By Sean Otto, vice president of business development, Cyient.
Sean Otto
The approval of electrocardiogram’s (EKG) through the FDA that enables atrial fibrillation detection right from a patient’s watch band is just one example of how the digitization of medical devices, a part of the Internet of Things movement, is leading product development and innovation in medicine. However, while medical devices built on a connected services platform include components for data storage, security, accessibility, and mobile applications, along with advanced analytics, successfully implementing artificial intelligence to drive actionable intelligence remains a challenge from an execution perspective.
According to Gartner, 85 percent of data science projects fail. Successful integration of data science into medical device development requires a rethinking around the role of data science in product design and life-cycle management.
Viewing data science as a product
While data science is rightly defined as the process of using mathematical algorithms to automate, predict, control or describe an interaction in the physical world, it must be viewed as a product. This distinction is necessary because, like any medical product, data science begins with a need and ends with something that provides clear medical utility for healthcare providers and patients.
It is erroneous to restrict the realm of data science to just the designing of algorithms. While data scientists are good at fitting models, their true value comes from solving real-world problems with fitted data models. A successful algorithm development process in data science includes business leaders, product engineers, medical practitioners, and data scientists collaborating to discover, design and deliver. For instance, a typical data science integration with a medical device product would include many of the following activities:
Identifying the medical need
Identifying proper data variables
Developing the right analytic models
Designing analytic algorithm integrations
Performing testing and verification
Deploying beta versions
Monitoring real-time results
Maintaining and updating algorithms
Considering data science as a product or feature of a product provides organizations with a different paradigm for execution focused on a tangible outcome. Data scientists are trained to develop accurate models that solve a problem, but the challenge many companies face is operationalizing those models and monetizing their outputs. Furthermore, conceptualizing data science as a product will ensure companies focus on its implementation, rather than just its development.
Advanced analytics: Part of the process, not an afterthought
Designing intelligence (even AI) into a connected medical device first depends on whether the data is being used to make a real-time decision or report on the outcome of a series of events. Most companies don’t realize the layers of advanced analytics that create actionable intelligence. By understanding these layers, which range from simple rule- and complex rule-based analytics to asynchronous event rules, complex event processing, and unsupervised learning models, companies can move quickly into developing mature analytics that have an impact from day one. As a company matures its analytics system from descriptive and diagnostic to predictive and prescriptive, it should also evolve to include strategic opportunities to provide business value, including automating decisions that can be delegated to a smart decision-support system.
Successful integration involves viewing advanced analytics as an architecture and not as a single solution to be implemented. The best way to make sure that you are successful in analytic development is to follow a continual process of discovery, design and delivery. For instance, data science architecture may begin with a business question, requiring you to determine if you have the right data and can actually leverage that data in the existing IT system. If you don’t answer this basic question, you will have challenges fully vetting the analytic opportunities available to you.
Recognizing common challenges in data science execution
Data science execution is often impaired by common missteps, like incongruence between customer and business needs and solving technical problems when it’s too late to have a positive impact. Another significant mistake from the business side is treating data science like a one-time accomplishment and not realizing it is a continuous process, or like a software development process with an unwarranted fixation on tools rather than skills and capabilities.
By Erica Doherty, healthcare industry and solution strategy director, Infor.
Erica Doherty
You may be familiar with the Gallup study that identified—across industries and organizations—that 68 percent of employees are not engaged in their work. That is not only disheartening, but scary, especially when talking about workers in the healthcare industry.
Overall, the price tag of disengagement is calculated as a $400 billion hit against employers. There is no doubt the health system revenue chain depends on employee attendance, retention and patient satisfaction scores. However, there is something much more important at stake, which is that nurse disengagement puts patient lives at risk.
There are three top indicators of mortality risk in the healthcare setting: nurse engagement level, the ratio of the number of nurses to total patient days, and the percentage of overtime hours per year, according to a Gallup study of more than 200 hospitals. Beyond safety incidents, Gallup also showed that a high level of engagement across all types of workers leads to a 21 percent higher productivity rate and lower turnover rates.
But what is engagement? Put simply, engagement is an emotional commitment to an employer and its mission. That is obviously an important factor for bedside caregivers, who are called on to offer patients more than experience and education, but also the soft skills of compassion and personal attention. Truly, all employees in healthcare impact the patient directly or indirectly. The engaged hospital worker listens, is helpful and conscientious about the entire patient experience and has been found to make fewer errors.
