The curious case of a mistaken patient identity

May 10, 2019/7330 views / 0 Comments/in BLOG, Medical Record Mix-ups, Patient Errors, Patient Identification, Patient Safety /by Matt Gibson

Mistaken patient identities in the healthcare industry are nothing new – a lot of people have faced it, and it occurs almost every day in the US. However, this time, it was not news of someone who suffered from it, but rather a couple who got saved from just being another mistaken patient identity. This mishap was properly detected and the victims were fortunately saved from a huge financial loss.

The actual story

A Florida-based couple would have been the victims of mistaken patient identity and almost lost a lot of money. Mrs. Barding detected the error when she identified that Cigna, her insurance company, was processing a whopping $2.2 million in medical bills.

How did she figure it out? With the help of Mr. Barding, the couple identified that the bills were actually associated with his identical twin, Vance Barding, who was burned in a work accident and sadly passed away six weeks later from complications.

Mrs. Barding told that Cigna billed them for her brother-in-law’s care and had deducted $3000 from her health reimbursement account. However, after notifying the insurance company, they verified the claim and stopped billing the couple, as well as returning the money to Mrs. Barding’s account. This was all due to the mistaken patient identity.

Cigna also stated that there are always a large number of claims which are made in error by different healthcare providers, and they have thus discussed with the latter in order to be more vigilant about such erroneous bills.

The healthcare provider in question is Orlando Health and it was provided incorrect information, due to which this whole situation arose. However, as it was made aware, they worked with necessary parties in order to rectify the mistake. This was a fortunate case where the would-be victims were saved due to the vigilance of the wife. Unfortunately, not every victim has a Mrs. Barding beside them.

Some statistics regarding mistaken patient identity errors

A survey conducted by Patient Safety & Quality Healthcare (PSQH) revealed that 54% of the respondents are unhappy with the current patient identification methods. Another research shows that 10% of the overall patients are misidentified during entry. This mostly happens due to the large healthcare systems, which have a lot of patients to cover, and thus they make mistakes due to human errors, miscommunication, and sometimes in order to save time. The PSQH survey also shows that 89% of the respondents believe that proper patient identification is a vital part and is of paramount importance to their organizations. On the other hand, only 4% believe that the current patient identification process is completely accurate.

How to avoid patient identification errors?

Patient identification using biometrics is the only way to eliminate this problem. It not only is error-free, but it is also instantaneous, speeding up the process for patient care, as well as safe.

RightPatient AI is used by a number of notable hospitals as well as thousands of outpatient sites, transforming the experience of the patients as well as the healthcare professionals. It not only eliminates the errors, but it also saves time in order to focus on patient care. It is also fully compatible with any EHR system as well as third-party apps, thus creating a seamless experience for the end-user. It uses iris scanning to identify the patients and then pull the relevant data from their EHR. Take Terrebonne General Medical Center (TGMC) as an example. It is located in an area where a lot of people share common names, either first or last. Thus, it posed risks of incorrect record documentation, patient record mix-ups, and providing wrong prescriptions. RightPatient has helped TGMC in eliminating this issue entirely using Photo Biometrics along with iris scanning. It has an advantage over most other biometric modalities – iris scanning does not require any physical contact on the patient’s end, thus, no risks of infections or diseases via contact. Duplication and errors are all things of the past with RightPatient. 17 years of experience in AI and human recognition is proof of it.

EHRs: Why are physicians and patients dissatisfied with them?

September 5, 2018/11683 views / 0 Comments/in AI, Analytics, Artificial Intelligence, BLOG, Clinical Efficiency, EHR, Health Care, healthcare, Patient Experience, Patient Identification, Patient Outcomes, Patient Safety /by Michael Trader

Electronic health records (EHRs) are supposed to make things easier for doctors, improve health outcomes for patients, and create a better experience for everyone. However, most research indicates the opposite. There is a high level of EHR dissatisfaction among practitioners and the impact on patient experience has been underwhelming. So, what has gone wrong?

When EHR system use became mandated, clinicians were expected to experience initial growing pains as they were forced to learn new skills. However, as comfort levels grew, their perceptions were expected to change over time, resulting in better communication and care. Unfortunately, doctors are still complaining about EHRs even after several years of widespread implementation and use. In fact, research shows that EHRs have become a major contributing factor to physician burnout.

