---

Compliance is essential to ensure that medicines work properly and to track the safety and efficacy profiles of a medication during clinical trials and for once a medication reaches the marketplace.

Non-compliance causes thousands of medication-related hospital admissions every year, issues with drug resistance, difficulties in clinical trial data collection, wasted medicine and high medical costs. It is a widespread problem that particularly effects medications for chronic illnesses. 

Historically, patient self-reporting or pill counts have been used as compliance measures, but these measures are unreliable, and now healthcare providers are turning to alternative solutions.

This article looks at technology in the area of patient compliance, an area where AI is having a huge impact on the life sciences industry. According to CMS research, technologies facilitating patient compliance raise a host of intellectual property considerations. In the context of patient compliance platforms, inventions will most likely exist around the process of receiving personal patient data, learning from the data using machine learning, and then using the trained machine learning system to predict the likelihood a patient will not take their medication at the correct time. Patent claims may be directed to ‘a computer-implemented method for providing a health assistant system’ or ‘a system for medication adherence management’.

According to Advanced RX research, failure to comply with treatments and follow up visits can have detrimental results not only for patients but for the U.S. economy as well. In fact, noncompliant patients make up for 10 to 25 percent of nursing home and hospital admissions each year, which costs the health care system of the U.S. over $ 100 billion annually. According to studies, in the U.S. estimated costs of medication, noncompliance is 0 to 9 billion per year and these figures are expected to grow in the future.

This doesn’t include indirect costs of billion from missed productivity in the workplace and lost patient earnings. Not to mention the complications that arise when doctors’ orders are not followed, which has already resulted in an estimated 125,000 deaths each year among patients with treatable conditions.

According to the health system efficiency and quality vice president of The Commonwealth Fund in New York, Anne-Marie Audet, the problem in a new era of patient care, lies in lack of patient motivation. Audet also stated, “Our system is so much geared toward acute care, but we’re moving toward investing in primary care and preventive care which means people will have to be even more engaged in their health. Generally, I think we’ve failed [as an industry] to really establish the connection between what happens in the small amount of time that people spend in the health care system and in the 99 percent of the time they spend outside of it.” She also mentioned that you could learn to activate patients; however, it is an acquired skill.

The key to reducing health care costs and improving quality care is encouraging patients to comply with medication and treatment regimes recommended.

Researchers are Developing Solutions for Noncompliance

The U.S. Department of Health and Human Services reports that one of the main contributing factors to noncompliance with medication is that patients don’t understand the medical recommendations. According to studies, this risk of non-adherence due to patients not receiving proper instructions by the provider of how to follow medication regimes is substantially high.

One asthma study pointed out the importance of properly instructing patients on how taking their medications affect their chronic conditions. The study found that 38 percent of the patients involved in the study adhered to the regiment and the other 62 percent were under the impression they were to take their medication as needed.

Additional studies found that communication between doctors and patients was ineffective, as physicians were not explaining the benefits the prescribed medication have on their condition, which led to compliance issues.

In considering noncompliance predictive factors, researchers are working on developing new tools and techniques to assist physicians in tailoring treatment plans to each individual patient that will provide them with the motivation they need to collaborate in their own care.

Why people fail to comply with treatment and medication as well as factors that contribute to patient compliance improvement, have been studied globally across various medical conditions from hypertension to chronic diseases. The findings of such studies have concluded the following three factors to have the best effects on patient compliance with treatments and medications.

• Understanding of medical directions
• Involvement in the Process
• Compliance reminders

Involvement in the Process

Many non-compliant patients feel they don’t have the proper support system to help them keep track of their daily medication usage or feel they are not involved in their own care process.

Research shows that patients of physicians who encourage them to be more involved actively in their diagnosis and treatment plan results in patient satisfaction and adherence to treatment regiments.

One study indicated that when patients view their physician as trustworthy, they are more apt to comply with following their recommendations.

Compliance reminders

Compliance reminders can be set to help patients with chronic conditions know when it’s time to take their medications. This has shown to increase compliance substantially, leading to better care outcomes.

A Chicago Medicine, University pilot program sent text messages to patients with diabetes as medication reminders, which successfully improved self-care and enhanced patient support. The program also showed a significant reduction in health care costs compared to what they were prior to the test. For each participant, the cost of care reduced by $ 812, which saved ,332 in the emergency department, inpatient, and outpatient visits, offset by a 0 raise in drug costs.

