Skip to content

Self-Supervised Multimodal Learning for Computational Anesthesia Drug Repurposing: Leveraging Foundation Models to Decode Cross-Modal Relationships Between Molecular Structures, Neural Signatures, and Perioperative Outcomes

Self-Supervised Multimodal Learning for Computational Anesthesia Drug Repurposing: Leveraging Foundation Models to Decode Cross-Modal Relationships Between Molecular Structures, Neural Signatures, and Perioperative Outcomes

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2600128757
Enrollment
Unknown
Registered
2026-07-24
Start date
2026-07-24
Completion date
Unknown
Last updated
2026-08-03

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

None

Interventions

Observation Group:None

Sponsors

Shenzhen People's Hospital
Lead Sponsor

Eligibility

Sex/Gender
All
Age
18 Years to No maximum

Inclusion criteria

Inclusion criteria: 1.Age = 18 years old; 2.Underwent non-cardiac elective surgery at Shenzhen People's Hospital between May 20, 2025, and May 20, 2026; 3.Availability of analyzable routine perioperative clinical data within the Anesthesia Information Management System (AIMS) and/or Electronic Medical Record (EMR) system;

Exclusion criteria

Exclusion criteria: 1.Patients undergoing cardiac surgery, emergency surgery, or trauma surgery; 2.Pregnant or lactating women; 3.Severe loss of critical demographic or outcome data, rendering analysis impossible; 4. The patient had explicitly refused to have their medical records used by researchers.

Design outcomes

Primary

MeasureTime frame
In-hospital/30-day mortality;Postoperative Acute Kidney Injury (AKI);

Secondary

MeasureTime frame
Intraoperative hypotension;Exploratory association between drug exposure and outcomes;

Countries

China

Contacts

Public ContactXintong Dong

Shenzhen People's Hospital

dxt0812@126.com+86 755 2553 3018

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Aug 10, 2026