Artificial Intelligence, Machine Learning and Robotics in Healthcare — By Dr. Tunde Alaofin

In this age of innovation, robots and other intelligence devices start to move out of secured, controlled and predictable environment of our factories and industries to face the complexity and unpredictability of our daily environments. They are now co-occupants in our living rooms, offices, roads and our medical facilities. The only way to prevent catastrophes and avoid failure at the tasks they are programmed to do, especially in delicate and life or death environment like hospitals, is for robots to learn how to adapt on the go. Robots have to learn new techniques and strategies to enable them to react quickly and efficiently in their new environment. These are techniques for rapid and robust manipulation of objects.

New technologies hold a lot of promise in treating and diagnosing illnesses. When medical professionals adopt these new methods, they become more robust and rapid in their interventions. One of the technologies that can enable such patient outcomes is artificial intelligence (AI). AI refers to the study of machine algorithms to enable them to carry out cognitive functions like solving problems, making decisions, recognizing objects or reasoning. One cognitive function performed by artificial intelligence is pattern recognition and prediction. This is also called machine learning and is the basis behind making machines more adaptable. To narrow the discussion, focus in this analysis is on robot-assisted surgery. If healthcare specialists adopt artificial intelligence and machine learning, they can become more effective at dealing with difficult surgical environments and would thus save more lives.

Robots help enhance dexterity or deal with inefficiencies in the human hand during surgery. When a technologically- unaided surgeon operates on a patient, they may have problems with maintaining a steady hand. If a surgeon has tremors, they may make a mistake and cut or pierce the wrong part. Through surgical robots like “Surgeon Waldo,” a physician console and a remote patient cart can convert the doctor’s movement into steady movement (Smith, 2019). As a result, the surgeon would only operate on the exact area intended. This would eliminate unnecessary injury and blood loss. Alternatively, in case the surgeon has a weak hand that may not withstand a long procedure, these types of robots help in boosting endurance and strength. Artificial intelligence thus helps surgeons to reduce mistakes that stem from human inefficiencies. These mistakes can cause blood loss, pain, injury and sometimes even fatal outcomes.

Apart from eliminating motor errors, artificial intelligence and machine learning enable robots to detect deviations from treatment paths, thus correcting them. When surgeons want to operate, they usually have a plan. If the plan is fed into a machine, the robot can easily recognize when the surgeons have not followed it. Sometimes medics deliver non-optimal treatment because there is no machine learning (Smith, 2019). With time, this may undermine the effectiveness of the procedure. Treatment outcomes could be unsatisfactory if the intended path is not the implemented plan.

On top of treatment plan compliance, one of the most groundbreaking uses of robotics in surgery is radiation precision. If a person has tumors or cancerous lesions in sensitive parts of the body, invasive surgery may not be an option. Not only do they stand the risk of experiencing excessive damage, but they may also impair other body functions. For instance, invasive brain surgeries are risky because they can cause hemorrhages, which may lead to a stroke and, eventually, death. Other tumors in the kidney, lungs and other sensitive areas, may also lead to dilapidating outcomes if they are manipulated directly by hand. This is where machine learning and robotics come in (Malik & Rathaur, 2017). Through a technology called cyberknife (, people with lesions in sensitive areas can receive radiation therapy without any invasion at all. The robot already detects where the tumor is. It then targets it using the least uncomplicated path. Machine learning helps to calculate and find the best position to aim the laser beam through. This is typical of most supervised forms of machine learning. They enable the computer to predict results through an algorithm. Usually, the precision is within millimeters of the locations. As a result of the technology, some patients can have these robot-assisted surgeries done in the morning and on the same day, they can go about their daily business. Not only does that restore their health, but it does so through the least disruptive method possible.