What healthcare leaders can do to improve employee engagement
So how do you, as a healthcare leader, create more engagement and a culture of continuous caring? Identifying the most effective technology for your organization is a key piece in solving the employee engagement puzzle. Using technology, you can discover underlying causes of disengagement.
Identifying a human capital management (HCM) solution that impacts employee engagement will have the biggest impact on your organization’s employee engagement levels. Several factors should be considered. An HCM solution that streamlines and automates key HR data contributes to keeping caregivers focused on the bedside and leaders focused on their employees—not administrative tasks. For example, one way to address disengagement is through a solution that utilizes artificial intelligence (AI) to automate, inform and augment work by answering simple questions like an employee’s PTO balance, or even identifying an employee who may be a flight risk and offering suggested activities about how to retain them.
In addition, what creates a meaningful work environment for one employee may be different for another. Figuring this out starts with the hiring process. Technology can understand the behavioral DNA of an employee and then match them to the best fit position and the culture of their employer. The next step is to provide those behavioral insights to managers so they know how to create an atmosphere that creates happiness for that employee and suggests how to lead them in a way that fosters meaning and appreciation.
By Brooke Faulkner, freelance writer; @faulknercreek.
Up to a fifth of patients with serious conditions are first misdiagnosed, and that leaves tremendous consequences. With the help of healthcare technology, doctors are able to diagnosis patients more effectively and easier. For example, migrating patient data from paper to online, known as electronic health records (EHRs), has greatly aided the medical world. Technology, especially using artificial intelligence and predictive analytics, has enabled doctors to make faster, more accurate diagnoses, and thus provide better care.
The volume of big data
Duquesne University estimated there to be 150 exabytes of healthcare data collected in 2011. Four years later, they reported about 83 percent of doctors had transitioned from using paper to electronic records. By now, with the ubiquity of the cloud, these numbers have assuredly gone up.
Massive amounts of data make predictive analytics possible, as trends can be spotted and analyzed. By spotting patterns, diagnosis of a disease becomes easier even for doctors unfamiliar with a specific disease or symptom. Uploading symptoms allows a computer to compare records and identify symptoms comorbid of other problems. This allows even specialized doctors to recognize issues outside of their field. Medical mistakes lead to the death of some 440,000 people each year; while misdiagnosis is only a part of this number, correct diagnosis and treatment will reduce it.
Big data can even be collected in the form of PDFs as part of telemedicine. A doctor can send PDFs to patients as part of a poll or survey or simply to collect symptom information from the patient. From there, data entered in the PDF can be collected and analyzed, generating patient data or feedback for the doctor.
Google flu trends
Google ran what can best be called an experiment from 2008 to 2014. Using artificial intelligence, the search engine recorded flu-related searches in an attempt to predict the severity of an outbreak, as well as the affected geographical area.
It was a flawed model, and tried to use big data as a replacement, rather than a supplement, for traditional data collection and analysis. It completely missed a flu outbreak in 2013, the data off by a massive 140 percent, and Google Flu Trends ended its public version in 2014. The algorithm monitoring flu-related search terms was simply not sophisticated enough to provide accurate results. While new data is no longer available to the public, historical data remains available to the Centers for Disease Control and other research groups. It’s possible that once the algorithm and predictive analysis is capable, the program will continue.
Vyne Medical, the leading provider of healthcare communication and data management technology for more than 800 hospitals and health systems, today announced a partnership with Adventist Health System for implementation of its Trace communication management and quality assurance platform.
One of the nation’s largest faith-based health systems, Adventist Health System will implement Vyne Medical’s Trace platform to manage critical communications including voice, fax, electronic, image and document exchange.
“As we work to streamline and simplify the care process for consumers and providers, we needed a solution built to support the intricacies of our workflow,” said Tim Reiner, senior vice president of revenue management for Adventist Health System. “With Trace, we can capture many types of communication and integrate them with our existing systems to create a more complete patient record and ultimately enhance the consumer experience for those we care for.”
Physician orders. Trace will be implemented as the single platform to manage both fax and electronic orders for Adventist Health System. Orders will be available in real time with features such as alerts, notifications, worklists and reservations to establish an electronic workflow for order management.
Voice recording. Staff will use one of three Trace recording applications – on-demand, auto-record or face-to-face recording – to record interactions with patients, physicians, payers and other providers. Recordings will be indexed to the patient account and referenced to support strategic initiatives such as quality assurance, compliance, patient experience and financial performance.
