Chapter 11 AI and big data in post-marketing surveillance
-
Rishabha Malviya
Abstract
Post-marketing surveillance, or PMS, involves monitoring a drug’s safety after clinical trials and successful market introduction. The “timely identification” of “novel” adverse drug reactions (ADRs) that differ from one another in terms of their “clinical nature, degree, and frequency” is the main goal of PMS. Examples of new technologies covered in the chapter include machine learning, artificial intelligence, and big data analytics. Many obstacles exist when using AI in post-marketing surveillance, and these technologies have made data privacy protection more difficult. Drug safety monitoring benefits greatly from big data analytics since it makes it easier to identify issues early on and to keep an eye out for potential signals in real time. The creation of adaptable, fact-based quality assurance frameworks that encourage innovation and more informed decision-making can be aided by AI solutions. They can also assist in meeting EU MDR/IVDR regulations for PMS practitioners and manufacturers of medical devices. Moreover, many obstacles are discussed regarding privacy protection when using AI for post-marketing surveillance. Therefore, complicated algorithms are used in healthcare AI applications, which give private AI firms access to patient medical data even when “anonymization” is employed, thus posing a risk to privacy.
Abstract
Post-marketing surveillance, or PMS, involves monitoring a drug’s safety after clinical trials and successful market introduction. The “timely identification” of “novel” adverse drug reactions (ADRs) that differ from one another in terms of their “clinical nature, degree, and frequency” is the main goal of PMS. Examples of new technologies covered in the chapter include machine learning, artificial intelligence, and big data analytics. Many obstacles exist when using AI in post-marketing surveillance, and these technologies have made data privacy protection more difficult. Drug safety monitoring benefits greatly from big data analytics since it makes it easier to identify issues early on and to keep an eye out for potential signals in real time. The creation of adaptable, fact-based quality assurance frameworks that encourage innovation and more informed decision-making can be aided by AI solutions. They can also assist in meeting EU MDR/IVDR regulations for PMS practitioners and manufacturers of medical devices. Moreover, many obstacles are discussed regarding privacy protection when using AI for post-marketing surveillance. Therefore, complicated algorithms are used in healthcare AI applications, which give private AI firms access to patient medical data even when “anonymization” is employed, thus posing a risk to privacy.
Kapitel in diesem Buch
- Frontmatter I
- Preface V
- Foreword VII
- Contents IX
- Chapter 1 Introduction to smart pharma: foundation of AI and big data 1
- Chapter 2 Emerging technology in pharma and the role of AI and blockchain 19
- Chapter 3 Partnership and collaboration in the pharmaceutical industry 37
- Chapter 4 Education and training in smart pharma 55
- Chapter 5 Drug manufacturing and quality control with artificial intelligence 77
- Chapter 6 Drug development and clinical trial via artificial intelligence 97
- Chapter 7 AI-driven clinical decision support systems for pharma executives 121
- Chapter 8 AI-based pharmacovigilance and drug safety 143
- Chapter 9 Intellectual property and data privacy in the pharmaceutical sector 163
- Chapter 10 Regulatory affairs and compliance in the pharmaceutical sector 183
- Chapter 11 AI and big data in post-marketing surveillance 201
- Chapter 12 Challenges and ethical considerations 219
- Chapter 13 Future trends and innovations of AI in healthcare 237
- Index 253
Kapitel in diesem Buch
- Frontmatter I
- Preface V
- Foreword VII
- Contents IX
- Chapter 1 Introduction to smart pharma: foundation of AI and big data 1
- Chapter 2 Emerging technology in pharma and the role of AI and blockchain 19
- Chapter 3 Partnership and collaboration in the pharmaceutical industry 37
- Chapter 4 Education and training in smart pharma 55
- Chapter 5 Drug manufacturing and quality control with artificial intelligence 77
- Chapter 6 Drug development and clinical trial via artificial intelligence 97
- Chapter 7 AI-driven clinical decision support systems for pharma executives 121
- Chapter 8 AI-based pharmacovigilance and drug safety 143
- Chapter 9 Intellectual property and data privacy in the pharmaceutical sector 163
- Chapter 10 Regulatory affairs and compliance in the pharmaceutical sector 183
- Chapter 11 AI and big data in post-marketing surveillance 201
- Chapter 12 Challenges and ethical considerations 219
- Chapter 13 Future trends and innovations of AI in healthcare 237
- Index 253