The aforementioned Mayo Clinic Proceedings study also found that as many as 84.5% of physicians are using EHRs and the majority of them are not satisfied. Most physicians feel that EHRs are inefficient and require too much manual data entry where time is spent on clerical tasks rather than patient interactions.

Likewise, patients are also not satisfied with EHRs as they notice doctors spending more time looking at the computer screen during their visits. Research shows that gaze time (amount of time the doctor looks at the patient) is directly related to patient satisfaction.

Apart from data entry issues, a RAND study identified many other reasons for EHR dissatisfaction among physicians. For example, most physicians agreed that EHR interfaces were not intuitive, thus hampering their workflow instead of augmenting it. They also complain that EHRs are not implemented well enough to facilitate the proper exchange of information. Many physicians feel overloaded with irrelevant information.

Doctors also noticed that templates provided with EHR systems degraded the quality of their reports. Even more worrisome is that most physicians found that EHRs are not improving over time.

Undoubtedly, these studies indicate the need for a system update and technology that frees doctors from having to spend time on routine clerical or data entry tasks. This technology would ideally enable clinicians to focus on their primary responsibility – carefully listening to, observing, and getting to know their patients so they can provide the highest level of care.

This is where RightPatient can help by providing an AI system that automatically identifies patients when they arrive and then engages with them to collect useful information that is pushed into the EHR system. This enables clinicians to understand much more about a patient’s condition while reducing their data entry burden. With RightPatient, doctors receive concise, relevant, and real-time information regarding their patients to save time, increase efficiency, and improve the patient experience.

Making the most of patient wait times

August 14, 2018/10763 views / 0 Comments/in AI, Analytics, Artificial Intelligence, BLOG, Clinical Efficiency, Health Care, healthcare, Patient Experience, Patient Identification, Patient Outcomes, Patient Safety /by Mizan Rahman

The U.S. healthcare system has long suffered from the problem of excessive patient waiting times. In 2015, 32% of visits to the ED resulted in patient wait times of up to an hour. Obtaining an initial outpatient appointment with a physician can take a month or more. The fact is that waiting times can be unbearably long for patients and doctors are often helpless in solving the issue.

Long waiting times can have a negative impact on a patient’s health by causing delays in consultations. Furthermore, wait times reduce patient satisfaction scores with healthcare service providers. Research has shown that patient satisfaction scores were affected across almost every aspect of care delivery when waiting times were long, with patients reporting lower levels of confidence in the care provider. Longer waiting times not only impact overall patient satisfaction, they also negatively affect the way that patients perceive the information, instruction, and care provided by their caregivers and physicians.

Clinics have adopted various methods to improve satisfaction while a patient is waiting for an appointment. These typically involve providing information regarding different disease conditions, tips on practicing a healthy lifestyle, etc.; essentially, they try their best to make waiting areas comfortable and informative. Additionally, some clinics use office staff to gather information from the patient. However, in many cases, the information provided by the clinic may not be relevant to the patient. Similarly, gathering information about the patient through staff is an expensive activity with limited benefits.

As we have seen, patient wait times can have a negative impact on both patients and their clinicians. However, what if there was a way to utilize these waiting times more productively? Can patients be engaged in a more meaningful way while they are waiting? This is precisely where RightPatient can help.

RightPatient can help to improve the patient experience and optimize wait times through its autonomous check-in process. When patients arrive for scheduled outpatient visits, RightPatient automatically recognizes them and engages through an AI-driven chat session. This enables patients to learn about their conditions as important clinical information is collected, which is automatically fed into the EHR. The clinical team can review this information prior to the consultation, saving time and increasing efficiency by eliminating the need for manual data entry into the EHR system. Physicians can then spend this time interacting directly with the patient to bolster satisfaction and clinical outcomes.

RightPatient enables doctors to spend more time focused on what they want to be doing – listening to patients, addressing their emotional and physical well-being, and spending less time worrying about data entry into health records. Satisfied and engaged patients also respond more favorably to more personal interactions with their caregivers, creating a win-win environment.

Reducing opioid abuse by knowing the right patient

July 16, 2018/13726 views / 0 Comments/in AI, Analytics, Artificial Intelligence, Big Data, BLOG, Data Integrity, data mining, Health Care, healthcare, Medical Record Mix-ups, Patient Errors, Patient Identification, Patient Matching, Patient Outcomes, Patient Safety, population health, precision medicine, Predictive Analytics, value-based care /by Michael Trader

The US is enduring a massive opioid abuse epidemic. Not only are they widely prescribed, but prescription opioids are now more widely abused than street drugs. If we look at the anatomy of the opioid crisis, it is genuinely frightening. In 2016, 116 people died each day due to opioid overdose, resulting in more than 42,000 fatalities in a single year.

