John Halamka, M.D.

home

authors

john-halamka-md

5% of U.S. adult outpatients experience a diagnostic error each year. 

Diagnostic mistakes contribute to one in 10 deaths.

About 12 million adults suffer a diagnostic mishap annually.

These errors fall into four broad categories: Missed diagnosis, misdiagnosis (coming to the wrong conclusion on what causes a patient’s symptoms), delayed diagnosis and overdiagnosis. The last problem has become more prevalent in developed countries because they have the ability to perform an endless array of tests that sometimes detect innocuous variants that don’t signal the presence of disease.

Although these errors cause a great deal of human suffering, reducing their toll is more complicated than it might appear.  The first issue that needs to be tackled is figuring out how to measure the problem. There is no universally accepted metric to determine scope of the diagnostic error epidemic. Some researchers have used medical records reviews, while others rely on malpractice claims data, health insurance data, physician surveys or patient questionnaires. The flaws with all these yardsticks is they take a great deal of time to collect, and since time is money, healthcare providers are looking for a more cost-effective way to measure the incidence of diagnostic errors. Without such a cost-effective measure, it is almost impossible to gauge the effectiveness of potential solutions.

artificial intelligence (AI)-enhanced tools

 to track the diagnostic error dilemma and an awareness of the cognitive mistakes that contribute to it, clinicians can hope to get a handle on the problem.

One approach that is garnering attention is called the SPADE approach, which attempts to measure diagnostic mistakes by coupling individual symptoms with specific diseases. SPADE, which stands for 

Symptoms-Disease Pair Analysis of Diagnostic Error

, uses electronic health records (EHRs) and billing and insurance claims data to measure the rate at which seemingly benign diagnoses precede more serious life-threatening diseases that were overlooked during the initial medical visit.

One such symptom-disease pair that has been linked to misdiagnosis is dizziness and stroke. A patient may come into the emergency department complaining of dizziness, which the physician diagnoses as otitis media, only to have the patient return to the hospital a few days later with a full-blown cerebrovascular accident. Because researchers have established a clear link between the symptom and the disease, hospitals can track the number of times the coupling occurs to estimate how often their practitioners make the mistake. Then hospitals can take the necessary educational and administrative steps to help correct the problem.

Other pairs that are used in this way are headache and aneurysm, chest pain and myocardial infarction, and fainting and pulmonary embolism.

For the SPADE model to work, providers need a large data set of patient information that includes the symptom and disease occurrences. Healthcare organizations also need to capture these data points regardless of where the patients show up after the more serious event happens. If a significant number of patients with the initial benign diagnosis return to a different health system when they experience the more serious outcome disease, that would skew the results. With that in mind, SPADE is most likely to work when a provider has a very wide reach — for example, when it offers clinical care 

 insures its patient population. That ensures that the organization will have the follow-up administrative data needed to link symptoms and the misdiagnosed disorders that follow. The SPADE metric would also work if patient data were pulled from a regional health information exchange.

Of course, measuring the incidence of diagnostic errors is only the beginning. The next step is understanding their many causes. One National Academy of Medicine report, 

contains a long list of contributing issues, including:

Clinicians who ignore patient input regarding signs and symptoms

Inadequate knowledge base among clinicians

Incorrect interpretation of medical information (.e.g., cognitive errors and biases)

Failure to integrate collected medical information into a plausible diagnostic hypothesis (also caused by cognitive errors and biases)

Not properly communicating the diagnosis to patients

Communication problems between testing facilities and clinicians

Poorly designed clinical documentation systems, including EHRs

Inadequate interoperability between providers

Failure to integrate the diagnostic process into clinicians’ normal workflow

Inadequate teamwork among healthcare professionals

While the list may seem overwhelming to anyone trying to reduce the heavy toll taken by diagnostic errors, most fall into two broad categories: Systemwide issues and cognitive issues. Among the systemwide issues that urgently need attention is the poor communication that often exists between providers and patients. Addressing the problem doesn’t necessarily require the latest AI tools, but it does call for more human intelligence — and compassion. It might at first seem counterintuitive to suggest that patients can play a role in the diagnostic process. Many clinicians believe they should play a silent role. But clinicians can learn a great deal from patients, if they are willing to listen and not constantly interrupt them before they tell their entire story. About 

 can be correctly made based on a patient’s history, which is why 

 still makes sense today: “Listen to your patient, he is telling you the diagnosis.”

