Review Paper on Machine learning-based prediction of Corona Virus

Effective contact tracing of SARS-CoV-2 enables quick and efficient diagnosis of COVID-19 and might mitigate the burden on healthcare system. Prediction models that combine several features to approximate the danger of infection are developed. These aim to help medical examiners worldwide in treatment of patients, especially within the context of limited healthcare resources. They established a machine learning approach that trained on records from 51,831 tested individuals (of whom 4769 were confirmed to own COVID-19 coronavirus). Test set contained data from the upcoming week (47,401 tested individuals of whom 3624 were confirmed to own COVID-19 disease). Their model predicted COVID-19 test results with highest accuracy using only eight binary features: sex, age ≥60 years, known contact with infected patients, and also the appearance of 5 initial clinical symptoms appeared. Generally, supported the nationwide data publicly reported by the Israeli Ministry of Health, they developed a model that detects COVID-19 cases by simple features accessed by asking basic inquiries to the affected patient. Their framework may be used, among other considerations, to prioritize testing for COVID-19 when testing resources are limited and important. Keywords: Machine Learning, SARS-COV-2, COVID-19, Coronavirus.

Classification of Imbalanced Data Represented as Binary Features

Typically, classification is conducted on a dataset that consists of numerical features and target classes. For instance, a grayscale image, which is usually represented as a matrix of integers varying from 0 to 255, enables one to apply various classification algorithms to image classification tasks. However, datasets represented as binary features cannot use many standard machine learning algorithms optimally, yet their amount is not negligible. On the other hand, oversampling algorithms such as synthetic minority oversampling technique (SMOTE) and its variants are often used if the dataset for classification is imbalanced. However, since SMOTE and its variants synthesize new minority samples based on the original samples, the diversity of the samples synthesized from binary features is highly limited due to the poor representation of original features. To solve this problem, a preprocessing approach is studied. By converting binary features into numerical ones using feature extraction methods, succeeding oversampling methods can fully display their potential in improving the classifiers’ performances. Through comprehensive experiments using benchmark datasets and real medical datasets, it was observed that a converted dataset consisting of numerical features is better for oversampling methods (maximum improvements of accuracy and F1-score were 35.11% and 42.17%, respectively). In addition, it is confirmed that feature extraction and oversampling synergistically contribute to the improvement of classification performance.

[18F]FDG PET/MRI enables early chemotherapy response prediction in pancreatic ductal adenocarcinoma

Purpose In this prospective exploratory study, we evaluated the feasibility of [18F]fluorodeoxyglucose ([18F]FDG) PET/MRI-based chemotherapy response prediction in pancreatic ductal adenocarcinoma at two weeks upon therapy onset. Material and methods In a mixed cohort, seventeen patients treated with chemotherapy in neoadjuvant or palliative intent were enrolled. All patients were imaged by [18F]FDG PET/MRI before and two weeks after onset of chemotherapy. Response per RECIST1.1 was then assessed at 3 months [18F]FDG PET/MRI-derived parameters (MTV50%, TLG50%, MTV2.5, TLG2.5, SUVmax, SUVpeak, ADCmax, ADCmean and ADCmin) were assessed, using multiple t-test, Man–Whitney-U test and Fisher’s exact test for binary features. Results At 72 ± 43 days, twelve patients were classified as responders and five patients as non-responders. An increase in ∆MTV50% and ∆ADC (≥ 20% and 15%, respectively) and a decrease in ∆TLG50% (≤ 20%) at 2 weeks after chemotherapy onset enabled prediction of responders and non-responders, respectively. Parameter combinations (∆TLG50% and ∆ADCmax or ∆MTV50% and ∆ADCmax) further improved discrimination. Conclusion Multiparametric [18F]FDG PET/MRI-derived parameters, in particular indicators of a change in tumor glycolysis and cellularity, may enable very early chemotherapy response prediction. Further prospective studies in larger patient cohorts are recommended to their clinical impact.

Clustering Results Interpretation of Continuous Variables Using Bayesian Inference

The present study is devoted to interpretable artificial intelligence in medicine. In our previous work we proposed an approach to clustering results interpretation based on Bayesian Inference. As an application case we used clinical pathways clustering explanation. However, the approach was limited by working for only binary features. In this work, we expand the functionality of the method and adapt it for modelling posterior distributions of continuous features. To solve the task, we apply BEST algorithm to provide Bayesian t-testing and use NUTS algorithm for posterior sampling. The general results of both binary and continuous interpretation provided by the algorithm have been compared with the interpretation of two medical experts.

