Synthetic data in medical research

Kokosi, Theodora; Harron, Katie

doi:10.1136/bmjmed-2022-000167

Cited by 26 publications

(10 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These data can perpetuate and/or accentuate biases underlying the original data used to create the data generation model, might lack interpretability due to the black-box nature of underlying algorithms leading to lack of trust in using for real applications, might reveal confidential information in an adversarial attack, and lack consensus on evaluation of data quality. 60,61,72 These challenges are being carefully addressed by development of regulatory policies around using these data for improving patient outcomes. 60 Regulatory considerations (with a focus on fit-for-purpose risk-based framework) for the use of AI/ML for precision medicine…”

Section: Data Sharing Distributed Learning and Synthetic Data Generationmentioning

confidence: 99%

Current Status and Future Directions: The Application of Artificial Intelligence/Machine Learning for Precision Medicine

Naik,

Goyal,

Foschini

et al. 2024

Clin Pharma and Therapeutics

View full text Add to dashboard Cite

Technological innovations, such as artificial intelligence (AI) and machine learning (ML), have the potential to expedite the goal of precision medicine, especially when combined with increased capacity for voluminous data from multiple sources and expanded therapeutic modalities; however, they also present several challenges. In this communication, we first discuss the goals of precision medicine, and contextualize the use of AI in precision medicine by showcasing innovative applications (e.g., prediction of tumor growth and overall survival, biomarker identification using biomedical images, and identification of patient population for clinical practice) which were presented during the February 2023 virtual public workshop entitled “Application of Artificial Intelligence and Machine Learning for Precision Medicine,” hosted by the US Food and Drug Administration (FDA) and University of Maryland Center of Excellence in Regulatory Science and Innovation (M‐CERSI). Next, we put forward challenges brought about by the multidisciplinary nature of AI, particularly highlighting the need for AI to be trustworthy. To address such challenges, we subsequently note practical approaches, viz., differential privacy, synthetic data generation, and federated learning. The proposed strategies – some of which are highlighted presentations from the workshop – are for the protection of personal information and intellectual property. In addition, methods such as the risk‐based management approach and the need for an agile regulatory ecosystem are discussed. Finally, we lay out a call for action that includes sharing of data and algorithms, development of regulatory guidance documents, and pooling of expertise from a broad‐spectrum of stakeholders to enhance the application of AI in precision medicine.

show abstract

Section: Data Sharing Distributed Learning and Synthetic Data Generationmentioning

confidence: 99%

Current Status and Future Directions: The Application of Artificial Intelligence/Machine Learning for Precision Medicine

Naik,

Goyal,

Foschini

et al. 2024

Clin Pharma and Therapeutics

View full text Add to dashboard Cite

show abstract

“…Consequently, the use of synthetic data has gained popularity as a potential approach to enhance research reproducibility and implement differential privacy for protected health information [51]. The goal of data synthesis is to create a dataset that closely resembles the original individuallevel data and retrain prediction models [52]. Synthesized data can expedite methodological advancements in medical research and assist in processing high-dimensional and challenging medical data.…”

Section: Challenges and Future Directions For ML Applicationmentioning

confidence: 99%

Application of Machine Learning Based on Structured Medical Data in Gastroenterology

Kim,

Gong,

Bang

2023

Biomimetics

View full text Add to dashboard Cite

The era of big data has led to the necessity of artificial intelligence models to effectively handle the vast amount of clinical data available. These data have become indispensable resources for machine learning. Among the artificial intelligence models, deep learning has gained prominence and is widely used for analyzing unstructured data. Despite the recent advancement in deep learning, traditional machine learning models still hold significant potential for enhancing healthcare efficiency, especially for structured data. In the field of medicine, machine learning models have been applied to predict diagnoses and prognoses for various diseases. However, the adoption of machine learning models in gastroenterology has been relatively limited compared to traditional statistical models or deep learning approaches. This narrative review provides an overview of the current status of machine learning adoption in gastroenterology and discusses future directions. Additionally, it briefly summarizes recent advances in large language models.

show abstract

“…Real-world evidence, 33,39 is shaped into an engineered 'ground truth', artificially augmented and synthesized 60,61 to simulate temporal context and longitude 62 -conditions necessary to measure performance against desired patient outcomes. This approach is not sustainable, as it is both resource-intensive and fails the tests of explainability and reproducibility.…”

Section: Data Value Predicament In Health Innovationmentioning

confidence: 99%

Telehealth’s Role Enabling Sustainable Innovation and Circular Economies in Health

Kalogeropoulos¹

2023

THMT

View full text Add to dashboard Cite

Digital health interventions, including the use of telehealth augmented by artificial intelligence (AI), support an increasingly broad range of improvement goals for prevention and treatment. Limitations obstructing the many digital benefits of the targeted healthcare innovations from reaching their full potential include the lack of robust usability and user-centered design, nimble regulatory policy, and lack of adequate high-quality evidence and methodologies to evaluate the performance generalization and clinical robustness. We explore health innovation using different value systems and solutions proposed to overcome the fundamental limitations arising in the data value system. We propose a new telehealth paradigm and incorporate intervention designs, which combine clinical innovation with innovation in data resource development. Machine learning and AI have the potential to enable circular economies for digital and health innovation, in which sustainable solutions can be offered within a data-enabled collaborative and shared digital ecosystem. Alignment of industry standards, adjustments to regulatory policies, and the embrace of new governance models for telehealth-based innovation are essential for this new approach for health innovation scaling, clinical adoption, and social innovation.

show abstract

Synthetic data in medical research

Cited by 26 publications

References 16 publications

Current Status and Future Directions: The Application of Artificial Intelligence/Machine Learning for Precision Medicine

Current Status and Future Directions: The Application of Artificial Intelligence/Machine Learning for Precision Medicine

Application of Machine Learning Based on Structured Medical Data in Gastroenterology

Telehealth’s Role Enabling Sustainable Innovation and Circular Economies in Health

Contact Info

Product

Resources

About