**12. Computer simulation and the future of diagnostic expertise**

In 1996, the American Journal of Roentgenology published a report of three cases of diagnostic errors in radiology. After assessing the clinicians' defense of their decisions, the author concluded that the radiologists missed out on the diagnosis because they did not think of the lesion rather than not know of it. It is popularly known as the *aunt Minnie effect*—that is if a woman in a picture looks like Aunt Minnie, she must be aunt Minnie [43]. Improving patient care means, we have to look for ways to minimize diagnostic errors- an umbrella term that includes as varied factors as personal or social bias, heuristics and even failure of perception [44]. Debiasing programs work but may take a lifetime to refine, even doctors who are willing to accept error on their part [44]. In the present world however, where software changes by the day, we do not happen to have that luxury of time.

Populations in countries have increased but investments in health and education have not kept pace with the same. Add to that an increasingly unstable world both politically and environmentally. All of these changes mean shifting populations and overburdened hospital based care provider. With the rise in longevity and polypharmacy, one diagnostician may not be and indeed, cannot be held accountable, for missing out on a few pertinent points here and there, while assessing a case. In today's outpatient medicine practice, especially, that of Oral Medicine and Radiology, there is hardly any time to think. And much to our chagrin, the reduced pay of practicing doctors, and increased work time of a hospital based doctor only means, what the New England Journal of Medicine, recently referred to as *subsistence-level intellectual mode* [45]. In such a scenario, the probability of diagnostic errors grows by leaps and bounds.

Where computer simulation steps in, is this very ripe environment of piling information and very few humans, qualified to process it. As of now, there are gaping holes in the way AI processes the information it collects, and human mind is, as yet, ahead of it. AI is heavily reliant on data sets that its algorithms work on. The stark problem with these data sets is that they are not representative of the wide gamut of humanity out there that needs treatment. For AI to pick a patient on its scanner, first of all the patient should have access to a device that lets this patient connect to its virtual world. Disadvantaged populations or displaced populations may not have that. This inherent bias of the system leaves it firmly in the field of speculation over its accuracy and therefore dependability.

Algorithms, however, tend to improve themselves over time; deleting redundancies and communicating across other platforms as they pick more and more data, as has been discussed earlier in the chapter. With the advent of quantum computing, in what has been defined by The Economist as the field's Sputnik moment, Google has recently demonstrated its ability to perform a task in little over 3 min, what might take most powerful classical computers about 10,000 years to complete [46]. In a world, where Common Health of Android and Apple Health of iOS, will increasingly guide the logistics of collecting and collimating data, medical or otherwise, from Electronic health records, medical devices, software, apps, and smartphones, the art of diagnosis will witness seismic changes. The quality of information being used to create data sets is one of the many hurdles.

Yet, as the horse carriage eventually gave way to sophisticated cars, we will have to yield a part of the field to computer simulation. But as we do that, we have to remember, the algorithm, as yet, does not have a totalitarian power over the mind. At the end of the day, the most important part of patient care is after all, care. And a responsive warm doctor in the field of Oral Medicine and Radiology is still very much preferred over subservience to any cold computing device. Computer simulations, then, are just another set of tools in our armamentarium and we need to research how to use the same for the benefit and better experience of everyone involved.

## **13. Conclusion**

In a world, increasingly driven on ever evolving computation, diagnostic medicine has to adapt to change. Harnessing the power of AI to prevent logjams of channeling information collected into a cohesive whole will benefit both the doctor providing care and the patient receiving it. Computer simulation is a vital tool and how, and how much will it change the topography of diagnostic medicine, remains to be seen.

**87**

**Author details**

\*, Akhilanand Chaurasia<sup>2</sup>

2 King George's Medical University, Lucknow, India

\*Address all correspondence to: samanishratalam@gmail.com

© 2020 The Author(s). Licensee IntechOpen. This chapter is distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/ by/3.0), which permits unrestricted use, distribution, and reproduction in any medium,

3 Bidgley Inc., Mountain View, California, USA

provided the original work is properly cited.

1 Rama Dental College, Kanpur, India

and Mohammad Husain Khan3

Saman Ishrat1

*Computer Simulation and the Practice of Oral Medicine and Radiology*

*DOI: http://dx.doi.org/10.5772/intechopen.90082*

*Computer Simulation and the Practice of Oral Medicine and Radiology DOI: http://dx.doi.org/10.5772/intechopen.90082*
