Uncovering the prognostic gene signatures for the improvement of risk stratification in cancers by using deep learning algorithm coupled with wavelet transform

Objective.To test the hypothesis that a multicenter-validated computer deep learning algorithm detects MRI-negative focal cortical dysplasia (FCD).Methods.We used clinically-acquired 3D T1-weighted and 3D FLAIR MRI of 148 patients (median age, 23 years [range, 2-55]; 47% female) with histologically-verified FCD at nine centers to train a deep convolutional neural network (CNN) classifier. Images were initially deemed as MRI-negative in 51% of cases, in whom intracranial EEG determined the focus. For risk stratification, the CNN incorporated Bayesian uncertainty estimation as a measure of confidence. To evaluate performance, detection maps were compared to expert FCD manual labels. Sensitivity was tested in an independent cohort of 23 FCD cases (13±10 years). Applying the algorithm to 42 healthy and 89 temporal lobe epilepsy disease controls tested specificity.Results.Overall sensitivity was 93% (137/148 FCD detected) using a leave-one-site-out cross-validation, with an average of six false positives per patient. Sensitivity in MRI-negative FCD was 85%. In 73% of patients, the FCD was among the clusters with the highest confidence; in half it ranked the highest. Sensitivity in the independent cohort was 83% (19/23; average of five false positives per patient). Specificity was 89% in healthy and disease controls.Conclusions.This first multicenter-validated deep learning detection algorithm yields the highest sensitivity to date in MRI-negative FCD. By pairing predictions with risk stratification this classifier may assist clinicians to adjust hypotheses relative to other tests, increasing diagnostic confidence. Moreover, generalizability across age and MRI hardware makes this approach ideal for pre-surgical evaluation of MRI-negative epilepsy.Classification of evidence.This study provides Class III evidence that deep learning on multimodal MRI accurately identifies FCD in epilepsy patients initially diagnosed as MRI-negative.

Download Full-text

Risk Score Stratification of Alzheimer’s Disease and Mild Cognitive Impairment using Deep Learning

10.1101/2020.11.09.20226746 ◽

2020 ◽

Author(s):

Sanjay Nagaraj ◽

Tim Q Duong

Keyword(s):

Alzheimer’S Disease ◽

Deep Learning ◽

Cognitive Impairment ◽

Mild Cognitive Impairment ◽

Risk Stratification ◽

Risk Score ◽

Learning Algorithm ◽

Clinical Variables ◽

Deep Learning Algorithm ◽

Neurocognitive Tests

ABSTRACTAlzheimer Disease (AD) is a progressive neurodegenerative disease that can significantly impair cognition and memory. AD is the leading cause of dementia and affects one in ten people age 65 and older. Current diagnoses methods of AD heavily rely on the use of Magnetic Resonance Imaging (MRI) since non-imaging methods can vary widely leading to inaccurate diagnoses. Furthermore, recent research has revealed a substage of AD, Mild Cognitive Impairment (MCI), that is characterized by symptoms between normal cognition and dementia which makes it more prone to misdiagnosis.A large battery of clinical variables are currently used to detect cognitive impairment and classify early mild cognitive impairment (EMCI), late mild cognitive impairment (LMCI), and AD from cognitive normal (CN) patients. The goal of this study was to derive a simplified risk-stratification algorithm for diagnosis and identify a few significant clinical variables that can accurately classify these four groups using an empirical deep learning approach. Over 100 variables that included neuropsychological/neurocognitive tests, demographics, genetic factors, and blood biomarkers were collected from EMCI, LMCI, AD, and CN patients from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. Feature engineering was performed with 5 different methods and a neural network was trained on 90% of the data and tested on 10% using 10-fold cross validation. Prediction performance used area under the curve (AUC) of the receiver operating characteristic analysis.The five different feature selection methods consistently yielded the top classifiers to be the Clinical Dementia Rating Scale - Sum of Boxes (CDRSB), Delayed total recall (LDELTOTAL), Modified Preclinical Alzheimer Cognitive Composite with Trails test (mPACCtrailsB), the Modified Preclinical Alzheimer Cognitive Composite with Digit test (mPACCdigit), and Mini-Mental State Examination (MMSE). The best classification model yielded an AUC of 0.984, and the simplified risk-stratification score yielded an AUC of 0.963 on the test dataset.Our results show that this deep-learning algorithm and simplified risk score derived from our deep-learning algorithm accurately diagnose EMCI, LMCI, AD and CN patients using a few commonly available neurocognitive tests. The project was successful in creating an accurate, clinically translatable risk-stratified scoring aid for primary care providers to diagnose AD in a fast and inexpensive manner.

Download Full-text

Detecting faults in VSC-HVDC systems by deep learning and K-means

Recent Advances in Electrical & Electronic Engineering (Formerly Recent Patents on Electrical & Electronic Engineering) ◽

10.2174/2352096513999201105155206 ◽

2020 ◽

Vol 13 ◽

Author(s):

Roohollah Sadeghi Goughari ◽

Mehdi Jafari Shahbazzadeh ◽

Mahdiyeh Eslami

Keyword(s):

Signal Processing ◽

Deep Learning ◽

Wavelet Transform ◽

Transmission Lines ◽

Fault Location ◽

Learning Algorithm ◽

Hvdc Transmission ◽

Deep Learning Algorithm ◽

Processing Techniques ◽

Signal Processing Techniques

Background: In this paper, two methods and their comparison used to determine the fault locaton in VSC-HVDC transmission lines. Fast and reliable control are features of these systems. Methods: Additionally, wavelet transform from advanced techniques of signal processing is employed for the purpose of extracting important characteristics of fault signal from both sides of the line by PMU. To do so, Deep learning is used to identify the relation between the extracted features from wavelet analysis of the fault current and variations under fault conditions. As such, wavelet transform and advanced signal processing techniques are used to extract important features of fault signal from both sides of the line by the PMU. Results: The results show the high accuracy of finding fault location by the deep learning algorithm method compared to the k-means algorithm with an error rate of <1%. Conclusion: Studies on the 50 kV VSC-HVDC transmission line with a length of 25 km in MATLAB have been simulated.

Download Full-text

Accuracy of Deep-learning Algorithm for Detection and Risk Stratification of Lung Nodules

Case Medical Research ◽

10.31525/ct1-nct04022512 ◽

2019 ◽

Author(s):

Keyword(s):

Deep Learning ◽

Risk Stratification ◽

Learning Algorithm ◽

Lung Nodules ◽

Deep Learning Algorithm

Download Full-text

The Forecasting of PM2.5 Using a Hybrid Model Based on Wavelet Transform and an Improved Deep Learning Algorithm

IEEE Access ◽

10.1109/access.2019.2944755 ◽

2019 ◽

Vol 7 ◽

pp. 142814-142825 ◽

Cited By ~ 56

Author(s):

Weibiao Qiao ◽

Wencai Tian ◽

Yu Tian ◽

Quan Yang ◽

Yining Wang ◽

...

Keyword(s):

Deep Learning ◽

Wavelet Transform ◽

Hybrid Model ◽

Learning Algorithm ◽

Model Based ◽

Deep Learning Algorithm

Download Full-text

Using wavelet transform and dynamic time warping to identify the limitations of the CNN model as an air quality forecasting system

10.5194/gmd-2019-346 ◽

2020 ◽

Author(s):

Ebrahim Eslami ◽

Yunsoo Choi ◽

Yannic Lops ◽

Alqamah Sayeed ◽

Ahmed Khan Salman

Keyword(s):

Deep Learning ◽

Wavelet Transform ◽

Air Quality ◽

Dynamic Time Warping ◽

Learning Algorithm ◽

Post Processing ◽

Time Warping ◽

Deep Learning Algorithm ◽

Dynamic Time ◽

Air Quality Forecasting

Abstract. As the deep learning algorithm has become a popular data analytic technique, atmospheric scientists should have a balanced perception of its strengths and limitations so that they can provide a powerful analysis of complex data with well-established procedures. Despite the enormous success of the algorithm in numerous applications, certain issues related to its applications in air quality forecasting (AQF) require further analysis and discussion. This study addresses significant limitations of an advanced deep learning algorithm, the convolutional neural network (CNN), in two common applications: (i) a real-time AQF model, and (ii) a post-processing tool in a dynamical AQF model, the Community Multi-scale Air Quality Model (CMAQ). In both cases, the CNN model shows promising accuracy for ozone prediction 24 hours in advance in both the United States and South Korea (with an overall index of agreement exceeding 0.8). For the first case, we use the wavelet transform to determine the reasons behind the poor performance of CNN during the nighttime, cold months, and high ozone episodes. We find that when fine wavelet modes (hourly and daily) are relatively weak or when coarse wavelet modes (weekly) are strong, the CNN model produces less accurate forecasts. For the second case, we use the dynamic time warping (DTW) distance analysis to compare post-processed results with their CMAQ counterparts (as a base model). For CMAQ results that show a consistent DTW distance from the observation, the post-processing approach properly addresses the modeling bias with predicted IOAs exceeding 0.85. When the DTW distance of CMAQ-vs-observation is irregular, the post-processing approach is unlikely to perform satisfactorily. Awareness of the limitations in CNN models will enable scientists to develop more accurate regional or local air quality forecasting systems by identifying the affecting factors in high concentration episodes.

