The Cost-effectiveness of Artificial Intelligence Acute Kidney Injury Prediction Auxiliary Software (Acura AKI)

NCT06685367 | Recruiting

• 1 other identifier: Huede-113001
• Study Type: interventional
• Target: 3,600
• Locations: 1 country
• Sites: 1

Brief Summary

"Huede" AI Aided AKI Prediction Software, Acura AKI, uses machine learning algorithms to predict the risk of AKI within the next 24 hours and provide a ranking of feature importance. By using Acura AKI, physicians can assess the risk of AKI, focusing on high-risk patients to provide care decisions. This study will be conducted in a prospective randomized clinical trial in adult ICUs, implementing the Acura AKI system for predicting AKI. The study aims to determine whether early prediction and intervention using the Acura AKI system can improve the outcomes of critically ill patients with adverse kidney conditions. The study endpoint is to evaluate the cost-effectiveness of using Acura AKI, including the incidence of AKI, dialysis rates, mortality rates, length of hospital stay, and treatment costs.

Conditions

Acute Kidney Injury; Intensive Care; Renal Replacement Therapy

Keywords

Acute Kidney Injury; Intensive Care Units; Critical Ill; Prevention; Artificial Intelligence; Machine Learning; Clinical Decision Support System; Dialysis; Renal Replacement Therapy; Cost-effectiveness

Outcome Measures

Primary Outcomes (1)

• Acute kidney injury (AKI) incidence

  Acute kidney injury (AKI) incidence in ICU. AKI is defined by an increase in KDIGO creatinine stage.

  Assessed from time of randomization to time of AKI occurrence (within 7 days post randomization)

Secondary Outcomes (6)

• Percentage of recommendations implemented by the primary care team.

  24 hours after Randomization

• Dialysis rate

  Assessed from time of randomization to time of receipt of inpatient dialysis (within 14 days post randomization)

• Mortality rate

  Assessed from time of randomization to date of death from any cause, within 14 days of randomization

• Length of hospital stay

  Assessed from time of randomization to date of hospital discharge, assessed up to 30 days

• Change in treatment costs

  Assessed from time of randomization to 60 days post hospital discharge date, accessed up to 90 days

Study Arms (2)

With Acura AKI

EXPERIMENTAL

The group with Acura AKI will receive the Acura AKI software, which identifies high-risk AKI patients and sends alert messages to nephrologists and ICU pharmacists. Upon receiving the alert, they will make treatment suggestions.

Device: Acura AKI

Without Acura AKI

NO INTERVENTION

The group without Acura AKI will be managed based on standard medical procedures.

Interventions

Acura AKI DEVICE

When the AI algorithm (Acura AKI) identifies a high-risk AKI patient, nephrologists and ICU pharmacists will receive an alert message. Upon receiving the alert, they will review the patient's electronic health record and make treatment suggestions based on AKI bundle care protocols. They will also coordinate with the patient's primary care team to ensure that the recommendations are implemented

With Acura AKI

Eligibility Criteria

• Age: 20 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Over 20 years old
• Admitted to adult ICU
• Hospital stay of more than 30 hours

You may not qualify if:

• Known to have acute kidney injury at enrollment
• Currently undergoing hemodialysis treatment
• No available blood or urine test data
• Pregnant women
• HIV-positive patients
• Those who have not provided informed consent form

Sponsors & Collaborators

• Huede Healthtech Co., Ltd.: lead

Study Sites (1)

Taichung Veterans General Hospital (TCVGH)

Taichung, Taiwan

RECRUITING

MeSH Terms

Conditions

Acute Kidney Injury

Condition Hierarchy (Ancestors)

Renal Insufficiency; Kidney Diseases; Urologic Diseases; Female Urogenital Diseases; Female Urogenital Diseases and Pregnancy Complications; Urogenital Diseases; Male Urogenital Diseases

Study Officials

• Chun-Te Huang

  Taichung Veterans General Hospital (TCVGH)

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Chun-Te Huang

CONTACT

+8864-23592525; huangchunte@gmail.com

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: SINGLE
• Who Masked: PARTICIPANT
• Purpose: PREVENTION
• Intervention Model: PARALLEL
• Sponsor Type: INDUSTRY
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: October 11, 2024
• First Posted: November 12, 2024
• Study Start: October 17, 2024
• Primary Completion: September 15, 2025
• Study Completion: September 15, 2025
• Last Updated: November 12, 2024

Record last verified: 2024-11

Locations

TW (1)