Accuracy of machine learning-based prediction of medication adherence in clinical research

Koesmahargyo, Vidya; Abbas, Anzar; Zhang, Li; Guan, Lei; Feng, Siwei; Yadav, Vijay; Galatzer‐Levy, Isaac R.

doi:10.1016/j.psychres.2020.113558

Cited by 29 publications

(22 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We were unable to find examples of introduction of machine learning algorithms for retrospective assessments of non-adherence using clinical exemptions in decision-making. The usefulness of integrated pharmacy and health service records in predicting future patient adherence [ 63 ] or estimating individualised optimal heparin doses [ 64 ] is promising. There are also high hopes for machine learning to contribute identification of statistical patterns of prescribing quality [ 65 ] but their effectiveness in identifying meaningful and credible conclusion on clinician’s guideline concordance and decision parameters are still under investigation [ 66 ].…”

Section: Discussionmentioning

confidence: 99%

Guideline Adherence As An Indicator of the Extent of Antithrombotic Overuse and Underuse: A Systematic Review

Cardona

Craig

Jones

et al. 2022

View full text Add to dashboard Cite

Thromboembolic events are a common risk in adults with atrial fibrillation, those with previous cerebrovascular accidents and undergoing emergency or elective surgeries. The widespread availability of antithrombotic agents and differing guidelines contribute to practice variations and increased risk of complications and deaths. The objective of this review was to investigate the extent of overuse and underuse of antithrombotics for primary or secondary prevention as measured by deviation from prescribing guideline recommendations. We conducted a systematic review of Medline and EMBASE for quantitative articles published between 2000 and 2021 and used a modified version of the Hoy's risk of bias assessment tool. Here we report evidence from the past decade about wide practice variations in hospitals and primary care, and discuss clinician and patient-driven determinants of non-adherence to guidelines. Finally, we summarise implications for practice, identify enhanced ways of measuring overuse and underuse, and propose potential solutions to the measurement challenges. 2 Cardona et al.

show abstract

Section: Discussionmentioning

confidence: 99%

Guideline Adherence As An Indicator of the Extent of Antithrombotic Overuse and Underuse: A Systematic Review

Cardona

Craig

Jones

et al. 2022

View full text Add to dashboard Cite

show abstract

“…For example, machine learning has been used to identify factors related to adherence to nicotine replacement therapy ( 42 ) as well as diabetes and Crohn's disease medication ( 43 , 44 ), and asthma self-management ( 45 ). Koesmahargyo et al ( 46 ) assessed the accuracy of medication dosing data to predict medication non-adherence through machine learning in a study using a large sample of participants from a range of clinical trials, who were observed via a smartphone application that used videos of the patients taking their prescribed medication. The real-time measurement of dosing was able to dynamically predict medication adherence with high accuracy over the trial period as well as over the subsequent day and week ( 46 ).…”

Section: Current Ai Technologies To Increase Medication Adherence In Ncd Patientsmentioning

confidence: 99%

“…Koesmahargyo et al ( 46 ) assessed the accuracy of medication dosing data to predict medication non-adherence through machine learning in a study using a large sample of participants from a range of clinical trials, who were observed via a smartphone application that used videos of the patients taking their prescribed medication. The real-time measurement of dosing was able to dynamically predict medication adherence with high accuracy over the trial period as well as over the subsequent day and week ( 46 ). Machine learning models were also found to be effective in identifying the key variables to understand the adherence levels of hypertensive patients ( 47 ) and to even predict adherence to lifestyle patterns, such as the Mediterranean diet ( 48 ).…”

Section: Current Ai Technologies To Increase Medication Adherence In Ncd Patientsmentioning

confidence: 99%

Artificial Intelligence Solutions to Increase Medication Adherence in Patients With Non-communicable Diseases

Babel

Taneja

Malvestiti³

et al. 2021

Front. Digit. Health

View full text Add to dashboard Cite

Artificial intelligence (AI) tools are increasingly being used within healthcare for various purposes, including helping patients to adhere to drug regimens. The aim of this narrative review was to describe: (1) studies on AI tools that can be used to measure and increase medication adherence in patients with non-communicable diseases (NCDs); (2) the benefits of using AI for these purposes; (3) challenges of the use of AI in healthcare; and (4) priorities for future research. We discuss the current AI technologies, including mobile phone applications, reminder systems, tools for patient empowerment, instruments that can be used in integrated care, and machine learning. The use of AI may be key to understanding the complex interplay of factors that underly medication non-adherence in NCD patients. AI-assisted interventions aiming to improve communication between patients and physicians, monitor drug consumption, empower patients, and ultimately, increase adherence levels may lead to better clinical outcomes and increase the quality of life of NCD patients. However, the use of AI in healthcare is challenged by numerous factors; the characteristics of users can impact the effectiveness of an AI tool, which may lead to further inequalities in healthcare, and there may be concerns that it could depersonalize medicine. The success and widespread use of AI technologies will depend on data storage capacity, processing power, and other infrastructure capacities within healthcare systems. Research is needed to evaluate the effectiveness of AI solutions in different patient groups and establish the barriers to widespread adoption, especially in light of the COVID-19 pandemic, which has led to a rapid increase in the use and development of digital health technologies.

show abstract

“…1 below). Importantly, new evidence demonstrates that direct remote measurements of adherence can be used directly to make dynamic predictions about adherence behavior in the future [ 9 ].…”

Section: Technology Solutions For Treatment Non-adherencementioning

confidence: 99%

Technology for Measuring and Monitoring Treatment Compliance Remotely

Christie

Abbas

Koesmahargyo

2021

JPD

Self Cite

View full text Add to dashboard Cite

Medication non-adherence during clinical trials is an ongoing challenge that can result in insufficient safety and efficacy data. For patients with Parkinson’s disease and other neurological disorders, symptomatology such as forgetfulness compounds traditional obstacles to adherence. Today, sponsors and clinical study sites can call upon various technology tools that improve adherence by monitoring and confirming dosage in near real-time. These tools have the potential to improve the quality of data gleaned from these studies.

show abstract

Accuracy of machine learning-based prediction of medication adherence in clinical research

Cited by 29 publications

References 18 publications

Guideline Adherence As An Indicator of the Extent of Antithrombotic Overuse and Underuse: A Systematic Review

Guideline Adherence As An Indicator of the Extent of Antithrombotic Overuse and Underuse: A Systematic Review

Artificial Intelligence Solutions to Increase Medication Adherence in Patients With Non-communicable Diseases

Technology for Measuring and Monitoring Treatment Compliance Remotely

Contact Info

Product

Resources

About