Artificial Intelligence in Medicine (Case Study) The future of 'standard' medical practice might be here sooner than anticipated, where a patient could see a computer before seeing a doctor. Through advances in artificial intelligence (AI), it appears possible for the days of misdiagnosis and treating disease symptoms rather than their root cause to move behind us. DID you know that if you ever needed surgery for a rare condition, you could be operated on by a highly specialised surgeon sitting in an office more than 10,000km away? Such a scenario is possible today with robotic surgery. Robotic surgery was first introduced to the world in 2000 (and came to Malaysia only 3 years later). It was pioneered in the field of urological cancer surgeries such as prostate cancer surgeries, followed by kidney and bladder cancer surgeries. This method then made its way to other areas like functional and reconstructive surgeries such as pelvic organ prolapse and severe urinary incontinence using mesh or artificial urinary sphincter. The method is now gaining traction in other surgical disciplines such as colorectal, ENT, cardiothoracic and gynaecology. Robotic surgery brings many advantages. It has enabled surgeons to "see" better, gain greater access to structures, improve dexterity, reduce tremor, and be able to operate in greater comfort, especially during complicated surgical procedures. It allows the surgeon to suture with greater ease due to the greater degree of motion it allows. Ultimately, it has saved operating time and resulted in better operative techniques. Today, there are already more than 5,600 robots in 67 countries with more than 7,200,000 procedures performed. About 80 percent of prostate cancer surgeries are done robotically in the US and 70 percent in the UK. According to an article published in the "Laparoscopic, Endoscopic and Robotic Surgery" journal, in 2019, a mathematical model was created to compare robotic and standard laparoscopic procedures, and to determine the more effective surgical treatment from a patient's point of view. The robotic approach clearly stood out as the preferred option in two of the studied surgeries (prostate and lung). At the same time, 72 studies have evaluated various robotic surgeries and concluded that they were associated with reduced morbidity, less blood loss, reduced hospital stays, and comparable clinical outcomes when held against the corresponding open procedures. They also offer a shorter operative duration and a faster learning curve compared to laparoscopic methods. One of the innovations introduced in robotic surgery recently, and which has taken it to another level, is augmented reality (AR). AR allows us to visualise how a real-life environment looks like with a digital augmentation overlaid on it. A simple example of an AR programme is one that allows an interior designer to visualise how a room would look like when it is filled with the desired furniture and fittings. AR helps in remotely guided operations, where an expert located in one part of the world can visually guide surgeons in another continent to perform surgeries in real time and without the necessity of being physically present. It is also used as a platform for teaching, where junior surgeons can learn the intricacies of surgical procedures without crowding an actual surgery and risk breaching the sterility of the operation theatre. The true advantage of AR is that it can allow even complex operations to take place at a moment's notice minus the hassle of travel. Irrespective of the patient's location, he or she gets the best expertise available even when the area is not immediately accessible. Ultimately, this means that procedures are safer, guided properly and patients receive the best care possible. Innovations like these erase boundaries and eliminate logistical obstacles to good medical treatment. Patients no longer need to wait for long periods or make extensive journeys to get the help they need. Aided by the latest mobile tools and gadgets, a consultant surgeon can deliver complicated surgeries from anywhere in the world, allowing patients to receive the best treatment without ever leaving their hometowns. Advances in computational power paired with massive amounts of data generated in healthcare systems make many clinical problems ripe for AI applications. Below are two recent applications of accurate and clinically relevant algorithms that can benefit both patients and doctors through making diagnosis more straightforward. The first of these algorithms is one of the multiple existing examples of an algorithm that outperforms doctors in image classification tasks. In the fall of 2018, researchers at Seoul National University Hospital and College of Medicine developed an AI algorithm called DLAD (Deep Learning based Automatic Detection) to analyse chest radiographs and detect abnormal cell growth, such as potential cancers. The algorithm's performance was compared to multiple physician's detection abilities on the same images and outperformed 17 of 18 doctors. Thus far, algorithms in medicine have shown many potential benefits to both doctors and patients. However, regulating these algorithms is a difficult task. The U.S. Food and Drug Administration (FDA) has approved some assistive algorithms, but no universal approval guidelines currently exist. On top of that, the people creatingalgorithms to use in the clinic aren't always the doctors that treat patients, thus in some cases, computationalists might need to learn more about medicine while clinicians might need to learn about the tasks a specific algorithm is or isn't well suited to. Adapted Sources: Greenfield, D. (2019). Artificial Intelligence in Medicine: Applications, implications, and limitations. Science in the News. https://sitn.hms.harvard.edu/flash/2019/artificial-intelligence-in-medicine-applications-implications-and-limitations/ Lo, W. H. L. (2021). Robotic surgery. News Straits Times. https://www.msn.com/en-my/health/other/robotic-surgery/ar-BB1dF3L9?ocid=msedgdhp Question Suggest FOUR (4) performance indices to measure quality or efficiency of AI medical consultation. You have to describe how information is collected, interpreted and applied. (Need four types of graph which have the correct data)