Data-centric AI: Perspectives and Challenges

Zha, Daochen; Bhat, Zaid Pervaiz; Lai, Kwei-Herng; Yang, Fan; Hu, Xia

doi:10.48550/arxiv.2301.04819

Cited by 9 publications

(8 citation statements)

References 28 publications

(29 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[30] AI researchers highlighted a growing body of research in AI technology development for healthcare settings, including the 'human-in-the-loop' approach and the 'data-centric AI movement'. [7,31,32] Regulation was a topic raised by several participant groups.…”

Section: Table 4: Cross-cutting Themes Trustmentioning

confidence: 99%

User and developer views on using Artificial Intelligence technologies to facilitate the early diagnosis of skin cancers in primary care settings: A qualitative study (Preprint)

Jones,

Calanzani,

Scott

et al. 2024

Preprint

View full text Add to dashboard Cite

BACKGROUND Skin cancers, including melanoma and keratinocyte cancers, are amongst the commonest cancers worldwide and their incidence is rising in most populations. Earlier detection of skin cancer leads to better outcomes for patients. Artificial Intelligence (AI) technologies have been applied to skin cancer diagnosis, but many technologies lack clinical evidence and/or the appropriate regulatory approvals. There are few qualitative studies examining the views of relevant stakeholders, or evidence about implementation and positioning of AI technologies in the skin cancer diagnostic pathway. OBJECTIVE To understand the views of several stakeholder groups on the use of AI technologies to facilitate the early diagnosis of skin cancer including patients, members of the public, general practitioners, primary care nurse practitioners, dermatologists, and AI researchers. METHODS A qualitative, semi-structured interview study with 29 stakeholders. Participants were purposively sampled based on age, gender, and geographical location. Interviews were conducted via Zoom between September 2022 and May 2023. Transcribed recordings were analysed using thematic framework analysis. The framework for the non-adoption, abandonment, and challenges to scale-up, spread, and sustainability (NASSS) was used to guide the analysis, to help understand the complexity of implementing diagnostic technologies in clinical settings. RESULTS Major themes were ‘the position of AI in the skin cancer diagnostic pathway’ and ‘the aim of the AI technology’; cross-cutting themes included trust, usability and acceptability, generalisability, evaluation and regulation, implementation, and long-term use. There was no clear consensus on where AI should be placed along the skin cancer diagnostic pathway but most participants saw the technology in the hands of either patients or primary care practitioners. Participants were concerned about the quality of the data used to develop and test AI technologies, and the impact this could have on their accuracy in clinical use with patients from a range of demographics and the risk of missing skin cancers. Ease of use and not increasing the workload of, already strained, healthcare services were important considerations for participants. Healthcare professionals and AI researchers reported a lack of established methods of evaluating and regulating AI technologies. CONCLUSIONS This study is one of the first to examine the views of a wide range of stakeholders on the use of AI technologies to facilitate early diagnosis of skin cancer. The optimal approach and position in the diagnostic pathway for these technologies have not yet been determined. AI technologies need to be developed and implemented carefully and thoughtfully, with attention paid to the quality and representativeness of the data used for development, to achieve their potential.

show abstract

Section: Table 4: Cross-cutting Themes Trustmentioning

confidence: 99%

User and developer views on using Artificial Intelligence technologies to facilitate the early diagnosis of skin cancers in primary care settings: A qualitative study (Preprint)

Jones,

Calanzani,

Scott

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…In search of responsible solutions, this project follows guidelines proposed in the literature, such as how to develop and use AI responsibly (DIGNUM, 2019), AI for all (RAMOS, 2021), Guidelines for Trustworthy AI (ZHANG; ZHANG, 2023), Ethics of AI (UNESCO), and others. We also adopt the principles of Data-Centric AI (DCAI) (ZHA et al, 2023;WHANG et al, 2023), putting data at the heart of an AI system development process. For such, we applied the FAIR (Findable, Accessible, Interoperable, and Reusable) data principles (WILKINSON et al, 2016), guidelines to improve the Findability, Accessibility, Interoperability, and Reuse of data, aiding scientific advancement and promoting.…”

