Professor Kefah Mokbel’s Post

Eight in 10 (81.4 percent) supported patient consent for AI model use during treatment decisions. In a scenario in which an AI decision model selected a different treatment regimen than the oncologist planned to recommend, most respondents said they would present both options and let the patient decide (36.8 percent), with those from academic settings more likely than those from other settings to let the patient decide (odds ratio, 2.56). Three-quarters of respondents (76.5 percent) agreed that oncologists should protect patients from biased AI tools, but only 27.9 percent were confident in their ability to identify poorly representative AI models.

One of our core tenets is putting the Artera #MMAI models through extensive validation. We are proud to partner with Hackensack Meridian Health and Nitin Yerram, M.D. to investigate new clinical endpoints to better guide treatment decisions after #prostatectomy. https://heyor.ca/Spv4Mq #precisionmedicine #prostatecancer #AI #personalizedcancercare

As a prognostic biomarker, HER2 status helps predict the aggressiveness of the cancer. As a predictive biomarker, HER2 status determines the eligibility for HER2-targeted therapies. HER2 immunohistochemistry (IHC) scoring is used in the diagnosis and treatment planning of breast cancer. This AI solution may serve as a valuable decision support tool for pathologists, aimed at improving the reproducibility and consistency of HER2 scoring. It is particularly effective in identifying HER2-low breast cancers.

The performance of the human epidermal growth factor receptor 2(HER2) AI solution supports consideration as a decision support tool to pathologists to improve HER2 scoring in routine clinical practice. https://lnkd.in/eMfTJ9ey

The American Society of Clinical Oncology (ASCO) released, “Principles for the Responsible Use of Artificial Intelligence in Oncology,” to guide ASCO’s consideration of all aspects of artificial intelligence (AI). With this manuscript, the Society joins colleagues across medicine in offering principles that should be applied in development and implementation of AI. Colleagues- give this a read and then perhaps read it again!

Wednesday Vibes 😎   ASCO is behind us, time flies. According to some information shared in an ASCO AI Community of Practice discussion, there were more abstracts submitted related to AI than ever before. So many great sessions!!   With all this activity, you may have missed that they released Guiding Principles for AI in oncology https://lnkd.in/ebCUBGDB  These include, transparency, informed stakeholders, equity and fairness, accountability, oversight and privacy and human-centered application   I especially appreciate the discussion around the need for understanding of AI and human-centered application. The importance of patients having a seat at the table as well in these discussions is critical.    I do hope that we'll also see more discussion around the implications of the use of AI for communication of information and dissemination of data. This, too, impacts the entire healthcare community. Our words matter, content matters -- and language is the 'currency' of these systems.

#MCED - multicancer early detection tests are becoming more and more popular, but there needs to be a better strategy for improving patient adhaerence - https://lnkd.in/duUrXf_e -one excellent free access paper dedicated to the topic. NM Genomix offers jointly with Inspire2Live and OncoInv a #proteomics MCED test strongly supported with #ai

In this study, a machine learning Artificial Intelligence was made to automatically detect rare gastrointestinal stromal tumors. Here's how it performed and what was learned. #AI #ML #futurism #IntelligenceFactory #digitaltransformation #DX https://lnkd.in/gWQKyjzC

Over the past year or so, we have seen #AI transform the #LifeSciences industry and 2024 is no exception. A couple of weeks ago, Asep Medical Holdings Inc. CEO Dr. Bob Hancock shared how his team successfully leveraged AI to develop new and improved treatments for biofilm infections. They created a neural network that AI could use to predict new peptides that had the potential to achieve higher activity against biofilms. Using this new approach, scientists were able to predict whether patients will subsequently acquire sepsis in 9 out of 10 patients in the ICU. This is an impressive achievement, especially considering how important early detection is to #PatientOutcomes. #DigitalTransformation #Innovation #FutureOfHealthcare

In this study, a machine learning Artificial Intelligence was made to automatically detect rare gastrointestinal stromal tumors. Here's how it performed and what was learned. #AI #ML #futurism #IntelligenceFactory #digitaltransformation #DX https://lnkd.in/gXnt9v_q