Probabilistic Non-Negative Matrix Factorization with Binary Components

Non-negative matrix factorization is used to find a basic matrix and a weight matrix to approximate the non-negative matrix. It has proven to be a powerful low-rank decomposition technique for non-negative multivariate data. However, its performance largely depends on the assumption of a fixed number of features. This work proposes a new probabilistic non-negative matrix factorization which factorizes a non-negative matrix into a low-rank factor matrix with constraints and a non-negative weight matrix. In order to automatically learn the potential binary features and feature number, a deterministic Indian buffet process variational inference is introduced to obtain the binary factor matrix. Further, the weight matrix is set to satisfy the exponential prior. To obtain the real posterior distribution of the two factor matrices, a variational Bayesian exponential Gaussian inference model is established. The comparative experiments on the synthetic and real-world datasets show the efficacy of the proposed method.

Some Formal Implications of Deletion Saltation

In a phonological saltation alternation, a segment or class “skips” a relatively similar category to surface as something less similar, as when /ɡ/ alternates with [x], skipping [k]. White (2013) and Hayes and White (2015) argue that saltation is unnatural—difficult to learn in the laboratory and diachronically unstable. They propose that the phonological grammar includes a learning bias against such unnatural patterns. White and Hayes further demonstrate that Harmonic Grammar (HG; Legendre, Miyata, and Smolensky 1990) cannot model typical saltation without nondefault mechanisms that would require extra steps in acquisition, making HG consistent with their proposed learning bias. I identify deletion saltation as a distinct saltation subtype and show that HG, with faithfulness formalized in standard Correspondence Theory (CT; McCarthy and Prince 1995), can model this pattern. HG/CT thus predicts that deletion saltation, unlike typical (here called segment-scale) saltation, is natural. Other frameworks fail to distinguish the two saltation types—they can either model both types, or neither. Consequently, if future empirical work finds deletion saltation to be more natural than other saltation patterns, this would support weighted-constraint models such as HG over ranked-constraint models such as Optimality Theory (OT; Prince and Smolensky 1993, 2004); would support CT over the *MAP model of faithfulness (Zuraw 2013); and would support formalizing CT featural-faithfulness constraints in terms of IDENT constraints, binary features, or both.

Analysis of the effects of related fingerprints on molecular similarity using an eigenvalue entropy approach

Two-dimensional (2D) chemical fingerprints are widely used as binary features for the quantification of structural similarity of chemical compounds, which is an important step in similarity-based virtual screening (VS). Here, using an eigenvalue-based entropy approach, we identified 2D fingerprints with little to no contribution to shaping the eigenvalue distribution of the feature matrix as related ones and examined the degree to which these related 2D fingerprints influenced molecular similarity scores calculated with the Tanimoto coefficient. Our analysis identified many related fingerprints in publicly available fingerprint schemes and showed that their presence in the feature set could have substantial effects on the similarity scores and bias the outcome of molecular similarity analysis. Our results have implication in the optimal selection of 2D fingerprints for compound similarity analysis and the identification of potential hits for compounds with target biological activity in VS.

Machine learning-based prediction of COVID-19 diagnosis based on symptoms

Effective screening of SARS-CoV-2 enables quick and efficient diagnosis of COVID-19 and can mitigate the burden on healthcare systems. Prediction models that combine several features to estimate the risk of infection have been developed. These aim to assist medical staff worldwide in triaging patients, especially in the context of limited healthcare resources. We established a machine-learning approach that trained on records from 51,831 tested individuals (of whom 4769 were confirmed to have COVID-19). The test set contained data from the subsequent week (47,401 tested individuals of whom 3624 were confirmed to have COVID-19). Our model predicted COVID-19 test results with high accuracy using only eight binary features: sex, age ≥60 years, known contact with an infected individual, and the appearance of five initial clinical symptoms. Overall, based on the nationwide data publicly reported by the Israeli Ministry of Health, we developed a model that detects COVID-19 cases by simple features accessed by asking basic questions. Our framework can be used, among other considerations, to prioritize testing for COVID-19 when testing resources are limited.