The question is, why is this happening? How are 11.5 million individuals misusing prescription opioids? How is it that each year, 2.1 million people misuse opioids for the first time? It seems that, at present, there is no clear path to stunting this epidemic. Opioid abuse is already costing the US economy more than half a billion dollars annually.

How did we get to this point?

Since the 1990s, the pharmaceutical industry started pushing opioids and assured doctors that these drugs were safe. Consequently, doctors began widespread prescription of these drugs. However, blaming the pharmaceuticals industry and doctors alone ignores many other pertinent factors.

There have been many changes regarding the prevalence of various diseases over the last three decades. Slowly and steadily, medicine has become dominated by chronic and painful health conditions. It is estimated that one-third of the U.S. population or 100 million Americans are living with a chronic and acute pain condition. Among them, one-fifth are living with moderate to severe pain. Considering these statistics, it follows that opioids would be widely prescribed. However, 8-12 percent of those prescribed opioids result in patients developing an addiction.

Opioid misuse is not just limited to those living with painful conditions. Many of the prescribed opioids end up in the wrong hands. Many addicted to opiates hide their identity or medical conditions and visit various clinics under different aliases. For doctors, it is challenging to identify the right patient.

How can we reverse the epidemic?

To bend the trend downwards, efforts must be implemented at every level. At the community level, we must educate the public and raise awareness about the health risks of opioid abuse. Policymakers should advance legislation to address the problem. Above all, there is a need to change the way medicine is practiced; healthcare providers must take higher precautions at the clinical level.

Clinicians cannot and should not deprive people in pain from drugs that can bring them needed comfort. However, big data and technology can assist them in differentiating between the right patient and the wrong one. This is where RightPatient can play a vital role. Powered by artificial intelligence, the platform can help clinicians to thwart medical identity fraud and ensure that a patient’s complete and accurate medical history can be retrieved.

By recognizing the correct patient, clinicians can better understand the validity of patient complaints along with a patient’s disease history. When and where was the patient last prescribed an opioid? Did the patient rightly identify himself/herself?

RightPatient can be one way to prevent opioid abuse.

How Can You Protect Your Investment in a Population Health Solution?

February 9, 2018/14238 views / 0 Comments/in AI, Analytics, Artificial Intelligence, Big Data, BLOG, Data Integrity, data mining, Health Care, healthcare, Medical Record Mix-ups, Patient Errors, Patient Identification, Patient Matching, Patient Outcomes, Patient Safety, population health, precision medicine, Predictive Analytics, value-based care /by Mizan Rahman

Healthcare in the U.S. is going to see a paradigm shift in the next five years that will move it from a fee-for-service (FFS) payment model towards a value-based model. Simply said, those who produce better results and improve patient quality of care at lower costs will reap higher dividends. This shift will require better use of technology and significant changes to many platforms and their capabilities, including more investment in big data, analytics, and patient matching systems. These investments in population health management technologies will provide the real-time information needed to make more informed decisions.

Population health solutions play a critical role in moving healthcare from a treatment-based to a prevention-based model. These platforms enable providers to better prepare for patient-reported outcomes, provide data regarding social determinants of health and activity-based costing, and match extracted data outcomes with the right patient.

Current state of U.S. healthcare

The U.S. spends more on healthcare per capita than any other nation in the world but fails to produce better results for life expectancy and other health outcomes. Moreover, U.S. taxpayers fund more per capita on healthcare (64%) than those in other countries, including those with universal health programs.

These facts suggest that encounter-based medicine might be contributing to sub-optimal results in the U.S. and there is a need for change. That change is prompting the rise of population health management and data analytics technologies.

The population-based model is based on aggregating patient data across various health information resources, forming a comprehensive, longitudinal health record for each patient, and leveraging analytics to produce insights that clinical teams can use to improve care and lower costs. In addition to health and financial data derived from electronic health records (EHRs) and medical claims, information such as a patient’s socio-economic status, personal support network, and habitat conditions can be useful in building preventative care strategies.