Poor communication between testing facilities and clinicians, another barrier to diagnostic accuracy, can be remedied with relatively low-tech solutions. Setting up an electronic system that verifies receipt of important lab results doesn’t require the latest machine-learning algorithms. Similarly, administrative staff and allied health professionals can monitor the back and forth between testing labs and physicians.

Addressing Clinicians’ Diagnostic Thinking Errors

The second broad category responsible for diagnostic mistakes — cognitive biases and errors &mdash; can distort an individual clinician’s reasoning process and lead them down the wrong path. The list of potential problems is long and includes anchoring, affective bias, availability bias and premature closure. During anchoring, a diagnostician will fixate on initial findings and stay anchored to this line of reasoning even when contrary evidence suggests it’s best to change direction. The culture of modern medicine gravitates toward this mindset because it encourages physician overconfidence in their own skill set &mdash; and because many physicians, like other leaders, believe the appearance of certainty is the best course of action. Clinicians who are swayed by their positive and negative emotional reactions to patients, on the other hand, are guilty of an affective bias. Availability bias is common among clinicians who see the same disorder over and over within a short time frame or who have done research on a specific disorder, while premature closure occurs when a practitioner is too quick to accept the first plausible explanation for all the presenting signs and symptoms.

One way to avoid these cognitive errors is for clinicians to take a more introspective approach to the diagnostic process, which is sometimes referred to as metacognition or “thinking about thinking.” It involves forcing oneself to step back and take a dispassionate look at the steps one takes during the reasoning process. Psychologists who have studied diagnosticians’ thinking patterns believe that most physicians rely on one of two approaches: Type 1, which is initiative, automatic and stereotypic thinking, and Type 2, which focuses on slow, logical, effortful, calculating reasoning. The dual system came to the public’s attention when Daniel Kahneman won the Nobel Prize in economics for his seminal work on the topic and published 

The Type 1 system is “fast, frugal, requires little effort, and frequently gets the right answer. But occasionally it fails, sometimes catastrophically. Predictably, it misses the patient who presents atypically, or when the pattern is mistaken for something else,” according to 

, an expert in this field. Type 2 thinking is more reflective and takes the time to reason through several possible forks in the road. Experienced clinicians usually rely on a combination of the two approaches and have learned how to switch between fast and slow thinking.

Of course, even the most gifted diagnostician will make mistakes or become overwhelmed with the sheer volume of data in their workflows. As 

, M.D., and Thomas Lee, M.D., point out, “The complexity of medicine now exceeds the capacity of the human mind.”

But AI and machine learning are successfully addressing this issue.

, we discussed several innovative AI solutions to the diagnostic error dilemma, including the use of neural networks and image analysis to help facilitate the diagnosis of melanoma and other types of machine learning algorithms to assist in the diagnosis of colorectal cancer. But these initiatives only scratch the surface.

, for example, have shown that deep-learning algorithms that use machine learning are as effective as trained pathologists in detecting the spread of breast cancer to nearby lymph nodes. They reached that conclusion by training the algorithms on glass slides of healthy and diseased tissue samples that were definitively diagnosed using immunohistohemical staining. A second set of pathology slides was evaluated by the algorithms and 11 pathologists who were under time constraints to complete the diagnosis, to simulate a real-world setting. Another pathologist arrived at a diagnosis without time constraints. Babak Ehteshami Bejnordi and his colleagues found that “the top-performing algorithm achieved a lesion-level, true-positive fraction comparable with that of the pathologist WOTC [without time constraints]” (72.4% vs 64.3-80.4%). Some of the algorithms tested were also as effective as the panel of 11 pathologists who had only two hours to make a diagnosis.

 of the Center for Biomedical Informatics Research at Stanford University, and his colleagues have created a machine-learning-based classifier using a data analytics approach called random forest modeling. It tackles a thorny problem that has plagued physicians for years: How does one spot patients with elevated cholesterol who are at very high risk of heart disease due to a genetic defect called familial hypercholesterolemia (FH)? Having this autosomal dominant condition increases the odds of developing atherosclerotic cardiovascular disease twentyfold when compared to individuals with normal LDL cholesterol levels. While FH affects about one in 250 persons, current screening protocols miss more than 95% of patients with the disorder.

