Deep Neural Network for Predicting Diabetic Retinopathy from Risk Factors

Extracting information from individual risk factors provides an effective way to identify diabetes risk and associated complications, such as retinopathy, at an early stage. Deep learning and machine learning algorithms are being utilized to extract information from individual risk factors to improve early-stage diagnosis. This study proposes a deep neural network (DNN) combined with recursive feature elimination (RFE) to provide early prediction of diabetic retinopathy (DR) based on individual risk factors. The proposed model uses RFE to remove irrelevant features and DNN to classify the diseases. A publicly available dataset was utilized to predict DR during initial stages, for the proposed and several current best-practice models. The proposed model achieved 82.033% prediction accuracy, which was a significantly better performance than the current models. Thus, important risk factors for retinopathy can be successfully extracted using RFE. In addition, to evaluate the proposed prediction model robustness and generalization, we compared it with other machine learning models and datasets (nephropathy and hypertension–diabetes). The proposed prediction model will help improve early-stage retinopathy diagnosis based on individual risk factors.

Download Full-text

Classification among Microaneurysms, Exudates, and Lesion free Retinal Regions in the Eye Images using Transfer Learned CNNs

International Journal of Engineering and Advanced Technology - Regular Issue ◽

10.35940/ijeat.b4539.129219 ◽

2019 ◽

Vol 9 (2) ◽

pp. 5508-5512

Keyword(s):

Neural Network ◽

Machine Learning ◽

Diabetic Retinopathy ◽

Glucose Level ◽

Vision Loss ◽

Early Stage ◽

Training Data ◽

Fundus Images ◽

Diabetic Mellitus ◽

Start Process

When pancreas fails to secrete sufficient insulin in the human body, the glucose level in blood either becomes too high or too low. This fluctuation in glucose level affects different body organs such as kidney, brain, and eye. When the complications start appearing in the eyes due to Diabetic Mellitus (DM), it is called Diabetic Retinopathy (DR). DR can be categorized in several classes based on the severity, it can be Microaneurysms (ME), Haemorrhages (HE), Hard and Soft Exudates (EX and SE). DR is a slow start process that starts with very mild symptoms, becomes moderate with the time and results in complete vision loss, if not detected on time. Early-stage detection may greatly bolster in vision loss. However, it is impassable to detect the symptoms of DR with naked eyes. Ophthalmologist harbor to the several approaches and algorithm which makes use of different Machine Learning (ML) methods and classifiers to overcome this disease. The burgeoning insistence of Convolutional Neural Network (CNN) and their advancement in extracting features from different fundus images captivate several researchers to strive on it. Transfer Learning (TL) techniques help to use pre-trained CNN on a dataset that has finite training data, especially that in under developing countries. In this work, we propose several CNN architecture along with distinct classifiers which segregate the different lesions (ME and EX) in DR images with very eye-catching accuracies.

Download Full-text

Prediction of incident myocardial infarction using machine learning applied to harmonized electronic health record data

BMC Medical Informatics and Decision Making ◽

10.1186/s12911-020-01268-x ◽

2020 ◽

Vol 20 (1) ◽

Author(s):

Divneet Mandair ◽

Premanand Tiwari ◽

Steven Simon ◽

Kathryn L. Colborn ◽

Michael A. Rosenberg

Keyword(s):

