Clinical Validation of an Artificial Intelligence System for the Interpretation of Laboratory Test Results Combined With a Structured Medical History

NCT07810491 | Not Yet Recruiting

• 3 other identifiers: LP004FEDS.01.02-IP.01-0078/24BNW/NWN/0052/KB1/34/26
• Study Type: interventional
• Target: 899
• Locations: 1 country
• Sites: 2

Brief Summary

This study evaluates a certified artificial intelligence (AI) based software system that automatically interprets laboratory test results in combination with a structured, dynamically generated medical history questionnaire. The purpose of the study is to determine how accurately and how safely the system assigns a patient to a category of urgency of medical contact, and how closely the interpretations produced by the system correspond to the assessment of an expert physician. Adults treated at two university hospitals in Katowice, Poland, who are referred for laboratory testing, complete an electronic medical history questionnaire after their laboratory results become available. The system then generates an interpretation for each laboratory result, including a category of urgency of medical contact, a suggested medical specialty and suggested further laboratory tests. The attending physician independently records a clinical assessment of the same laboratory results and medical history without access to the output of the system. An independent expert physician subsequently establishes the reference assessment, blinded to the authorship of the assessments being compared. The interpretation report is released to the participant only after the assessment of the attending physician has been recorded and locked. The study is conducted in two phases. The first phase (609 participants) is exploratory and uses the initial version of the system. The second phase (290 participants) is confirmatory and uses the final, frozen version of the system. All outcome measures are assessed in both phases; the pre-specified confirmatory hypothesis test applies to the second phase. The endpoints of this study are properties of the software system, namely the concordance of its output with an expert reference assessment. Health outcomes of participants are not measured.

Conditions

Diagnostic Techniques and Procedures; Clinical Laboratory Techniques; Triage

Keywords

clinical decision support; laboratory medicine; triage; artificial intelligence; diagnostic accuracy; patient-facing communication; medical device software

Outcome Measures

Primary Outcomes (2)

• Percentage of Participants for Whom the Urgency Category Assigned by the Software Was Not Lower Than the Category Assigned by the Expert Physician (Patient Triage Safety Indicator)

  The urgency category assigned by the software is compared with the urgency category assigned by an expert physician serving as the reference standard. The urgency categories, ordered from highest to lowest, are: immediate medical contact, urgent medical contact, routine medical contact, and no need for medical contact. A participant is counted in the numerator when the category assigned by the software is the same as or higher than the category assigned by the expert physician. The measure is the percentage of participants counted in the numerator. Range: 0 to 100 percent; higher values indicate better performance. The measure is assessed separately in each study phase and data from the two phases are not combined. Each comparison is based on data locked at the time of enrollment; the expert assessment is performed retrospectively, in batches, on a locked dataset, and the calendar timing of the batch review does not affect the measured quantity.

  Through completion of the expert reference assessment for all enrolled participants, up to 16 months after study start

• Percentage of Participants for Whom the Urgency Category Assigned by the Software Was Identical to the Category Assigned by the Expert Physician (Patient Triage Accuracy)

  The urgency category assigned by the software is compared with the urgency category assigned by an expert physician serving as the reference standard. The urgency categories, ordered from highest to lowest, are: immediate medical contact, urgent medical contact, routine medical contact, and no need for medical contact. A participant is counted in the numerator when the category assigned by the software is identical to the category assigned by the expert physician. The measure is the percentage of participants counted in the numerator. Range: 0 to 100 percent; higher values indicate better performance. The measure is assessed separately in each study phase and data from the two phases are not combined. Each comparison is based on data locked at the time of enrollment; the expert assessment is performed retrospectively, in batches, on a locked dataset, and the calendar timing of the batch review does not affect the measured quantity.

