MediKarma Validates Agentic AI in Clinical Study With Dallas Endocrinology

Feb 22, 2026
MediKarma reported that its Agentic AI platform achieved a 50% A1C improvement rate in a 120-day study with Dallas Endocrinology, leading to a 20,000-unit deployment with Family Health Choice.

San Francisco-based MediKarma reported successful results from a 120-day clinical intervention study with Dallas Endocrinology, validating its Agentic AI platform’s clinical efficacy, announced in a press release. The study showed that 50% of participants reduced or maintained healthy A1C levels, while the platform achieved a 35% monthly active user rate and 100% participant engagement.

The trial deployed “Diabetes Jill,” an autonomous agent functioning as a 24/7 extension of the care team. MediKarma’s system connects to healthcare providers, retrieves patients’ clinical histories, and builds personalized profiles within minutes, enabling proactive patient guidance without manual data handling.

The company stated that these outcomes supported a 20,000-unit deployment with Family Health Choice, which selected MediKarma’s platform to automate patient engagement and improve care gap closure. MediKarma plans to enhance the system further using behavioral science models to increase engagement and clinical performance.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Life AI Weekly or Daily AI Brief.

Also, consider following us on social media:

Healthcare & Life Sciences AI AI Brief AI Brief (X)
Free newsletter

Life AI Weekly

Weekly coverage of AI applications in healthcare, drug development, biotechnology research, and genomics breakthroughs.

Guide
Specialist Ambient Medical Scribe Vendors

Specialist Ambient Medical Scribe Vendors

AI scribes that turn medical consultations into draft clinical notes

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.