Leveraging Data Analytics to Improve Patient Adherence

Real-world data show lower levels of patient adherence in the newer patients as compared to the clinical trials. Medication adherence is affected by a wide variety of factors, including health disparities, the nature of the disease, treatment complexities, and more. Declining levels of patient adherence adversely impact patient outcomes and product performance alike.

Most pharma companies are focusing on and exploiting data analytics, in particular, pharma analytics, to explore and understand the factors hindering patient adherence.

Using pharma analytics to study the factors affecting patient adherence

Analyses of huge volumes of diverse datasets across geographies, diseases, and other factors helped in the understanding of what factors impact patient adherence. Some of them include:

Financial burden

The economic distress that the patient faces due to the expensive dosages of medicines can lead to missed doses or even complete medication drop-offs. This is particularly common in patients of low-income groups suffering from rare diseases like cancer which involve expensive therapies and ongoing treatment at substantial out-of-pocket costs. Patients usually do cost-benefit analyses and decide to stop the treatment owing to excessive costs.

Physicians

When a drug is relatively new or has poor safety profiles, it becomes difficult for physicians to work confidently with such medications. In addition, a physician’s lack of exposure to certain therapies may also affect their ability in handling patients with high-risk illnesses.

Patient

Analyses indicate that prolonged tests, consultations, and various therapies put a strain on the patient and result in them getting disengaged. Conditions like polypharmacy which requires patients to remember multiple medications, could gradually lead to forgetfulness, disinterest, and eventually an overall deterioration in the patient outcomes.

Brand

Complexities in drug administration, such as ease of intake (oral Vs intravenous) and additional instructions on the medications (crushing tablets, opening or closing capsules, etc.), also are responsible for improving patient adherence to medication. Analyses show that medication’s tolerability profile and side effects that it results in are primary factors in the patient’s decision towards medication regimens.

Social Determinants of Health

Insights point to the fact that social determinants play a key role in creating awareness about the immediate care and treatment available to patients. In the case of certain populations, including low-income groups, underprivileged sections of the community, elderly people, and others, there’s a lot of hardship in dealing with the complexities of the treatment procedures and undergoing continuous medication.

Role of data analytics in improving patient adherence

By incorporating diverse datasets ( such as claims data , EHR etc ) , patient drug fill days, and therapy durations, along with the use of predictive analytics we could pave the way for improving patient medication adherence.

Understanding patient demographics — An insight obtained from analytics on patient demographics can help healthcare providers plan better and also create customized intervention strategies.

Analyzing patient copays — While patient adherence might be adversely affected due to the financial burden on patients, prior analysis and ascertaining appropriate cost-sharing options can prepare them and improve medication adherence.

Arranging patient prescription supply — Using data-driven insights, the purchasing cycle for patient prescription medications can be planned well in advance to ensure smoother availability of the medications in required dosages.

Data analytics, including machine learning and pharma analytics, plays a vital role in understanding the patient adherence factors and thereby taking measures towards improving them. Taking into consideration the below factors could considerably enhance patient adherence:

Use diverse datasets

Analyses produce meaningful insights only when performed with high-quality data. Predictive analytics and machine learning techniques also yield accurate results only when superior data is used. Investing in master data management and big data capabilities can ensure richer data quality and diversity. Working with third-party vendors to gather data and using non-conventional datasets like Census, Bureau of Labor Statistics , pharmacy and medical claims , EHR etc. provides better and more reliable results.

Automate your predictive analytics

The traditional methods used in predictive analytics are highly time-consuming and demand a lot of expertise. Using the modern techniques of machine learning in healthcare and automation capabilities in modeling proves easier and produces more accurate outcomes.

Converting outputs to strategy

Extensive datasets and advanced modeling techniques will be truly useful only when used in conjunction with industry expertise. Translating the complex modeling results and statistical conclusions into an intervention strategy that helps non-data science stakeholders get a clear picture is recommended. This would, in turn, increase the shareholders’ trust and pave the way for newer dimensions.

Final Thoughts

Data analytics plays a significant role in analyzing and interpreting the causes associated with patient adherence levels. In addition, commercial analytics also gives actionable insights into the impact of medication adherence on sales and marketing functions.

References

[1] Fred Kleinsinger , The Unmet Challenge of Medication Nonadherence ( Jul. 2018 ), The Permanente Journal

[2] Brody JE. The cost of not taking your medication [Internet] New York, NY: The New York Times; 2017.

[3] Peterson AM, Takiya L, Finley R. Meta-analysis of interventions to improve medication adherence. Am J Health Syst Pharm. 2003 Apr 1;60(7):657–65.

[4] Wu JR, Moser DK. Medication adherence mediates the relationship between heart failure symptoms and cardiac event-free survival in patients with heart failure. J Cardiovasc Nurs. 2018

[5] Kleinsinger F. Working with the noncompliant patient. Perm J. 2010 Spring