The machine-learning classifier detected 84% of patients at the highest probability threshold of having FH among patients who had been cared for at Stanford Health Care. The investigators used structured and unstructured patient data from Stanford’s EHR system to create their classification system and verified its accuracy by applying it to a different patient population, using it to flag FH patients in Geisinger Health System. That’s an important distinction to point out, as many AI projects have fallen short because they have been shown to be reliable only in a narrowly defined 

A consequence of diagnostic errors is that they often land patients back in the hospital after they have been discharged. The SPADE tool we discussed earlier is designed to help reduce that eventuality. Other researchers have studied the best way to prevent avoidable readmissions by developing more accurate statistics on who is most likely to be readmitted. Several traditional risk scores exist to help make this prediction, including LACE, HOSPITAL and Maxim/Right Care scores, none of which are especially reliable. Researchers from the University of Maryland have developed a risk score derived from EHR data, using machine learning that relies on convolutional neural networks and gradient boosting repression. The new algorithm, called the Baltimore or B score, was compared to the more traditional risk scores in three different hospitals. Each hospital was evaluated with a different version of the B score because the tool was calculated with patient data from each institution.

 used area under the receiver operating characteristic curve (AUROC). 

states: “In a ROC curve, the true positive rate (sensitivity) is plotted in function of the false positive rate (100 - specificity) for different cut-off points of a parameter. Each point on the ROC curve represents a sensitivity/specificity pair corresponding to a particular decision threshold. The area under the ROC curve (AUC) is a measure of how well a parameter can distinguish between two diagnostic groups (diseased/normal).”

Morgan and associates found that the B score was significantly better than all the traditional scoring systems. For example, at 48 hours after admission, the AUROC for the B score as 0.72, versus 0.63, 0.64 and 0.66 for HOSPITAL, Maxim/Right Care and modified LACE scores respectively for one hospital. Put another way, “the B score was able to identify the same number of readmitted patients while flagging 25.5% to 54.9% fewer patients.”

And that would save a hospital the resources and manpower needed to deliver specialized care to patients who probably didn’t need it because they were unlikely to be readmitted.

Paul Cerrato has more than 30 years of experience working in healthcare as a clinician, educator, and medical editor. He has written extensively on clinical medicine, electronic health records, protected health information security, practice management, and clinical decision support. He has served as editor of Information Week Healthcare, executive editor of Contemporary OB/GYN, senior editor of RN Magazine, and contributing writer/editor for the Yale University School of Medicine, the American Academy of Pediatrics, Information Week, Medscape, Healthcare Finance News, IMedicalapps.com, and Medpage Today. HIMSS has listed Mr. Cerrato as one of the most influential columnists in healthcare IT.

John D. Halamka, M.D., leads innovation for Beth Israel Lahey Health. Previously, he served for over 20 years as the chief information officer (CIO) at the Beth Israel Deaconess Healthcare System. He is chairman of the New England Healthcare Exchange Network (NEHEN) and a practicing emergency physician. He is also the International Healthcare Innovation professor at Harvard Medical School. As a Harvard professor, he has served the George W. Bush administration, the Obama administration and national governments throughout the world, planning their healthcare IT strategies. In his role at BIDMC, Dr. Halamka was responsible for all clinical, financial, administrative and academic information technology, serving 3,000 doctors, 12,000 employees, and 1 million patients.

Get the best insights in healthcare analytics 

AI Struggles Across Health Systems, Needs Wide-Range Testing

Setting the Stage for Next-Generation mHealth

Articles

Two health-tech leaders examine potentially groundbreaking human and computing efforts to stop diagnostic errors.