For example, a patient diagnosed as prediabetes would be classified as high-risk in an encounter-based model. However, this does not take into consideration the patient’s lifestyle and behavioral patterns. Many prediabetics can avoid developing diabetes by modifying habits such as diet and exercise. Patients who smoke, abuse drugs, or have a sedentary lifestyle are much more at risk of developing the disease. Identifying these genuinely high-risk patients requires access to accurate data that is linked to the correct record.

Challenges in moving to a population health solution

At present, a tremendous amount of patient data is available but it is not unified – it exists within different institutions and across various platforms. Thus, the available information is very difficult to match with the right patient (if not impossible in some cases) and such data has little practical value. Population health solutions need a system that can match patients with their available data and provide information on the best recommendations for preventative care, helping to improve outcomes and save resources.

Therefore, the most important variable in extracting value from a population health solution is ensuring that a patient’s captured data is matched to the correct record. Better data warehousing and mining capabilities will serve no purpose if healthcare providers lack the ability to match the output with the right patient. At present, not only do patient identification issues exist within a single healthcare institution, but these issues become even worse when patient data is exchanged across multiple systems, with error rates rising to 60%.

Failure to properly identify a patient means loss of historical medical history, social indicators, financial information, medications, allergies, pre-existing conditions, etc. – vital information that puts the patient and healthcare provider at greater risk. These data integrity failures can significantly dilute the efficacy of population health initiatives.

In fact, the transition from fee-for-service to value-based healthcare is only going to work if healthcare entities invest in patient matching technology alongside their investments in big data and analytics platforms. These investments should go hand-in-hand since patient matching errors can have such a substantial impact on data quality.

Population health management is among the top six categories in healthcare that are attracting investments from venture capital firms. Other segments include genomics and sequencing, analytics and big data, wearables and biosensing, telemedicine, and digital medical devices.

Thus, the industry is investing in technologies that will play a significant role in value-based care and population health management. However, the success of any population health initiative depends on the right patient being identified every time so that medical records and the corresponding patient data are not mixed-up. Considering the data fragmentation that exists in healthcare and lack of standards around patient identifiers, AI-based systems like RightPatient are the only way to ensure reliable identification of patients across various data platforms and maximized investment in population health management.

How RightPatient Prevents Chart Corrections in Epic and Other EHRs

January 29, 2018/12271 views / 0 Comments/in BLOG, Chart Corrections, Data Integrity, Health Care, healthcare, Medical Record Mix-ups, Patient Errors, Patient Identification, Patient Matching, Patient Outcomes, Patient Safety, value-based care /by Michael Trader

I’ve visited enough of our customers to know that hospital emergency rooms and free-standing EDs can sometimes be chaotic environments. Unlike most outpatient registration areas, patients who arrive to the ED do not have scheduled appointments and often go through a triage process with a nurse where they are “arrived” within the electronic health record (EHR) system. This is essentially a quick registration that begins the documentation of a patient’s visit information on his/her medical record. Unfortunately, this process often results in what are known as chart corrections.

As one might imagine, a clinician’s primary focus is on the health and safety of the patient. Nurses that triage patients are trying to enter patients into the EHR system so they can receive the appropriate care as quickly as possible. Unfortunately, data entry errors during this process are commonplace. For example, EHR system users may create a “John Doe” or “Jane Doe” medical record if they cannot properly identify the patient. Or, users may mistakenly select the wrong record because it shares a similar name with the patient in need of care.

When EHR users select the wrong patient medical record, all subsequent information pertaining to that visit is entered into that record (sometimes referred to as a medical record “overlay”). This is a data integrity failure and results in data entry errors that need to be resolved with a chart correction. So, a chart correction in the Epic EHR or other EHR systems is the process of fixing a “wrong chart entry” or overlay record that was caused by a patient identification error.

Wrong patient, wrong record data integrity failures within the EHR system can have disastrous consequences. At best, the healthcare provider must spend internal Health Information Management (HIM) resources to perform chart corrections and resolve medical record overlays, costing $60-$100 per hour for an average of 200 hours per overlay record. At worst, wrong patient errors can affect clinical decision making, patient safety, quality of care, and patient lives. This is why organizations like AHIMA have strongly advocated safeguards that healthcare providers can use to prevent medical record mix-ups, improve data integrity, and reduce the risk of adverse events.

