AI MEDICAL AGENTS · TERTIARY HOSPITALS
AI does not replace physicians.
It brings evidence to every decision.
MEV supports claims, coding, and referrals inside the EMR/OCS screens your clinicians already use. Every recommendation is backed by evidence, every decision is signed off by a physician, and the entire process is recorded.
Three steps,
inside the screens you already use.
There is no separate system to deploy. MEV recommends within the EMR/OCS workflow, and your clinicians make the final call.
EMR/OCS integration
MEV connects to your existing systems on the hospital's internal network. Data never leaves the hospital.
Analysis · recommendation · evidence
It generates recommendations and drafts for claims, coding, and referrals, and attaches supporting evidence to every result.
Physician sign-off · record
A physician makes the final decision. Who approved what, and when, is preserved in the audit trail.
Revenue, records, care delivery —
all three, at once.
The three service areas stand on equal footing. In each, MEV produces recommendations and drafts, and your clinicians sign off.
Reimbursement & Claims Optimization AI
Screens every claim for denial risk and missed charges before submission, protecting revenue you have rightfully earned.
- Identify denial risk before submission
- Recover missed charges
- Improve first-pass claim accuracy
Automated Clinical Coding & Recommendation
Translates clinical documentation, imaging reports, and procedure notes into recommended diagnosis and fee-schedule codes. The physician signs off.
- Reduce time spent on repetitive coding
- Reduce variation between coders
- Coding accuracy drives claims and statistical accuracy
Referral & Return-Referral AI Agent
Identifies patients ready for return referral, drafts referral and return-referral letters, and tracks return-referral rate metrics.
- Manage return-referral rates for Tertiary General Hospital designation review
- Reduce time spent drafting referral correspondence
We demonstrate value by what we do
and how we do it.
This is what MEV actually does. Measured outcomes from client hospitals will be published separately once the data has been validated.
One agent reads the full clinical and billing context
It interprets documentation, imaging reports, procedures, and claims together, recommending as a single coherent flow rather than as disconnected tools.
Prevent claim denials before submission
Detects items at risk of denial before the claim is filed, and points to the specific correction with supporting evidence.
Identify return-referral candidates automatically
Flags patients who meet the criteria and drafts referral and return-referral letters, supporting your metric management.
Automated clinical coding recommendations
Recommends diagnosis and fee-schedule codes from documentation, imaging reports, and procedures, and checks for omissions.
Evidence-linked claim accuracy
Connects coding and claims through shared evidence, improving accuracy and readiness for HIRA quality assessments.
Engineered to the standards
tertiary hospitals require.
Data never leaves the hospital. Decisions remain with physicians. Every step is traceable. And MEV is not a separate system — it operates inside the existing EMR/OCS workflow.
Data governance
Patient data never leaves the hospital network.
- ·On-premises and air-gapped deployment supported
- ·Data is pseudonymized before processing; no identifiable information is transmitted externally
- ·Designed to the requirements of the Medical Service Act and the Personal Information Protection Act
Regulatory compliance
Designed to the requirements of the Medical Service Act and the Personal Information Protection Act, with the clinical validity of every output verified.
- ·Compliance with the Medical Service Act and the Personal Information Protection Act built in from the design stage
- ·Built-in procedures for verifying clinical validity and supporting evidence
Human-in-the-loop
AI prepares the recommendation and the draft. The physician decides.
Explainable AI · XAI
No output is released without its evidence.
- ·Every recommendation cites the source documentation, codes, and guidelines behind it
- ·Source tags show at a glance which evidence each recommendation rests on
Built by a team fluent in
medicine, AI, and regulation.
MEV brings together clinical practice, claims review, AI engineering, and healthcare regulation in one team.
Leadership
Taehoon Ko, PhD
Founder & CEOMedical InformaticsAssistant Professor, Department of Medical Informatics, College of Medicine, The Catholic University of Korea · Director, Big Data Center, Seoul St. Mary’s Hospital
A medical informatics researcher specializing in medical AI and clinical big data at The Catholic University of Korea College of Medicine and Seoul St. Mary’s Hospital. Dr. Ko translates deep clinical-data expertise into MEV’s claims, coding, and referral products.
