goFOODTM: An Artificial Intelligence System for Dietary Assessment.

Accurate estimation of nutritional information may lead to healthier diets and better clinical outcomes. We propose a dietary assessment system based on artificial intelligence (AI), named goFOODTM. The system can estimate the calorie and macronutrient content of a meal, on the sole basis of food images captured by a smartphone. goFOODTM requires an input of two meal images or a short video. For conventional single-camera smartphones, the images must be captured from two different viewing angles; smartphones equipped with two rear cameras require only a single press of the shutter button. The deep neural networks are used to process the two images and implements food detection, segmentation and recognition, while a 3D reconstruction algorithm estimates the food's volume. Each meal's calorie and macronutrient content is calculated from the food category, volume and the nutrient database. goFOODTM supports 319 fine-grained food categories, and has been validated on two multimedia databases that contain non-standardized and fast food meals. The experimental results demonstrate that goFOODTM performed better than experienced dietitians on the non-standardized meal database, and was comparable to them on the fast food database. goFOODTM provides a simple and efficient solution to the end-user for dietary assessment.

Reducing Inpatient Hypoglycemia in the General Wards Using Real-time Continuous Glucose Monitoring: The Glucose Telemetry System, a Randomized Clinical Trial.

OBJECTIVE: Use of real-time continuous glucose monitoring (RT-CGM) systems in the inpatient setting is considered investigational. The objective of this study was to evaluate whether RT-CGM, using the glucose telemetry system (GTS), can prevent hypoglycemia in the general wards. RESEARCH DESIGN AND METHODS: In a randomized clinical trial, insulin-treated patients with type 2 diabetes at high risk for hypoglycemia were recruited. Participants were randomized to RT-CGM/GTS or point-of-care (POC) blood glucose testing. The primary outcome was difference in inpatient hypoglycemia. RESULTS: Seventy-two participants were included in this interim analysis, 36 in the RT-CGM/GTS group and 36 in the POC group. The RT-CGM/GTS group experienced fewer hypoglycemic events (<70 mg/dL) per patient (0.67 [95% CI 0.34-1.30] vs. 1.69 [1.11-2.58], P = 0.024), fewer clinically significant hypoglycemic events (<54 mg/dL) per patient (0.08 [0.03-0.26] vs. 0.75 [0.51-1.09], P = 0.003), and a lower percentage of time spent below range <70 mg/dL (0.40% [0.18-0.92%] vs. 1.88% [1.26-2.81%], P = 0.002) and <54 mg/dL (0.05% [0.01-0.43%] vs. 0.82% [0.47-1.43%], P = 0.017) compared with the POC group. No differences in nocturnal hypoglycemia, time in range 70-180 mg/dL, and time above range >180-250 mg/dL and >250 mg/dL were found between the groups. The RT-CGM/GTS group had no prolonged hypoglycemia compared with 0.20 episodes <54 mg/dL and 0.40 episodes <70 mg/dL per patient in the POC group. CONCLUSIONS: RT-CGM/GTS can decrease hypoglycemia among hospitalized high-risk insulin-treated patients with type 2 diabetes.

The Effect of Continuous Glucose Monitoring in Preventing Inpatient Hypoglycemia in General Wards: The Glucose Telemetry System.

BACKGROUND: Few studies have examined the use of continuous glucose monitoring (CGM) devices in the general wards. The aim of this pilot study was to examine whether CGM readings can be successfully transmitted from the bedside to a central monitoring device in the nursing station, and whether a glucose telemetry system can prevent hypoglycemic events. METHODS: We present pilot data on 5 consecutive insulin treated general medicine patients with type 2 diabetes (T2DM) whose glucose values were observed with CGM (DEXCOM) and the results were transmitted to a central nursing station monitoring system using DEXCOM Follow and Share 2 software. CGM alarms were set-up at glucose <85 mg/dl. RESULTS: Duration of CGM observation was 4.0 ± 1.6 days (mean ± SD). During CGM, the overall time spent within blood glucose (BG) target of 70-179 mg/dl was 64.68 ± 15% (mean ± SD), on hypoglycemia (<70 mg/dl) was 0.30% ± 0.39, and time spent on hyperglycemia (≥180 mg/dl) was 35.02% ± 15.5. Two patients had 3 actions of prevention of potential hypoglycemia (CGM BG <70 mg/dl for >20 minutes) captured by alarm. No patients had CGM glucose value <54 mg/dl. CONCLUSIONS: This pilot study indicates that the use of CGM values in hospitalized patients can be successfully transmitted to a monitoring device in the nursing station, improving patient surveillance in insulin treated patients with diabetes.

Implementation findings from a hybrid III implementation-effectiveness trial of the Diabetes Prevention Program (DPP) in the Veterans Health Administration (VHA).

BACKGROUND: The Diabetes Prevention Program (DPP) is an effective lifestyle intervention to reduce incidence of type 2 diabetes. However, there are gaps in knowledge about how to implement DPP. The aim of this study was to evaluate implementation of DPP via assessment of a clinical demonstration in the Veterans Health Administration (VHA). METHODS: A 12-month pragmatic clinical trial compared weight outcomes between the Veterans Affairs Diabetes Prevention Program (VA-DPP) and the usual care MOVE!® weight management program (MOVE!). Eligible participants had a body mass index (BMI) ≥30 kg/m2 (or BMI ≥ 25 kg/m2 with one obesity-related condition), prediabetes (glycosylated hemoglobin (HbA1c) 5.7-6.5% or fasting plasma glucose (FPG) 100-125 mg/dL), lived within 60 min of their VA site, and had not participated in a weight management program within the last year. Established evaluation and implementation frameworks were used to guide the implementation evaluation. Implementation barriers and facilitators, delivery fidelity, participant satisfaction, and implementation costs were assessed. Using micro-costing methods, costs for assessment of eligibility and scheduling and maintaining adherence per participant, as well as cost of delivery per session, were also assessed. RESULTS: Several barriers and facilitators to Reach, Adoption, Implementation, Effectiveness and Maintenance were identified; barriers related to Reach were the largest challenge encountered by site teams. Fidelity was higher for VA-DPP delivery compared to MOVE! for five of seven domains assessed. Participant satisfaction was high in both programs, but higher in VA-DPP for most items. Based on micro-costing methods, cost of assessment for eligibility was $68/individual assessed, cost of scheduling and maintaining adherence was $328/participant, and cost of delivery was $101/session. CONCLUSIONS: Multi-faceted strategies are needed to reach targeted participants and successfully implement DPP. Costs for assessing patients for eligibility need to be carefully considered while still maximizing reach to the targeted population.