Written by Sandy Kim, Pharm.D.
The estimated 260,000+ independent pharmacies worldwide play a unique role in managing diverse patient populations and chronic diseases, making them valuable partners in clinical research.1 Huge collection of real-world data – more than 800 petabytes per year, according to the 2022 IQVIA report2 — Paint a comprehensive picture of patient medication use, adherence patterns, and feedback. Unfortunately, traditional clinical trials often face limitations in recruiting diverse participants and effectively collecting real-world data. Effectively leveraging this wealth of data requires innovative solutions that go beyond traditional methods. AI steps in as an innovative tool, providing a powerful means for data analysis and unlocking the true potential of pharmacy-based clinical trials.
Data challenges and AI solutions
Consider the following topical areas where data challenges arise in clinical trials and how AI can address them.
Data amount and type
Pharmacies collect large amounts of structured and unstructured data, including prescription records, dispensing patterns, and patient feedback. Analyzing this complex tapestry can be extremely difficult using traditional techniques. However, AI's ability to handle complex datasets can be beneficial.
- Natural Language Processing (NLP): This AI technology deciphers unstructured data, such as clinical records and patient experience feedback, and extracts valuable insights hidden within it.3,4 For example, NLP could identify patient emotions and medication concerns from pharmacy feedback, potentially informing future trial design.Five
- Machine learning: These algorithms identify patterns in prescription records, including previously unknown trends in medication adherence, potential drug-drug interactions, or risks for individual participants in clinical trials. will be revealed.6
Data integration and standardization
Inconsistent data formats and lack of standardization across pharmacies create integration hurdles and limit comprehensive analysis. Federated learning is emerging as a promising solution. These AI techniques enable distributed analysis of data across different pharmacies without compromising privacy, allowing researchers to gain valuable insights from a wealth of collective information. Although each pharmacy stores the data locally, AI algorithms can access and analyze the data without transmitting the raw data, protecting your privacy. This collaborative approach allows researchers to identify broader trends and patterns across diverse patient populations. 7,8
Identifying eligible participants
It is important to select appropriate participants for a clinical trial, taking into account medical history, compliance, and potential risk factors. Traditional methods can be time-consuming, subjective, and prone to bias because they rely on self-reported data. AI-powered algorithms analyze patient data with incredible speed and accuracy to more objectively identify ideal candidates who meet specific criteria.
Generating real-world evidence (RWE)
Real-world data from pharmacies paints a realistic picture of drug efficacy and safety in everyday settings, complementing the controlled environment of traditional clinical trials. AI analyzes this data to generate robust RWE and identify trends and patterns that are not apparent with traditional statistical methods. 9
Predictive modeling and risk assessment
By analyzing historical data and identifying patterns, AI can predict potential risks and adverse events during clinical trials. This proactive approach allows researchers to take safety precautions in advance, minimizing risk to participants and ensuring ethical behavior. Ten
Benefits for stakeholders
Clinical trials in the pharmacy setting offer unique benefits to pharmaceutical sponsors, pharmacies, and patients. Here are some ways each can earn rewards.
sponsor
- Faster and more efficient trial design and participant selection: AI streamlines processes and significantly reduces timelines and costs associated with participant recruitment and data analysis.
- Deeper insights from real-world data: AI-powered RWE generation provides a more comprehensive understanding of drug efficacy and safety, leading to more informed decisions and drug development strategies. This will lead to improvements.
- Reduce costs and improve clinical trial feasibility: AI optimizes processes and leverages RWE to significantly reduce the cost and complexity of conducting clinical trials, making them more accessible and viable. make it possible.9
pharmacy
- Enhance patient care by participating in cutting-edge research: By participating in AI-powered clinical trials, pharmacies can contribute to medical advances and give patients access to innovative treatments closer to home. Masu.
- Diversify revenue streams with participation fees and data analysis services: Pharmacies can leverage data and AI expertise to participate in clinical trials and generate additional revenue streams by providing data analysis services to other parties. can be produced.
- Improve operational efficiency with AI-powered tools: AI automates tasks like medication reconciliation and compliance monitoring, freeing up pharmacist time and improving overall operational efficiency.
patient
- Access to innovative treatments closer to home: Pharmacy-based trials make cutting-edge treatments more accessible to patients who may not be able to participate in traditional hospital-based trials.