- Education
- BS and PhD, Department of Industrial Engineering, College of Engineering, Seoul National University (Data Mining)
- Experience
- Former Research Assistant Professor, Office of Hospital Information, Seoul National University Hospital
- Assistant Professor, Department of Medical Informatics, College of Medicine, The Catholic University of Korea
- Director, AI Center, Catholic Information Convergence Institute, The Catholic University of Korea
- Director, Big Data Center, Division of Smart Hospital, Seoul St. Mary’s Hospital
- Honors
- 2024 Medical Informatics Academic Award, Korean Society of Medical Informatics
- 2024 Minister of Health and Welfare Commendation (Contributions to the Utilization of Healthcare Data)
- 2026 Minister of Health and Welfare Commendation (Contributions to ICT-Based Healthcare Policy)
Sae Won Choi, MD
Chief Medical OfficerEmergency Medicine · Medical InformaticsAttending Physician, Department of Emergency Medicine, Bucheon Sejong Hospital
A board-certified emergency physician with nine years at Seoul National University Hospital, serving concurrently in the Office of Hospital Information and the Department of Emergency Medicine. Dr. Choi bridges frontline emergency care and hands-on hospital information systems experience into MEV’s products.
- Education
- MD, College of Medicine, Seoul National University
- Completed Doctoral Coursework in Biomedical Engineering, College of Medicine, Seoul National University
- Experience
- Former Clinical Professor, Office of Hospital Information, Seoul National University Hospital
- Former Attending Physician, Department of Emergency Medicine, Veterans Health Service Medical Center
- Attending Physician, Department of Emergency Medicine, Bucheon Sejong Hospital
- Training
- Residency in Emergency Medicine, Seoul National University Hospital (2006–2010)
The questions hospitals ask
before they adopt.
Answers to the most common questions about AI medical agents, data security, regulatory compliance, and integration with your existing EMR/OCS.
What does MEV do?
MEV is an AI medical agent company serving tertiary and university hospitals. We support three functions — reimbursement and claims optimization (RCM), automated clinical coding, and referral and return-referral management — inside the clinician's existing EMR/OCS workflow. Every recommendation is accompanied by evidence, and every decision is signed off by a physician.
How is an AI medical agent different from conventional medical AI?
MEV's agent is not a single-purpose diagnostic aid. It supports the entire administrative workflow from documentation through coding, claims, and referrals. It generates recommendations and drafts inside the EMR/OCS screens, with no separate system to adopt, and attaches a source, physician sign-off, and an audit trail to every output.
How does MEV prevent claim denials? (claims review · RCM)
Before submission, MEV screens each claim against the review criteria for items at risk of denial and for missed charges, and shows the evidence for why each item is flagged. It also monitors HIRA quality-assessment metrics — including the New Bundled Payment system, DRG, and non-covered services — to protect rightfully earned revenue.
How does clinical coding automation work?
From clinical documentation, imaging reports, and procedure notes, MEV recommends diagnosis (KCD), fee-schedule, and procedure codes, and displays the supporting text from the record alongside each recommendation. The AI only recommends. The physician makes the final decision, and finalized codes flow directly into EDI claims.
What does the referral and return-referral agent do?
It automatically identifies patients ready for return referral, drafts referral and return-referral letters, and matches patients with partner facilities. It supports management of the return-referral rate, a key metric in Tertiary General Hospital designation review.
Does the AI replace the physician's judgment?
No. MEV follows a human-in-the-loop principle. The AI presents recommendations and drafts together with their evidence, and the final decision always rests with the physician. Who approved what, and when, is recorded in the audit log.
Is patient data secure? Does it ever leave the hospital?
Patient data never leaves the hospital network. MEV supports on-premises and air-gapped (network-separated) deployment, pseudonymizes data before processing, and transmits no identifiable information externally.
How does MEV comply with the Medical Service Act, the Personal Information Protection Act, and related regulations?
MEV is designed to the requirements of the Medical Service Act and the Personal Information Protection Act from the outset, with built-in procedures for verifying the clinical validity and evidence of every output. We also assess applicability under the MFDS medical device (SaMD) framework.
How does MEV integrate with our existing EMR/OCS?
MEV is not a stand-alone application. It operates inside the EMR/OCS screens your clinicians already use, presenting recommendations without a separate login or duplicate data entry, and without interrupting the flow of care.
How can we evaluate the impact and see a demonstration?
In a 30-minute demonstration, we walk you through the area that matters most to you — claims, coding, or referrals. Measured outcomes from client hospitals will be published separately once the data has been validated. We do not present estimates as facts.
First, confirm the fit
with your hospital's workflow.
In a 30-minute demonstration, we walk you through the area that matters most to you — claims, coding, or referrals.
Request a Demo