Neural Network ◽

Machine Learning ◽

Risk Factors ◽

Myocardial Infarction ◽

Logistic Regression ◽

Large Scale ◽

Deep Neural Network ◽

Low Frequency ◽

Common Data Model ◽

Electronic Health Record Data

Abstract Background With cardiovascular disease increasing, substantial research has focused on the development of prediction tools. We compare deep learning and machine learning models to a baseline logistic regression using only ‘known’ risk factors in predicting incident myocardial infarction (MI) from harmonized EHR data. Methods Large-scale case-control study with outcome of 6-month incident MI, conducted using the top 800, from an initial 52 k procedures, diagnoses, and medications within the UCHealth system, harmonized to the Observational Medical Outcomes Partnership common data model, performed on 2.27 million patients. We compared several over- and under- sampling techniques to address the imbalance in the dataset. We compared regularized logistics regression, random forest, boosted gradient machines, and shallow and deep neural networks. A baseline model for comparison was a logistic regression using a limited set of ‘known’ risk factors for MI. Hyper-parameters were identified using 10-fold cross-validation. Results Twenty thousand Five hundred and ninety-one patients were diagnosed with MI compared with 2.25 million who did not. A deep neural network with random undersampling provided superior classification compared with other methods. However, the benefit of the deep neural network was only moderate, showing an F1 Score of 0.092 and AUC of 0.835, compared to a logistic regression model using only ‘known’ risk factors. Calibration for all models was poor despite adequate discrimination, due to overfitting from low frequency of the event of interest. Conclusions Our study suggests that DNN may not offer substantial benefit when trained on harmonized data, compared to traditional methods using established risk factors for MI.

Download Full-text

PROUD-MAL: static analysis-based progressive framework for deep unsupervised malware classification of windows portable executable

Complex & Intelligent Systems ◽

10.1007/s40747-021-00560-1 ◽

2021 ◽

Author(s):

Syed Khurram Jah Rizvi ◽

Warda Aslam ◽

Muhammad Shahzad ◽

Shahzad Saleem ◽

Muhammad Moazam Fraz

Keyword(s):

Neural Network ◽

Machine Learning ◽

Static Analysis ◽

Deep Neural Network ◽

Early Stage ◽

Malware Detection ◽

Machine Learning Algorithms ◽

Organizational Network ◽

Depth Analysis ◽

Feature Attention

AbstractEnterprises are striving to remain protected against malware-based cyber-attacks on their infrastructure, facilities, networks and systems. Static analysis is an effective approach to detect the malware, i.e., malicious Portable Executable (PE). It performs an in-depth analysis of PE files without executing, which is highly useful to minimize the risk of malicious PE contaminating the system. Yet, instant detection using static analysis has become very difficult due to the exponential rise in volume and variety of malware. The compelling need of early stage detection of malware-based attacks significantly motivates research inclination towards automated malware detection. The recent machine learning aided malware detection approaches using static analysis are mostly supervised. Supervised malware detection using static analysis requires manual labelling and human feedback; therefore, it is less effective in rapidly evolutionary and dynamic threat space. To this end, we propose a progressive deep unsupervised framework with feature attention block for static analysis-based malware detection (PROUD-MAL). The framework is based on cascading blocks of unsupervised clustering and features attention-based deep neural network. The proposed deep neural network embedded with feature attention block is trained on the pseudo labels. To evaluate the proposed unsupervised framework, we collected a real-time malware dataset by deploying low and high interaction honeypots on an enterprise organizational network. Moreover, endpoint security solution is also deployed on an enterprise organizational network to collect malware samples. After post processing and cleaning, the novel dataset consists of 15,457 PE samples comprising 8775 malicious and 6681 benign ones. The proposed PROUD-MAL framework achieved an accuracy of more than 98.09% with better quantitative performance in standard evaluation parameters on collected dataset and outperformed other conventional machine learning algorithms. The implementation and dataset are available at https://bit.ly/35Sne3a.

