Recent advances in immunotherapy, such as the use of checkpoint inhibitors, are transforming the treatment of many cancers. Yet, not all patients respond predictably the same therapy based on a specific bio-target , and efforts are underway to identify and validate biomarkers capable of selecting the most suitable patients for these therapies. Detecting the presence of biomarkers in tissue by analyzing tissue samples and recognizing patterns within them, however, is a time-consuming task for pathologists and often results in less-than-optimal reproducibility.
However, a potential game-changing technology is on the horizon. Emerging artificial intelligence (AI) and machine learning (ML) based diagnostic pathology platforms using dynamic algorithms developed through deep neural networks have the potential to support pathologists and oncologists by improving the efficiency, reproducibility, accuracy and precision of their work. The recent FDA approval of Paige’s automated AI-based prostate cancer detection system as a prescreening tool for prostate carcinoma using hematoxylin and eosin WSIs represents promising progress in this field however, there remains no such diagnostic platform cleared for use with IHC, the gold-standard for identification of a protein target in tissue.
The technology is evolving rapidly, and is now being increasingly used in candidate selection by large drug developers, to potentially enrich clinical trials and further refine precision medicine. Not far in the future, the most promising application of this technology will be in the selection and stratification of patients for immunotherapy based on response predictions supported by AI-based data.
As Paige Prostate has demonstrated, such algorithms have the potential to be a versatile tool in anatomic pathology practice to increase detection accuracy in whole slide images of tissue which potentially translate to improved patient diagnostic outcomes.
The development pathway for this technology is fraught with uncertainty and risk and technology developers should seek the counsel and support of a development partner who is:
- Immersed in the business of Oncology and AI-based Drug Development. The development partner should have strong, existing relationship with study sites to expedite patient recruitment of the target patient population and PI early engagement with the technology.
- Data Science know-how. Development of AI-based solutions in clinical trials requires the management of diverse data formats; the development partner should have experience managing and integrating large data sets.
- Well-versed in AI-based regulatory compliance for product development. This partner will also understand the specific challenges technology development customers face, including interaction with the regulatory agency and the required regulatory pathway for AI/ML-based technology (particularly digital pathology platforms/algorithms).
- Specialized capabilities in managing prospective studies. Partnering with the right team with specialized knowledge of oncology and digital pathology to support the collection of data required by developers to train and validate algorithms. This approach provides access to multi-disciplinary experience in conducting Immuno-Oncology trials and in guiding developers through the regulatory approval process.
Clearly, there are also many challenging aspects of developing AI/ML-based diagnostic pathology platforms that have little to do with computer programming and data science. A significant portion of the process is the stock and trade of research development organizations that help to bring drugs and medical devices to market. The best solutions are likely to come from development partners who are leaders in the areas of operationalizing clinical trials, the application of technology to established practices in pathology and oncology coupled with the unique regulatory expertise and knowledge required for this rapidly expanding area of drug development and precision medicine.
CONTRIBUTOR
Dr. Kim M. Bonner, BSc (Hons) VMD PhD
