Explaining Support Vector Machines: A Color Based Nomogram

Belle, Vanya Van; Calster, Ben Van; Huffel, Sabine Van; Suykens, Johan A. K.; Lisboa, Paulo J. G.

doi:10.1371/journal.pone.0164568

Cited by 38 publications

(40 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This does not mean to say that efforts have not been made to imbue MDSS with knowledge representations that are comprehensible to humans. Examples include rule-based representations, usually compatible with medical reasoning [16]; and nomograms, commonly used by clinicians for visualizing the relative weights of symptoms on a diagnosis or a prognosis [17].…”

Section: Interpretability and Explainabilitymentioning

confidence: 99%

Societal Issues Concerning the Application of Artificial Intelligence in Medicine

Vellido

2018

Kidney Dis

View full text Add to dashboard Cite

Background: Medicine is becoming an increasingly data-centred discipline and, beyond classical statistical approaches, artificial intelligence (AI) and, in particular, machine learning (ML) are attracting much interest for the analysis of medical data. It has been argued that AI is experiencing a fast process of commodification. This characterization correctly reflects the current process of industrialization of AI and its reach into society. Therefore, societal issues related to the use of AI and ML should not be ignored any longer and certainly not in the medical domain. These societal issues may take many forms, but they all entail the design of models from a human-centred perspective, incorporating human-relevant requirements and constraints. In this brief paper, we discuss a number of specific issues affecting the use of AI and ML in medicine, such as fairness, privacy and anonymity, explainability and interpretability, but also some broader societal issues, such as ethics and legislation. We reckon that all of these are relevant aspects to consider in order to achieve the objective of fostering acceptance of AI- and ML-based technologies, as well as to comply with an evolving legislation concerning the impact of digital technologies on ethically and privacy sensitive matters. Our specific goal here is to reflect on how all these topics affect medical applications of AI and ML. This paper includes some of the contents of the “2nd Meeting of Science and Dialysis: Artificial Intelligence,” organized in the Bellvitge University Hospital, Barcelona, Spain. Summary and Key Messages: AI and ML are attracting much interest from the medical community as key approaches to knowledge extraction from data. These approaches are increasingly colonizing ambits of social impact, such as medicine and healthcare. Issues of social relevance with an impact on medicine and healthcare include (although they are not limited to) fairness, explainability, privacy, ethics and legislation.

show abstract

Section: Interpretability and Explainabilitymentioning

confidence: 99%

Societal Issues Concerning the Application of Artificial Intelligence in Medicine

Vellido

2018

Kidney Dis

View full text Add to dashboard Cite

show abstract

“…In our proposed system, four types of SVM‐based classifiers, namely linear SVM, quadratic SVM, Gaussian SVM, and cubic SVM, were used for the classification. SVM is regarded as one of the best supervised learning classifiers . Supposing the data

D = \{((),, {\overset{x}{true}}_{i}, y_{i}), i = 1 \dots N\}

and y i ∈ {−1, +1}, the SVM classifier is formulated as follows:

\begin{matrix} \min_{w, b, ξ} \frac{true}{1} {‖boldw‖}^{2} + C \sum_{i} {ξ_{i}}^{2} subject to : \\ y_{i} ((), w^{T} x_{i} + b) \geq 1 - ξ_{i}, ξ_{i} \geq 0, \forall i \end{matrix}

where C > 0 is the selected parameter and ξ comprises slack variables.…”

Section: Methodsmentioning

confidence: 99%

Cotton wool spots detection in diabetic retinopathy based on adaptive thresholding and ant colony optimization coupling support vector machine