Download Full-text

A 10-Year Probability Deep Neural Network Prediction Model for Lung Cancer

Cancers ◽

10.3390/cancers13040928 ◽

2021 ◽

Vol 13 (4) ◽

pp. 928

Author(s):

Hsiu-An Lee ◽

Louis R. Chao ◽

Chien-Yeh Hsu

Keyword(s):

Neural Network ◽

Lung Cancer ◽

Prediction Model ◽

Deep Neural Network ◽

Clinical Decision Making ◽

Stochastic Gradient Descent ◽

Research Database ◽

Proposed Model ◽

Neural Network Prediction ◽

Network Prediction

Cancer is the leading cause of death in Taiwan. According to the Cancer Registration Report of Taiwan’s Ministry of Health and Welfare, a total of 13,488 people suffered from lung cancer in 2016, making it the second-most common cancer and the leading cancer in men. Compared with other types of cancer, the incidence of lung cancer is high. In this study, the National Health Insurance Research Database (NHIRDB) was used to determine the diseases and symptoms associated with lung cancer, and a 10-year probability deep neural network prediction model for lung cancer was developed. The proposed model could allow patients with a high risk of lung cancer to receive an earlier diagnosis and support the physicians’ clinical decision-making. The study was designed as a cohort study. The subjects were patients who were diagnosed with lung cancer between 2000 and 2009, and the patients’ disease histories were back-tracked for a period, extending to ten years before the diagnosis of lung cancer. As a result, a total of 13 diseases were selected as the predicting factors. A nine layers deep neural network model was created to predict the probability of lung cancer, depending on the different pre-diagnosed diseases, and to benefit the earlier detection of lung cancer in potential patients. The model is trained 1000 times, the batch size is set to 100, the SGD (Stochastic gradient descent) optimizer is used, the learning rate is set to 0.1, and the momentum is set to 0.1. The proposed model showed an accuracy of 85.4%, a sensitivity of 72.4% and a specificity of 85%, as well as an 87.4% area under ROC (AUROC) (95%, 0.8604–0.8885) model precision. Based on data analysis and deep learning, our prediction model discovered some features that had not been previously identified by clinical knowledge. This study tracks a decade of clinical diagnostic records to identify possible symptoms and comorbidities of lung cancer, allows early prediction of the disease, and assists more patients with early diagnosis.

Download Full-text

Machine Learning Can Predict Deaths in Patients with Diverticulitis During their Hospital Stay

10.1101/2020.02.04.20020222 ◽

2020 ◽

Cited By ~ 1

Author(s):

Fahad Shabbir Ahmed ◽

Raza-Ul-Mustafa ◽

Liaqat Ali ◽

Imad-ud-Deen ◽

Tahir Hameed ◽

...

Keyword(s):

Neural Network ◽

Machine Learning ◽

Risk Factors ◽

At Risk ◽

Logistic Regression ◽

Deep Neural Network ◽

Statistical Significance ◽

Significant Risk ◽

Premature Death ◽

Second Phase

ABSTRACTIntroductionDiverticulitis is the inflammation and/or infection of small pouches known as diverticula that develop along the walls of the intestines. Patients with diverticulitis are at risk of mortality as high as 17% with abscess formation and 45% with secondary perforation, especially patients that get admitted to the inpatient services are at risk of complications including mortality. We developed a deep neural networks (DNN) based machine learning framework that could predict premature death in patients that are admitted with diverticulitis using electronic health records (EHR) to calculate the statistically significant risk factors first and then to apply deep neural network.MethodsOur proposed framework (Deep FLAIM) is a two-phase hybrid works framework. In the first phase, we used National In-patient Sample 2014 dataset to extract patients with diverticulitis patients with and without hemorrhage with the ICD-9 codes 562.11 and 562.13 respectively and analyzed these patients for different risk factors for statistical significance with univariate and multivariate analyses to generate hazard ratios, to rank the diverticulitis associated risk factors. In the second phase, we applied deep neural network model to predict death. Additionally, we have compared the performance of our proposed system by using the popular machine learning models such as DNN and Logistic Regression (LR).ResultsA total of 128,258 patients were used, we tested 64 different variables for using univariate and multivariate (age, gender and ethnicity) cox-regression for significance only 16 factors were statistically significant for both univariate and multivariate analysis. The mortality prediction for our DNN out-performed the conventional machine learning (logistic regression) in terms of AUC (0.977 vs 0.904), training accuracy (0.931 vs 0.900), testing accuracy (0.930 vs 0.910), sensitivity (90% vs 88%) and specificity (95% vs 93%).ConclusionOur Deep FLAIM Framework can predict mortality in patients admitted to the hospital with diverticulitis with high accuracy. The proposed framework can be expanded to predict premature death for other disease.

