ARTIFICIAL INTELLIGENCE IN MEDICINE

the anesthesia consultant

Physician anesthesiologist at Stanford at Associated Anesthesiologists Medical Group
Richard Novak, MD is a Stanford physician board-certified in anesthesiology and internal medicine.Dr. Novak is an Adjunct Clinical Professor in the Department of Anesthesiology, Perioperative and Pain Medicine at Stanford University, the Medical Director at Waverley Surgery Center in Palo Alto, California, and a member of the Associated Anesthesiologists Medical Group in Palo Alto, California.
email rjnov@yahoo.com
phone 650-465-5997

I’m fascinated by the topic of artificial intelligence in medicine. This is the third column in a series regarding robots in medicine. (See Robot Anesthesia and Robot Anesthesia II)

ai-medical-1-orig

AI already influences our daily life. Smartphones verbally direct us to our destination through mazes of highways and traffic. Computers analyze our shopping habits and populate our Internet screens with advertisements for products we’ve ogled in the past. Smartphones perform voice-to-text conversions by pattern recognition of human vocal sounds. Fingerprint scanners learn and then recognize the image of our thumbprints with exacting accuracy. Amazon’s Alexa is an AI-powered personal assistant that accepts verbal commands in our homes.

What about AI in medicine (AIM)? AIM is a bold enterprise on the horizon in clinical medicine. Hundreds of AIM scientific publications appear in medical journals each year. I’m not an AIM researcher, but I’m an expert clinician and I love to read. I’ve worked in almost every scenario of medical practice, and because my base is at Stanford University Medical Center in Silicon Valley, many of the advances of the high-tech industry are right here in my backyard. My medical board certifications are in internal medicine and anesthesiology—two fields which have significant overlap in their knowledge base but radically different practice settings. Internal medicine doctors work in clinics, where most diseases are chronic and the most valuable tools for doctors are excellent listening and diagnostic skills. Anesthesiologists work in operating rooms and intensive care units—acute care settings which demand vigilance, steady hands, and quick thinking.

Based on my experience and my reading, I foresee AIM/robots populating three clinical arenas in radically different roles. These arenas will be: 1) diagnosis of images, 2) clinics, and 3) operating rooms/intensive care units. Let’s look at each of these in turn.