In addition, 73 percent of test participants reported being satisfied with the program, while 88 percent claimed that interaction with health professionals play a big role in their engagement.

Moreover, the “Journal of the American Medical Association” (JAMA) published the findings of another clinical trial that evaluated using mobile text messaging to promote treatment adherence in adults treated for chronic diseases. The report stated that using the mobile phone text messaging system, almost doubled patient compliance rates as the adherence rate went from 50 percent to 67.7 percent, a 17.8 percent increase.

Who are the current players?

A number of new companies are developing AI-driven technologies to facilitate patient compliance. Companies are developing platforms that use software algorithms on smartphones to visually and automatically confirm patient identity, medication and ingestion, send ingestion/dose reminders, and adapt based on the unique patient behavioural profile. Some platforms have already been shown to increase adherence by over 50%.

As a result, more patients benefit from the full efficacy of their medication. Clinicians will have access to real-time data and more complete and accurate data collection from their patients. The knock-on effect of this should be faster and more successful clinical trials, safer medication on the marketplace, and less medical wastage.

Some of the bigger companies in the market at the moment who are providing these technologies include:

• AiCure: AI-based patient monitoring platform, for facial recognition to confirm that patients have ingested their medicine. Partners include AbbVie and NeuroBo.
• Brite Health: Adaptive personalised patient engagement platform, which personalises engagement strategies based on the unique behavioural profile of the user.
• Medisafe: Personalised medication management platform. Partners include Boehringer Ingelheim and Apple Health Records.
• Proteus Digital Health: develop smart-pills (ingestible digital sensors) with built-in machine learning capabilities that track medication adherence. Partners include Novartis and Otsuka.

It is likely that hospitals and the NHS will be key players in development and use of machine learning to facilitate patient compliance. An example is the machine learning system, developed by University College London Hospital, that was trained to predict the likelihood that individual patients will arrive on time for their MRI scan appointment and was found to be very accurate.

 

The AllazoEngine | Harnessing Artificial Intelligence to Change Patient Behavior

The AllazoEngine™ combines behavioral sciences and machine learning to predict which patients are at-risk for specific clinical outcomes like medication non-adherence.

DATA AGGREGATE

The AllazoEngine first incorporates claims data, patient demographics, coverage eligibility, and past intervention data. The system is able to leverage customer data as well as data from 3rd parties. Once the data is collected, the AllazoEngine then normalizes the data to enable the machine learning processes.

CALCULATE

The AllazoEngine™ then runs proprietary algorithms to enrich the data by calculating hundreds of additional variables, such as the level of synchronization across multiple medications and complexity of dosing regimen – factors that have been proven to be predictive of medication adherence behaviors.

PREDICT

The machine learning models used in the AllazoEngine™ have been trained across millions of patients and hundreds of millions of data points to accurately and reliably correlate thousands of data variables with levels of adherence. Collectively these models provide a robust prediction for each individual patient’s risk of being non-adherent in the future. The AllazoEngineTM also predicts each patient’s likelihood of being influenced by various outreach channels and messages.

PRIORITIZE

Based on these predictions, AllazoHealth prioritizes the patients who are both at risk of becoming non-adherent and whose behaviors can be changed through proactive interventions. This cuts out unnecessary and often burdensome patient outreach to streamline your intervention strategy. Furthermore, interventions are much more successful when intervening proactively with at-risk patients instead of waiting until patients become non-adherent.

OPTIMIZE

While knowing who to intervene with is important, knowing how and when to intervene is just as critical. The AllazoEngine™ predicts the impact of multiple intervention channels and messages to select the most ideal combination for each individual patient.

LEARN

With time, the AllazoEngine™ becomes more in-tune with and nuanced to the specific population of each client. In other words, as more interventions are delivered and patient behaviors analyzed, it becomes even better at delivering the right intervention, to the right patient, at the right time.

Summary

With patient noncompliance being a problem in the U.S. costing billions of dollars annually and expected to cost even more in the future, not to mention the many preventable deaths that already occurred, it is important to find out what’s causing this problem and then address it with a proper solution.

Researchers searching for answers found the problem lies in the lack of patients understanding how their medication benefits their condition or merely forget to take their medication as prescribed. Physicians providing patients with complete instructions on medication usage and health care can help patients to become more involved in their own treatment, while reminder programs can be set to remind patients when it’s time to take their medication.