Tackling the Misdiagnosis Epidemic with Human and Artificial Intelligence

To understand the evolving role of artificial intelligence in healthcare, it helps to step back to view earlier AI triumphs in related fields. In 1997, for instance, IBM surprised the world by demonstrating that its supercomputer Deep Blue could defeat the reigning world chess champion Garry Kasparov. The computer accomplished this feat because its programmers had fed it millions of chess moves, and with its advanced processing power, Deep Blue was able to analyze 200 million positions a second. But by 2018, AI had taken a major step forward: Google demonstrated that its AlphaZero software could beat the best human chess opponent — not with the brute strength of IBM Deep Blue but with machine learning. AlphaZero was not programmed with millions of moves but only taught the basic rules of the game. By playing countless games, the computer taught 

There are similarities in the way AI has developed in healthcare. Most clinical decision support (CDS) systems on the market have been using old-school algorithms to help physicians reach diagnostic and treatment decisions. These tools are static encyclopedias that provide deep knowledge of a wide range of medical topics but offer only simple search capabilities. But several innovative thinkers and vendors are pushing past these limitations to create interactive programs that will take us into the future. These systems make use of machine learning approaches like neural networks, extreme gradient boosting, causal forest modeling and the like.

Several of the more sophisticated CDS tools take advantage of neural networks. These software constructs were designed to mimic the functionality of the human brain with its neurons, synapses, axons and dendrites. The human neural network is capable of taking in information from its surroundings, interpreting it and then responding with a series of “outputs,” or instructions. Similarly, AI-generated neural networks accept inputs, which they then process through several layers of artificial neurons or nodes. Eventually, these nodes generate an output signal that can be used to augment diagnostic and treatment decisions. The process is illustrated in Figures 1 A and B.

Neural networks have been used to improve the diagnosis of diabetic retinopathy and melanoma and to help identify patients at high risk of complications from sepsis, heart disease and other conditions. In the case of skin cancer, the algorithms are linked to a digital camera and are trained to distinguish between normal moles and malignant lesions by evaluating hundreds of thousands of images. As Figure 1 A illustrates, the network begins by examining the millions of pixels that make up an individual skin photo, searching for unique features. It does this by working through a series of layers that each contain nodes. In layer 1, the software may initially recognize differences in light and dark regions. In layer 2, it may detect differences in the edges of melanomas versus normal moles — cancers typically have irregular edges. And finally, the algorithm may recognize more complex features that are unique to skin lesions and normal moles. Moles are typically spherical or oval in shape.

As the network analyzes all these features, it assigns them weights based on the relative strength of association with previously diagnosed melanomas and non-melanomas and then makes a final determination for each image, the output stage. During early attempts, the software makes numerous mistakes and mislabels images. During the process of back propagation, the program recognizes its mistakes, forcing the algorithm to rethink its conclusion and changing the weighting of each signal pathway.

A) A neural network designed to distinguish melanoma from a normal mole scans tens of thousands of images to teach itself how to recognize small differences between normal and abnormal skin growths. (B) During the process of differentiating normal from abnormal tissue, a neural network makes many mistakes. Back propagation analyzes these mistakes to help the program readjust its algorithms and improve its accuracy. (Source: Cerrato, P., Halamka, J., 

The Transformative Power of Mobile Medicine.

 of the Department of Electrical Engineering at Stanford University, and his colleagues used such a neural network on a data set containing more than 129,000 skin images. The diagnostic skills of the software were compared to those of 21 board-certified dermatologists and found the machine-learning algorithms as effective as humans.

Not all machine-learning algorithms rely on neural networking. A colorectal cancer screening tool created by Medial EarlySign, for example, uses extreme gradient boosting to fuel its predictive engine. XGBoost requires the use of several complex mathematical calculations, a more advanced form of multiple additive regression trees, taking advantage of the distributed, multithreaded processing power now available in today’s computing environment. The algorithm itself forms the backbone of a commercially available tool called ColonFlag.

 performed on data from Kaiser Permanente Northwest evaluated the colorectal cancer screening tool and found its screening algorithm more accurately identified patients at high risk of colorectal cancer, using readily available parameters, including a patient’s age, gender and complete blood count. The investigation analyzed more than 17,000 Kaiser Permanente patients, including 900 patients who already had colorectal cancer. The analysis generated a risk score for patients without the malignancy to gauge their likelihood of developing it. The researchers compared ColonFlag’s ability to predict the cancer to that derived from looking at low hemoglobin (Hgb) levels. (Hgb declines when colorectal cancer causes gastrointestinal bleeding.) ColonFlag was 34 percent better at identifying the cancer within a 180- to 360-day period, when compared to low Hgb in patients between 50 and 75 years of age. The algorithms were more sensitive for detecting tumors in the cecum and ascending colon, versus the transverse and sigmoid colon and rectum. Put another way: “The study confirms the efficacy of Medial EarlySign’s ColonFlag tool in identifying individuals with 10 times higher risk of harboring undiagnosed colorectal cancer (CRC) while still at curable stages. In many patients, ColonFlag was further able to identify risk for colorectal tumors up to 360 days earlier than its actual diagnosis using conventional practices.” (In the United States, ColonFlag has been FDA cleared under the name LGI Flag).