  1. Diagnosis of images    This will be the first major application of AIM. We already have electrocardiogram (ECG) machines which interpret a patient’s ECG tracing with high accuracy, and print out the diagnosis for the physician to read. This application debuted in the 1980s and is now the industry standard, although confirmation of diagnosis by a physician is important for some diagnoses such as ST-elevation myocardial infarction (STEMI). More than a few physicians have already lost the skill of reading an ECG themselves because of this device. Future applications of image analysis in medicine will be machine learning for diagnosis in radiology, pathology, and dermatology. The evaluation of digital X-rays, MRIs, or CT scans is the assessment of arrays of pixels. Expect that future computer programs will be as accurate or more accurate than human radiologists. The model for machine learning is similar to the fashion in which a human child learns. A child is not given a list of criteria which define what a dog looks like. Instead, the child sees an animal and his parents tell him that animal is a dog. After repeated exposures, the child learns what a dog looks like. Early on the child may be fooled into thinking that a wolf is a dog, but with increasing experience the child can discern with almost perfect accuracy what is or is not a dog. Machine learning is a subset of deep learning, a concept that makes automated decision-making possible. Deep learning is a radically different method of programming computers. It requires massive database entry, much like the array of dogs that a child sees in the example above, so that the computer can learn the skill of pattern matching. The program repetitively teaches a machine the identity of certain images, and the system hones this algorithm and becomes faster and more accurate in recognizing similar images. An AI computer which masters machine learning and deep learning will probably not give yes or no answers, but rather a percentage likelihood of a diagnosis, i.e. a radiologic image has greater than a 99% chance of being normal, or a skin lesion has greater than a 99% chance of being a malignant melanoma. At the present time the Food and Drug Administration (FDA) does not allow machines to make formal diagnoses, and such AI computer applications are only prototypes. But if you’re a physician who makes his or her living by interpreting digital images, there’s real concern about AI taking your job in the future. Some experts believe AIM devices will not replace radiologists, but rather will make their work more efficient and accurate. For example, AI computers can identify MRI or CT scans which are normal, freeing human radiologists to concentrate on scans where an abnormality exists. In this scenario, radiologists would not lose their jobs to AIM computers, instead radiologists who don’t use AIM machines may lose their jobs to radiologists who do use the AIM technology. In pathology, computerized digital diagnostic skills will be applied to microscopic diagnosis. In dermatology, machine learning will be used to diagnosis skin cancers, based on large learned databases of digital photographs. Dermatologists must rely on years of experience to learn to discern various skin lesions, but an AI computer can ingest hundreds of thousands of images in a period of months.
  2. Clinics  In the clinic setting, the desired AI application would be a computer that could input information on a patient’s history, physical examination, and laboratory studies, and via machine learning and deep learning, establish the patient’s diagnoses with a high percentage of success. AI computers will be stocked with information from multiple sources, including all known medical knowledge published in textbooks and journals, as well as the electronic health records (EHR)/ clinical data from thousands of previous hospital and clinic patients. AI machines can remember this vast array of information better than any human physician. AI machines will organize the input of new patient information into a flowchart, also known as a branching tree. A flowchart will mimic the process a physician carries out when asking a patient a series of questions. The flowchart program contains a series of “if . . . then . . .” branches that depend on the patient’s answers. AI will input the information sources from each new patient, and arrive at diagnoses. Once each diagnosis is established with a reasonable degree of medical certainty, an already-established algorithm for treatment of that diagnosis can be applied. For example, if the computer makes a diagnosis of asthma, then an established textbook treatment regimen of bronchodilators will be activated. It’s projected that AIM applications in clinic settings will decrease unnecessary diagnostic tests, lower therapeutic costs, and reduce the manpower needed for outpatient medicine.
  3. Operating rooms  The best current example of robot technology in the operating room is the da Vinci operating robot, used primarily in urology and gynecologic surgery. This robot is not intended to have an independent existence, but rather enables the surgeon to see inside the body in three dimensions and to perform fine motor procedures at a higher level. In my previous essays Robot Anesthesia and Robot Anesthesia II, I described models of robots designed to perform intravenous sedation or intubation of the trachea, products which are futuristic but currently have no market share. The good news for procedural physicians such as anesthesiologists or surgeons is this: it’s unlikely any AI computer or robot will be able to independently replace the manual skills such as airway management, endotracheal intubation, or surgical excision. Regarding anesthesiology, I expect future AIM robots will be hyperattentive monitoring devices which follow the vital signs of anesthetized patients, and then utilize feedback loops to titrate or adjust the depth of anesthetic drugs as indicated by these vital signs. Such a robot would not replace a human anesthesiologist, but could serve as an autopilot analogue during the maintenance or middle phase of long anesthetics, freeing up the anesthesia professional so that he or she need not be physically present. This parallels the original genesis of the role of a nurse anesthetist—to be present during stable phases of anesthetic management—so that the physician anesthesiologist could roam to other operating rooms as needed.

What will an AIM robot doctor look like? It’s unlikely it will look like a human. Most sources project it will look like a smartphone. I’d expect the screen to be bigger than a smartphone screen, so an AIM robot doctor will likely look like a tablet computer. For certain applications such as clinic diagnosis or new image retrieval, the AIM robot will have a camera, perhaps on a retractable arm so that the camera can approach various aspects of a patient’s anatomy as indicated. Individual patients will need to sign in to the computer software system—this will be done via tools such as retinal scanners, fingerprint scanners, or face recognition programs—so that the computer can retrieve that individual patient’s EHR data from an Internet cloud. It’s possible individual patients will be issued a card, not unlike a debit or credit card, which includes a chip linking them to their EHR data.

How will we define if these medical computers are truly intelligent? The accepted test for machine intelligence is the Turing test, as described by computer scientist Alan Turing in 1950. In the Turing test, a human evaluator interacts with two players via a computer keyboard. One of the players is a human and the other a machine. If the evaluator cannot reliably tell the machine from the human, the machine is said to have passed the test, and is deemed intelligent.

What will be the economics of AIM? Who will pay for it? Currently America spends 17.6% of its Gross National Product on healthcare, and this number is projected to reach 20% by 2025. Entrepreneurs realize that healthcare is a multi-billion dollar industry, and the opportunity to earn those healthcare dollars is a seductive lure. Companies are looking to merge increasing computing power available at steadily decreasing costs, big data from large EHR patient populations, and artificial intelligence with an aim to drive down the costs of health care while increasing effectiveness. Expect to see the development of increasingly cheaper AIM devices to augment the skills of human physicians, or maybe replace them in some job descriptions. The government’s medical costs may decrease if work currently done by expensive-to-train physicians is instead performed by nurse practitioners or nurses aided by artificial intelligence machines, supervised by relatively few human physicians. Google is working on an AIM project in the United Kingdom entitled DeepMind. DeepMind is using machine learning to analyze eye scans from more than a million patients, with the aim to create algorithms which can detect early warning signs of eye diseases that human physicians might miss. Google researchers have also developed an AIM computer to screen for and analyze the spread of breast cancer cells in lymph node tissue on pathology slide images. Scientists at the Memorial Sloan-Kettering Cancer Center in New York have programmed over 600,000 medical evidence reports, 1.5 million patient medical records, and two millions of pages of text from medical journals into IBM’s Watson computer. Equipped with more information than any human physician could ever remember, Watson is projected to become a diagnostic machine superior to any doctor.

