Validation of Machine Learning Based Personalized Nutrition Algorithm to Reduce Postprandial Glycemic Excursions Among North American Individuals With Newly Diagnosed Type 2 Diabetes

Not Applicable

Terminated

Brief Summary: This is an initial validation study of the Personal Nutrition Project (PNP) algorithm in a North American population with recently diagnosed Type 2 Diabetes (T2D). This is a 2-stage, single-group feeding study in 20 individuals, including 10 participants managed with lifestyle alone, and 10 managed with lifestyle plus metformin.

Detailed Description: The PNP algorithm, which uses a machine learning algorithm to predict postprandial glycemic, may be efficacious for generating tailored dietary advice to moderate the participant's glycemic response to food.

Recruitment & Eligibility

Inclusion Criteria

Age >21 years to <70 years
Diagnosed with T2DM within 2 years with an HbA1c<7%
Diabetes management by metformin or lifestyle intervention
Fasting C-peptide ≥ 0.5 mg/mL (0.17 nmol/L) (to exclude those for whom hyperglycemic exposure is driven by β-cell failure rather than dietary behaviors, as well as those requiring escalation of the medication regime)
Ownership a smart phone and are willing to use it to monitor multiple factors influencing glycemic response to glycemia (e.g., sleep, physical activity, diet, stress, medication, and hunger)

Exclusion Criteria

are unable or unwilling to provide informed consent;
are unable to participate meaningfully in an intervention that involves self-monitoring using software available in English (e.g., due to uncorrected sight impairment, illiterate, non-English-speaking, dementia);
are pregnant, are currently trying to become pregnant, or who become pregnant during the study
are institutionalized (e.g., in a nursing home or personal care facility, or those who are incarcerated and have limited control over self-management)
have had or are planning to have bariatric surgery during the study
have a history of heart disease, kidney disease, or retinopathy (to rule-out those with long-standing, undiagnosed T2D)
those with an active infection requiring antibiotics in the last 3 months or who develop an active infection requiring antibiotics during the study;
those who use acetaminophen and are unwilling or unable to discontinue its use during the study (acetaminophen affects CGM accuracy)39
immunosuppressive drugs within three months prior to participation and
Chronically active inflammatory or neoplastic disease in the three years prior to enrollment.
Patients with known food allergy.

Primary Outcome Measures

Name	Time	Method
Observed Incremental Area Under the Curve (iAUCobs)	2 Hours	Observed incremental area under the curve (iAUCobs) at 2 hours following each meal and snack will be evaluated via CGM using the Abbott Freestyle Libre Pro, which captures interstitial glucose every 5 minutes. A sensor is inserted into the participant's upper arm. Participants will be blinded to glycemia tracings.

Secondary Outcome Measures

Name	Time	Method

Locations (1): New York University School of Medicine
🇺🇸
New York, New York, United States
New York University School of Medicine
🇺🇸New York, New York, United States