Enhanced Patient-Centricity: How the Biopharmaceutical Industry Is Optimizing Patient Care through AI/ML/DL

Area of Science:

• Biomedical Informatics
• Computational Biology
• Health Data Science

Background:

• Artificial intelligence (AI), machine learning (ML), and deep learning (DL) leverage real-world data (RWD) for improved patient outcomes.
• These technologies were crucial during the COVID-19 pandemic for healthcare provider protection, care prioritization, trend prediction, and therapy optimization.
• AI/ML/DL applications span diagnosis, disease management, and patient journey mapping.

Purpose of the Study:

• To explore the literature on AI/ML/DL applications in the biopharmaceutical industry for patient-centric purposes.
• To examine the specific challenges hindering the full realization of AI/ML/DL potential in biopharmaceutical research.
• To identify the need for evolving regulatory frameworks, operating models, and data governance.

Main Methods:

• Literature review of recent publications on AI/ML/DL in biopharmaceuticals.
• Analysis of challenges faced by researchers in utilizing RWD for AI model development.
• Examination of data-related hurdles including multi-setting data, interoperability, governance, and privacy.

Main Results:

• AI/ML/DL offer significant opportunities for evaluating, predicting, and enhancing patient outcomes.
• The use of fit-for-purpose datasets for ML models is growing, aiding AI strategy development.
• Biopharmaceutical companies encounter substantial obstacles related to data integration, governance, and patient privacy.

Conclusions:

• Further development and research in AI/ML/DL for patient-centric goals require evolving regulatory frameworks and data governance.
• Addressing challenges in data management and interoperability is crucial for biopharmaceutical companies.
• Realizing the full promise of AI/ML/DL necessitates a collaborative approach to overcome existing hurdles.