RightPatient is the ideal safeguard to prevent wrong patient medical record errors and chart corrections within Epic and other EHR systems. The AI platform uses cognitive vision to instantly recognize patients when their photo is captured and automatically retrieve the correct medical record. This becomes a seamless module within EHR system workflows so there is no disruption to users.

Customers like University Health Care System in Augusta, GA are effectively using RightPatient to reduce chart corrections in Epic. In fact, UH saw a 30% reduction in Epic chart corrections within months after implementing RightPatient.

Healthcare providers using RightPatient to capture patient photos significantly reduce their risk of data integrity failures. This enhances patient safety and health outcomes while reducing costs – important goals in the age of population health and value-based care.

Value-Based Care: A Patient-Centered Approach Requires Knowing Your Patient

January 15, 2018/12329 views / 0 Comments/in Analytics, Big Data, BLOG, Data Integrity, data mining, Health Care, healthcare, Medical Record Mix-ups, Patient Errors, Patient Identification, Patient Matching, Patient Outcomes, Patient Safety, precision medicine, Predictive Analytics, value-based care /by Mizan Rahman

Aspirin, penicillin, monoclonal antibodies, interventional cardiology, and genome editing have undoubtedly revolutionized medicine. However, while all of these have been breakthroughs in the field of medicine, not much has changed in the way that doctors do their jobs. Patients visit their doctors, the doctors diagnose, they recommend tests, they prescribe drugs, and they are compensated according to the volume of work done or the number of procedures performed.

If medicine is to progress in the 21st century, things have to change at every level, including the way that doctors work and receive compensation, the way they identify the right patient, and the way that patients are treated.

The long-awaited system that is going to change the way doctors work and are compensated will soon become a reality. This new system is called value-based care.

Value-based care is about compensating doctors according to outcomes. This encourages more personal attention to patients and transitions the healthcare system from cure-based to preventive medicine. It is a system in which doctors receive a higher level of compensation for either better outcomes from procedures or enabling patients to avoid health-related problems altogether.

There are several benefits of a healthcare system where the right patient gets the right kind of care.

Value-based care can save patients a lot of money. Putting aside the historical projections of healthcare inflation, the U.S. is also facing major epidemics of chronic, non-communicative diseases like diabetes, high-blood pressure, and cancer. It is no secret that many of these ailments are preventable with timely intervention and/or the correct behavior. Value-based care creates an environment where doctors can help patients to avoid these diseases by intervening at the right time. A doctor would identify the right patient to design a prevention plan before a disease can manifest where things become more complicated and expensive.

Once the right patient, a patient with a high risk of developing a chronic illness, has been identified, the doctor would be encouraged to spend more time with her, teaching her to take better care of herself so that complications can be avoided. There would be a reward system for identifying the right patient and taking timely preventative measures. It would also result in higher patient satisfaction.

A value-based care system would also lower drug costs. Historically, manufacturers decide the price of their medications without taking into consideration the value that a particular drug has in terms of its effectiveness and overall patient wellbeing. A value-based system would also encourage the development of personalized medicine where treatment plans and even pharmaceuticals can be tailored to specific patient needs.

The backbone of the value-based care system would be patient identification and data mining. Many are already demonstrating why medicine should incorporate more data-based modeling to augment physician decision-making. Data mining helps doctors and the healthcare industry as a whole to better understand the outcomes of various therapeutic approaches. Ultimately, it can help to create the right kind of individualized solution for the right patient.

Unfortunately, realizing optimal results from data mining and value-based care has its challenges, especially as healthcare organizations start mining data that has been accumulated over long periods of time. On average, at least 8% of hospital patient records consist of duplicate data. Thus, an intelligent way to sort out these duplications and identify the right patient is desperately needed.

It is stated that value-based care is about the right patient getting the “right care, in the right place and at the right time.” Instead, the maxim should be, “RightPatient® enables the right care, in the right place, at the right time.”

RightPatient® guarantees that a patient medical record is never mixed up with another record and the hospital ecosystem will always recognize the patient with the help of cognitive vision. Mistakes from common patient names, fraud, human error and other issues are always prevented.

As we all know, chains are only as strong as their weakest link. In many hospitals or medical institutions, there is an urgent need to strengthen this weakest link throughout the entire system – overcoming the errors of false identity and data duplication with RightPatient. Only then can the benefits of value-based care and data mining be fully realized.

How Big is the Patient Mix-up Problem in the U.S.?

