Patient-Centered Genomic Diagnostic Testing for AML: A Quality Improvement Project
Bibliographic record
Abstract
PURPOSE The classification of AML and therapeutic options are now largely driven by genetically defined subtypes. Personalization of treatment relies on timely completion and reporting of cytogenetic and molecular tests, creating challenges in clinical practice. We initiated a quality improvement study with the aim to optimize the process for ordering of genomic diagnostic tests and to reduce test turnaround times (TATs). METHODS A multidisciplinary working group consisting of hematologists, laboratory scientists, technologists, and hematopathologists was formed and identified the following tests as necessary for expedited testing in patients with AML younger than 75 years: next-generation sequencing (NGS) myeloid panel, karyotype analysis, FLT3 PCR, NPM1 PCR, CBFB::MYH11 PCR, and RUNX1::RUNX1T1 PCR, and proposed a reflexive flow cytometry–triggered genomic diagnostic testing algorithm for newly diagnosed AML (ND-AML). We used the model of improvement and implemented three Plan-Do-Study-Act (PDSA) cycles: education and guidelines for management of ND-AML, implementation of the reflex laboratory-triggered diagnostic testing algorithm for ND-AML, and automation of NGS workflow. We assessed compliance with test ordering according to prescribed guidelines and TAT. RESULTS After PDSA 2, test ordering improved significantly to more than 90% of relevant tests being initiated at AML diagnosis; and TAT was reduced by 27.6% for NGS and by 54.8% for NPM1 PCR. After PDSA 3, TAT for NGS was overall reduced by 63.3% to 11.4 days and within our 14-day target. We were able to also meet our target TAT of 5 days or less for FLT3 and NPM1 PCRs. DISCUSSION A multidisciplinary approach with shared decision making between hematologists and laboratory practitioners was essential in the development of an algorithm for reflex testing in AML that resulted in improved test ordering and TAT.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.188 | 0.123 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.004 | 0.005 |
| Science and technology studies | 0.003 | 0.003 |
| Scholarly communication | 0.009 | 0.005 |
| Open science | 0.004 | 0.009 |
| Research integrity | 0.002 | 0.004 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".