Minimally invasive surgeries are now becoming a way to conduct many operations, and these also rely heavily on robotics and artificial intelligence. In a minimally invasive operation, the doctor cannot touch the actual body part that he wants to treat. This is often because the body part is very hard to reach, too small, or it may be too delicate. If an institution has a robotic assistant, it can still operate these areas through cameras and surgical instruments. The doctor would have access to remote hand controls in which they alter the movement of the instruments. The camera shows them exactly what or where they need to go. Artificial intelligence helps to keep the surgical tools in the correct working order (Virtua Health, 2020). The result is lower infection rates, which usually come when humans manipulate the inner parts of the body. Successful minimally invasive operations also lead to less scarring and greater chances of recovery.

While all the above benefits are real and meaningful, artificial intelligence in robot-assisted surgery has its limits. First, it cannot be regarded as a silver bullet for all delicate operations (Hashimoto et al., 2018). Even though it augments and supports decisions during operations, it is not a replacement for the human role in operations. Second, there are a lot of costs associated with such high-level applications of these technologies. Some of the robotic systems mentioned above are only available in certain institutions or parts of the world. This means that a vast majority of patients that require these interventions may not be able to access them. There are also risks associated with the use of artificial intelligence in surgeries. For instance, on the ones that conduct radiation, a machine may decide to pass radiation through a part of the brain that accounts for the person’s personality. If no human detects this machine decision, the robot may permanently change a patient’s personality merely because its algorithm told it that it was the best route. Things like human instinct and emotional intelligence cannot be replicated in a machine. Therefore, a doctor should always be on guard even when a robot does all of the procedures.


Artificial intelligence is critical in enabling rapid and robust manipulation of objects. This usually results in specific positive results during treatment. First, AI eliminates inefficiencies which stem from dexterity and endurance limitations. Additionally, AI keeps surgeons on the right treatment plan. Also, machine learning helps to calculate the best pathways to deliver radiation therapy. Finally, a robot helps surgeons to conduct minimally invasive surgery by guiding the surgical instruments into hard-to-reach places. The result of all these applications is more efficient medical procedures. Patients lose less blood and bear less pain. They don’t have to experience scarring or interruptions that come from tampering with their body parts. AI thus leads to better treatment outcomes.


Hashimoto, D., Rosman, G. & Meireless, O. (2018). Artificial Intelligence in Surgery: Promises and Perils. Annals of Surgery, 268(1), 70-76.

Malik, A. & Rathaur, V. (2017). Overview of artificial intelligence in medicine. Journal of Family Medicine and Primary Care, 8(7), 2328-2331.

Smith, R. (2019, Feb. 7). How Robots and AI are Creating the 21st-Century Surgeon. Retrieved from

Virtua Health (2020). Robotic surgery. Retrieved from


Don’t Be a Victim of Medical Errors – Part I – By Dr. Tunde Alaofin

Avoid Medical Errors - Doctor Shrugging

Medical misdiagnosis is one of the biggest healthcare safety concerns in the United States today according to The Institute of Medicine. In 2013, about 22 million Americans were misdiagnosed and over 100,000 died as a result (Leavitt & Leavitt, 2011).  Globally, misdiagnosis is responsible for millions of patient deaths every year. It is an immense and costly problem. Misdiagnosis also affects the economy by raising the already high price of healthcare delivery. The costs of an inaccurate or delayed diagnosis are very steep. It includes costs of late treatment, litigation, malpractice insurance payouts and the lost economic productivity of the patient. The dynamics of medical decision-making are changing in response to increased pressures on the global healthcare system. In developed countries, the amount of money spent on healthcare is typically the largest single component of gross domestic product (GDP) (Krugman & Wells, 2009).

The cost of healthcare influences the cost of insurance we all pay as well as government services for the uninsured. These rates will only continue to rise as baby boomers age and medicine becomes more and more advanced. Given the human and economic problems created by misdiagnosis, there is an added pressure to bring new efficiencies to the delivery of healthcare by creating an imperative for diagnoses to be made more quickly and accurately (Goldsmith, 2011). How would you measure the true cost to the person who loses their loved ones unnecessarily to medical error? This article is written to educate patients on some precautionary measures that can be taken so that they will not become victims of medical errors.

Why do diagnostic errors happen?