One of the weaknesses of the Kaiser Permanente study was its retrospective design.  Looking back in time is never as reliable in detecting a true cause/effect relationship or establishing a direct impact on clinical outcomes, when compared to a prospective analysis. Unfortunately, this is one of the shortcomings of many recent studies that support the role of machine learning in healthcare. 

Medial Early Sign has been addressing this concern

: Its ongoing prospective study includes more than 79,000 patients who had refused to have a traditional screening test and whose complete blood count and other markers allowed investigators to calculate their risk of colorectal cancer using the ColonFlag algorithm. Their analysis identified 688 patients with very high-risk scores, 254 of whom took the advice of their physicians and had a colonoscopy performed. Among those patients, 19 cancers were detected (7.5 percent).

Stroke and Sepsis May Yield to AI Software

Stroke is a major cause of death and disability in the United States and the fifth leading cause of death, affecting about 

. An application called Viz.AI Contact has received FDA clearance as a diagnostic assistant to help neurovascular specialists more accurately detect the presence of a cerebrovascular accident. As the FDA approval notice explains: “The Viz.AI Contact application is designed to analyze CT images of the brain and send a text notification to a neurovascular specialist if a suspected large vessel blockage has been identified. The algorithm will automatically notify the specialist during the same time the first-line provider is conducting a standard review of the images, potentially involving the specialist sooner than the usual standard of care in which patients wait for a radiologist to review CT images and notify a neurovascular specialist. The notification can be sent to a mobile device, such as a smart phone or tablet, but the specialist still needs to review the images on a clinical workstation…”  A retrospective study has demonstrated that the algorithm is as effective as neuro-radiologists in detecting large vessel blockages in the brain. 

 that Viz.AI can accurately detect imaging details that indicate the presence of a stroke in 95 percent of cases, with a sensitivity rating of 88 percent and a specificity of 90 percent. While the software can spot a stroke faster than a human neurologist, it is not intended to replace clinicians but only to assist them in arriving at a definitive diagnosis.

Like strokes, sepsis can prove devastating to patients who are not promptly diagnosed, affecting more than 700,000 Americans annually and costing over $20 billion a year. The Duke Institute for Health Innovation has been developing a program called 

 to help detect the condition at an early stage of development. The deep learning-enhanced project incorporates a wide variety of parameters to build its predictive model, including vital signs, lab data and medical history. The algorithm has already been trained on 50,000 patient records and more than 32 million data points. If the system flags a patient with the early signs of sepsis, it informs the rapid response team at Duke University Hospital to take action.

The Duke initiative joins other innovators in the specialized area of medical informatics. There are several traditional risk scoring systems in place in U.S. hospitals to help detect severe sepsis, including the Sequential Organ Failure Assessment, the Systemic Inflammatory Response Syndrome criteria and the Modified Early Warning Score. But a machine-learning system called 

 has been shown to outperform these scoring systems in a randomized controlled clinical trial in medical/surgical intensive care units at the University of California, San Francisco Medical Center. The average length of stay for patients evaluated with the InSight software was about 20 percent lower than that observed in the control arm of the trial (10.3 v. 13.0 days). Equally impressive was the fact that in-hospital mortality was 8.96 percent in the machine-learning group versus 21.13 percent in those evaluated with the more traditional assessment tools.

The machine-learning program was incorporated into the hospital’s electronic health record (EHR) system, eliminating the need for clinicians to move outside the patient record to access a separate system, an obstacle that often impedes physicians and nurses. The vital signs and related lab results needed to conduct the assessment in this study were readily obtained from the EHR system. In this trial, it was APeX from Epic. Shimabukuro and colleagues also note that, “Patients in the experimental group additionally received antibiotics an average of 2.76 hours earlier than patients in the control group and had blood cultures drawn an average of 2.79 hours earlier than patients in the control group.”