There’s a worldwide shortage of physicians. The earliest a human physician can enter the workforce is age 29, after completing 4 years of college, 4 years of medical school, and 3 years of the shortest residency (e.g. internal medicine, pediatrics, or family practice residency). A major advantage of AIM is that the machines won’t require 24 years of education. Can America afford to train people for almost three decades to then sit in a clinic and perform histories and physicals on patients who have chronic illnesses such as hypertension, hyperlipidemia, and obesity? Shifting these jobs to allied healthcare providers such as physician assistants or nurse practitioners is a cheaper alternative, but what could be cheaper than an AIM machine module which either assists one physician to evaluate a vast number of patients, or an AIM module of the future which replaces the physician entirely?

When can we expect to see new AIM tools adopted in clinical practice? Web-based smartphone apps such as Your.MD and Babylon already exist to assist physicians in diagnosis. You can anticipate the application of machine learning in the diagnosis of digital images soon. The DeepMind and Watson computers are blazing a trail toward machine learning in clinical medicine. Expect the FDA to assess the new technologies, and when it is safe and appropriate, to approve machine diagnosis as part of the practice of medicine. Remember how fast we advanced from a cell phone the size of a breadbox to the powerful smartphone that fits in the palm of your hand today. In the ten years since the introduction of the iPhone in 2007, who could have imagined the vast array of applications we carry in our pocket or purse in 2017?

AIM is coming. It will arrive be sooner than we think, and in all likelihood it will be more powerful and more wonderful than we could imagine. A brave prediction: AIM will change medicine more than any development since the invention of anesthesia in 1849.

I can’t wait to see it.

 

Recommended reading:

Hsieh, Paul. AI in Medicine: Rise of the Machines, Forbes, April 30, 2017. 

Mukherjee, Siddhartha. A.I. vs M.D. What Happens When Diagnosis is Automated? The New Yorker, April 3, 2017. 

Manney, Kevin. How Artificial Intelligence Will Heal America’s Sick Healthcare System. Newsweek, May 24, 2017. 

Omni staff. Artificial Intelligence in Medicine. Omni, 2016.

Bhavsar N, Norman A. Artificial Intelligence is Completely Transforming Healthcare. Futurism, April 3, 2017.

Dickson B. How Artificial Intelligence is Revolutionizing Healthcare, TheNextWeb.com, May 2017.

Russell S, Norvig P. Arificial Intelligence, A Modern Approach, 3rd Edition, 2010, Prentice Hall.

 

NOTE:

Coming in 2019, DOCTOR VITA, Dr. Novak’s second novel, an Orwellian science fiction tale of how Artificial Intelligence in Medicine will change the world we live in forever.

 

The most popular posts for laypeople on The Anesthesia Consultant include:

How Long Will It Take To Wake Up From General Anesthesia?

Why Did Take Me So Long To Wake From General Anesthesia?

Will I Have a Breathing Tube During Anesthesia?

What Are the Common Anesthesia Medications?

How Safe is Anesthesia in the 21st Century?

Will I Be Nauseated After General Anesthesia?

What Are the Anesthesia Risks For Children?

 

The most popular posts for anesthesia professionals on The Anesthesia Consultant  include:

10 Trends for the Future of Anesthesia

Should You Cancel Anesthesia for a Potassium Level of 3.6?

12 Important Things to Know as You Near the End of Your Anesthesia Training

Should You Cancel Surgery For a Blood Pressure = 178/108?

Advice For Passing the Anesthesia Oral Board Exams

What Personal Characteristics are Necessary to Become a Successful Anesthesiologist?