First, we should acknowledge that diagnosis is difficult, healthcare system is imperfect and, as human thinkers, doctors are fallible. . There are more than 12,000 identified diseases today according to the World Health Organization. Due to complexities of human body, one disease may manifest in ten different ways with ten different patients. This therefore make easy for doctors to misdiagnose patient.

Another reason is the complexity of the health system, communication barriers and disjointed care. In today world where people are so mobile, relocating from one city to another, patients change doctors like they change shoes and their medical records sometimes does not follow suit. In some cases, providers will not follow up with patients after health-care visits to encourage them to speak up and keep track of their health records. The tendency for medical error is very likely.

Research have shown serious ownership issues in that no one seems willing to take responsibility for misdiagnosis problem. It seems that diagnostic errors fall into our collective blind spot. Hospitals and health-care organizations think this is a doctor issue. Doctors think it’s a problem for other doctors, and educators don’t see it as their responsibility at all. This is why it’s so important that patients, as “consumers” of healthcare services, should be knowledgeable about their medical conditions with diagnostic tools.

There are some free medical diagnostic tools available to empower patients with the needed knowledge to make sense of their symptoms and change the way they speak to their doctors forever. In my next article, I will provide some empirical insights into how the use of these diagnostic tools can improve medical outcomes for patients.

Article By:

Dr. Tunde Alaofin

Don’t Be a Victim of Medical Errors – Part II – By Dr. Tunde Alaofin

There are five important roles patients should play to avoid being the victim of Medical Errors:Avoid Medical Errors - Confused Doctor

  • Get To Know Your New Partner –
  • Trust Your Health Care Professional
  • Educate Yourself
  • Take Control of Your Life
  • Speak Up

Get To Know Your New Partner

Isabel, a 3-year-old daughter of Jason and Charlotte Maude was misdiagnosed at a local hospital in England. Isabel spent two months in hospital, including a month in Pediatric Intensive Care Unit after experiencing multiple organ failure and cardiac arrest.

Isabel’s extensive suffering could have been avoided if the local emergency department and family physicians had stopped to ask ‘what else could this be instead of assuming her symptoms were typical of the chicken pox from which she was also suffering?’ Isabel was later diagnosed to be suffering from well-described complications of chicken pox: Toxic Shock Syndrome and Necrotizing Fasciitis.

Rather than suing the hospital for medical error or malpractices, Isabel Healthcare System was created, in honor of Isabel Maude and all patients whose lives have been impacted by missed or delayed diagnosis, to help clinicians around the world do the best job for their patients and to help patient make sense of their symptoms. Isabel – Symptom Checker software is one of the most powerful tools on the market that thousands of clinicians and patients rely on daily to produce a list of possible diagnoses on a timely basis ( I would encourage all patients to get to know this new partner and others like her in the marketplace.

Trust Your Health Care Professional

One of the most crucial element to reduce misdiagnosis is to collect the right data in time to make it part of the decision-making process. This means that patients need to provide accurate information to their medical providers. It is not uncommon for some patients to feel hesitant about sharing information. This is particularly true when this information could be embarrassing. Many of us have experienced seeing a doctor with what we feel to be an embarrassing situation. There is also a cultural component to this because, in some families, nationalities or genders, certain topics are considered taboo. These secrets can result in the doctors starting with incomplete information.

Doctors know this and will often make assumptions and come to different conclusions based first on the idea the patient is telling the truth and then a second potential diagnosis if the patient is not telling everything. Sometimes the withheld information can be as simple as the patient’s actual age, but it can even go as far as keeping secrets about drug use, medications taken, sexual history or previous illnesses. We need to remember that are physicians are trained to recognize patterns in symptoms and laboratory findings to generate a diagnosis.  It becomes more difficult when patients withhold information or present in an atypical fashion.  One of the goals of this article is to propose a unique approach to counter medical misdiagnosis by encouraging healthy partnerships between doctors, patients and intelligent software. When your medical provider pronounces a diagnosis, always get a second opinion.

