Skip to content

A Deep Learning Based Real-Time Prediction Model for Intraoperative Hemodynamic Events in Elderly Patients: Development and Validation

A Deep Learning Based Real-Time Prediction Model for Intraoperative Hemodynamic Events in Elderly Patients: Development and Validation

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2600125838
Enrollment
Unknown
Registered
2026-06-01
Start date
2026-06-01
Completion date
Unknown
Last updated
2026-06-08

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

Conditions

Intraoperative hypotension (IOH)

Interventions

Sponsors

Peking Union Medical College Hospital
Lead Sponsor

Eligibility

Sex/Gender
All
Age
65 Years to No maximum

Inclusion criteria

Inclusion criteria: 1.Model training phase: PUMCH retrospective cohort, January 1, 2013 to December 31, 2025. External validation phase: VitalDB database, August 2016 to June 2017. Prospective validation phase: PUMCH prospective cohort, January 1, 2026 to December 31, 2026. 2.Age >= 65 years. 3.General anesthesia.

Exclusion criteria

Exclusion criteria: 1.Surgeries requiring circulatory arrest, such as cardiac surgery, major vascular surgery, and other related procedures. 2.Procedures without airway-device-assisted mechanical ventilation, including laryngeal mask airway, endotracheal intubation, or tracheostomy, such as painless gastrointestinal endoscopy. 3.Patients with a definite preoperative diagnosis of hypotension, or with baseline SBP <90 mmHg or MAP <65 mmHg before induction. 4.Patients with more than 20% missing feature data.

Design outcomes

Primary

MeasureTime frame
Intraoperative hypotension (IOH);Post-induction hypotension (PIH);Intraoperative cardiac arrest (IOCA);

Countries

China

Contacts

Public ContactLe Shen

Peking Union Medical College Hospital

pumchshenle@163.com+86 10 6915 2021

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Jun 11, 2026