Sreng

Maneerat

Hamamoto

et al. 2019

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

Diabetic retinopathy is the major issue of diabetes-induced blindness worldwide but is curable if detected in time. Cotton wool spots (CWSs) are the critical lesions of diabetic retinopathy, which indicate not only advanced nonproliferative but also preproliferative diabetic retinopathy. It is crucial to detect CWSs for grading the severity of diabetic retinopathy. By grading the severity of diabetic retinopathy accurately, the eye specialist can make an effective treatment plan to protect the patient's vision against blindness. CWSs detection remains challenging because of their uneven appearance, in which some CWSs are not clearly visible and some resemble hard exudates. This paper proposed an automatic CWS detection method based on adaptive thresholding and ant colony optimization (ACO) coupled with support vector machine (SVM). One-hundred and sixtytwo features from five feature sets, namely morphologies, first-order statistics, gray-level co-occurrence matrix, gray-level run length matrix, and lacunarity, are extracted, and then four feature selection methods,namely genetic algorithm, particle swarm optimization, stepwise method, and ACO, are coupled with SVM classifiers. The evaluation results of the proposed methods on local, standard diabetic retinopathy database calibration level 1, and high-resolution fundus image database datasets containing 319 images indicate that ACO coupling cubic SVM performs better than the other pairs with sensitivity 90.16%, specificity 97.92%, accuracy 96.96%, and area under receiver operating characteristic curve 97.19%. , since 2009. He is currently a Dean of the School of Information and Telecommunication Engineering, Tokai University. His current research interests include information design. Especially, he is interested in medical information, human interface design, and virtual reality. He has about 60 papers published in Transactions and Journals and about 85 papers presented at international conferences. Prof. Hamamoto is a member of the IEEE and many national societies in Japan. He also takes active part in national societies as a committee member. RonakornPanjaphongse (Non-member) received the M.D. degree from the Faculty of Medicine Siriraj Hospital, Bangkok, Thailand, in 2001. He is currently the Head of the Retinal Unit, Ophthalmology Department, Bhumibol Adulyadej Hospital, Royal Thai Air Force, Bangkok, Thailand. His interests include studies related to retinal diseases, especially in diabetic retinopathy, including applying artificial intelligence for medical imaging.

show abstract

“…Support vector machine is a supervised learning model with an associated learning algorithm that analyzes data used for classi cation and regression [19]. The objective of applying SVM is to nd the best line in two dimensions or the best hyperplane in more than two dimensions to help the space be separated into classes [19]. In the present study, recursive feature elimination was integrated with the SVM classi er…”

Section: Development Validation and Performance Of Ml-based Modelsmentioning

confidence: 99%

Predicting Prostate Cancer Upgrading of Biopsy Gleason Grade Group at Radical Prostatectomy Using Machine Learning-Assisted Decision-support Models

Tang

Peng

Wang

et al. 2020

Preprint

View full text Add to dashboard Cite

Objective: To develop a machine learning (ML)-assisted model capable of accurately predicting the probability of biopsy Gleason grade group upgrading before making treatment decisions by integrating multiple clinical characteristics.Materials and Methods: We retrospectively collected data from PCa (prostate cancer) patients who underwent systematic biopsy and radical prostatectomy from January 2015 to December 2019 at Tongji Hospital of Tongji Medical College, Huazhong University of Science and Technology. The study cohort was divided into training and testing datasets in a 70:30 ratio for further analysis. Four ML-assisted models were developed from 16 clinical features using logistic regression (LR), logistic regression optimized by Lasso regularization (Lasso-LR), random forest (RF) and support vector machine (SVM). The area under the curve (AUC) was applied to determine the model with the highest discrimination. Calibration plots were used to investigate the extent of over- or underestimation of predicted probabilities relative to the observed probabilities in models. Results: In total, 530 PCa patients were included, with 371 patients in the training dataset and 159 patients in the testing dataset. The Lasso-LR model showed good discrimination with an AUC, accuracy, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) of 0.776, 0.712, 0.679, 0.745, 0.730 and 0.695, respectively, followed by SVM (AUC 0.740, 95%CI: 0.690–0.790), LR (AUC 0.725, 95%CI: 0.674–0.776) and RF (AUC 0.666, 95%CI: 0.618–0.714). Validation of the model showed that the Lasso-LR model had the best discriminative power (AUC 0.735, 95%CI: 0.656–0.813), followed by SVM (AUC 0.723, 95%CI: 0.644–0.802), LR (AUC 0.697, 95%CI: 0.615–0.778) and RF (AUC 0.607, 95%CI: 0.531–0.684) in the testing dataset. Both the Lasso-LR and SVM models were well-calibrated. Conclusions: The Lasso-LR model had good discrimination in the prediction of patients at high risk of harboring incorrect Gleason grade group assignment, and the use of this model may be greatly beneficial to urologists in treatment planning, patient selection, and the decision-making process for PCa patients.

show abstract

Explaining Support Vector Machines: A Color Based Nomogram

Cited by 38 publications

References 38 publications

Societal Issues Concerning the Application of Artificial Intelligence in Medicine

Societal Issues Concerning the Application of Artificial Intelligence in Medicine

Cotton wool spots detection in diabetic retinopathy based on adaptive thresholding and ant colony optimization coupling support vector machine

Predicting Prostate Cancer Upgrading of Biopsy Gleason Grade Group at Radical Prostatectomy Using Machine Learning-Assisted Decision-support Models

Contact Info

Product

Resources

About