Better Leukemia Diagnostics Through AI (BELUGA)
Trial statusRecruiting
Trial phaseNot listed
Trial typeObservational
Biological sexAll
Age18+
SponsorMunich Leukemia Laboratory
About this trial
To the best of our knowledge, BELUGA will be the first prospective trial investigating the usefulness of deep learning-based hematologic diagnostic algorithms. Taking advantage of an unprecedented collection of diagnostic samples consisting of flow cytometry datapoints and digitalized blood-smears, categorization of yet undiagnosed patient samples will prospectively be compared to current state-of-the-art diagnosis at the Munich Leukemia Laboratory (hereafter MLL). In total, a collection of 25,000 digitalized blood smears and 25,000 flow cytometry datapoints will be prospectively used to train an AI-based deep neuronal network for correct categorization. Subsequently, the superiority will be challenged for the primary endpoints: sensitivity and specificity of diagnosis, most probable diagnosis, and time to diagnose. The secondary endpoints will compare the consequences regarding further diagnostic work-up and, thus, clinical decision making between routine diagnosis and AI guided diagnostics. BELUGA will set the stage for the introduction of AI-based hematologic diagnostics in a real-world setting.
Eligibility criteria
This trial accepts healthy volunteersQualifiers
Patients having been diagnosed with a suspected hematological disorder
The suspected diagnoses constitute a primary diagnosis
Only samples of patients min.18 years of age will be used
Samples must suffice quality attributes which are denoted in "
Disqualifiers
The sample is not fit for state-of-the-art diagnosis or fails initial quality control. For quality insurance, we will exclude samples in heparin- instead of EDTA. Samples with damage due to atmospheric reasons (freeze-thaw damage or elevated temperature) will be excluded.
Samples with too scarce material jeopardizing routine gold-standard diagnosis will be excluded.
Bone marrow aspirates without sufficient material to assess malignant or healthy hematopoiesis.
Trial population
The training cohort of BELUGA consists of 50,000 annotated samples for which cytomorphological smears (25,000 samples) and immunophenotyping (25,000 samples) data points have been collected. This cohort serves as a foundation for the DNN to perform training. Our test cohort will consist of all samples for which cytomorphology and immunophenotyping will be performed for one year.
Trial design
Design model
Case-control
Time perspective
Prospective
Treatments tested in this trial
Automated AI-Guided Diagnosis of Hematological Malignancies
Diagnostic testIn BELUGA, we want to investigate whether the automated analysis of blood (from peripheral blood and bone marrow aspirates) smears and flow-cytometry-based analyses can provide a benefit for diagnostic quality and, ultimately, patient care.
Treatment groups
No treatment groups listed
Trial outcomes
Primary outcomes
1
Sensitivity and Specificity of AI Guided diagnostics in Hematology
As a primary endpoint, we will examine the ability of DNN to classify disorders according to (after initial assessment disease/healthy) to the gold-standard diagnosis. The gold-standard diagnosis is defined as an integrated diagnosis, including cytomorphology, flow cytometry, cytogenetics, FISH, and molecular genetics. DNN will independently provide a bi-directional (probabilistic) diagnosis, with the most probable diagnosis. The primary analysis will include a direct comparison between the human cytomorphological examination and the pattern recognition software. Secondly, this result will be provided to downstream diagnostic departments to assess phenotypic diagnosis's usefulness for genetic characterization. We hypothesize that the turn-around time will be significantly enhanced, further providing quality at sooner timepoint.
Time frame
08-01-2020 until 07-31-2021Secondary outcomes
1
comparison of clinical consequences
We will compare the clinical recommendation obtained after routine gold-standard diagnostics and after AI-guided categorization of all samples enrolled in this study
Time frame
08-01-2020 until 07-31-20212
predictive diagnostic value
We will assess the predictive value of unsupervised categorization and diagnosis in comparison to gold-standard routine testing.
Time frame
08-01-2020 until 07-31-20213
turn-around-time
We will measure the turn-around-time of gold-standard diagnostics in comparison to AI-guided diagnosis.
Time frame
08-01-2020 until 07-31-20214
enumerate entity-specific benchmarks (e.g., blast count in leukemia) count)
We will assess secondary disease specific values determined by AI/DNN based unsupervised diagnosis versus routine testing.
Time frame
08-01-2020 until 07-31-2021Sponsors and contacts
Click on the lead sponsor to view all of their trials.
Source ClinicalTrials.gov