AI Transforms Oncology Trials; Aethlon Advances Hemopurifier Cancer Study in Australia

Semi-autonomous and autonomous foundation models are helping cancer research and anticancer drug development by streamlining clinical trials and reducing the risk of failure in the transition from phase II to phase III trials. These tools effectively remove the need for large-scale recruitment and can help speed up regulatory processes.

A collaboration between a large pharma company and specialized AI companies led to the creation of the largest multimodal foundation model in oncology based on electronic health records, laboratory tests, pathology images, pathology reports, radiology images, radiology reports and unstructured notes from the patient hospital journey. Patient 'embeddings' extracted by the self-supervision models help to address a range of important questions, such as predicting who might best respond to a particular treatment and how to provide these potential benefits at scale using a system widely accessible to healthcare providers.

A key benefit of the latest AI systems is that they allow accurate generalisation on relatively small sets of data, thereby facilitating progress at a fraction of the time, workforce and ultimately cost involved with conventional routes of research and development. Models trained on many millions of patients are already being utilized and indicate potential for early cancer detection and toxicity prediction.

In 2024, the first ever predictive biomarker for an antibody–drug conjugate based on pathology-applied AI, and involving TROP2 normalised membrane ratio, was shown to be effective in directing treatment with datopotamab deruxtecan in patients with non-small cell lung cancer enrolled in the TROPION-Lung01 trial. The model uses the Quantitative Continuous Scoring (QCS) platform, a computational pathology fully supervised AI solution that allows for identification of cancer cells and target protein expression level quantification within the subcellular compartments of cancer cells at single-cell resolution.

The development of QCS has been substantially accelerated through the implementation of state-of-the-art frontier foundation models to reduce or eliminate the need for handcrafted annotations during algorithmic development, shortening the development time from an estimated 2.5 years to roughly 5.5 months.

Separately, Aethlon Medical is conducting a basket oncology trial to study the impact of the Hemopurifier as a potential treatment in patients with various solid tumors who have stable or progressive disease during anti-PD-1 monotherapy treatment. The Hemopurifier is an investigational extracorporeal device designed to bind and remove harmful extracellular vesicles (EVs), nanoparticles 50-500nm in diameter, from the blood through a combination of plasma separation, size exclusion, and binding to a proprietary affinity resin.

The device has received FDA Breakthrough Device designation for the treatment of people with advanced or metastatic cancer who are either unresponsive to or cannot tolerate standard of care therapy, and with cancer types in which exosomes are indicated in the development or severity of the disease. The trial is intended to assess the Hemopurifier's safety, feasibility, and optimal dosing.

Following treatment of the first three patients (Cohort 1), who completed a single 4-hour Hemopurifier treatment without device deficiencies or immediate complications, the study design is for Cohort 2 participants to receive two Hemopurifier treatments over one week to help determine whether there is a dose response with additional Hemopurifier treatments. All Cohort 1 participants also completed a 7-day safety follow-up. No serious adverse events (SAEs) or Dose-Limiting Toxicities (DLTs) related to the Hemopurifier have been reported to date.

To accelerate enrollment, Aethlon Medical is working with clinical trial facilitator Trialfacts to perform clinical trial advertising, online prescreenings, and refer potential participants to the three sites in Australia participating in the trial. Cohort 2 recruitment and treatment are being conducted under an amended protocol that allows patients receiving combination therapies with pembrolizumab or nivolumab to participate in the trial.

The company expects to report early data from Cohort 2 and receive Safety Board determination about progressing to Cohort 3 by late March/early April. Currently, Hemopurifier treatment requires a dialysis catheter and dialysis machine, and nephrologists and dialysis nurses to supervise and administer the treatment. To potentially make it easier for medical centers and patients, Aethlon Medical has started to evaluate the potential of using the Hemopurifier with a simplified blood treatment system that could replace the use of dialysis infrastructure.