CONNECTEVE's AI Tool Validated for Knee Osteoarthritis Diagnosis

By StartupKorea Business Desk | Jun 08, 2026

AI Innovations in Knee Osteoarthritis Diagnosis

CONNECTEVE, a South Korean startup specializing in healthcare AI, has announced significant validation for its knee X-ray diagnostic tool, CONNEVO KOA. Recent studies published in international journals have confirmed the tool's high diagnostic accuracy, clinical utility, and potential for cost reduction in treating knee osteoarthritis.

Clinical Validation and Performance

The CONNEVO KOA system was developed using a dataset of approximately 40,000 knee X-rays from the Osteoarthritis Initiative, supported by the National Institutes of Health (NIH). The AI tool demonstrated an impressive accuracy rate of 94.2% in classifying the severity of osteoarthritis based on the Kellgren-Lawrence (KL) grading system. This was highlighted in a study published in the Journal of Arthroplasty, which analyzed 2,546 knee X-rays from two major hospitals in South Korea.

Furthermore, the tool proved particularly effective in cases where human experts often disagree, maintaining an area under the curve (AUC) of 0.87 for moderate severity classifications (KL grade 2), a figure the company claims is among the highest reported in public studies.

Enhancing Medical Staff Efficiency

A separate study presented at the International Congress of Knee Surgery and Sports Traumatology (ICKKS) in May 2026 further demonstrated the AI's potential to assist medical professionals. In this multi-center study, seven radiologists evaluated 1,000 knee X-rays without AI assistance and then with the AI's help after four weeks. The results showed significant improvements in sensitivity, specificity, and accuracy across the board, particularly among less experienced radiologists, who performed comparably to their more seasoned counterparts when aided by the AI.

Cost-Effectiveness and Future Applications

The economic impact of the CONNEVO KOA tool was also evaluated in a study published in the Journal of Bone and Joint Surgery. The findings suggested that the AI-assisted diagnostic process could save approximately $3,125 per patient while also increasing quality-adjusted life years (QALY) by 0.26 years. However, the study noted that these results are based on model estimates and require further validation in real clinical settings.

CONNECTEVE is set to conduct further evaluations in actual clinical environments this year, having formed a consortium with prominent hospitals like Samsung Medical Center and Chung-Ang University Hospital as part of a government-supported initiative.

Regulatory Approvals and Future Directions

The company has also made strides in regulatory approvals, having received Class IIa certification under the CE Medical Device Regulation in Europe and recognition as a new medical technology by the Abu Dhabi Department of Health in the UAE. CEO Doo-Hyun Noh emphasized the importance of standardizing KL grading for knee osteoarthritis diagnosis, stating that CONNECTEVE aims to expand its AI capabilities beyond diagnostic assistance to include X-ray-based biomarkers and treatment decision support.

Founded in 2021 by Professor Doo-Hyun Noh from Seoul National University Hospital, CONNECTEVE has raised a total of 18.8 billion KRW (approximately $14 million) in funding, including a Series A round in 2025.

Source: Platum. This is an original English briefing based on the cited report.