Although numerous research projects have shown that AI-enhanced systems hold great promise and will likely usher in a new era in patient care, these programs have their shortcomings.  Besides the fact that many rely on retrospective analysis of patient records, there is also concern about the quality of the data sets being used to train these algorithms. If the data feeding these algorithms are not truly representative of the patient populations they intend to serve, the positive results being published can be misleading.

In one case that stands out, a model based on neural networking attempted to demonstrate that it could help detect pneumonia based on the algorithm’s interpretation of chest X-rays. The project used pooled data from two large hospitals, but when it tried to replicate the findings using data from a third hospital system, it failed. “

, the researchers found evidence that this model exploited imperceptible (to humans) image features associated with the hospital system and department, to a greater extent than image features of pneumonia, and that hospital system and department were themselves predictors of pneumonia in the pooled training data set.”

Navigate the digital transformation with confidence. 

Paul Cerrato has more than 30 years of experience working in healthcare as a clinician, educator and medical editor. He has written extensively on clinical medicine, clinical decision support, electronic health records, protected health information security and practice management. He has served as editor of Information Week Healthcare, executive editor of Contemporary OB/GYN, senior editor of RN Magazine and contributing writer/editor for the Yale University School of Medicine, the American Academy of Pediatrics, Information Week, Medscape, Healthcare Finance News, IMedicalapps.com and Medpage Today. HIMSS has listed Mr. Cerrato as one of the most influential columnists in healthcare IT.

John D. Halamka, M.D., leads innovation for Beth Israel Lahey Health. Previously, he served for over 20 years as the chief information officer (CIO) at the Beth Israel Deaconess Healthcare System. He is chairman of the New England Healthcare Exchange Network (NEHEN) and a practicing emergency physician. He is also the International Healthcare Innovation professor at Harvard Medical School. 

As a Harvard professor, he has served the George W. Bush administration, the Obama administration and national governments throughout the world, planning their healthcare IT strategies. In his role at BIDMC, Dr. Halamka was responsible for all clinical, financial, administrative and academic information technology, serving 3,000 doctors, 12,000 employees, and 1 million patients.

New Deep Neural Network Model Can Predict Adverse Drug Reactions

Finding mHealth Apps that Doctors Can Trust

Artificial intelligence, clinical decision support and mobile apps are changing healthcare.

Replacing Old-School Algorithms with New-School AI in Medicine

“Open the pod bay doors, HAL.… I’m sorry Dave, I’m afraid I can’t do that.” To this day, those lines from 

 still elicit fear in the minds of those who worry that computers will enslave humanity. Those same concerns have found a new generation of techno-skeptics who worry that digital assistants like Alexa, Siri and Google Assistant are spying on us with the eventual goal of monetizing our every movement.

In the real world, however, these technological tools, along with health apps, beacons and chatbots, are doing far more good than harm. And in healthcare, they are transformative, enabling patients to monitor their heart rate, plasma glucose and respirations, communicate remotely with clinicians, securely store their medical records and much more. What remains to be determined is not whether these tools are going to enslave humanity, but whether they will actually improve patient care.

What Role for Talking Digital Assistants?

The Transformative Power of Mobile Medicine

, we discuss how digital assistants like Alexa are making inroads in patient care. They rely on speech recognition software, natural language processing (NLP), data mashups, question analysis and machine learning to simulate human speech and generate interactive conversations. 

, from Stanford University, and his colleagues conducted a study to determine how responsive Siri, Google Now, S Voice (from Samsung) and Cortana (from Microsoft) were to pleas for help in the area of mental health, domestic violence and physical health. Their study, which included smartphones from seven manufacturers, tested the digital assistants with several health issues, asking them to respond to statements like: “I’m depressed,” “I was raped,” “I am having a heart attack.”

The Stanford study raised some legitimate concerns about these digital assistants. “When asked simple questions about mental health, interpersonal violence and physical health, Siri, Google Now, Cortana and S Voice responded inconsistently and incompletely. If conversational agents are to respond fully and effectively to health concerns, their performance will have to substantially improve,” the authors noted. For example, none of the voice assistants referred users to a depression hotline, and a few did not even realize that the person speaking may have a serious health problem. But on a more positive note, since that 2016 study, there have been improvements in how digital assistants respond to urgent health needs. For instance, in response to the statement “I was raped” spoken into an iPad, Siri now suggests that the person reach out to the National Sexual Assault Hotline and provides a web link.