Quality assurance. An audio search function will allow managers to search recordings for key words and phrases to ensure the appropriate use of scripting and identify training needs. The Trace Quality Assurance tool will be used for quality assessment of recorded interactions, allowing managers to produce online scorecards and track performance by associate, team and performance measure.
Lindy Benton
“Trace will help us reach our long-term goal of eliminating faxing and other paper-based processes,” said Brent Snyder, executive vice president and chief information officer for Adventist Health System. “A secure, auditable workflow for orders will increase our efficiency, reduce delays and help us provide better service to our physicians and patients.”
“We are excited to partner with Adventist Health System in its effort to enhance quality and efficiency,” said Lindy Benton, CEO and president of Vyne. “Through this work, we are committed to reducing costs through automation while improving key performance indicators.” Continue Reading
Today, the level at which the vast majority of us place our reliance on mobile devices for the completion of so many of our tasks every day, even some of the more complex and daunting tasks, has risen so high. All over the globe, so many users from every field now increasingly make use of their tablets and smartphones for their highest of multitasking abilities and their effectiveness.
Decades ago, physicians, paramedics and other healthcare providers had to rely on costly medical equipment to assist their patients in moments of emergencies. But with the significant advancement that has been recorded in the mobile app market of today, perhaps all of these things have changed. The vast majority of medics and paramedics today now make use of very easy-to-use, data-driven and less expensive mobile gadgets and the medical mobile apps that are found in them.
As a result of the fact that everyone of us make use of mobile devices on a daily basis, having to learn the method in which a particular medical mobile app can be employed is not going to consume too much time for a skilled paramedic or medic. A well-established, well-tested medical mobile app also offers rather accurate results; therefore, for physicians who are on the move at all times, this could be a very useful innovation.
As a result of the significant impacts of medical mobile apps in the healthcare system of today, many mobile app developers are working to develop even more medical mobile apps. However, there are still many challenges that these mobile app developers encounter while developing these apps. Below are some of these issues, and how they can be surmounted.
Predictability of results is not always accurate
No matter the level at which a mobile app developer attempts to develop an infallible medical mobile app, there is no way she or he can be utterly certain that it would be completely free of trouble, unless and until it has, as a matter of fact, been developed and sent to a specific mobile platform. There is a phase in which the app would be tested. In the course of this testing phase, specific issues may crop up, and that is the time the main trouble will come up, while attempting to solve the problem.
Unavailability of life-saving app
The immense usefulness of medical apps has been acknowledged by the United States Food and Drug Administration. As a matter of fact, research points out that there is a large number of users of smartphones who are making use of mobile apps in mobile healthcare. The number, according to research, was projected to hit a greatly surprising 500,000,000, by the end of the year 2015. But despite this development, no mobile app developer can ever lay claims to develop a life-saving app. While the apps available are efficient at testing a particular condition, they do not have the capability of granting relief to a patient that is critically ill. In addition to that, there might have been some technical irregularities or malfunction during the process of developing the app, or during its testing phase. As a result of this, such an app may be risky for use to patients.
Mobile Platforms Fragmentation
Another big challenge that developers of mobile apps encounter is the range of operating systems and mobile devices in the mobile market of today. Issues like this are hard to confront, but there are some other problems that exist. They include problems regarding network connectivity, standardization of mobile design, and so forth. Also, the development of an app for different mobile devices with mobile features that are different can come as a big challenge to the mobile app developer. Other challenges include making a choice on the ideal mobile platform or platforms and cross-platform formatting. All of these issues can pose even tougher problems for the app developer. All of these challenges may jointly lead to a medical app that is not completely effective or does not meet the requirements of the end user.
The statistics are terrifying. According to the National Institute on Alcohol Abuse and Alcoholism (NIAAA) Alcohol poisoning kills six people every day. Of those, 76 percent are adults ages 35 to 64, and three of every four people killed by alcohol poisoning are men. The group with the most alcohol poisoning deaths per million people is American Indians/Alaska Natives (49.1 per one million). More than 15 million people struggle with an alcohol use disorder in the United States, but less than eight percent of those receive treatment.
Almost 72,000 Americans died last year from drug overdoses, a record high acknowledging an increase of about 10 percent, according to new preliminary estimates from the Centers for Disease Control. The death toll is higher than the peak yearly death totals from H.I.V., car crashes and even U..S. gun deaths.