  Through completion of the expert reference assessment for all enrolled participants, up to 16 months after study start

Secondary Outcomes (8)

• Sensitivity for the Immediate Medical Contact Category

  Through completion of the expert reference assessment for all enrolled participants, up to 16 months after study start

• Sensitivity for the Urgent Medical Contact Category

  Through completion of the expert reference assessment for all enrolled participants, up to 16 months after study start

• Agreement on Urgency Category Measured by Quadratic Weighted Cohen's Kappa

  Through completion of the expert reference assessment for all enrolled participants, up to 16 months after study start

• Per-Result Concordance on Recommended Medical Specialty

  Through completion of the expert reference assessment for all enrolled participants, up to 16 months after study start

• Per-Result Concordance on Recommended Additional Laboratory Tests

  Through completion of the expert reference assessment for all enrolled participants, up to 16 months after study start

Study Arms (1)

AI-Based Interpretation of Laboratory Test Results

EXPERIMENTAL

Single arm. All participants complete an electronic, dynamically generated medical history questionnaire administered by the software after their laboratory results become available, and subsequently receive a software-generated interpretation report. The report is released to the participant only after the independent clinical assessment of the attending physician has been recorded and locked. No control group is used. The assessments of the attending physician, of an independent expert physician and of large language models are comparators of assessment and do not constitute study arms.

Diagnostic Test: AI-based laboratory result interpretation software

Interventions

AI-based laboratory result interpretation software DIAGNOSTIC_TEST

A CE-marked class IIa medical device software for the automated interpretation of laboratory test results, operated within its intended purpose. The software administers a structured medical history questionnaire in which subsequent questions are selected dynamically on the basis of the laboratory results and of previous answers. For each laboratory result the software generates one interpretation, comprising a category of urgency of medical contact (immediate, urgent, routine, or no need for medical contact), a suggested medical specialty, a list of suggested further laboratory tests, and an explanatory text addressed to the patient. Interpretations are not aggregated by the software. The interpretation report is generated once per participant, after completion of the questionnaire, and is released to the participant after the assessment of the attending physician has been recorded and locked. The generated report is not used to direct the clinical management of the participant.

Also known as: LabTest Checker

AI-Based Interpretation of Laboratory Test Results

Eligibility Criteria

• Age: 18 Years - 79 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Treated at one of the two participating clinical centers of the Medical University of Silesia
• Age 18 years or older and under 80 years
• Presence of symptoms justifying the initiation of a diagnostic work-up
• Meets the criteria for ordering at least one of the 29 specialist laboratory panels included in the study
• Able to complete an electronic questionnaire in Polish independently, using a smartphone or a personal computer
• Holds a Polish national identification number (PESEL)
• Written informed consent covering all three components of the study

You may not qualify if:

• Pregnancy
• Age 80 years or older
• Inability to provide informed consent, including cognitive impairment or a language barrier
• Participation in another clinical study that could affect the results
• Refusal of consent to any of the three components of the study

Sponsors & Collaborators

• Labplus Sp. z o.o.: lead
• Medical University of Silesia in Katowice: collaborator

Study Sites (2)

Independent Public Clinical Hospital named after Andrzej Mielecki, Medical University of Silesia

Katowice, Poland

Location

Prof. K. Gibinski University Clinical Center, Medical University of Silesia

Katowice, Poland

Location

Related Publications (1)

• Szumilas D, Ochmann A, Zieba K, Bartoszewicz B, Kubrak A, Makuch S, Agrawal S, Mazur G, Chudek J. Evaluation of AI-Driven LabTest Checker for Diagnostic Accuracy and Safety: Prospective Cohort Study. JMIR Med Inform. 2024 Aug 14;12:e57162. doi: 10.2196/57162.

  PMID: 39149851 RESULT

Study Officials

• Jerzy Chudek, MD, PhD

  Medical University of Silesia in Katowice

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Jerzy Chudek, MD, PhD

CONTACT

+48322591202; clinicaltrials@labplus.pl

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: NA
• Masking: NONE
• Purpose: DIAGNOSTIC
• Intervention Model: SINGLE GROUP
• Sponsor Type: INDUSTRY
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: August 17, 2026
• First Posted: September 9, 2026
• Study Start: August 19, 2026
• Primary Completion (Estimated): October 31, 2027
• Study Completion (Estimated): December 31, 2027
• Last Updated: September 9, 2026

Record last verified: 2026-09

Data Sharing

• IPD Sharing: Will not share

Locations

PL (2)