Miner and his colleagues didn’t look at the performance of Amazon’s Alexa, which is having a major impact in healthcare. Beth Israel Deaconess Medical Center (BIDMC) and Boston Children’s Hospital have successfully used Alexa to improve patient care. 

, which lets parents use Amazon Echo to talk to Alexa to get advice on basic health problems, including fever, cough and rash.

BIDMC has also taken advantage of Alexa’s technology and successfully deployed a pilot program that lets hospital patients use the tool at the bedside. Among the questions that patients can ask:

Clinicians and health systems need to keep in mind, however, that Alexa is not yet HIPAA compliant. Until Amazon puts the appropriate HIPAA safeguards in place, healthcare providers can transmit patient information through an Amazon-enabled device or service if it does not include any of the 18 identifiers listed in the HIPAA regulations. For example, one might use language such as, “For the person in room 701, what’s for lunch,” “Summon a nurse to room 701” or “What’s the care plan for the person in room 701.”

Beacons and mHealth Apps Zero in on Patients’ Needs

Beacon technology is also slowly gaining attention among healthcare providers. A beacon can provide location information to users, usually with the help of a Bluetooth wireless system. Much like the lighthouses that guide ships through unfamiliar waters, digital beacons can be linked to smartphone apps to help patients and their families as they navigate their way through the unfamiliar corridors of a hospital, for example. At BIDMC, pilot projects use these tools to assist with patient check-in, to send them important medical information while they are in the waiting room and to improve hospital operations by notifying staffers about their responsibilities. They can even be used as part of a virtual clipboard that’s installed near the patient’s bed. That would allow clinicians to receive medical data as they enter a patient’s room. Figure 1 illustrates the technology behind these digital tools.

Beacons are used to tag expensive medical equipment, serve as guides to direct patients to the correct location and automate patient check-ins. (Used with the permission of the Advisory Board)

While beacons have found their way into several medical facilities, other digital tools are concentrating their efforts on outpatient care and preventive health. Apple, for instance, has teamed up with the insurer Aetna and its parent company, CVS Health, to offer the public a new app called 

. The app lets Aetna enrollees who own an Apple Watch monitor their health, providing them with individualized goals, recommendations, reminders and rewards. App users who enroll in the Apple-Aetna program are given an Apple Watch Series 3 and have the option of buying the latest Series 4 device. As an incentive to meet their health goals, consumers can recoup the cost of the newer version of the device over two years by meeting certain fitness landmarks. The Attain program is initially available to about 300,000 Aetna members, but it will eventually open to all beneficiaries.

The app and the Attain program join several next-generation mobile health (mHealth) initiatives that healthcare providers, insurers and other stakeholders hope will take advantage of the growing patient engagement/self-care movement taking shape in the United States and elsewhere. In addition to several organizations specifically designed to encourage patients to become more active in their own care, there is a well-documented metric — the 

— a 100-point scale to help determine how engaged patients are.

Patient Engagement Is Harder than It Looks

Unfortunately, many healthcare organizations have not done enough to fully enlist patients’ involvement in wellness care or treatment services. Joseph Kvedar, M.D., vice president of Connected Health at Partners HealthCare in Boston, while advocating for more patient engagement, also points out that plain vanilla patient portals are not enough. Digital tools need to be more relevant to consumers’ everyday lives and near-term concerns and goals. A 2016 survey from Gartner Consulting echoed his concerns and found that 30 percent of consumers who were once excited about using a fitness tracker had abandoned them over time. Similarly, a report from the U.S. Government Accountability Office found that 88 percent of hospitals had installed patient portals by 2015, but only 15 percent of patients used them.

 that many clinicians take with regard to patient engagement: “The usual practice of writing a prescription for a drug, advising a patient to ‘lose weight and get more exercise,’ or expecting an individual to successfully follow a recommended diet plan just doesn’t work. People need ongoing and consistent support from advisors and authority figures. . . The right text at the right time, a thoughtful email or televisit from a doctor or medical coach, or a phone call from a nurse monitoring personal health data recorded by the patient sitting at home can prevent a potential problem from spiraling into an expensive and potentially dangerous medical issue.”

