. The PPT diet relies on a machine learning algorithm that integrates clinical and microbiome features to predict personal postprandial glucose responses. During the intervention, all participants were connected to continuous glucose monitoring (CGM) and self-reported dietary intake using a smartphone application.
Among 225 participants randomized (58.7% women, mean ± SD age 50 ± 7 years, BMI 31.3 ± 5.8 kg/m, HbA, 5.9 ± 0.2% [41 ± 2.4 mmol/mol], fasting plasma glucose 114 ± 12 mg/dL [6.33 ± 0.67 mmol/L]), 200 (89%) completed the 6-month intervention. A total of 177 participants also contributed 12-month follow-up data. Both interventions reduced the daily time with glucose levels >140 mg/dL (7.8 mmol/L) and HbA levels, but reductions were significantly greater in PPT compared with MED. The mean 6-month change in "time above 140" was -0.3 ± 0.8 h/day and -1.3 ± 1.5 h/day for MED and PPT, respectively (95% CI between-group difference -1.29 to -0.66, < 0.001). The mean 6-month change in HbA was -0.08 ± 0.19% (-0.9 ± 2.1 mmol/mol) and -0.16 ± 0.24% (-1.7 ± 2.6 mmol/mol) for MED and PPT, respectively (95% CI between-group difference -0.14 to -0.02, = 0.007). The significant between-group differences were maintained at 12-month follow-up. No significant differences were noted between the groups in a CGM-measured oral glucose tolerance test.
In this clinical trial in prediabetes, a PPT diet improved glycemic control significantly more than a MED diet as measured by daily time of glucose levels >140 mg/dL (7.8 mmol/L) and HbA. These findings may have implications for dietary advice in clinical practice.
比较基于机器学习的个性化餐后靶向（PPT）饮食与地中海饮食（MED）对糖尿病前期患者血糖控制和代谢健康的临床疗效。
我们将 225 例糖尿病前期患者随机分为 MED 饮食组或 PPT 饮食组，进行为期 6 个月的饮食干预和随后 6 个月的随访。PPT 饮食依赖于一种机器学习算法，该算法整合了临床和微生物组特征，以预测个人的餐后血糖反应。在干预期间，所有参与者都通过智能手机应用程序接受连续血糖监测（CGM）和自我报告的饮食摄入。
在 225 名随机分配的参与者中（58.7%为女性，平均年龄为 50 ± 7 岁，BMI 为 31.3 ± 5.8 kg/m，HbA 为 5.9 ± 0.2%[41 ± 2.4 mmol/mol]，空腹血糖为 114 ± 12 mg/dL[6.33 ± 0.67 mmol/L]），有 200 名（89%）完成了 6 个月的干预。共有 177 名参与者还提供了 12 个月的随访数据。两种干预均降低了每日血糖水平>140 mg/dL（7.8 mmol/L）和 HbA 的时间，但 PPT 组的降低幅度明显大于 MED 组。6 个月时，“血糖>140”的平均变化分别为 MED 组-0.3 ± 0.8 小时/天和 PPT 组-1.3 ± 1.5 小时/天（95%CI 组间差值为-1.29 至-0.66，<0.001）。6 个月时，HbA 的平均变化分别为 MED 组-0.08 ± 0.19%（-0.9 ± 2.1 mmol/mol）和 PPT 组-0.16 ± 0.24%（-1.7 ± 2.6 mmol/mol）（95%CI 组间差值为-0.14 至-0.02，=0.007）。在 12 个月的随访中，组间差异仍具有统计学意义。CGM 测量的口服糖耐量试验中两组间无显著差异。
在这项糖尿病前期的临床试验中，与 MED 饮食相比，PPT 饮食在通过每日血糖水平>140 mg/dL（7.8 mmol/L）和 HbA 来改善血糖控制方面有显著改善。这些发现可能对临床实践中的饮食建议有影响。
