Clinical Evaluation of a Functional Combinatorial Precision Medicine Platform to Predict Patient-Specific Treatment Outcomes in Acute Myeloid Leukemia

Introduction: Acute myeloid leukemia (AML) is an aggressive form a leukemia that remains difficult to treat, often with rapid and frequent disease relapse due to drug-resistant clonal selection. A range of combination therapies have been designed to overcome this hurdle, however, identifying the most appropriate combination therapy at each line of treatment remains a challenge. Functional precision medicine platforms that use ex vivo drug sensitivity data from primary patient samples have shown potential to guide treatments in a range of cancers. We have recently developed an ex vivo combinatorial drug sensitivity platform, quadratic phenotypic optimization platform (QPOP), that analyses a predesigned array of 155 test combinations performed on a primary patient sample to rank and compare all possible therapeutic combinations from a 12-drug set. In this study, we evaluated the use of QPOP to predict treatment outcomes in an AML cohort treated with a variety of combination therapies. Furthermore, we also explored QPOP’s combination therapy ranking function to identify novel or under-utilized combinations that may benefit larger groups of AML patients when appropriately guided.

Methods: Prospective clinical feasibility study of QPOP in AML was performed at National University Hospital (NUH) in Singapore. Peripheral blood or bone marrow aspirations were collected from AML patients, recruited between 26^th November 2019 and June 15^th 2023. Following CD34+ cell selection, the enriched malignant blast population was subjected to an array of 155 test combinations derived from an orthogonal array composite design. Phenotypic cell viability data from this test was subsequently used by QPOP to derive drug combination scores and rankings for all possible combinations. Median turnaround time for QPOP patient-specific reports was 8 (±2.1) days. Patients were treated with current standard of care options as guided by the clinician. The primary outcomes of this study were to determine the concordance between treatment outcomes as guided by clinicians and QPOP drug combination scores and rankings. Secondary outcomes of this study were to identify high-ranking, potentially effective combinations that may be nover or under-utilized for future studies.

Results: 40 patients were recruited to the study with 49 samples analyzed by QPOP. Samples collected until 21 January 2022 were also used to refined ex vivo drug dosing levels for 12-drug, 3-level test combination arrays. Excluding patients diagnosed as non-AML and patient without available clinical concordance data, QPOP response concordance was evaluable for 19 patients. A 75% positive predictive value (PPV) and a 72.7% negative predictive value (NPV) was determined for a QPOP normalized cell viability (NCV) cutoff of 0.65. The area under the curve of the receiver operator curve, AUC = 0.75, suggesting acceptable predictivity. Concordance analysis of with samples (n = 10) collected after 21January 2022 demonstrated an 80% PPV, 80% NPV, AUC = 0.80 for an NCV cutoff of 0.62, suggesting that current ex vivo dosage settings for test array can further improve test accuracy. Combination therapy with the BCL2 inhibitor venetoclax and hypomethylating agent azacytidine is standard-of-care for AML. QPOP NCV cutoff of 0.62 also exhibited 100% concordance (5/5) with venetoclax+azacytidine treatment further demonstrating the accuracy of QPOP to predict treatment outcomes in AML. Amongst top ranked QPOP-derived combinations, venetoclax/fludarabine was amongst the most frequently reoccurring top-ranked combinations. With appropriate functional combinatorial precision medicine testing, patients who may benefit from addition of venetoclax to fludarabine-based chemotherapy regimens, such as fludarabine/busulfan reduced-intensity conditioning chemotherapy, may be accurately identified.

Conclusions: This clinical study demonstrates the feasibility of QPOP to predict treatment outcomes and accurately identify both response and resistance to combination therapy. Following platform workflow optimization, initial concordance analysis suggests excellent predictivity. Expansion of this clinical study is needed to confirm these results. This study also suggests that underutilized combinations may be effective across a larger population of AML patients with appropriate ex vivo drug testing and deserve further clinical interrogation.