Machine learning for predicting acute kidney failure using high-frequency vital data during cardiac surgery with cardiopulmonary bypass

Status

Recruiting

Phases

Unknown

Study type

Observational

Source

DRKS

Registry ID

DRKS00038853

Enrollment

800

Registered

2026-01-05

Start date

2025-09-22

Completion date

Unknown

Last updated

2026-01-12

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

Conditions

Kidney failure occurring within 72 hours according to KDIGO criteria.

Interventions

Group 1: Retrospective analysis of peri-operative routine data, including high-frequency vital-sign data, from surgeries performed with cardiopulmonary bypass (2025).

Eligibility

Sex/Gender

All

Age

18 Years to No maximum

Inclusion criteria

Inclusion criteria: Cardiac surgical operation with cardiopulmonary bypass (heart-lung machine)

Exclusion criteria

Exclusion criteria: Pre-existing renal failure Cardiac surgical operative procedure with heart-lung machine performed within the past 30 days

Design outcomes

Primary

Measure	Time frame
Kidney failure occurring within 72 hours according to KDIGO criteria. This is used as a binary classifier for the purpose of evaluation.	—

Secondary

Measure	Time frame
Postoperative intensive-care treatment duration and 30-day mortality.	—

Countries

Germany

Contacts

Public ContactDavid Bürger

Med. Hochschule Hannover

buerger.david@mh-hannover.de+495322289

Outcome results

None listed

Source: DRKS (via WHO ICTRP) · Data processed: Feb 4, 2026