Medical big data: promise and challenges
By C. Lee, Hyung-Jin Yoon. Kidney Research and Clinical Practice, 2017
490 citations recorded by the source corpus.
The concept of big data, commonly characterized by volume, variety, velocity, and veracity, goes far beyond the data type and includes the aspects of data analysis, such as hypothesis-generating, rather than hypothesis-testing. Big data focuses on temporal stability of the association, rather than on causal relationship and underlying probability distribution assumptions are frequently not required. Medical big data as material to be analyzed has various features that are not only distinct from big data of other disciplines, but also distinct from traditional clinical epidemiology. Big data technology has many areas of application in healthcare, such as predictive modeling and clinical decision support, disease or safety surveillance, public health, and research. Big data analytics frequently exploits analytic methods developed in data mining, including classification, clustering, and regression. Medical big data analyses are complicated by many technical issues, such as missing values, curse of dimensionality, and bias control, and share the inherent limitations of observation study, namely the inability to test causality resulting from residual confounding and reverse causation. Recently, propensity score analysis and instrumental variable analysis have been introduced to overcome these limitations, and they have accomplished a great deal. Many challenges, such as the absence of evidence of practical benefits of big data, methodological issues including legal and ethical issues, and clinical integration and utility issues, must be overcome to realize the promise of medical big data as the fuel of a continuous learning healthcare system that will improve patient outcome and reduce waste in areas including nephrology.
Subfields: Artificial Intelligence, Health Informatics, Health Information Management
View Paper: https://www.semanticscholar.org/paper/433a6460a07ad6c2e24e8ef9c8d197b07303416d
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Health Informatics
In Health Information Management
Citations in the corpus
- Demystifying Membership Inference Attacks in Machine Learning as a Service (2019, unknown): “alarming, such as healthcare [41], e-commerce, banking, and government often deploy simpler model types, such as decision trees as model understanding is prioritized”
- Towards Demystifying Membership Inference Attacks (2018, background): “Additionally, areas where membership inference would be most alarming, such as healthcare [26], e-commerce, banking, and government often deploy simpler model types, such as decision trees as model understanding is prioritized for safe use of predictive services.”
- Artificial Intelligence and Machine Learning in Pathology: The Present Landscape of Supervised Methods (2019, background): “Data completeness and generalizability are other important considerations when developing and training AI/ML algorithms.(8) Unfortunately, despite the convenience of collecting real-world information from electronic health records, the retrieved medical data are often incomplete.”
- Concurrence of big data analytics and healthcare: A systematic review (2018, background): “Studies have demonstrated that Big Data analytics differ from traditional analytical approach in terms that instead of tracking care quality and outcomes in retrospective view by using deductive reasoning, it uses inductive reasoning for prospective analysis of data [91].”
- Deep neural network models for computational histopathology: A survey (2019, background): “, expert annotations) is a major bottleneck in achieving clinically satisfactory performance in medical imaging (Lee and Yoon, 2017).”