- Potential for personalized medicine approaches based on AI-driven analytics: AI can analyze individual patient data from the pharmacy and tailor treatment plans and dosages for optimal patient outcomes.
Ethical considerations and regulatory landscape
However, bringing AI-powered clinical trials into the pharmacy setting requires careful consideration of data privacy and security issues, as well as regulatory compliance. Robust data security measures and clear patient consent procedures are essential when using AI in healthcare. Encryption, compliance with regulations such as Good Machine Learning Practice (GMLP), General Data Protection Regulation (GDPR), HIPAA, and anonymization technologies are essential to protecting patient privacy and building trust.11, 12 It is important to ensure compliance with data privacy regulations and clinical research ethical guidelines. Regulators are actively developing frameworks for AI in healthcare, and navigating this evolving landscape will require collaboration between researchers, industry experts, and regulators.
conclusion
Leveraging AI to analyze data in pharmacy-based clinical trials has tremendous potential to revolutionize drug development and healthcare delivery. By unlocking vast insights hidden in real-world pharmacy data, AI can accelerate trial design, personalize treatment plans, and ultimately improve patient outcomes. As we move forward, a commitment to ethical considerations, ensuring data privacy and fostering collaboration between stakeholders will be critical to realizing the full potential of this innovative technology. .
References:
- National Association of Community Pharmacists. (2023). NCPA Digest: Key statistics about independent pharmacy. https://ncpa.org/annual-report
- IQVIA Human Data Science Institute. (2022). 2023 IQVIA Human Data Science Institute Trend Report. https://www.iqvia.com/blogs/2023/02/iqvia-institute-research-highlights-2022
- Harrison, CJ, Sidey-Gibbons, CJ Machine learning in medicine: A practical introduction to natural language processing. BMC Med Res Method 21, 158 (2021). https://doi.org/10.1186/s12874-021-01347-1
- Khanbhai M, Anyadi P, Symons J, Flott K, Darzi A, Mayer E. Applying natural language processing and machine learning techniques to patient experience feedback: a systematic review. BMJ Healthcare Inform. 2021 Mar;28(1):e100262. doi:10.1136/bmjhci-2020-100262. PMID: 33653690; PMCID: PMC7929894.
- JZ State Reid (July 6, 2022). NLP analyzes the past to inform the future of clinical trial design. Applied clinical trials online.
- Aki Shinozaki (2020). Electronic medical records and machine learning in approaches to drug development. Intech open. doi: 10.5772/intechopen.92613
- Rahman, A., Hossain, M.S., Muhammad, G. other. Federated learning-based AI approaches in smart healthcare: Concepts, taxonomy, challenges, and open questions. cluster computing 26, 2271–2311 (2023). https://doi.org/10.1007/s10586-022-03658-4
- Zhang, Huang, et al. “Recent methodological advances in federated learning for healthcare.” arXiv:2310.02874 [cs.LG]. October 4, 2023.
- Zhaoi Chen, Xiong Liu, William Hogan, Elizabeth Shenkman, Jiang Bian. Application of artificial intelligence in drug development using real-world data. Drug Discovery Today, 2020. PMID: 33358699 DOI: 10.1016/j.drudis.2020.12.013
- “AI models help predict adverse events from new drug combinations.” AACR Cancer Researchers/Other Health Professionals, April 8, 2022.
- GDPR Local. Latest trends in AI-era data protection and GDPR in clinical trials. February 21, 2024). Retrieved from GDPR Local.
- Mai, B., Roman, A., Suarez, A. (20 June 2023). Forward thinking for integrating AI into clinical trials. Clinical Researcher, 37(3). Retrieved from ACRP Home News & Press
About the author:
Dr. Sandy Kim has over five years of experience in outpatient care and a passion for clinical research. Her recent research in the biotechnology industry has focused on oncology, and she has made significant contributions to cutting-edge research.
Dr. Kim actively collaborates with pharmacy and research medical professionals and platform startups to explore innovative and collaborative approaches in clinical research. She is particularly interested in supporting pharmacy in the community and integrating advances in AI into clinical trial systems. Dr. Kim is a champion of clinical research driven by a commitment to patient safety and ethical research. She actively promotes collaborative approaches involving community and independent pharmacy services in clinical trials.