Download Full-text

Anomaly Detection Approach Based on Deep Neural Network and Dropout

Baghdad Science Journal ◽

10.21123/bsj.2020.17.2(si).0701 ◽

2020 ◽

Vol 17 (2(SI)) ◽

pp. 0701

Author(s):

Zaid Hussien et al.

Keyword(s):

Neural Network ◽

Feature Selection ◽

Intrusion Detection ◽

Anomaly Detection ◽

Deep Neural Network ◽

Detection System ◽

Early Stage ◽

High Detection Rate ◽

Network Intrusion ◽

Proposed Model

Regarding to the computer system security, the intrusion detection systems are fundamental components for discriminating attacks at the early stage. They monitor and analyze network traffics, looking for abnormal behaviors or attack signatures to detect intrusions in early time. However, many challenges arise while developing flexible and efficient network intrusion detection system (NIDS) for unforeseen attacks with high detection rate. In this paper, deep neural network (DNN) approach was proposed for anomaly detection NIDS. Dropout is the regularized technique used with DNN model to reduce the overfitting. The experimental results applied on NSL_KDD dataset. SoftMax output layer has been used with cross entropy loss function to enforce the proposed model in multiple classification, including five labels, one is normal and four others are attacks (Dos, R2L, U2L and Probe). Accuracy metric was used to evaluate the model performance. The proposed model accuracy achieved to 99.45%. Commonly the recognition time is reduced in the NIDS by using feature selection technique. The proposed DNN classifier implemented with feature selection algorithm, and obtained on accuracy reached to 99.27%.

Download Full-text

Predicting mortality in SARS-COV-2 (COVID-19) positive patients in the inpatient setting using a Novel Deep Neural Network

10.1101/2020.12.13.20247254 ◽

2020 ◽

Author(s):

Maleeha Naseem ◽

Hajra Arshad ◽

Syeda Amrah Hashimi ◽

Furqan Irfan ◽

Fahad Shabbir Ahmed

Keyword(s):

Neural Network ◽

Machine Learning ◽

Risk Factors ◽

Deep Neural Network ◽

Multivariate Analyses ◽

High Accuracy ◽

Inpatient Setting ◽

Learning Models ◽

Rt Pcr ◽

Machine Learning Models

ABSTRACTBackgroundThe second wave of COVID-19 pandemic is anticipated to be worse than the initial one and will strain the healthcare systems even more during the winter months. Our aim was to develop a machine learning-based model to predict mortality using the deep learning Neo-V framework. We hypothesized this novel machine learning approach could be applied to COVID-19 patients to predict mortality successfully with high accuracy.MethodsThe current Deep-Neo-V model is built on our previously statistically rigorous machine learning framework [Fahad-Liaqat-Ahmad Intensive Machine (FLAIM) framework] that evaluated statistically significant risk factors, generated new combined variables and then supply these risk factors to deep neural network to predict mortality in RT-PCR positive COVID-19 patients in the inpatient setting. We analyzed adult patients (≥18 years) admitted to the Aga Khan University Hospital, Pakistan with a working diagnosis of COVID-19 infection (n=1228). We excluded patients that were negative on COVID-19 on RT-PCR, had incomplete or missing health records. The first phase selection of risk factor was done using Cox-regression univariate and multivariate analyses. In the second phase, we generated new variables and tested those statistically significant for mortality and in the third and final phase we applied deep neural networks and other traditional machine learning models like Decision Tree Model, k-nearest neighbor models and others.ResultsA total of 1228 cases were diagnosed as COVID-19 infection, we excluded 14 patients after the exclusion criteria and (n=)1214 patients were analyzed. We observed that several clinical and laboratory-based variables were statistically significant for both univariate and multivariate analyses while others were not. With most significant being septic shock (hazard ratio [HR], 4.30; 95% confidence interval [CI], 2.91-6.37), supportive treatment (HR, 3.51; 95% CI, 2.01-6.14), abnormal international normalized ratio (INR) (HR, 3.24; 95% CI, 2.28-4.63), admission to the intensive care unit (ICU) (HR, 3.24; 95% CI, 2.22-4.74), treatment with invasive ventilation (HR, 3.21; 95% CI, 2.15-4.79) and laboratory lymphocytic derangement (HR, 2.79; 95% CI, 1.6-4.86). Machine learning results showed our DNN (Neo-V) model outperformed all conventional machine learning models with test set accuracy of 99.53%, sensitivity of 89.87%, and specificity of 95.63%; positive predictive value, 50.00%; negative predictive value, 91.05%; and area under the curve of the receiver-operator curve of 88.5.ConclusionOur novel Deep-Neo-V model outperformed all other machine learning models. The model is easy to implement, user friendly and with high accuracy.

