Love it or hate it, Artificial Intelligence is here to stay.

Is it an oxymoron? Some would most certainly agree; on the basis of ‘artificial’ being that which is made or produced rather than occurring naturally, coupled with the definition of ‘intelligence’ as the ability to acquire and apply knowledge and skills.

Others absolutely disagree.

The terms ‘artificial’ and ‘intelligence’ are not conflicting; with the argument that human intelligence itself is artificial – which is to say it’s the result of conscious effort, rather than an innate ability in which we are all equal.

What these advocates perceive as oxymoronic is the concept of technology being made humanlike.

Whatever AI is, not only is it divisive, but generally, there are also the feelings of both concern and excitement for it, in almost equal terms.

Like we need something else to feel incongruent about.

What constitutes intelligence is a broad and philosophical debate in itself. Ostensibly, and somewhat arrogantly, the basic consideration is that the only type of intelligence is human; that nothing else possesses intellect and aptitude.

Notably, AI exists only in technology; bona fide stupidity is undoubtedly in the realm of human expertise.

What would make AI truly intelligent is for it to create the logarithm for idiocy and take it from there.

The term itself refers to the ability of machines to perform tasks that would normally require human thought.

It involves the development of algorithms and programs that typically, can define and recognise patterns, make decisions, and solve problems: the ability to reason, and learn.

The debate among AI researchers, ethicists and philosophers is whether technology can ever replicate true human intelligence by possessing intuition, creativity and emotional acuity.

Arguably, AI is one of humankind’s most definitive developments.

Already, it impacts so many aspects of our lives – sometimes insidiously.

Certainly and increasingly, the medical profession incorporates AI into the smart monitoring and management of medical conditions, requiring limited or no human input.

AI is not a new term.

It was originally conceived in the 1950s; although it took fifty years for it to become a practical tool.

Chat Generative Pre-trained Transformer (ChatGPT) is an AI chatbot, developed by OpenAI and introduced to the world in November 2022.

Replicating human-like engagement, it can answer questions – including clinical ones encountered by medical and dental professionals in day-to-day practice.

This naturally raises the question of whether ChatGPT can be trusted with the cognition of scientific evidence for clinical decision making: whether it effectively replaces the orthodox evidence synthesis practice of information searches, data collection and critical appraisal for evidence-based responses.

When this question was put to ChatGPT, it responded with:

“As an AI language model, I am designed to generate text based on the patterns and relationships that I have learned from the input data I was trained on. While I can generate text that is related to scientific evidence and clinical decision-making, it is important to note that I am not a substitute for professional medical advice, diagnosis, or treatment.

When it comes to using text generated by AI language models for clinical decision-making, it is important to exercise caution and carefully evaluate the information presented. While language models like GPT have shown great promise in natural language processing tasks, they are not perfect and can make errors or generate misleading or inaccurate information.

Therefore, it is recommended to always consult with qualified medical professionals and rely on peer-reviewed scientific literature when making clinical decisions. AI language models like GPT can be used as a tool to help inform clinical decision-making, but they should not be the sole source of information or guidance.”

It’s a rational reply.

That clinicians should always consider any and all limitations of searches – whether AI generated or not – in conjunction with other evidence, issues and complexities is standard practice.

AI can only base its capabilities on the available data.

In dentistry, AI is across all dental disciplines: operative dentistry, periodontics, orthodontics, oral and maxillofacial surgery, and prosthodontics.

The majority of these applications are diagnosis based on radiographic or optical images.

Other tasks are constrained by data availability, uniformity, and the computational power of handling 3D data.

Evidence-based dentistry (EBD) is considered the gold standard for decision making in dentistry; while AI machine learning (ML) acquire knowledge from human expertise and is seen as a valuable tool for improved efficiency in routine procedures.

Still in its nascent stage, AI – most particularly deep learning – is data-intensive.

For accurate algorithms, large volumes of annotated data are required, creating a market for large datasets.

It gives rise to complex ethical questions, like who owns this data: the patient or the healthcare provider? Consent must be sought from patients before their radiographs are subsumed in the process of AI development.

Significantly, there are current concerns that patient data may be unethically used by the healthcare and insurance industries for targeted advertising and premium adjustments.

Also, if a diagnostic disagreement arises between the dentist and the AI technology, how is it resolved? And more importantly, where does accountability lie for any erroneous diagnosis by AI technology?

Potentially, AI and dentistry can work together for enhanced patient care and optimum results.

The capacity of AI is to meet the criteria: reproduce itself, maintain an internal environment, grow, adapt, respond, be organised and utilise resources.

We’re asking a lot. And heading toward the ultimate question of whether AI is alive. And in that case, we have to then ask about purpose.

Could be hard when we may not have one ourselves, by then.

BOOK NOW

Note: All content and media on the Bacchus Marsh Dental House website and social media channels are created and published online for informational purposes only. It is not intended to be a substitute for professional medical advice and should not be relied on as health or personal advice.

Services we mentioned: