inContAlert: Machine Learning Algorithms for Individual Bladder Filling Level Prediction

NCT05952700 | Completed

• 1 other identifier: Az. O 1305/1 -GB
• Study Type: observational
• Target: 36
• Locations: 1 country
• Sites: 1

Brief Summary

The aim of this study is to evaluate the bladder filling level of the study participants using the inContAlert sensor. The generated data will be used for the evaluation and optimization of the machine learning algorithms to be able to make precise predictions about the individual bladder fill level. In particular, the hypothesis that the bladder filling level can be estimated by the algorithm will be tested. When testing the hypothesis, it should be determined which deviation (measured by the mean absolute percentage error) of the estimation/prediction differs from the actual value (obtained by measuring the urine output using a measuring cup in combination with kitchen scales).

Conditions

Monitoring of the Bladder Filling

Keywords

bladder monitoring; digital Health; bladder filling level; incontinence; neurourology; neurogenic bladder; spinal cord injury

Outcome Measures

Primary Outcomes (1)

• Difference between the predicted bladder filling level and the actual value

  Difference (measured as mean absolute error in percent) of the predicted bladder filling level (measured in ml) and the actual value (determined by measuring the volume of urine in ml with a measuring cup in combination with a kitchen scale).

  December 2023

Interventions

inContAlert DEVICE

InContAlert is a non-invasive sensor technology to measure the bladder filling level for incontinence patients. The device is fixed about 2cm above the pubic bone using a patch or strap and does not require surgery. The data collected from the patient is analyzed using deep learning algorithms. The bladder filling level determined in this way is then displayed on an app.

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

The selection of the study participants is based on a voluntary basis by inContAlert GmbH.

You may qualify if:

• informed consent

You may not qualify if:

• Missing informed consent

Sponsors & Collaborators

• inContAlert GmbH: lead
• University of Bayreuth: collaborator

Study Sites (1)

inContAlert GmbH

Bayreuth, Germany

Location

MeSH Terms

Conditions

Urinary Bladder, Neurogenic; Spinal Cord Injuries

Condition Hierarchy (Ancestors)

Neurologic Manifestations; Nervous System Diseases; Urinary Bladder Diseases; Urologic Diseases; Female Urogenital Diseases; Female Urogenital Diseases and Pregnancy Complications; Urogenital Diseases; Male Urogenital Diseases; Signs and Symptoms; Pathological Conditions, Signs and Symptoms; Spinal Cord Diseases; Central Nervous System Diseases; Trauma, Nervous System; Wounds and Injuries

Study Officials

• Jannik Lockl, Dr.

  inContAlert GmbH

  STUDY DIRECTOR

Study Design

• Study Type: observational
• Observational Model: CASE ONLY
• Time Perspective: PROSPECTIVE
• Sponsor Type: INDUSTRY
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: June 5, 2023
• First Posted: July 19, 2023
• Study Start: March 1, 2023
• Primary Completion: July 31, 2024
• Study Completion: July 31, 2024
• Last Updated: April 20, 2025

Record last verified: 2025-04

Data Sharing

• IPD Sharing: Will not share

Locations

DE (1)