Download Full-text

Abstract 17510: The First Prediction Model for Response to Autologous Bone Marrow-derived Mononuclear Cells After Myocardial Infarction Based on the REPAIR-AMI Trial

Circulation ◽

10.1161/circ.132.suppl_3.17510 ◽

2015 ◽

Vol 132 (suppl_3) ◽

Author(s):

Peter-Paul Zwetsloot ◽

Birgit Assmus ◽

Stefan Koudstaal ◽

Hendrik Gremmels ◽

Sandra Erbs ◽

...

Keyword(s):

Risk Factors ◽

Myocardial Infarction ◽

Bone Marrow ◽

Prediction Model ◽

Treatment Response ◽

Mononuclear Cells ◽

Autologous Bone Marrow ◽

Individual Risk ◽

Autologous Bone ◽

Individual Risk Factors

Background: Administration of autologous bone marrow-derived mononuclear cells (BM-MNC) resulted in favorable outcomes after myocardial infarction (MI) compared to placebo in the REPAIR-AMI trial. Pre-clinical studies have shown that individual risk factors negatively influence cell function. To date, it is not known how these risk factors modify treatment effect in clinical trials and if potential (non-)responders can be identified. Aim: To investigate the effect of individual risk factors on functional outcome after BM-MNC therapy and to establish a prediction model for treatment response in patients with MI. Methods: Data from the REPAIR-AMI trial were used, consisting of 186 patients who had complete baseline and follow-up measurements. We performed univariable and multivariable linear regression with 18 predefined baseline characteristics using the difference in baseline EF and after 4 months (ΔEF4) as primary outcome. Our main goal was to identify interaction terms of predictors with BM-MNC treatment; i.e. effect modifiers of treatment response. An individual estimate of treatment effect over placebo (ΔΔEF4) was created by extrapolating an ‘untreated’ reference value for ΔEF4, based on the placebo-arm and comparing it to the observed value after treatment. Treatment response was defined as a ΔΔEF4 of >5% (so 5% over a predicted placebo value). Discrimination was quantified by the area under the ROC-curve (AUC). Results: The predictors age, weight, baseline EF and ESV showed an interaction with cell treatment in multivariable analysis with backward selection. Subsequently, the prediction model for individual ΔΔEF4 included age (-0.18/year, p=0.008), weight (+0.16/kg, p=0.01), baseline EF (-0.46/%, p=0.0001) and ESV (-0.09/ml, p=0.06). The predictive capacity for response to therapy showed an AUC of 79.2% (95% CI 69.7-88.6), which retained 74.8% (95% CI 65.0-84.5) after shrinkage. Conclusion: Response to BM-MNC administration after MI is influenced by age, weight, and baseline cardiac parameters. Using these continuous predictors, potential treatment responders can be accurately identified. Interestingly, an adverse risk-factor profile was associated with greater response, with potential implications for future patient selection.

