ABSTRACT
The global COVID-19 pandemic has demonstrated the urgent need for diagnostic tools that can be both readily applied and dynamically calibrated by non-specialists, in terms of a sensitivity/specificity tradeoff that complies with relevant healthcare policies and procedures. This article describes the design and deployment of a novel machine learning algorithm, Structural Machine Learning (SML), that combines memetic grammar-guided program synthesis with self-supervised learning in order to learn effectively from small data sets while remaining relatively resistant to overfitting. SML is used to construct a signal processing pipeline for audio time-series, which then serves as the diagnostic mechanism for a wide-spectrum, infrasound-to-ultrasound e-stethoscope. In blind trials supervised by a third party, SML is shown to be superior to Deep Learning approaches in terms of the area under the ROC curve, while allowing for transparent interpretation of the decision-making process.
- A.J. DeGrave, J.D. Janizek, and S.-I. Lee. 2021. AI for radiographic COVID-19 detection selects shortcuts over signal. Nature Machine Intelligence 3, 77 (Jul 2021), 610--619. Google ScholarCross Ref
- E.R. DeLong, D.M. DeLong, and D.L. Clarke-Pearson. 1988. Comparing the Areas under Two or More Correlated Receiver Operating Characteristic Curves: A Nonparametric Approach. Biometrics 44, 3 (1988), 837--845.Google ScholarCross Ref
- H.A. Haenssle et al. 2018. Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists. Annals of Oncology: Official Journal of the European Society for Medical Oncology 29, 8 (Aug 2018), 1836--1842.Google ScholarCross Ref
- J. De Fauw et al. 2018. Clinically applicable deep learning for diagnosis and referral in retinal disease. Nature Medicine 24, 9 (Sep 2018), 1342--1350.Google ScholarCross Ref
- K.F. Chung et al. 2022. Cough hypersensitivity and chronic cough. Nature Reviews. Disease Primers 8, 1 (30 June 2022), 45.Google ScholarCross Ref
- P. Rajpurkar et al. 2017. CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning. arXiv:1711.05225 [cs, stat] (Nov 2017).Google Scholar
- Center for Devices Health and Radiological. 2022. (AI/ML)-Enabled Medical Devices. https://tinyurl.com/ydz73a2wGoogle Scholar
- J. Laguarta, F. Hueto, and Subirana B. 2020. COVID-19 Artificial Intelligence Diagnosis Using Only Cough Recordings. IEEE Open Journal of Engineering in Medicine and Biology 1 (2020), 275--281.Google ScholarCross Ref
- A. Nguyen, J. Yosinski, and J. Clune. 2015. Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. In 2015 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). 427--436.Google Scholar
- V.N. Vapnik and Y. Alexey. 1971. Chervonenkis. On the uniform convergence of relative frequencies of events to their probabilities. Theory of Probability and its Applications 16, 2 (1971), 264--280.Google Scholar
- G. Volpicelli, A. Lamorte, and T. Villén. 2020. What's new in lung ultrasound during the COVID-19 pandemic. Intensive Care Medicine 46 (2020), 1445--1448.Google ScholarCross Ref
Index Terms
- Synthesizing Effective Diagnostic Models from Small Samples using Structural Machine Learning: a Case Study in Automating COVID-19 Diagnosis
Recommendations
Improve Computer-Aided Diagnosis With Machine Learning Techniques Using Undiagnosed Samples
In computer-aided diagnosis (CAD), machine learning techniques have been widely applied to learn a hypothesis from diagnosed samples to assist the medical experts in making a diagnosis. To learn a well-performed hypothesis, a large amount of diagnosed ...
Use of supervised machine learning to detect abuse of COVID-19 related domain names
AbstractA comprehensive evaluation of supervised machine learning models for COVID-19 related domain name detection is presented. One representative conventional machine learning implementation and nineteen state-of-the-art deep learning ...
Graphical abstractDisplay Omitted
Highlights- Supervised machine learning is studied to detect COVID-19 related domain names.
Machine Learning: The State of the Art
The two fundamental problems in machine learning (ML) are statistical analysis and algorithm design. The former tells us the principles of the mathematical models that we establish from the observation data. The latter defines the conditions on which ...
Comments