How do you imagine the future of medical care? Cherubic young doctors holding your hand as you tell them what ails you? Genetic advances or nanotechnology gobbling up cancerous cells and banishing heart disease? Rick Novak describes a flawed future Eden where the only doctor you’ll ever need is Doctor Vita, the world’s first artificial intelligence physician, endowed with unlimited knowledge, a capacity for machine learning, a tireless work ethic, and compassionate empathy.

artificial-intelligence-in-medicine

In this science fiction saga of man versus machine, Doctor Vita blends science, suspense, untimely deaths, and ethical dilemma as the technological revolution crashes full speed into your healthcare.

robo_aberta

Set on the stage of the University of Silicon Valley Medical Center, Doctor Vita is the 1984 of the medical world– a prescient tale of Orwellian medical advances.

LEARN MORE ABOUT RICK NOVAK’S FICTION WRITING AT RICK NOVAK.COM BY CLICKING ON THE PICTURE BELOW:

DSC04882_edited

 

 

ROBOT ANESTHESIA II

the anesthesia consultant

Physician anesthesiologist at Stanford at Associated Anesthesiologists Medical Group
Richard Novak, MD is a Stanford physician board-certified in anesthesiology and internal medicine.Dr. Novak is an Adjunct Clinical Professor in the Department of Anesthesiology, Perioperative and Pain Medicine at Stanford University, the Medical Director at Waverley Surgery Center in Palo Alto, California, and a member of the Associated Anesthesiologists Medical Group in Palo Alto, California.
email rjnov@yahoo.com
phone 650-465-5997

Are anesthesiologists on the verge of being replaced by a new robot? In a word, “No.” The new device being discussed is the iControl-RP anesthesia robot.

THE iCONTROL-RP ANESTHESIA ROBOT

On May 15, 2015, the Washington Post published a story titled, “We Are Convinced the Machine Can Do Better Than Human Anesthesiologists.”

 

In recent years there have been significant advances in the automated delivery of the intravenous anesthetic drugs propofol and remifentanil. (Orliaguet GA, Feasibility of closed-loop titration of propofol and remifentanil guided by the bispectral monitor in pediatric and adolescent patients: a prospective randomized study, 2015 Apr;122(4):759-67). Propofol is an ultra-short-acting hypnotic drug that causes sleep. Remifentanil is an ultra-short-acting narcotic that relieves pain. Administered together, these drugs induce what is referred to as Total Intravenous Anesthesia, or TIVA. Total Intravenous Anesthesia is a technique anesthesiologists use when they choose to avoid using inhaled gases such as sevoflurane and nitrous oxide. Anesthesiologists administer TIVA by adjusting the flow rates on two separate infusion pumps, one infusion pump containing each drug.

A closed-loop system is a machine that infuses these drugs automatically. These systems include several essential items: The first is a processed electroencephalogram (EEG) such as a bi-spectral monitor (BIS monitor) attached to the patient’s forehead which records a neurologic measure of how asleep the patient is. The BIS monitor calculates a score between 0 and 100 for the patient’s level of unconsciousness, with a score of 100 corresponding to wide awake and 0 corresponding to a flat EEG. A score of 40 – 60 is considered an optimal amount of anesthesia depth. The second and third essential items of a closed-loop automated system are two automated infusion pumps containing propofol and remifentanil. A computer controls the infusion rate of a higher or lower amount of these drugs, depending on whether the measured BIS score is higher or lower than the 40- 60 range.

Researchers in Canada have expanded this technology into a device they call the iControl-RP, which is in clinical trials at the University of British Columbia. The iControl-RP is a closed-loop system which makes its own decisions. The initials RP stand for the two drugs being titrated: remifentanil and propofol. In addition to monitoring the patient’s EEG level of consciousness (via a BIS monitor device called NeuroSENSE), this new device monitors traditional vital signs such as blood oxygen levels, heart rate, respiratory rate, and blood pressure, to determine how much anesthesia to deliver.

Per published information on their research protocol, the iControl-RP allows either remifentanil or propofol to be operated in any of three modes: (1) closed-loop control based on feedback from the EEG as measured by the NeuroSENSE; (2) target-controlled infusion (TCI), based on previously-described pharmacokinetic and pharmacodynamic models; and (3) conventional manual infusion, which requires a weight-based dose setting. (Reference: Closed-loop Control of Anesthesia: Controlled Delivery of Remifentanil and Propofol Dates, Status, Enrollment Verified by: Fraser Health, August 2014, First Received: January 15, 2013, Last Updated: March 5, 2015, Phase: N/A, Start Date: February 2013, Overall Status: Recruiting, Estimated Enrollment: 150).