Download Full-text

Using wavelet transform and dynamic time warping to identify the limitations of the CNN model as an air quality forecasting system

Geoscientific Model Development ◽

10.5194/gmd-13-6237-2020 ◽

2020 ◽

Vol 13 (12) ◽

pp. 6237-6251

Author(s):

Ebrahim Eslami ◽

Yunsoo Choi ◽

Yannic Lops ◽

Alqamah Sayeed ◽

Ahmed Khan Salman

Keyword(s):

Deep Learning ◽

Wavelet Transform ◽

Air Quality ◽

Dynamic Time Warping ◽

Learning Algorithm ◽

Post Processing ◽

Time Warping ◽

Deep Learning Algorithm ◽

Dynamic Time ◽

Air Quality Forecasting

Abstract. As the deep learning algorithm has become a popular data analysis technique, atmospheric scientists should have a balanced perception of its strengths and limitations so that they can provide a powerful analysis of complex data with well-established procedures. Despite the enormous success of the algorithm in numerous applications, certain issues related to its applications in air quality forecasting (AQF) require further analysis and discussion. This study addresses significant limitations of an advanced deep learning algorithm, the convolutional neural network (CNN), in two common applications: (i) a real-time AQF model and (ii) a post-processing tool in a dynamical AQF model, the Community Multi-scale Air Quality Model (CMAQ). In both cases, the CNN model shows promising accuracy for ozone prediction 24 h in advance in both the United States of America and South Korea (with an overall index of agreement exceeding 0.8). For the first case, we use the wavelet transform to determine the reasons behind the poor performance of CNN during the nighttime, cold months, and high-ozone episodes. We find that when fine wavelet modes (hourly and daily) are relatively weak or when coarse wavelet modes (weekly) are strong, the CNN model produces less accurate forecasts. For the second case, we use the dynamic time warping (DTW) distance analysis to compare post-processed results with their CMAQ counterparts (as a base model). For CMAQ results that show a consistent DTW distance from the observation, the post-processing approach properly addresses the modeling bias with predicted indexes of agreement exceeding 0.85. When the DTW distance of CMAQ versus observation is irregular, the post-processing approach is unlikely to perform satisfactorily. Awareness of the limitations in CNN models will enable scientists to develop more accurate regional or local air quality forecasting systems by identifying the affecting factors in high-concentration episodes.

Download Full-text

Deep learning diagnostic and risk-stratification pattern detection for COVID-19 in digital lung auscultations: clinical protocol for a case–control and prospective cohort study

BMC Pulmonary Medicine ◽

10.1186/s12890-021-01467-w ◽

2021 ◽

Vol 21 (1) ◽

Cited By ~ 1

Author(s):

Alban Glangetas ◽

Mary-Anne Hartley ◽

Aymeric Cantais ◽

Delphine S. Courvoisier ◽

David Rivollet ◽

...

Keyword(s):

Deep Learning ◽

Risk Stratification ◽

Learning Algorithm ◽

Signs And Symptoms ◽

Support Vector ◽

Nasopharyngeal Swab ◽

University Hospitals ◽

Deep Learning Algorithm ◽

Audio Recordings ◽

Lung Auscultation

Abstract Background Lung auscultation is fundamental to the clinical diagnosis of respiratory disease. However, auscultation is a subjective practice and interpretations vary widely between users. The digitization of auscultation acquisition and interpretation is a particularly promising strategy for diagnosing and monitoring infectious diseases such as Coronavirus-19 disease (COVID-19) where automated analyses could help decentralise care and better inform decision-making in telemedicine. This protocol describes the standardised collection of lung auscultations in COVID-19 triage sites and a deep learning approach to diagnostic and prognostic modelling for future incorporation into an intelligent autonomous stethoscope benchmarked against human expert interpretation. Methods A total of 1000 consecutive, patients aged ≥ 16 years and meeting COVID-19 testing criteria will be recruited at screening sites and amongst inpatients of the internal medicine department at the Geneva University Hospitals, starting from October 2020. COVID-19 is diagnosed by RT-PCR on a nasopharyngeal swab and COVID-positive patients are followed up until outcome (i.e., discharge, hospitalisation, intubation and/or death). At inclusion, demographic and clinical data are collected, such as age, sex, medical history, and signs and symptoms of the current episode. Additionally, lung auscultation will be recorded with a digital stethoscope at 6 thoracic sites in each patient. A deep learning algorithm (DeepBreath) using a Convolutional Neural Network (CNN) and Support Vector Machine classifier will be trained on these audio recordings to derive an automated prediction of diagnostic (COVID positive vs negative) and risk stratification categories (mild to severe). The performance of this model will be compared to a human prediction baseline on a random subset of lung sounds, where blinded physicians are asked to classify the audios into the same categories. Discussion This approach has broad potential to standardise the evaluation of lung auscultation in COVID-19 at various levels of healthcare, especially in the context of decentralised triage and monitoring. Trial registration: PB_2016-00500, SwissEthics. Registered on 6 April 2020.

Download Full-text