Educate Yourself

Patient’s self-motivation is very important because we have human doctors making human decisions about other humans. Patients need to be aware of what may influence their doctor’s decision-making.  Imagine a doctor comes to conclusion about a diagnosis. The patient has disease X that requires drug Y. The doctor may be reluctant to use this drug, because a patient he prescribed it to previously had died. This could cause the doctor to revise and reject the rational process of attitude formation. It isn’t always about a negative bias towards a person. Sometimes it is about good doctors who are intimidated by a previous bad result. Thus, with the use of a free diagnostic tool like Isabel and patients self education, they will be able to provide inputs, clues, reminders, or extra eyes that can help a physician come to a more accurate diagnosis. Remember that the goal is to promote diagnostic partnerships between doctors, patients and intelligent software to help reduce misdiagnosis.

Take Control of Your Life

Patients need to stay informed about their bodies and symptoms. Doctors will continue to spend time learning, but when most doctors spend the bulk of their time with patients and only about five hours a month learning about new diseases, we need to be knowledgeable and present possibilities to them (Hafner, NYTimes). However, as Katie Hafner points out in her article For Second Opinion, Consult a Computer? computer software “can analyze the equivalent of thousands of textbooks every second.” That means that as awareness grows, technology improves and patients and doctors become more accepting, the incidence of misdiagnosis will become increasingly rare. All of this points to the continued need to be an informed populace and to encourage doctors to continue to work with all available tools in order to help reduce the rate of misdiagnoses. We all have a part to play.

Speak Up

Medical researchers conclude that the majority of diagnostic errors arise from flaws in physician thinking, not technical mistakes. The stressful atmosphere of hospital-based medicine contributes to a high level of anxiety. Knowing the right questions to ask and being good advocates is important. Sometime it can be difficult, particularly when there are perceived power imbalances in the doctor-patient relationship. This is where patient advocates may have a role. Patient must know how and when to give feedbacks about errors if their symptoms persist, change or worsen. Your life may just depend on it.

Diagnostic mistakes account for about 15 percent of errors that result in harm to patients, according to the Institute of Medicine. Yet diagnostic software has been slow to make its way into clinical settings, and Dr. Dhaliwal, professor of clinical medicine at the University of California, San Francisco who is considered one of the most skillful clinical diagnosticians in practice today, uses Isabel as a “second check,” said he could understand why.

Not only is it hard to integrate software into an already busy daily work flow, he said, but “most of us don’t think we need help at diagnosis, especially with routine cases, which account for the majority of our work” (Hafner, NYTimes).

The bottom line comes back to the theme of the article: “Don’t Be a Victim of Medical Errors”. Diagnostic software simply provides information for a physician to consider when working with a patient. It is the patient’s knowledge and the level of advocacy that these ideas, clues, reminders, or extra eyes that can help a physician come to a more accurate diagnosis.

Article By:

Dr. Tunde Alaofin

Will Computer System Replace Your Family Doctor?

As a baby boomer entering the AARP and Medicare world, several thoughts come to mind and are of concern. Would it be better if I knew less about medicine, health care policies, need for cost containment, the abuse of self-referral, the potential that my own future health decisions might be made by individuals with limited medical education?

According to Money magazine, (March 2011 pages 98-106), the Association of American Medical Colleges has projected that in 2015 there will be 63,000 fewer physicians than it needs. Furthermore, an article in The Atlantic, “Artificial Intelligence Is the Next Killer App” referenced a statement by a Microsoft executive in a New York Times article speculating that future applications might include a “medical doctor in a box” that could help with basic medical issues.

Martin Ford told NPR’s Linda Wertheimer “Radiologists basically focus on looking at visual images from medical devices — things like X-Rays or CAT scans, that type of thing. Now, machines are getting much better at analyzing that type of visual information.”

How concerned or thrilled should I be that the intelligence designated to my future health care decisions will be potentially limited or artificial?

What does the practice of medicine mean? What makes a “good doctor?” What is it you want in your physician? For me, I want him/her to listen to my complaints/concerns. Not all patients know what symptoms to prioritize or what signs and symptoms might be significant or related. Personally, I need a physician to ask appropriate and sometimes probing questions. For instance, a complaint of being tired and unable to sleep should prompt questions such as are you going to the bathroom all the time? This additional information might mean the difference between getting a B12 shot or being evaluated and treated for diabetes or a prostate condition.