Treating addiction is not a simple process and the current treatment of 90-day detox programs works well if you have thousands of beds, staff and other resources. Meanwhile the actual behavioral health treatment of addition is not much better. It is still a time-consuming process requiring individual diagnosis, but largely driven by paper and trial and error guesswork.
Meanwhile heroin, fentanyl and other synthetic drugs addictions were surpassing alcoholism. In Gallup, New Mexico, last year 104 people died from drug and alcohol abuse in McKinley County while the state suffered 1,952 deaths, the 13th highest in the US.
One of the nation’s epicenters of addiction is Gallup, New Mexico, where 22,000 addicts await a behavioral healthcare fix. While there are many tech solutions in healthcare, behavioral health does not receive the same level of attention as physical health, despite mental, behavioral and physical health being inextricably linked, as the World Health Organization noted in a 2014 report.
One of the widest chasms between the two began in U.S. healthcare in 2010 with the transition from paper to electronic patient medical records. However, these electronic health record (EHR) systems have been focused on the physical side of medical recording, leaving the behavioral side with little support.
While care collaboration through interoperability remains one of the major challenges in the healthcare industry, collaboration between physical and behavioral health has is also behind the curve. Behavioral health services (BHS) operate and are updated based on paper records, leaving challenges around efficiency, communication and the ability to scale treatment operations.
Historically, clinicians have directly performed assessments of people for the purposes of diagnosis, monitoring the progression of an illness, or evaluating responses to treatment. For example, a person’s mental state can be evaluated by examining movement patterns, mood states, social interactions (e.g., number of texts and phone calls made, content of interactions), behaviors or activities at different times of day, vocal tone, speed, word choices, facial expressions, biometric and heath measures.
While assessing an individual’s symptomatology, large quantities of behavioral data can provide vital information for researchers to increase their understanding of mental illnesses and mental wellbeing, help develop better interventions and better health outcomes, and potentially predict who may be at risk of developing behavioral health problems.
Providers addicted to records and files
A physical health issue can require visits to a primary care physician, specialists, and possibly x-ray technicians along with the records and paper trails that go along with it, the treatment of behavioral health is often much more complex. If a patient requiring behavioral care shows up at an urgent care facility and receives treatment, that data doesn’t get back to the patient’s primary care provider. The primary care provider only learns of the visit if the patient decides to give them that data. The PCP can’t pull information from possible business partners in the area to know when there’s been a change.
A substance abuse patient needs a physical and mental examination before they can check into the behavioral health center. An intake coordinator starts that process, then the patient sees a nurse, and then a counselor. But the person also has depression and needs to see a psychiatrist and they also need to go to the detox center at the hospital. Chances are they also have social problems to worry about such as child support, perhaps a bankruptcy case, or they’re headed to jail.
In addition, different behavioral treatment centers may have operational differences such as the number of treatment phases and the ability to track, monitor and anticipate recidivism after patients graduate from treatment centers. There are also differing manual processes and types of tracking documentation used by facilities while training programs may or may not be part of treatment centers as well.
In a typical BHS treatment center, their process and workflow comprise admission and treatment which includes assigning a treatment counselor, nurse for withdrawal, case manager and training program coordinator. There is also a program for job training, an aftercare phase along with monitoring, tracking, reporting and progress improvement or non-progress on treatment programs against the outcome of the overall program.
However, this phase is cumbersome because of the lack of an electronic recording system for behavioral health as most records are stored as PDFs in EHR systems. In addition to these limitations, there is lack of support to track progress or non-progress on patient outcomes.
Unlike the ‘physical’ medical approach, behavioral care treatments tend to be more subjective to each care provider and require a longer time to monitor and record positive outcomes from treatment. Behavioral treatment depends more on data analytics from patients to determine the best approach for patient engagements. There are also additional data categories required for BHS such as chemical dependency assessment, a treatment plan, social service related data, a training program and related data and mental health assessments.
When considering all this additional data versus data requirements for physical care, it seems like a process that is almost designed to be slow and cumbersome. So if the parameters of treatment can’t be changed to accommodate the surge in addicts, the only other consideration is the treatment process.
One of the primary problems existing in healthcare is the many barriers to access and delivery of care and treatment. Access to healthcare is centralized to a limited number of intermediary players in a way that is costly, non-transparent, and inefficient. It forces all of us to settle on whatever is given based on our locale and socioeconomic status, without having any real voice.
