According to the World Health Organization, approximately 27% of the global population suffers from sleep-related issues. Data from the Chinese Sleep Research Society reveals that over 500 million people in China experience sleep disorders, with the average sleep duration for adults being just 6.75 hours—well below the healthy standard.

Sleep disorders are not just symptoms but also significant manifestations of central nervous system (CNS) diseases. Due to the difficulty of penetrating the blood-brain barrier and the complexity of disease mechanisms, CNS drug development has long been considered a "black hole" inR&D.

However, with recent technological breakthroughs, substantial progress has been made in treatingindications such as Alzheimer's disease, schizophrenia, depression, migraines, and insomnia. Despite these advancements, the development of new CNS drugs still faces numerous challenges, and the widespread application of AI is seen as a potential solution to address these issues.

Data Without “Amnesia” — Precision in Every Record

Patients with CNSdisorders often experience cognitive impairments or other behavioral issues. Traditional paper-basedCOAs rely heavily on patients’ memory and comprehension, which can lead to inconsistent or missing data and compromise the reliability ofstudy outcomes. For instance, in Alzheimer’s disease studies, patients may struggle to accurately complete diaries or recall symptom changes, increasing the likelihood of data bias during site visits.

Powered by AI, electronic Clinical Outcome Assessments (eCOA) enable real-time data capture alongside automated processing and analysis, significantly enhancing dataquality. Intelligent algorithms can instantly detect potential risks or anomalies—for example, identifying subtle trends in motorfunctionscores among Parkinson’s patients. Meanwhile, AI-powered remoteinspection ensures greater data consistency, minimizes manual errors, and mitigates the risk of missing data.

ACCMED-eCOA — AI-Driven, Exceptionally Advanced

1.Compliant withgeneral multi-therapeutic standards, flexibly adaptable to common CNS assessmentCOAs, includingMMSE, MoCA, UPDRS, CDR,to ensure data accuracy and cross-study comparability.

2. AI-assisted adaptive testing leverages intelligent algorithms to dynamically adjust the difficulty and sequence of questions , reducing redundancy in traditional validation and improving testing efficiency.

3. Support global trials and multilingual settings by optimizing cultural and contextual relevance, ensuring COAs are easily understood across regions. For example, in multinational Alzheimer’s disease trials, it can automatically adapt the language of COAs like HADS and NPI-Q to fit local expression habits.