Asked 20 years ago whether self-driving cars or identification by retinal scanning would be feasible, there likely would have been a collective “Dream on!”. And yet, these are not only our present day reality, they represent only the icing on the cake. From Siri to Alexa and Tesla, interactions with machine-based artificial intelligence or AI permeate in our daily lives. Netflix and Amazon serve as our most loyal personal shoppers, always knowing just what else we may wish to view or purchase. Could machines come to serve as our personal doctors, where life and death hang on the line?
To get to an answer, we can assess how AI has impacted medical research, what strides have been made in converting research & development into commercialized AI-based technology. We can then begin to truly evaluate whether in another 20 years, AI might displace physicians or more benignly, serve as their personal assistants.
AI is essentially a branch of computer science whereby data are collected and algorithms created based on patterns found across the data using deep machine learning or neural networks. The output may be a diagnostic, prognostic or disease prediction that appears as if a human had analyzed the data and determined the output, all at a fraction of the time it would take a human to complete. For AI to be reliable, it is absolutely critical that the data numbers be high and of sufficient breath and quality to avoid skewed, biased results that are not generalizable (Sinz, Pitkow, Reimer, Bethge, & Tolias, 2019). Otherwise, we’re left with garbage in, garbage out. The AI field has matured wherein the scope and quality of training data, augmentation of data and enhanced computational power have resulted in ever more precise output, enabling processes that are particularly repetitive, ripe for AI (Gardezi, Elazab, Lei, & Wang, 2019).
Several areas of medicine have been particularly amenable to AI based on the sheer volume of data readily available: radiology, ophthalmology and pathology (Ahuja, 2019; Gardezi et al., 2019). The data are derived from the vast numbers of patient-derived images and recordings that these medical segments collect to make diagnoses: from X-rays to CT scans, MRI imaging, retinal imaging and tissue histology images.
The field of opthalmology has pioneered the way with the first-ever FDA approved AI-medical device that was granted to IDx based on the autonomous analysis of 900 patient retinal images. Their diagnostic, the IDx-DR retinal imaging device, can detect higher than mild levels of diabetic retinopathy (DR) in diabetic patients with an accuracy of 87.4% (Abràmoff, Lavin, Birch, Shah, & Folk, 2018). It is the first authorized medical device screening tool that does not require a clinician to interpret retinal images for (DR) (FDA, 2018).
Another compelling example is AI applications in radiology, specifically breast mammography diagnostics. Based on 100,000 breast mammogram images, Google’s health research arm very recently announced that their AI-trained software resulted in 5.7% fewer false positive and 9.4% fewer false negative rates than trained radiologists (Collins, 2020). While their AI-software has not been approved yet by the FDA for diagnostic purposes, the results are proving out the revolutionary impact of AI in medical research.
AI in pathology has also made strides on the research and development front, particularly in cancer diagnostics given its extensive dependence on (digitized) tissue morphology. The push for some form of automatized assistance comes partially from interobserver (aka pathologist) variability in the analysis of H&E stained tissue and the sheer volume of images (Harbias, Salmo, & Crump, 2017)Advances in AI-research by Philips led the FDA to grant approval of their IntelliSite Pathology Solution, the first ever whole slide review imaging system to be marketed (FDA, 2017). While pathologists are still required to review and interpret the images, they can do so from digitized images rather than tissue samples.
The market has been bullish on AI medical R&D being translated into commercial products. In 2016, the lion’s share of AI-based investments went to the healthcare sector over other sectors (CB Insights Research, 2017). The appetite for AI-based medicine continues to increase at a rate of 40% and is expected to top $6.6 billion by 2021 (Frost & Sullivan, 2020). With funding supporting AI R&D and a marketplace appearing ready to adopt, discussions abound over the implications of AI for physicians in the workforce. The doomsday scenario that they would be replaced by machines is a fair concern. Just take a look at the IDX-DR case: opthalmologist are no longer required to screen for diabetic retinopathy in instances where the IDX-DR screening tool is used. Other the other hand, AI-based tools can be relegated to high volume repetitive workloads and facilitation of clinical workflows without impacting the billable reimburseables.
There may likely be some shifts in the physician workforce, but the optimist in me believes that AI can be leveraged to create new opportunities for physicians. By relegating more of the routine, repetitive workload to AI, it could importantly provide precious time back to physicians staving off physician burnout, a true modern day symptom afflicting many overworked providers. This could ultimately translate into more face time with patients — “yes, the doctor is in.”