Nearly every major medical breakthrough in history has resulted from years, sometimes decades, of intellectual work by humans. These developments, which range from sophisticated heart surgery to life-saving flu shots, have enhanced and saved countless lives. But will human intellect always be the most important factor in the medical field? The emergence of cutting-edge technology, such as artificial intelligence (AI), is transforming how we approach health care. AI is already causing a stir because of its ability to produce human-like reactions in real time. But what if it could push boundaries even further and become an integral part of the innovation process?
AI is one of the most significant technologies advancing the world today, primarily due to improving efficiency across different fields and fostering new ideas. In medicine, an AI model called AlphaFold can predict how different proteins may bind to DNA, with accuracy across different types of proteins.
This recent breakthrough is very important because it reduces the time needed to develop new drugs and other medical treatments. Doctors who previously spent extensive hours working on protein binding with DNA can now redirect their focus on methodology that only humans can perform. Beyond this, many other time-consuming tasks researchers face could eventually be automated by AI.
Sardar Jaman, a Bronx Science alumnus and current Applied Mathematics and Biology researcher at Cornell University, highlighted this efficiency: “In my math research paper, we had to analyze lots of data. Something that took weeks manually took only days with Python data analysis,” Jaman said. This underscores the clear advantage in efficiency when AI is integrated into the process.
But how exactly is it used in the field of medicine today? The purpose of evidence-based medicine is to establish clinical correlations and insights via developing associations and patterns from the existing database of information. Traditionally, statistical methods have been employed to establish these patterns and associations. Computers learn the art of diagnosing a patient via two broad techniques — flowcharts and database approach.
The flowchart-based approach involves translating the process of history-taking, where a physician asks a series of questions, and arrives at a probable diagnosis by combining the complex symptoms presented. This requires feeding a large amount of data into machine-based cloud networks, as there is a wide range of symptoms and disease processes encountered in routine medical practice. The outcomes of this approach are limited, because the machines are not able to observe and gather cues – which can only be observed by a doctor during the patient encounter.
On the contrary, the database approach utilizes the principle of deep learning, or pattern recognition, that involves teaching a computer via repetitive algorithms in recognizing what certain groups of symptoms or certain clinical and radiological images look like. An example of this approach is Google’s artificial brain project, launched in 2012.
The earliest version of this system was trained to recognize images of cats using 10 million YouTube videos. Over time, its efficiency improved as it processed more data. After just three days of learning, it achieved 75% accuracy in identifying cats. While this may seem unrelated to medicine, it highlights how AI can learn complex visual patterns through repeated exposure. When applied to the medical field, the same deep learning principles enable AI to identify diseases by recognizing specific patterns in diagnostic images. This capability can accelerate scientific breakthroughs and improve the efficiency and accuracy of disease diagnosis — processes that might otherwise take significantly longer for human experts.
In an interview that I conducted with Zubayer Rifat, a Bronx Science alumnus currently studying Neuroscience and Computer Science at the University of Michigan, he said, “I used ML (Machine Learning) models in MATLAB, which was a tool that was mandated for my neurocognitive injury research and made my work more efficient.” He expressed a clear satisfaction with his experience with ML models, which have significantly supported his research in neurocognitive injury and highlighted the potential of AI to transform and advance medical research practices.
One of the most popular examples of AI in healthcare is AI-Assisted MRI. The reconstructed imaging by AI-Assisted MRI is not limited to being beneficial for humans, however. In fact, they can also be used to monitor the health of other living organisms such as plants or even animals. For example, the diagram shown below visualizes the root diameters of maize and barley plants. This opens opportunities for scientists to figure out the health and other potential physical attributes of plants that we normally would not be able to figure out.
Why is this significant? Artificial intelligence can generate accurate and detailed MRIs using only a quarter of the raw data that is traditionally required for a full MRI. This, in turn, makes medical or research work related to very important tools such as MRI much more efficient. Anuroop Sriram, a research engineer at Meta, has been utilizing AI with MRI scans because he believes that, “Reducing the scan time has the potential to make MRIs more accessible, improve patient comfort, and reduce medical costs.”
ETHICAL CONCERNS
While various scenarios have shown us that AI will help mankind move forward, there are still ethical concerns that need to be taken into account. The rise of surgical robots that operate instead of human surgeons, as well as robotic nurses that care for patients instead of human nurses, threatens potential job opportunities for a lot of people. In fact, Zubayer Rifat said, “If these machines keep improving, there will be a time where we won’t need to innovate new concepts ourselves. Rather, the machine will do it for us.”
Socially, patients are likely to lose empathy, kindness, and appropriate behavior when dealing with robotic physicians and nurses, because these robots do not possess human attributes such as compassion, a something that is necessary for a patient’s mental health. Thus, there could a surge of lower satisfaction reviews from patients in hospitals where AI health care is prominent.
Additionally, one of the most important roles of AI is the ability to properly analyze a patient and diagnose them if they have any disease – but clinical data collected by robots can be hacked into and used for malicious purposes that minimize privacy and security.
Similarly, if the AI-Assisted MRI Machine shown above predicted a patient’s lung health in an accurate manner but the patient is given the wrong medicine or surgical process, it can lead to problems with the patient’s health. Any mistake or glitch especially in healthcare can lead to lethal issues.
Thus, before implementing such applications in medicine, multiple trials must be conducted to ensure that sudden accidents or glitches never occur when they are utilized on patients.
Hence, we need to be careful with how we utilize the new upcoming innovations presented by AI. There is still room for a lot of testing to see if it can truly live up to the expectations of the future. Just like electricity or any other major innovation, AI can be a very powerful tool that can help progress us forward but it needs to be utilized with caution especially in a high risk industry where people’s lives are on the line like medicine. While the latest scientific breakthroughs with AI are emerging as we speak, recent trends confirm that AI will bring lots of new innovations in the field of medicine.
The emergence of cutting-edge technology, such as artificial intelligence (AI), is transforming how we approach health care.