ELITE, Evidence-Based Longevity Interventions and Targeted Engagement, was a randomized, open-label, two-active-arm Phase IIa pilot conducted at Sheba Medical Center in Ramat Gan, Israel. The purpose of ELITE was to characterize individual response to multidomain healthy-aging interventions over approximately eight weeks by combining a clinical measure of muscular, immune and cognitive function with frequent digital monitoring between study visits. The primary outcome was change from baseline to Week 8 in the Muscular-Immune-Cognitive Composite (MIC-C). The study hypothesis was that repeated digital measurements could capture the trajectory of individual response over time and relate that trajectory to clinical change measured at Week 8. Prespecified secondary outcomes included safety, study completion and overall protocol adherence.
The protocol-defined intervention was algorithmic polytherapy, integrating a multicomponent pharmacologic and investigational-product regimen with longitudinal digital response monitoring and physician-supervised decision support. In this eight-week pilot, randomized treatment assignments remained fixed. Algorithm-derived response states were generated and reviewed by physicians but did not trigger treatment reassignment.
ELITE enrolled 31 community-dwelling adults aged 50 to 80 years without diabetes and with a body-mass index of at least 25 kg/m2. Participants were randomized 1:1 to one of two active treatment regimens. Arm A received metformin plus semaglutide, and Arm B received metformin plus empagliflozin. Both groups also received the investigational AgeBiotics products AB-01 and AB-02 as common components of the multidomain intervention. Individual study products could be interrupted or discontinued for clinical or safety reasons under physician supervision.
Between clinic visits, participants completed structured assessments through the ANI.AI application, including tongue, left-eye, right-eye, face and wrist imaging, a short micro-survey and a voice recording. Multispectral measurements of the tongue, face and wrist were collected with a dedicated capture device. These repeated digital measurements were integrated with scheduled clinical, functional, laboratory and multi-omic assessments to create a longitudinal view of biological and functional change during treatment.
The ANI.AI platform generated a Composite Response Score (CRS/ADAPT Score) from longitudinal digital biomarker data. The CRS tracked change relative to each participant's baseline and was used within a Bayesian response framework with four prespecified states for physician review: KEEP, AUGMENT, SWITCH and STOPP. The study also included a complementary longitudinal digital health composite to characterize broader multidomain change across repeated digital measurements. These digital measures were prespecified for evaluation in relation to the Week 8 MIC-C clinical outcome.