Response-adapted therapy in Hodgkin lymphoma

Electrophysiological Studies in Combination With Interim-Positron Emission Tomography Scan for Prevention of Severe Brentuximab-Vedotin-Induced Neurotoxicity

Brentuximab-vedotin (BV)-induced neurotoxicity (BVIN), a frequent adverse event caused by this monoclonal antibody, is the primary reason for dose modification or drug discontinuation, and is characterized by sensory, motor, and/or autonomic peripheral nerve dysfunctions. Although reversible, BVIN can persist for months or years after treatment and negatively affect quality of life (QoL). Currently, BVIN is managed by dose adjustment or drug interruption, leading to an increased risk of disease relapse. Therefore, early recognition and appropriate management are essential to improve clinical outcomes. In this real-life study, we identified predictive factors for moderate/severe BVIN to reduce the risk of irreversible neuropathy. A total of 22 patients treated with BV were enrolled and BVIN was monitored by electro-neurography and neurological examinations every 2 cycles of therapy, while QoL by clinical questionnaires. We showed that recovery rate from moderate/severe BVIN was low, and sensory nerves were the most affected, negatively impacting QoL. BV dose reduction based on interim PET re-evaluation in patients with hematological response resulted in a significant reduction of BVIN onset with high long-term QoL. Therefore, electrophysiological tests could be useful tools to prevent moderate/severe BVIN onset, and their combination with interim PET imaging could allow dosage adjustments thus simultaneously minimizing risks of disease relapse and BVIN development. However, further studies on larger prospective randomized cohorts are needed to confirm our preliminary results.

A machine learning model of response to hypomethylating agents in myelodysplastic syndromes

Hypomethylating agents (HMA) prolong survival and improve cytopenias in individuals with higher-risk myelodysplastic syndrome (MDS). Only 30-40% of patients, however, respond to HMAs, and responses may not occur for more than 6 months after HMA initiation. We developed a model to more rapidly assess HMA response by analyzing early changes in patients’ blood counts. Three institutions’ data were used to develop a model that assessed patients’ response to therapy 90 days after the initiation using serial blood counts. The model was developed with a training cohort of 424 patients from 2 institutions and validated on an independent cohort of 90 patients. The final model achieved an area under the receiver operating characteristic curve (AUROC) of 0.79 in the train/test group and 0.84 in the validation group. The model provides cohort-wide and individual-level explanations for model predictions, and model certainty can be interrogated to gauge the reliability of a given prediction.

•

We developed a model to more rapidly assess patients’ response to hypomethylating agents

•

The model’s predictions use exclusively routinely collected blood count data

•

The model confirmed prior findings and identified potential new prognostic factors

•

Model predictions are interpretable on both the individual and cohort-wide level