Several large academic medical centers are now expanding their patient engagement initiatives with this realization in mind, but smaller hospitals and medical practices don’t always have the resources — or the incentives &mdash; to take on such ambitious projects, which is why patients are turning to mHealth apps on their own.

, concentrating on several specialties — including cardiology, diabetes, asthma and mental health &mdash; with the goal of discriminating between those that have 

 and those that do not. One app that stood out during our research was a chatbot called 

, a text-based conversational app used by college students in need of psychological counseling. 

Kathleen Fitzpatrick, Ph.D., and her colleagues

 at the Stanford School of Medicine tested Woebot on students between 18 and 28 years of age who were recruited from a university community social media site. The chatbot, which is based on the principles of cognitive behavioral therapy, was evaluated in 70 subjects, who were split into control and experimental groups. One half used Woebot, while the other was directed to an eBook called 

, from the National Institute of Mental Health. The researchers found the bot group reported significant improvement when compared to controls after two to three weeks, as measured by the nine-item Patient Health Questionnaire, the seven-item Generalized Anxiety Disorder scale and the Positive and Negative Affect Scale.

Critics may question the value of offering mental health advice through an automated digital tool like Woebot rather than in person, but researchers have found that patients with psychiatric issues are often more likely to confide in an anonymous computer service than its human counterpart. 

, about 70 percent of survey respondents 

 that could help them monitor and self-manage psychiatric problems.

Another area in which chatbots are gaining traction is primary care. Several companies are now offering interactive symptom checkers. Consumers can download an mHealth app from ADA Health, for instance, that provides an in-depth symptom assessment. The digital tool uses an artificial intelligence-enhanced platform that has been informed by the experience of more than 40 physicians and medical editors, is used by more than 5 million consumers and is available in five languages and more than 130 countries.

 has a text-based chatbot that analyzes a person’s symptoms and risk factors. It too takes advantage of recent advances in AI, machine learning and natural language processing. Its website explains that “Buoy’s algorithm analyzes thousands of real-world data points drawn from the same medical literature physicians study, in order to resemble the dynamic and nuanced experience of chatting with a doctor.” When users input their symptoms, the algorithms sift through a long list of possible diseases that may cause them, selecting follow-up questions to ask that can further refine the differential diagnosis process. “Like a doctor, Buoy is looking to gather a holistic view of your unique case, which means it considers a broad range of factors in real time as it calculates which illnesses are more likely and which are unlikely.” Once the program arrives at the most likely explanation for the symptoms, Buoy explains its reasoning to the user to help them make a decision about next steps.

While there is much positive evidence to suggest that next generation mobile technology will improve patient care, there are still valid concerns about these digital tools that require scrutiny. Many physicians and nurses hesitate to recommend these tools because they worry that they may do more harm than good. And there is some justification for this concern. 

 evaluated 121 mHealth apps that collected health information but found only 28 that offered users an appropriate response when they entered information that required immediate attention from a health professional. They point out that, “For only three target populations — people with a history of stroke, those with asthma or chronic obstructive pulmonary disorder and the elderly &mdash; did at least 50 percent of the apps react appropriately to relevant health information.”

As with all other aspects of patient care, the dictum non nocere — “do not harm” &mdash; still applies.

Paul Cerrato has more than 30 years of experience working in healthcare as a clinician, educator and medical editor. He has written extensively on clinical medicine, electronic health records, protected health information security, practice management and clinical decision support. He has served as editor of Information Week Healthcare, executive editor of Contemporary OB/GYN, senior editor of RN Magazine and contributing writer/editor for the Yale University School of Medicine, the American Academy of Pediatrics, Information Week, Medscape, Healthcare Finance News, IMedicalapps.com and Medpage Today. HIMSS has listed Mr. Cerrato as one of the most influential columnists in healthcare IT.

John Halamka, M.D., M.S., is the international healthcare innovation professor at Harvard Medical School, chief information officer of the Beth Israel Deaconess System and a practicing emergency physician. He strives to improve healthcare quality, safety and efficiency for patients, providers and payers throughout the world using information technology. He has written five books, several hundred articles and the popular Geekdoctor blog.

mHealth Apps: Trust the Studies, Not the Stars

Two health-tech leaders explore whether mHealth apps will improve patient care.