January 11, 2018/12573 views / 0 Comments/in AI, Artificial Intelligence, BLOG, Health Care, healthcare, Medical Record Mix-ups, Patient Errors, Patient Identification, Patient Matching, Patient Outcomes, Patient Safety, Privacy /by Patrick May

Hollywood has created several films featuring a person that was wrongly informed about cancer or another fatal disease with the patient being told that they only have a few months/days left to live. Upon hearing this news, the patient goes on a spending spree and adventure only to discover in the end that things have been mixed up. This might make for a great movie but in the real world, if such a patient mix-up happens, the outcomes may be far worse.

But just how frequently does this medical record mix-up problem happen in real life?

It seems that the problem of so-called mistaken patient identity is big enough to cause serious problems – something that is very evident from the article published in the Boston Globe, reporting 14 cases of mistaken identity.

Reports indicate that medical errors due to patient mix-ups are a recurrent problem. Consequently, a wrong person may be operated on, the wrong leg may be amputated, the wrong organ may be removed, etc. In fact, CNN reported that in 6.5 years, in Colorado alone, more than 25 cases of surgery on the wrong patient have been reported, apart from more than 100 instances of the wrong body parts being operated on.

It would be challenging to estimate the true total number of patient mix-ups simply because the vast majority of them go unreported until something untoward happens. Even in cases where complications do occur, most medical organizations would not be eager to publicize them.

Today, it is widely accepted that medical errors are the third largest killer in the U.S.; that is, far more people die of medical errors compared to diseases like pneumonia or emphysema. It is now estimated that more than 700 patients are dying each day due to medical mistakes in U.S. hospitals. This figure clearly indicates that medical errors often occur even though a fraction of them will have fatal outcomes. It also tells us that cases of patient mix-ups may be shockingly high and indeed underreported.

Though several thousand cases of mistaken patient identity have been recorded, it remains the most misunderstood health risk, something that hospitals barely report, and an outcome that patients do not expect to happen.

The U.S. healthcare system is extremely complex, making it challenging for a single solution to resolve this issue. There have been lots of efforts to implement a unique identity number for each patient (a national identifier) but political roadblocks have proven difficult to navigate. The chances are bleak that any such national system would be created, as patients remain profoundly worried about the privacy of their data.

At present, perhaps the best option is that each hospital finds its own way to solve this problem by developing some internal system to make sure that patient mix-ups don’t happen. Or, a better idea is to leave this task to the professional organizations that specialize in the business of improving patient identification. The RightPatient® Smart App is a perfect example of an innovative solution that is powered by deep learning and artificial intelligence to turn any device like a tablet or smartphone into a powerful tool to completely eliminate the problem of mistaken patient identity.

Technological solutions are often meant to augment human efforts, not to replace them. Here are some of the ways to avoid patient mix-ups:

Always confirm two unique patient identifiers within the EHR (Electronic Health Record), like patient name and identity number. Though this is a standard practice, many mistakes still occur due to similar first or last names. Thus, an app like RightPatient can help to eliminate the chances of such an error.
Two identifications should be used for all critical processes.
There must be a system to alert staff if two patients have a similar first or last name.
Avoid placing patients with similar names in the same room.

Although patient misidentification and medical record mix-ups continue to plague the U.S. healthcare system, there is hope to address this serious issue with solutions like RightPatient. Now, we just need healthcare providers to make this a priority and take action.

How Opioid Abuse Exposes Hospitals

December 20, 2017/10665 views / 0 Comments/in AI, Analytics, Artificial Intelligence, Big Data, BLOG, Data Integrity, Health Care, healthcare, Machine Learning, Patient Identification, Patient Outcomes, Patient Safety, Predictive Analytics /by Michael Trader

Whenever I’m talking to a healthcare provider about RightPatient, the topic of “frequent flyers” inevitably arises. For those who might not be aware, frequent fliers are patients that use different aliases to obtain healthcare services. It’s estimated that between 2-10% of patients arriving at the emergency department (ED) provide some kind of false or misleading information about themselves. Typically, these patients are lying about their identity to obtain prescription medications, and most of these are for opioids.

Since these patients lie about their identity or demographic information, hospitals often end up writing off a considerable amount of money for their services – up to $3 million annually on average. Aside from these financial losses, frequent fliers also pose other risks to providers that are associated with patient safety and quality of care. Why? Because they also frequently lie about prescription drug use or addiction.

