Interview with Mo Abdolell, Founder and CEO of DensitasAug 30, 2021
Categories: Breast Cancer Risk, Breast Density, General, Interview, Mammography Image Quality
Sustainable breast cancer screening service delivery requires efficient patient and process management. Mo Abdolell, CEO and Founder of Densitas, speaks with Caroline Lair, Founder of The Good AI.
Mo Abdolell discusses the motivation for establishing Densitas, the opportunity for moving the needle in breast cancer screening with scalable A.I. solutions that can reduce healthcare disparities through better population health management, and the need for scientific rigour to mitigate the risk of biased A.I.
Mo shares his perspective on the role of A.I. in radiology.
As Gary Kasparov remarked about Centaur chess, the combination of AI and human intelligence will outperform both A.I. alone and humans alone. There have been studies that show this is true in radiology as well.
He discusses how clinical and diagnostic confidence is predicated on correctness, completeness, consistency, and availability of good quality data/information, which emphasizes the need for effective patient and process management along the patient pathway that precedes diagnostic examination.
Our view is that sustainable breast cancer screening service delivery requires efficient patient and process management and that the ability of the radiologist or computer-aided detection and diagnosis [software] to be effective is predicated on quality control.
Mo also touches on why A.I. is a lightning rod for the issue of bias and how to mitigate the risk of introducing bias into A.I. models in medical applications, especially in medically underserved regions.
The challenge with A.I., as with any other predictive modeling strategy, is to ensure that there is no systematic skewness in your training data that would steer the model to systematically miss-classify new inputs. For example […] different socio-economic, cultural, and ethnic groups [may] not have access to or seek out medical care equivalently. In medicine, we can be prone to the same kinds of systematic bias and so we need to be particularly diligent that we are methodologically rigorous when we train A.I. models.
And he shares his excitement in the company’s progress in global market expansion.
We have a healthy pipeline of additional product features and solutions that will be released over the next year that will propel our platform even further to establish intelliMammo™ as a critical mammography enterprise solution for mammography facilities.