Machine learning application for the prediction of SARS-CoV-2 infection using blood tests and chest radiograph.

Triaging and prioritising patients for RT-PCR test had been essential in the management of COVID-19 in resource-scarce countries. In this study, we applied machine learning (ML) to the task of detection of SARS-CoV-2 infection using basic laboratory markers. We performed the statistical analysis and trained an ML model on a retrospective cohort of 5148 patients from 24 hospitals in Hong Kong to classify COVID-19 and other aetiology of pneumonia. We validated the model on three temporal validation sets from different waves of infection in Hong Kong. For predicting SARS-CoV-2 infection, the ML model achieved high AUCs and specificity but low sensitivity in all three validation sets (AUC: 89.9-95.8%; Sensitivity: 55.5-77.8%; Specificity: 91.5-98.3%). When used in adjunction with radiologist interpretations of chest radiographs, the sensitivity was over 90% while keeping moderate specificity. Our study showed that machine learning model based on readily available laboratory markers could achieve high accuracy in predicting SARS-CoV-2 infection.

Distinct effects of beta-amyloid and tau on cortical thickness in cognitively healthy older adults.

INTRODUCTION: Published reports of associations between ß-amyloid (Aß) and cortical integrity conflict. Tau biomarkers may help elucidate the complex relationship between pathology and neurodegeneration in aging. METHODS: We measured cortical thickness using magnetic resonance imaging, Aß using Pittsburgh compound B positron emission tomography (PiB-PET), and tau using flortaucipir (FTP)-PET in 125 cognitively normal older adults. We examined relationships among PET measures, cortical thickness, and cognition. RESULTS: Cortical thickness was reduced in PiB+/FTP+ participants compared to the PiB+/FTP- and PiB-/FTP- groups. Continuous PiB associations with cortical thickness were weak but positive in FTP- participants and negative in FTP+. FTP strongly negatively predicted thickness regardless of PiB status. FTP was associated with memory and cortical thickness, and mediated the association of PiB with memory. DISCUSSION: Past findings linking Aß and cortical thickness are likely weak due to opposing effects of Aß on cortical thickness relative to tau burden. Tau, in contrast to Aß, is strongly related to cortical thickness and memory.

Dropout in Neural Networks Simulates the Paradoxical Effects of Deep Brain Stimulation on Memory.

Neuromodulation techniques such as deep brain stimulation (DBS) are a promising treatment for memory-related disorders including anxiety, addiction, and dementia. However, the outcomes of such treatments appear to be somewhat paradoxical, in that these techniques can both disrupt and enhance memory even when applied to the same brain target. In this article, we hypothesize that disruption and enhancement of memory through neuromodulation can be explained by the dropout of engram nodes. We used a convolutional neural network (CNN) to classify handwritten digits and letters and applied dropout at different stages to simulate DBS effects on engrams. We showed that dropout applied during training improved the accuracy of prediction, whereas dropout applied during testing dramatically decreased the accuracy of prediction, which mimics enhancement and disruption of memory, respectively. We further showed that transfer learning of neural networks with dropout had increased the accuracy and rate of learning. Dropout during training provided a more robust "skeleton" network and, together with transfer learning, mimicked the effects of chronic DBS on memory. Overall, we showed that the dropout of engram nodes is a possible mechanism by which neuromodulation techniques such as DBS can both disrupt and enhance memory, providing a unique perspective on this paradox.

Detection of COVID-19 Using Deep Learning Algorithms on Chest Radiographs.

PURPOSE: To evaluate the performance of a deep learning (DL) algorithm for the detection of COVID-19 on chest radiographs (CXR). MATERIALS AND METHODS: In this retrospective study, a DL model was trained on 112,120 CXR images with 14 labeled classifiers (ChestX-ray14) and fine-tuned using initial CXR on hospital admission of 509 patients, who had undergone COVID-19 reverse transcriptase-polymerase chain reaction (RT-PCR). The test set consisted of a CXR on presentation of 248 individuals suspected of COVID-19 pneumonia between February 16 and March 3, 2020 from 4 centers (72 RT-PCR positives and 176 RT-PCR negatives). The CXR were independently reviewed by 3 radiologists and using the DL algorithm. Diagnostic performance was compared with radiologists' performance and was assessed by area under the receiver operating characteristics (AUC). RESULTS: The median age of the subjects in the test set was 61 (interquartile range: 39 to 79) years (51% male). The DL algorithm achieved an AUC of 0.81, sensitivity of 0.85, and specificity of 0.72 in detecting COVID-19 using RT-PCR as the reference standard. On subgroup analyses, the model achieved an AUC of 0.79, sensitivity of 0.80, and specificity of 0.74 in detecting COVID-19 in patients presented with fever or respiratory systems and an AUC of 0.87, sensitivity of 0.85, and specificity of 0.81 in distinguishing COVID-19 from other forms of pneumonia. The algorithm significantly outperforms human readers (P<0.001 using DeLong test) with higher sensitivity (P=0.01 using McNemar test). CONCLUSIONS: A DL algorithm (COV19NET) for the detection of COVID-19 on chest radiographs can potentially be an effective tool in triaging patients, particularly in resource-stretched health-care systems.