In the past, a good physician knew his/her patients. He/she was there at your birth and then at the birth of your children — the Marcus Welby, M.D. or Dr. Kildare who did it all. As medicine and science and technology evolved, the medical specialist was born. That was actually necessary given the accelerated influx of information and research discoveries. To know all areas of medicine thoroughly is virtually impossible. The problem with the specialist scenario, however, is making sure you are going to the “right” one. It is more than a matter of competence. Specialists tend to be very focused and may “listen” only to those symptoms/signs relative to their specialty and assume some other specialist is dealing with “everything else.” In most instances, triage from an astute general internist or primary physician or other health care provider is required.

In addition to listening, there is also the laying on of the hands, palpation, and the physical examination. How many doctors these days even know how to take a good history or perform an accurate physical exam? The typical visit usually consists of an EKG, a stress test, an X-Ray, and a bill.

As identified in the February 26 New York Times article, “Treat the Patient, not the CT Scan,” patients are not “looked at” anymore. As a patient, either in the office or in the hospital, does your doctor look at you, shake your hand or is he/she fixated on the intake information, the chart and/or the monitors?

Medicine has become dependent on lab tests and imaging examinations; the “art” of medicine is being lost. Even more disturbing, is that most laboratory examinations highlight when the results are too high, too low, or abnormal in some way. Medicine is being dumbed down at the same time that technology and communication of results is becoming faster.

Compound all of this with the growing list of non-physician health care providers each with varying levels of education, experience, licensure and credentials, and then add to this list, Artificial Intelligence (AI). Who (or what) has privileges to order and analyze lab and imaging examinations? Can AI be taught to evaluate, e.g., interpret, an “abnormal pattern” on an X-Ray? Will the computer be able to differentiate between “abnormal” and an “abnormal finding” that is artificially created by technique or positioning?

Currently, 4-5 years of training after medical school is typically required for radiologists to be able to make this differential accurately. Before any treatment plan is determined I want to know that a trained experienced physician specializing in what is being clinically questioned analyzes the lab and/or image examination, and is not being compensated or rewarded in some way for ordering the examinations in the first place.

An academic subspecialized radiologist is an unbiased patient advocate. With regard to “Watson” and AI, I cannot help but think of the frustration I feel when I am speaking to a computer regarding directory assistance, a credit card company, a bank, etc. and the computer does not understand my query. I often find myself yelling into the phone that I need a “representative” and the computer responds “sorry, I did not get that, did you say “lost card?” I hope the AI “medical doctor in a box” will understand while I am coughing and saying “I can’t breathe.” I hope the frustration of being misunderstood will kick in enough adrenalin to either help relieve my symptoms or kill me and put me out of my misery.

So where is medicine going? Is it better to sit back and assume that things are changing for the better? More non-physician healthcare professionals and AI to tell me how I am doing? It will be hard for me not to question decisions about my health and wonder who and how the ultimate decision for my treatment is being made.

Add to these concerns, the issue of the decision-making involvement of the insurance companies. It is the insurance company’s employee who will determine what treatment I can have or test that will be authorized for payment. It is hard not to worry that many insurance companies are focused on their financial bottom line. Their executives are very aware that morbidity is much more costly than mortality. I would hate to think the goal of health care reform is being focused not on decreasing morbidity but on increasing mortality (e.g., death squads).

Radiologists have been the earliest physician adapters to technology and I am not anti-technology or opposed to non-physician assistants being involved with patient care but I am concerned with appropriate and inaccurate information being communicated and acted on without validation and appropriate oversight. In my opinion and for me personally, I want trained experienced personnel to listen, examine and treat the patient, not the lab test or the X-Ray result.

So is knowledge power or would it be better to know less and think less about these things. How sad to feel that “ignorance may be bliss.”

Article By:

Helene Pavlov, M.D.

Fellow, American College of Radiology; Radiologist in Chief, Hospital for Special Surgery