The impact of commercial health datasets on medical research and health-care algorithms

Alberto, Isabelle Rose I.; Alberto, Nicole Rose I.; Ghosh, Arnab; Jain, Bhav; Jayakumar, Shruti; Martinez-Martin, Nicole; McCague, Ned; Moukheiber, Dana; Moukheiber, Lama; Moukheiber, Mira; Moukheiber, Sulaiman; Yaghy, Antonio; Zhang, Andrew; Celi, Leo Anthony

doi:10.1016/s2589-7500(23)00025-0

Cited by 16 publications

(9 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The integration of Big Data science and AI will bring about increased efficiency, necessitate changes in laboratory infrastructure, and necessitate a shift in workforce training, requiring modifications in pathologists and technologists training curricula especially in low middle income countries [ 23 ]. At present, these solutions heavily rely on commercially available datasets primarily sourced from high-income countries, which consist of populations living near hospitals and with easier access to healthcare [ 24 ]. In contrast, lower-income countries like Pakistan face challenges in generating and refining data, often due to limited infrastructure and expertise.…”

Section: Discussionmentioning

confidence: 99%

Insights from semi-structured interviews on integrating artificial intelligence in clinical chemistry laboratory practices

Jafri,

Farooqui,

Grant

et al. 2024

BMC Med Educ

View full text Add to dashboard Cite

Background Artificial intelligence (AI) is gradually transforming the practises of healthcare providers. Over the last two decades, the advent of AI into numerous aspects of pathology has opened transformative possibilities in how we practise laboratory medicine. Objectives of this study were to explore how AI could impact the clinical practices of professionals working in Clinical Chemistry laboratories, while also identifying effective strategies in medical education to facilitate the required changes. Methods From March to August 2022, an exploratory qualitative study was conducted at the Section of Clinical Chemistry, Department of Pathology and Laboratory Medicine, Aga Khan University, Karachi, Pakistan, in collaboration with Keele University, Newcastle, United Kingdom. Semi-structured interviews were conducted to collect information from diverse group of professionals working in Clinical Chemistry laboratories. All interviews were audio recorded and transcribed verbatim. They were asked what changes AI would involve in the laboratory, what resources would be necessary, and how medical education would assist them in adapting to the change. A content analysis was conducted, resulting in the development of codes and themes based on the analyzed data. Results The interviews were analysed to identify three primary themes: perspectives and considerations for AI adoption, educational and curriculum adjustments, and implementation techniques. Although the use of diagnostic algorithms is currently limited in Pakistani Clinical Chemistry laboratories, the application of AI is expanding. All thirteen participants stated their reasons for being hesitant to use AI. Participants stressed the importance of critical aspects for effective AI deployment, the need of a collaborative integrative approach, and the need for constant horizon scanning to keep up with AI developments. Conclusions Three primary themes related to AI adoption were identified: perspectives and considerations, educational and curriculum adjustments, and implementation techniques. The study’s findings give a sound foundation for making suggestions to clinical laboratories, scientific bodies, and national and international Clinical Chemistry and laboratory medicine organisations on how to manage pathologists’ shifting practises because of AI.

show abstract

Section: Discussionmentioning

confidence: 99%

Insights from semi-structured interviews on integrating artificial intelligence in clinical chemistry laboratory practices

Jafri,

Farooqui,

Grant

et al. 2024

BMC Med Educ

View full text Add to dashboard Cite

show abstract

“…This section begins with analyzing a paper by I. R. Alberto et al (2023), investigating the importance and potential misuse of health data [24]. The authors identify an insufficiency in current data frameworks, especially the issue of 'data poverty' in lower-income countries, and advocate for more inclusive health data collection practices.…”

Section: Privacy Gdpr and Ethical Considerations In Aimentioning

confidence: 99%

Artificial Intelligence Ethics and Challenges in Healthcare Applications: A Comprehensive Review in the Context of the European GDPR Mandate

Mohammad Amini,

Jesus,

Fanaei Sheikholeslami

et al. 2023

MAKE

View full text Add to dashboard Cite

This study examines the ethical issues surrounding the use of Artificial Intelligence (AI) in healthcare, specifically nursing, under the European General Data Protection Regulation (GDPR). The analysis delves into how GDPR applies to healthcare AI projects, encompassing data collection and decision-making stages, to reveal the ethical implications at each step. A comprehensive review of the literature categorizes research investigations into three main categories: Ethical Considerations in AI; Practical Challenges and Solutions in AI Integration; and Legal and Policy Implications in AI. The analysis uncovers a significant research deficit in this field, with a particular focus on data owner rights and AI ethics within GDPR compliance. To address this gap, the study proposes new case studies that emphasize the importance of comprehending data owner rights and establishing ethical norms for AI use in medical applications, especially in nursing. This review makes a valuable contribution to the AI ethics debate and assists nursing and healthcare professionals in developing ethical AI practices. The insights provided help stakeholders navigate the intricate terrain of data protection, ethical considerations, and regulatory compliance in AI-driven healthcare. Lastly, the study introduces a case study of a real AI health-tech project named SENSOMATT, spotlighting GDPR and privacy issues.

show abstract

“…This issue is critical in healthcare, where data on rare diseases are inherently scarce, yet vital for understanding disease progression and aiding patient care [13], [14], [15]. The scarcity of comprehensive time series medical data, compounded by stringent privacy laws like the Health Insurance Portability and Accountability Act (HIPAA) in the U.S., restricts access to large-scale medical datasets [16]. These constraints significantly impact the robustness and generalizability of AI models in medical research.…”

Section: Introductionmentioning

confidence: 99%

Image Encoded Time Series Classification of Small Datasets: An Innovative Architecture Using Deep Learning Ensembles

Indrasiri,

Kashyap,

Pathirana

2024

Preprint

View full text Add to dashboard Cite

Convolutional neural networks (CNNs) are often favored for their strong learning abilities in tackling automatic intelligent models. The classification of time series data streams spans across many applications of intelligent systems. However, the scarcity of effective Machine Learning architectures to handle limited time-series data adversely affects the realization of some crucial applications. In particular, healthcare-related applications are inherently concerned with limited time series datasets. Indeed, building effective artificial intelligence (AI) models for rare diseases using conventional techniques can pose a significant challenge. Utilizing recent advances in deep learning and signal processing techniques, this study introduces a new ensemble deep learning (DL) approach for time series categorization in the presence of limited datasets. Physiological data, such as ECG and voice, are used to demonstrate the functionality of the proposed DL architecture with data obtained from IoT and non-IoT devices. The proposed framework comprises a self-designed deep CNN-LSTM along with ResNet50 and MobileNet transfer learning approaches. The CNN-LSTM architecture includes an enhanced squeeze and excitation block that improves overall performance.This architecture processes time series data transformed into a 3-Channel image structure via improved recurrence plot (RP), Gramian angular field (GAF), and fuzzy recurrence plot (FRP) methods. The proposed model demonstrated superior classification accuracy on the ECG5000 and TESS datasets compared to other state-of-the-art techniques, validating its efficacy for binary and multiclass classification.

show abstract

The impact of commercial health datasets on medical research and health-care algorithms

Cited by 16 publications

References 44 publications

Insights from semi-structured interviews on integrating artificial intelligence in clinical chemistry laboratory practices

Insights from semi-structured interviews on integrating artificial intelligence in clinical chemistry laboratory practices

Artificial Intelligence Ethics and Challenges in Healthcare Applications: A Comprehensive Review in the Context of the European GDPR Mandate

Image Encoded Time Series Classification of Small Datasets: An Innovative Architecture Using Deep Learning Ensembles

Contact Info

Product

Resources

About