Section: Navigating Equity and Ethical Challengesmentioning

confidence: 99%

BioAutoML: Democratizing Machine Learning in Life Sciences

Bonidia,

Carvalho

2024

Anais Estendidos Do XXIV Simpósio Brasileiro De Computação Aplicada À Saúde (SBCAS 2024)

View full text Add to dashboard Cite

Recent technological advances have allowed an exponential expansion of biological sequence data, and the extraction of meaningful information through Machine Learning (ML) algorithms. This knowledge improved the understanding of the mechanisms related to several fatal diseases, e.g., Cancer and COVID-19, helping to develop innovative solutions, such as CRISPR-based gene editing, coronavirus vaccine, and precision medicine. These advances benefit our society and economy, directly impacting people’s lives in various areas, such as health care, drug discovery, forensic analysis, and food analysis. Nevertheless, ML approaches to biological data require representative, quantitative, and informative features. Necessarily, as many ML algorithms can handle only numerical data, sequences need to be translated into a feature vector. This process, known as feature extraction, is a fundamental step for elaborating high-quality ML-based models in bioinformatics, by allowing the feature engineering stage, with the design and selection of suitable features. Feature engineering, ML algorithm selection, and hyperparameter tuning are often time-consuming processes that require extensive domain knowledge and are performed by a human expert. To deal with this problem, we developed a new package, BioAutoML, which automatically runs an end-to-end ML pipeline. BioAutoML extracts numerical and informative features from biological sequence databases, automating feature selection, recommendation of ML algorithm(s), and tuning of hyperparameters, using Automated ML (AutoML). Our experimental results demonstrate the robustness of our proposal across various domains, such as SARS-CoV-2, anticancer peptides, HIV sequences, and non-coding RNAs. BioAutoML has a high potential to significantly reduce the expertise required to use ML pipelines, aiding researchers in combating diseases, particularly in low- and middle-income countries. This initiative can provide biologists, physicians, epidemiologists, and other stakeholders with an opportunity for widespread use of these techniques to enhance the health and well-being of their communities.

show abstract

“…Data-Centric Approach: This refers to an approach in which data are the central focus of a system or process [16,18]. A data-centric approach involves a relatively fixed model that prioritizes the collection, storage, and analysis of high-quality data to train AI algorithms, improve their performance, and leverage data to inform decision-making and problem-solving processes [16,18,19]. This approach often involves using advanced analytics such as machine learning or artificial intelligence to uncover patterns, trends, or insights that may not be immediately apparent from the data [19].…”

Section: Data-centric and Data-driven Aimentioning

confidence: 99%

Re-think Data Strategy and Integration for Artificial Intelligence: Concepts, Opportunities and Challenges

Aldoseri¹,

Al-Khalifa²

2023

Preprint

View full text Add to dashboard Cite

The use of artificial intelligence (AI) is becoming more prevalent across industries as diverse as healthcare, finance, and transportation. Artificial intelligence is based on the analysis of large data sets and requires a continuous supply of high-quality data. However, using data for AI is not without its challenges. This paper comprehensively reviews and critically examine the challenges of using data for AI, including data quality, data volume, privacy and security, bias and fairness, interpretability and explainability, ethical concern, and technical expertise and skills. This paper examines e these challenges in details and offers advices on how companies can address them. By understanding and addressing these challenges, organizations can harness the power of AI to make smarter decisions and gain a competitive advantage in the digital age.

show abstract

Data-centric AI: Perspectives and Challenges

Cited by 9 publications

References 28 publications

User and developer views on using Artificial Intelligence technologies to facilitate the early diagnosis of skin cancers in primary care settings: A qualitative study (Preprint)

User and developer views on using Artificial Intelligence technologies to facilitate the early diagnosis of skin cancers in primary care settings: A qualitative study (Preprint)

BioAutoML: Democratizing Machine Learning in Life Sciences

Re-think Data Strategy and Integration for Artificial Intelligence: Concepts, Opportunities and Challenges

Contact Info

Product

Resources

About