In Phase 1 of the iControl-RP testing involving 50 study subjects, propofol will be administered in closed-loop mode and a remifentanil infusion will be administered based on a target-controlled infusion. In phase 2 involving 100 study subjects, both propofol and remifentanil will be administered in closed-loop mode. The investigators aim to demonstrate that closed-loop control of anesthesia and analgesia based on EEG feedback is clinically feasible.

In both phases, an anesthesiologist will monitor the patient as per routine practice and have the ability to modify the anesthetic or analgesic drugs being administered. That is, he or she will be able to adjust the target depth of hypnosis, adjust the target effect site concentration for remifentanil, immediately switch to manual control of either infusion, administer a bolus dose, or immediately stop the infusion of either drug. iControl-RP is connected to the NeuroSENSE EEG monitor, the two infusion pumps for separately controlled propofol and remifentanil administration, and the operating room patient vital signs monitor. A user interface allows the anesthesiologist to set the target EEG depth level, switch between modes of operation (manual, target-controlled infusion, or closed-loop), and set manual infusion rates or target effect-site concentrations for either drug as required.

Per the article in the Washington Post. (Todd C. Frankel, Washington Post, May 15, 2015), one of the machine’s co-developers Mark Ansermino, MD said, “We are convinced the machine can do better than human anesthesiologists.” The iControl-RP has been used to induce deep sedation in adults and children undergoing general surgery. The device had been used on 250 patients so far.

Why is this robotic device only a small step toward replacing anesthesiologists?

A critical realization is that anesthetizing patients requires far more skill than merely titrating two drug levels. Every patient requires (1) preoperative assessment of all medical problems from the history, physical exam, and laboratory evaluation of each individual patient, so that the anesthesiologist can plan and prescribe the appropriate anesthesia type; (2) placement of an intravenous line through which the TIVA drugs may be administered; (3) mask ventilation of an unconscious patient (in most cases), followed by placement of an airway tube to control the delivery of oxygen and ventilation in and out of the patient’s lungs; (4) observation of all vital monitors during surgery, with the aim of directing the diagnosis and treatment of any complication that occurs as a result of anesthesia or the surgical procedure; (5) removal of the airway tube at the conclusion of most surgeries, and (6) the diagnosis and treatment of any complication in the newly awake patient following the anesthetic.

In the future, closed-loop titration of drugs may lessen an anesthesiologist’s workload and free him or her for other activities. In the distant future, closed-loop titration of drugs may free a solitary anesthesiologist to initiate and monitor multiple anesthetics simultaneously from a control booth via multiple video screens and interface displays. But the handling of all tasks (1) – (6) by an automated robotic device is still the stuff of science fiction. The Washington Post article said an early role for the machine could be in war zones or remote areas where an anesthesiologist is unavailable. One could conjecture that a closed-loop anesthesia system may be used to facilitate surgery in outer space some day as well.

In either case, an anesthesiologist or some other highly-trained medical professional will still be required on site to achieve tasks (1) – (6).

The iControl-RP has not been approved by the U.S. Food and Drug Administration.

The iControl-RP team has struggled to find a corporate backer for its project. Dr. Ansermino, the anesthesiologist inventor in Vancouver, told the Washington Post, “Most big companies view this as too risky,” but he believed a device like this was inevitable. “I think eventually this will happen,” Ansermino told the Washington Post, “whether we like it or not.”

That may be, but I suspect companies are risk averse regarding the iControl-RP because investment is guided by analysts and physicians who must consider the practical applications and risks of any new medical device. The issues of leaving (1) – (6) up to a robotic device are impractical at best, and dangerous to the patient at worse.

 

The most popular posts for laypeople on The Anesthesia Consultant include:

How Long Will It Take To Wake Up From General Anesthesia?

Why Did Take Me So Long To Wake From General Anesthesia?

Will I Have a Breathing Tube During Anesthesia?

What Are the Common Anesthesia Medications?

How Safe is Anesthesia in the 21st Century?

Will I Be Nauseated After General Anesthesia?

What Are the Anesthesia Risks For Children?

 

The most popular posts for anesthesia professionals on The Anesthesia Consultant  include:

10 Trends for the Future of Anesthesia

Should You Cancel Anesthesia for a Potassium Level of 3.6?

12 Important Things to Know as You Near the End of Your Anesthesia Training

Should You Cancel Surgery For a Blood Pressure = 178/108?

Advice For Passing the Anesthesia Oral Board Exams

What Personal Characteristics are Necessary to Become a Successful Anesthesiologist?

 

Learn more about Rick Novak’s fiction writing at ricknovak.com by clicking on the picture below:  

DSC04882_edited