What’s worse is that this behavior is not limited to frequent fliers. Any patient can lie about their addiction. Many of these patients lie about their addiction to opioids, specifically. As we all know by now, the U.S. has a serious problem with opioid addiction, a crisis that killed over 33,000 Americans last year. This crisis has no rules or boundaries, and does not seem to select for a particular demographic. Anyone is susceptible to getting hooked on opioids because they are so addictive.

The opioid epidemic has far-reaching consequences that extend beyond the health of the patient; however, in the ED, this is the primary concern of a clinical team. Considering the circumstances, this question seems relevant – “how can healthcare providers ensure high quality of care when patients lie about their identity and/or drug use?”

RightPatient can play an important role in helping to answer this question. Our AI platform can accurately recognize the patient and offer key clinical insights by detecting patterns in the patient’s appearance over time. Clinicians won’t need to rely on the ~~words~~ lies coming out of a patient’s mouth, patients with no ID, or expensive tests. RightPatient automatically knows who the patient is and whether or not they are at risk of opioid abuse.

ED nurses who suspect a patient of abusing opioids will typically search the patient’s belongings to make sure they aren’t prescribed something that could cause an adverse event or even kill them. Unfortunately, the human eye, clinical intuition, and patient reliability have many shortcomings. Luckily, RightPatient can augment clinical diagnostics with cognitive vision to help fight the opioid epidemic and save a lot of lives and money in the process.

Data Personalization in Healthcare

December 10, 2017/8167 views / 0 Comments/in Analytics, Big Data, BLOG, Health Care, healthcare, Patient Identification, Patient Outcomes, Patient Safety /by Mizan Rahman

Personalization in healthcare – everyone talks about personalized medicine, how about data personalization?

One size does not fit all. Thus, medicine is seeing a shift from a standard model of care to a personalized model of care. The emergence of cloud computing, wearables, machine learning, and continuous progress in data management has made the delivery of personalized medicine more possible. Personalized data along with predictive analytics would change the way medicine is practiced today. It has the power to create a proactive health system that can help to address diseases at their earliest phase. Personalized data will help to craft medical solutions “especially for you,” rather than a single solution for all. It would also help consultants to free up time so that they can concentrate on developing a lasting and trusting relationship with patients.

When the human genome was first decoded, there was tremendous excitement about the ability to predict diseases and provide personal health solutions; however, soon it became evident that our overall health cannot be determined by analyzing small snippets of our DNA, as valuable as they might be for understanding specific risks. Medical or health-related decisions cannot be made in the absence of better personal data or a more holistic understanding of the person being treated.

With the help of personalized data, it would be possible to shift from the so-called model based on diagnosis and treatment to one of early disease detection and even a predictive model of medicine, along with personalized solutions.

Traditional medicine has depended not only on the phenotype and genotype data but other variables as well – a personal relationship with the patient, understanding patient lifestyle issues, surroundings, life events, social and family conditions, and much more. Data personalization can help to bring back that edge to automated systems through the customization of data. Data personalization is about delivering the right information about the patient, to the right person, at the right place, at the right time, in the right way. More than ever before, this is now conceivable due to better availability of personal data, personal devices, services, and applications.

Data personalization would make it possible to create a reasoning engine that has the ability to predict and make recommendations by using personal data of the patient provided by various resources.

Data personalization can take personal medicine many steps forward by adding the human touch and predictive analytics.

Perhaps in making medicine personal and predictive, personal information is what seems to be missing. If included in the algorithm, it would surely make predictive analytics more accurate and dependable. Personalized data would help to serve patients in the best possible way by shifting focus from merely disease determination to prevention, timely intervention, and better treatment.

Data personalization should not be taken as something new in medicine; in fact, it is a more natural way of providing health services, and closer to the traditional practice of medicine as it is about integrating the psychological, behavioral, and other measures that have become possible due to improvements in technology.

Combining the human biology with existing knowledge of epidemiology and clinical medicine would result in more personalized care. It is more like giving a human touch to the technology – something that has been a characteristic of traditional medicine, supporting the notion that doctors know their patients far better when a closer relationship is established. Thus, personalized data can augment that missing human factor in modern practice.

As more electronic personal data becomes accessible, systems become more intelligent. Having better learning capabilities and better availability of personalized data would revolutionalize the way we provide healthcare.