Testing and refining an AI algorithm to predict acute leukemia subtypes from routine laboratory data

Testing and refining an AI algorithm to predict acute leukemia subtypes from routine laboratory data - AIPAL-Validation

Status

Active, not recruiting

Phases

Unknown

Study type

Observational

Source

DRKS

Registry ID

DRKS00037360

Enrollment

5000

Registered

2025-07-09

Start date

2024-07-02

Completion date

Unknown

Last updated

2025-10-06

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

C92.00 C91.00 C92.4

Interventions

Group 1: Patients with newly diagnosed acute leukemia are recruited. Patients present with the features age, complete blood cell (CBC) count (total white blood cell count (WBC

10? per L), monocyte and lymphocyte counts (10? per L), platelet count (10? per L), mean corpuscular volume (MCV

fL), mean corpuscular hemoglobin concentration (MCHC

g/L), lactate dehydrogenase (LDH

IU/L), fibrinogen (g/L) and prothrombin time (%) at the earliest possible point in leukemia diagnosis (i.e., at hospital admission) are analyzed by a machine learning algorithm. The model classifies t

Eligibility

Sex/Gender

All

Inclusion criteria

Inclusion criteria: Diagnosis of acute leukemia

Exclusion criteria

Exclusion criteria: None

Design outcomes

Primary

Measure	Time frame
Precision in the prediction of acute leukemia subtypes by the machine learning algorithm using the features aquired at diagnosis, assessed via AUROC and F1 score. Nine laboratory features and age will be entered.	—

Secondary

Measure	Time frame
Robustness and generalisability of the machine learning algorithm in the prediction of acute leukemia subtypes at the time of diagnosis.	—

Countries

Germany

Contacts

Public ContactAmin Turki

Universitätsklinikum Essen

amin.turki@uk-essen.de+49-201-7230

Outcome results

None listed

Source: DRKS (via WHO ICTRP) · Data processed: Feb 4, 2026