A Model of Computer-assisted Prescription of Erythropoiesis-stimulating Agents (ESA) in Patients Under Hemodialysis

NCT04185519 | Completed

• 1 other identifier: KMUHIRB-F(I)-20190094
• Study Type: interventional
• Target: 126
• Locations: 1 country
• Sites: 1

Brief Summary

This is a randomized, double-blind controlled trial to compare AI (model) with the physician on prescribing ESA dose to maintain hemoglobin near the therapeutic target, 11g/dl.

Conditions

End Stage Renal Disease

Outcome Measures

Primary Outcomes (1)

• hemoglobin (Hb) levels

  Primary analysis will be conducted after database lock and unblinded. For hemoglobin (Hb) levels, the logistic regression model will include treatment (AI vs. conventional), center, and treatment-by-center interaction as factors, and mean change of the hemoglobin (Hb) levels from 11g/dl during the evaluation period as dependent variables, model-based point estimates and 95% confidence interval (CI) for the treatment effects will be calculated to test the primary outcome

  6 monthes

Study Arms (2)

AI (model)

EXPERIMENTAL

This is a randomized, double-blind controlled trial to compare AI (model) with the physician on prescribing ESA dose to maintain hemoglobin near the therapeutic target, 11g/dl. A blind check by another physician for the prescriptions from both physician and AI (model) is arranged for safety purpose.

Device: AI (model)

DR1

NO INTERVENTION

Another physician will fail the prescription if the prescribed ESA dose, by his/her experience, will lead the participant's hemoglobin outside the range between 9 and 13 g/dl.

Interventions

AI (model) DEVICE

The process of the experiment (brief describe) This is a randomized, double-blind controlled trial to compare AI (model) with the physician on prescribing ESA dose to maintain hemoglobin near the therapeutic target, 11g/dl. A blind check by another physician for the prescriptions from both physician and AI (model) is arranged for safety purpose. Another physician will fail the prescription if the prescribed ESA dose, by his/her experience, will lead the participant's hemoglobin outside the range between 9 and 13 g/dl. Once the failed rate by AI is higher than the physician is 5%, , the study will be terminated. There will be three periods, namely ry 3 months.

AI (model)

Eligibility Criteria

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

You may qualify if:

• signed informed consent
• Age older than 20 year old.
• End stage renal disease under regular hemodialysis with three times per week and duration of each session at least 4 hours
• Having at least consecutive 6 months data of both Hb and biochemical study during dialysis before enrollment and at least one Hb level within the range of 11-12 g/dl
• Having at least one prescription of ESA supplement to keep Hb within the range of 10-12 g/dl in the past 6 months before the enrollment
• Having received ESA of the same brand at least 6 months before the enrollment

You may not qualify if:

• Ever receiving blood transfusion in the past 12 months
• Active bleeding with blood loss more than250cc in 3 months before the enrollment
• Active infection or malignancy
• Study subject can not follow with the study protocol 3. End of Study
• The eligible subject will not be allowed to continue the study once informed consent is withdrawn or event happening meets the following criteria:
• Taking extra ESAs, Androgens and iron-chelating agents
• Undergoing surgery with massive haemorrhage, or blood transfusion
• Receiving systemic chemotherapy or radiotherapy or immunosuppressive therapies.
• The end of study will be 6 months later after the randomization of last study subject or failed prescription rate higher than 5%, which comes earlier.

Sponsors & Collaborators

• Kaohsiung Medical University Chung-Ho Memorial Hospital: lead

Study Sites (1)

Kaohsiung Medical University Chung-Ho Memorial Hospital (KMUH)

Kaohsiung City, TW, 807, Taiwan

Location

Related Publications (1)

• Lim LM, Lin MY, Hsu C, Ku C, Chen YP, Kang Y, Chiu YW. Computer-assisted prescription of erythropoiesis-stimulating agents in patients undergoing maintenance hemodialysis: a randomized control trial for artificial intelligence model selection. JAMIA Open. 2025 Mar 27;8(2):ooaf020. doi: 10.1093/jamiaopen/ooaf020. eCollection 2025 Apr.

  PMID: 40161549 DERIVED

MeSH Terms

Conditions

Kidney Failure, Chronic

Interventions

Models, Biological

Condition Hierarchy (Ancestors)

Renal Insufficiency, Chronic; Renal Insufficiency; Kidney Diseases; Urologic Diseases; Female Urogenital Diseases; Female Urogenital Diseases and Pregnancy Complications; Urogenital Diseases; Male Urogenital Diseases; Chronic Disease; Disease Attributes; Pathologic Processes; Pathological Conditions, Signs and Symptoms

Intervention Hierarchy (Ancestors)

Models, Theoretical; Investigative Techniques

Study Design

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

Model Details: Informed consent must be signed before any procedures related to the study for any participant. The subject who meets the inclusion and exclusion criteria will be enrolled and a total of 126 subjects needed to have the power to test the hypothesis. In addition to the Hb levels and EAS doses, all HD-related bio information data in 12 consecutive months before enrollment will be uploaded into the model for further ESA dose prediction. Before randomization, the study subject will continue to receive the ESA by the prescription from the physician. Randomization period All eligible subjects will be randomized 1:1 by their age, gender, and HD vintage into control arm and intervention arm. After randomization, the study subject will enter the study after the nearest Hb measurement coming.

Study Record Dates

• First Submitted: November 17, 2019
• First Posted: December 4, 2019
• Study Start: July 24, 2019
• Primary Completion: July 30, 2020
• Study Completion: July 30, 2020
• Last Updated: September 1, 2021

Record last verified: 2019-09

Data Sharing

• IPD Sharing: Will not share

Locations

TW (1)