From Hume to Wuhan: An Epistemological Journey on the Problem of Induction in COVID-19 Machine Learning Models and its Impact Upon Medical Research

Vega, Carlos

doi:10.1109/access.2021.3095222

Cited by 8 publications

(5 citation statements)

References 53 publications

(52 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nobody questions the huge opportunities that Artificial Intelligence (AI) and ML bring to bioinformatics and computer-aided diagnosis [43], but these opportunities come with challenges [44][45][46][47]. The first is data, which needs to adhere to high-quality standards that vary from area to area.…”

Section: Data-centric Aimentioning

confidence: 99%

“…As Goyal et al note, the decision flows of computer-aided diagnosis solutions often differ from those of clinicians, hampering interpretability and inspection of the results [49] due to the black-box nature of ML models. From a design point of view, dividing the task into several sub-tasks (e.g., (1) detecting pathologies, then (2) diagnosing the disease from the pathologies) can ease both interpretability and maintenance [47].…”

Section: Models Interpretabilitymentioning

confidence: 99%

See 1 more Smart Citation

Analysis: Flawed Datasets of Monkeypox Skin Images

2023

Self Cite

View full text Add to dashboard Cite

The self-proclaimed first publicly available dataset of Monkeypox skin images consists of medically irrelevant images extracted from Google and photography repositories through a process denominated web-scrapping. Yet, this did not stop other researchers from employing it to build Machine Learning (ML) solutions aimed at computer-aided diagnosis of Monkeypox and other viral infections presenting skin lesions. Neither did it stop the reviewers or editors from publishing these subsequent works in peer-reviewed journals. Several of these works claimed extraordinary performance in the classification of Monkeypox, Chickenpox and Measles, employing ML and the aforementioned dataset. In this work, we analyse the initiator work that has catalysed the development of several ML solutions, and whose popularity is continuing to grow. Further, we provide a rebuttal experiment that showcases the risks of such methodologies, proving that the ML solutions do not necessarily obtain their performance from the features relevant to the diseases at issue.

show abstract

Section: Data-centric Aimentioning

confidence: 99%

Section: Models Interpretabilitymentioning

confidence: 99%

Analysis: Flawed Datasets of Monkeypox Skin Images

2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…Often models are designed in an end-to-end way that attempts to map input data with the final result with a single model. For instance, a medical imaging CAD system can be designed as a chain of several models, with the first dedicated to finding pathologies and the subsequent models mapping pathologies to diseases or conditions (e.g., through several one class classifiers) (Vega, 2021 ). This approach eases solution maintainance and increases interpretability, allowing inspection of the intermediate results.…”

Section: Limitations Associated With Machine Learning/deep Learningmentioning

confidence: 99%

Machine learning models for diagnosis and prognosis of Parkinson's disease using brain imaging: general overview, main challenges, and future directions

Cruz

Husch

Hutter

2023

Front. Aging Neurosci.

View full text Add to dashboard Cite

Parkinson's disease (PD) is a progressive and complex neurodegenerative disorder associated with age that affects motor and cognitive functions. As there is currently no cure, early diagnosis and accurate prognosis are essential to increase the effectiveness of treatment and control its symptoms. Medical imaging, specifically magnetic resonance imaging (MRI), has emerged as a valuable tool for developing support systems to assist in diagnosis and prognosis. The current literature aims to improve understanding of the disease's structural and functional manifestations in the brain. By applying artificial intelligence to neuroimaging, such as deep learning (DL) and other machine learning (ML) techniques, previously unknown relationships and patterns can be revealed in this high-dimensional data. However, several issues must be addressed before these solutions can be safely integrated into clinical practice. This review provides a comprehensive overview of recent ML techniques analyzed for the automatic diagnosis and prognosis of PD in brain MRI. The main challenges in applying ML to medical diagnosis and its implications for PD are also addressed, including current limitations for safe translation into hospitals. These challenges are analyzed at three levels: disease-specific, task-specific, and technology-specific. Finally, potential future directions for each challenge and future perspectives are discussed.

show abstract

“…DL is expected to provide more accurate, faster and objective (in that it reports quantitative analysis) diagnosis [12]. However, these systems might fail to translate into real-world scenarios, presenting multiple challenges for safe applications [19]. It has been reported that ML-based health systems produce systematic errors on patient subgroup classification, consequently generating wrong predictions and flawed risk estimations [21].…”

Section: Introductionmentioning

confidence: 99%

The effect of dataset confounding on predictions of deep neural networks for medical imaging

Cruz

Husch²,

Hutter³

2022

nldl

View full text Add to dashboard Cite

The use of Convolutional Neural Networks (CNN) in medical imaging has often outperformed previous solutions and even specialists, becoming a promising technology for Computer-aidedDiagnosis (CAD) systems. However, recent works suggested that CNN may have poor generalisation on new data, for instance, generated in different hospitals. Uncontrolled confounders have been proposed as a common reason. In this paper, we experimentally demonstrate the impact of confounding data in unknown scenarios. We assessed the effect of four confounding configurations: total, strong, light and balanced. We found the confounding effect is especially prominent in total confounder scenarios, while the effect on light and strong confounding scenarios may depend on the dataset robustness. Our findings indicate that the confounding effect is independent of the architecture employed. These findings might explain why models can report good metrics during the development stage but fail to translate to real-world settings. We highlight the need for thorough consideration of these commonly unattended aspects, to develop safer CNN-based CAD systems.

show abstract

From Hume to Wuhan: An Epistemological Journey on the Problem of Induction in COVID-19 Machine Learning Models and its Impact Upon Medical Research

Cited by 8 publications

References 53 publications

Analysis: Flawed Datasets of Monkeypox Skin Images

Analysis: Flawed Datasets of Monkeypox Skin Images

Machine learning models for diagnosis and prognosis of Parkinson's disease using brain imaging: general overview, main challenges, and future directions

The effect of dataset confounding on predictions of deep neural networks for medical imaging

Contact Info

Product

Resources

About