Dr. Jay Anders, CMO at Medicomp, cautions that clinicians are concerned about AI tools’ hallucinations and inconsistent outputs, so more governance and stronger guardrails are needed to get their buy-in.
David Lareau, President and CEO of Medicomp Systems, argues that healthcare AI is failing not because of poor data quality in isolation, but because clinical data remains structurally fragmented across …Continue
On this episode of Tell Me Where IT Hurts, host Jay Anders, MD, welcomes Piyanun Yenjit, founder and managing director of APUK Co., Ltd. and a longtime leader in hospital …Continue
At A Glance Four safeguards behind trustworthy healthcare AI 1Purpose-built clinical data foundation A clinical vocabulary engineered for point-of-care use with full synonymy, specialty coverage, and mappings to SNOMED CT, …Continue
How reliable is the clinical data powering healthcare AI? In this episode of The Akros Advantage, Demi Radeva speaks with Dr. Jay Anders, CMO at Medicomp Systems, about the hidden …Continue
The Bottom Line Most healthcare organizations have solved data aggregation. The unsolved problem is activation – making clinical data computable, contextual, and trustworthy enough for clinicians, analytics teams, and AI …Continue
Kimberly Brandt, Chief Operating Officer and Deputy Administrator at the Centers for Medicare & Medicaid Services (CMS), joins host Jay Anders, MD, Chief Medical Officer of Medicomp Systems, on this …Continue
Most healthcare AI products share a critical blind spot: there’s no validated clinical knowledge layer beneath the model. Without it, outputs are inconsistent, unexplainable and difficult to trust at scale. …Continue
Key Insights When AI reads a diagnosis or procedure billing code, it sees only what fits inside that administrative category — the clinical specificity is not always captured with structured …Continue
A decade after health care dreaded the complexity of ICD-10, the industry now faces a bigger problem: diagnosis codes still aren’t specific enough to safely power AI-driven clinical decision-making.
AI scribes sound confident even when wrong. CDI experts break down hallucinations vs. context errors — and how to catch what review misses.
Ambient AI codes for the payer, not the patient — and that gap could cost patients access to precision therapies.
Key Insights The clinical context gap is the difference between a billing code chosen to process a claim and the structured clinical diagnosis a physician needs to treat a patient …Continue