Effect of machine learning re-sampling techniques for imbalanced datasets in 18F-FDG PET-based radiomics model on prognostication performance in cohorts of head and neck cancer patients.

PURPOSE: Biomedical data frequently contain imbalance characteristics which make achieving good predictive performance with data-driven machine learning approaches a challenging task. In this study, we investigated the impact of re-sampling techniques for imbalanced datasets in PET radiomics-based prognostication model in head and neck (HNC) cancer patients. METHODS: Radiomics analysis was performed in two cohorts of patients, including 166 patients newly diagnosed with nasopharyngeal carcinoma (NPC) in our centre and 182 HNC patients from open database. Conventional PET parameters and robust radiomics features were extracted for correlation analysis of the overall survival (OS) and disease progression-free survival (DFS). We investigated a cross-combination of 10 re-sampling methods (oversampling, undersampling, and hybrid sampling) with 4 machine learning classifiers for survival prediction. Diagnostic performance was assessed in hold-out test sets. Statistical differences were analysed using Monte Carlo cross-validations by post hoc Nemenyi analysis. RESULTS: Oversampling techniques like ADASYN and SMOTE could improve prediction performance in terms of G-mean and F-measures in minority class, without significant loss of F-measures in majority class. We identified optimal PET radiomics-based prediction model of OS (AUC of 0.82, G-mean of 0.77) for our NPC cohort. Similar findings that oversampling techniques improved the prediction performance were seen when this was tested on an external dataset indicating generalisability. CONCLUSION: Our study showed a significant positive impact on the prediction performance in imbalanced datasets by applying re-sampling techniques. We have created an open-source solution for automated calculations and comparisons of multiple re-sampling techniques and machine learning classifiers for easy replication in future studies.

Tau deposition is associated with functional isolation of the hippocampus in aging.

The tau protein aggregates in aging and Alzheimer disease and may lead to memory loss through disruption of medial temporal lobe (MTL)-dependent memory systems. Here, we investigated tau-mediated mechanisms of hippocampal dysfunction that underlie the expression of episodic memory decline using fMRI measures of hippocampal local coherence (regional homogeneity; ReHo), distant functional connectivity and tau-PET. We show that age and tau pathology are related to higher hippocampal ReHo. Functional disconnection between the hippocampus and other components of the MTL memory system, particularly an anterior-temporal network specialized for object memory, is also associated with higher hippocampal ReHo and greater tau burden in anterior-temporal regions. These associations are not observed in the posteromedial network, specialized for context/spatial information. Higher hippocampal ReHo predicts worse memory performance. These findings suggest that tau pathology plays a role in disconnecting the hippocampus from specific MTL memory systems leading to increased local coherence and memory decline.

Radiomics Model to Predict Early Progression of Nonmetastatic Nasopharyngeal Carcinoma after Intensity Modulation Radiation Therapy: A Multicenter Study.

PURPOSE: To examine the prognostic value of a machine learning model trained with pretreatment MRI radiomic features in the assessment of patients with nonmetastatic nasopharyngeal carcinoma (NPC) who are at risk for 3-year disease progression after intensity-modulated radiation therapy and to explain the radiomics features in the model. MATERIALS AND METHODS: A total of 277 patients with nonmetastatic NPC admitted between March 2008 and December 2014 at two imaging centers were retrospectively reviewed. Patients were allocated to a discovery or validation cohort based on where they underwent MRI (discovery cohort, n = 217; validation cohort, n = 60). A total of 525 radiomics features extracted from contrast material-enhanced T1- or T2-weighted MRI studies and five clinical features were subjected to radiomic machine learning modeling to predict 3-year disease progression. Feature selection was performed by analyzing robustness to resampling, reproducibility between observers, and redundancy. Features for the final model were selected with Kaplan-Meier analysis and the log-rank test. A support vector machine was used as the classifier for the model. To interpret the pattern learned from the model, Shapley additive explanations (SHAP) was applied. RESULTS: The final model yielded an area under the receiver operating characteristic curve of 0.80 in both the discovery (95% bootstrap confidence interval: 0.80, 0.81) and independent validation (95% bootstrap confidence interval: 0.73, 0.89) cohorts. Analysis with SHAP revealed that tumor shape sphericity, first-order mean absolute deviation, T stage, and overall stage were important factors in 3-year disease progression. CONCLUSION: These results add to the growing evidence of the role of radiomics in the assessment of NPC. By using explanatory techniques, such as SHAP, the complex interaction of features learned by the model may be understood.© RSNA, 2019Supplemental material is available for this article.