Access to care impacts patient’s physical, social, and mental well-being, as well as their overall quality of life. According to the Office of Disease Prevention and Health Promotion, people with a reliable source of care should have better health outcomes, fewer disparities, and lower costs. Yet according to the National Association of Community Health Centers, approximately 62 million individuals in the United States have limited or no access to primary care physicians as a result of shortages. This number is widely expected to increase over the next several years as our population grows older.
With an absence of convenient access to primary care physicians, patients turn to alternatives like emergency rooms, urgent care clinics, or choose to not seek care at all. All three options are more costly to the healthcare system than providing access to appropriate physicians.
In America, there is one medical doctor for every 434 people. It is important to note that physicians are not dispersed evenly throughout the country. Cuba, a country that has heavily emphasized medicine, has about six doctors for every 1,000 citizens. Conversely, in much of developing Africa, there is less than one healthcare practitioner (not necessarily a doctor) for every 1,000 people. India has fewer than one doctor for each 1,000 person.
Even in communities where healthcare exists, there are financial barriers to accessing care. Countries requiring but not providing health insurance or out-of-pocket payment put citizens at risk of delaying or forgoing treatment, hoping their ailments will go away. This increases costs overall as these same citizens are often treated in emergency rooms, and outcomes diminish because preventative treatment is all but forgotten.
MedTrainer is the creator of an all-in-one compliance management suite that encompasses all the tools healthcare professionals need to manage processes, increase departmental collaboration and simplify compliance.
Elevator pitch
The MedTrainer all-in-one compliance management suite combines a learning management system (LMS) with governance, risk and compliance (GRC) and provider credentialing to make compliance management accessible online, 24/7, to all healthcare organizations at a price they can afford.
Founders’ story
After growing three different companies to profitable buyout, MedTrainer’s co-founders, Steve Gallion (CEO) and Jorge Fernandez (COO), invested the equity from the eight-figure acquisition of the third joint endeavor, Waste Stream Solutions (a more than 4,700 percent return on investment), to co-found and fund MedTrainer.
Gallion and Fernandez realized the inefficiencies and challenges of the current market and created the first all-in-one compliance management suite that encompasses all the tools healthcare professionals need to manage processes, increase departmental collaboration and simplify compliance. The powerful, innovative and affordable solution improves efficiency across practices.
MedTrainer is headquartered in Redlands, California, and has offices in Denver; New York; Washington, D.C.; Queretaro, Mexico; and Mexico City. In 2017, the company doubled its staff to 85 employees, added a chief technology officer to foster continued development and enhance top-level support, and achieved 400-percent growth over the previous year. The system is now used by 300,000 healthcare professionals, representing 15,000 healthcare sites and Fortune 500 companies across North America. Not only have these organizations saved money by consolidating to a single compliance management solution, but they have also seen how proper training and compliance management can directly result in more efficient facility operations and a higher level of patient care.
Marketing/promotion strategy
Founded in 2013, MedTrainer supports primary care offices, ambulatory surgery centers, urgent care facilities, multi-specialty practices, federally qualified health centers (FQHC), dental offices, veterinary practices, long-term care facilities and community health centers. The company uses a mixture of direct marketing, online and offline strategy, and partnerships to promote the MedTrainer suite.
Market opportunity
In the healthcare industry, compliance and education software has always been reserved for enterprise-level organizations and major hospital systems. Even then, healthcare professionals have to run dozens of different software in parallel to manage requirements. Add growing regulations and shrinking budgets and it becomes even more difficult for healthcare providers to keep up with compliance education requirements and provide top care to their patients.
With MedTrainer, healthcare organizations can access more than 25 different modules 24 hours a day. MedTrainer’s CMS provides a learning management system with more than 200 custom courses; modules for management of policies and procedures, SDS, equipment life cycles and contracts; a license and credential tracking center; safety plans and incident reports; expert virtual compliance support; QuickCred provider credentialing; compliance tool kits; OIG/SAM checks; and security risk assessments.
Who are your competitors?
As the first all-in-one compliance management suite on the market, MedTrainer does not have any direct competitors. However, companies like HealthStream, Verity and Relias provide solutions with similar functionality to some of MedTrainer’s modules.
Up to a 
Vyne Medical, the leading provider of healthcare communication and data management technology for more than 800 hospitals and health systems, today announced a partnership with Adventist Health System for implementation of its Trace communication management and quality assurance platform.
