Machine learning-based post-hoc analysis of gender-specific pharmacokinetics and pharmacodynamics of piperacillin in sepsis

Machine learning-based post-hoc analysis of gender-specific pharmacokinetics and pharmacodynamics of piperacillin in sepsis - GAPS

Status

Active, not recruiting

Phases

Unknown

Study type

Observational

Source

DRKS

Registry ID

DRKS00037606

Enrollment

2000

Registered

2025-08-04

Start date

2025-08-08

Completion date

Unknown

Last updated

2026-02-02

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

Conditions

A41

Interventions

Group 1: Patients who received antibiotic therapy with piperacillin as part of intensive care treatment for sepsis and who had at least one measurement of piperacillin serum levels. The primary aim of

Eligibility

Sex/Gender

All

Age

18 Years to No maximum

Inclusion criteria

Inclusion criteria: * Antibiotic therapy with piperacillin as part of intensive care treatment for sepsis * At least one piperacillin serum level measurement performed during the course of treatment

Exclusion criteria

Exclusion criteria: * incomplete data set

Design outcomes

Primary

Measure	Time frame
In this study, there is no primary endpoint in the conventional sense. The primary study objective is the completed development of a machine learning model that has been successfully tested and validated within our dataset. The aim of the study is to quantify the influence of sex on serum target level attainment and, consequently, on the dosage requirements of piperacillin, taking into account individual and clinical factors, as well as to develop precise, sex-sensitive dosing recommendations that enable optimized therapy planning and implementation. The exploratory investigation of sex-specific differences focuses on classification of individuals as a primary task of unsupervised machine learning. In the context of antibiotic therapy, clustering methods such as self-organizing maps can be used to model sex-specific differences in dosage requirements and target level attainment, while simultaneously accounting for interactions with other clinically relevant variables such as age, kidney function, and body composition.	—

Measure

Time frame

In this study, there is no primary endpoint in the conventional sense. The primary study objective is the completed development of a machine learning model that has been successfully tested and validated within our dataset. The aim of the study is to quantify the influence of sex on serum target level attainment and, consequently, on the dosage requirements of piperacillin, taking into account individual and clinical factors, as well as to develop precise, sex-sensitive dosing recommendations that enable optimized therapy planning and implementation. The exploratory investigation of sex-specific differences focuses on classification of individuals as a primary task of unsupervised machine learning. In the context of antibiotic therapy, clustering methods such as self-organizing maps can be used to model sex-specific differences in dosage requirements and target level attainment, while simultaneously accounting for interactions with other clinically relevant variables such as age, kidney function, and body composition.

—

Countries

Germany

Contacts

Public ContactUte Chiriac

Apotheke des Universitätsklinikums Heidelberg

ute.chiriac@med.uni-heidelberg.de+49 (0) 6 221 56 6761

Outcome results

None listed

Source: DRKS (via WHO ICTRP) · Data processed: Feb 7, 2026