Download Full-text

Reducing Uncertainties In Shear Wave Petrophysical Log Prediction By Using Deep Neural Network and Machine Learning Method

10.29118/ipa21-sg-228 ◽

2021 ◽

Author(s):

M. F. Abdurrachman

Keyword(s):

Neural Network ◽

Machine Learning ◽

Prediction Model ◽

Shear Wave ◽

Wave Velocity ◽

Shear Wave Velocity ◽

Deep Neural Network ◽

Oil And Gas ◽

Polynomial Regression ◽

Support Vector

Shear-wave velocity (Vs) log is one of the essential petrophysical well logs for reservoir characterisation in oil and gas exploration. Unfortunately, only a limited number of wells have a ready-to-use shear-wave velocity log. The common way to predict Vs from a Compressional-wave velocity (Vp) log is using empirical equations such as Castagna’s mud-rock line or Greenberg-Castagna equation. However, these methods only work for a specific rock type and are inflexible as every area has a complex and unique petrophysical characteristic relationship. Therefore, the Machine Learning (ML) methods (e.g., Multiple-linear Regression, Polynomial Regression, Support Vector Regression (SVR), Decision Tree, Random Forest, and XGBoost) and the Deep Learning (DL) method (e.g., Deep Neural Network (DNN)) that are suitable for big data analysis are proposed to solve this problem. These proposed methods aim to generate a complex Vs prediction model from multiple log data that can be used for general purposes, either for shale, limestone, sandstone, or other rocks. The study shows that the DNN and XGBoost can generate Vs prediction model with a correlation up to 94% overall in the R2 metric score, better than the empirical calculation for either shale, limestone, sandstone, or other rocks.

Download Full-text

Neural network–based identification of patients at high risk for intraoperative cerebrospinal fluid leaks in endoscopic pituitary surgery

Journal of Neurosurgery ◽

10.3171/2019.4.jns19477 ◽

2020 ◽

Vol 133 (2) ◽

pp. 329-335 ◽

Cited By ~ 8

Author(s):

Victor E. Staartjes ◽

Costanza M. Zattra ◽

Kevin Akeret ◽

Nicolai Maldaner ◽

Giovanni Muscas ◽

...

Keyword(s):

Neural Network ◽

Risk Factors ◽

Cerebrospinal Fluid ◽

Pituitary Adenoma ◽

High Risk ◽

Prediction Model ◽

Predictive Value ◽

Deep Neural Network ◽

Postoperative Morbidity ◽

Csf Leaks

OBJECTIVEAlthough rates of postoperative morbidity and mortality have become relatively low in patients undergoing transnasal transsphenoidal surgery (TSS) for pituitary adenoma, cerebrospinal fluid (CSF) fistulas remain a major driver of postoperative morbidity. Persistent CSF fistulas harbor the potential for headache and meningitis. The aim of this study was to investigate whether neural network–based models can reliably identify patients at high risk for intraoperative CSF leakage.METHODSFrom a prospective registry, patients who underwent endoscopic TSS for pituitary adenoma were identified. Risk factors for intraoperative CSF leaks were identified using conventional statistical methods. Subsequently, the authors built a prediction model for intraoperative CSF leaks based on deep learning.RESULTSIntraoperative CSF leaks occurred in 45 (29%) of 154 patients. No risk factors for CSF leaks were identified using conventional statistical methods. The deep neural network–based prediction model classified 88% of patients in the test set correctly, with an area under the curve of 0.84. Sensitivity (83%) and specificity (89%) were high. The positive predictive value was 71%, negative predictive value was 94%, and F1 score was 0.77. High suprasellar Hardy grade, prior surgery, and older age contributed most to the predictions.CONCLUSIONSThe authors trained and internally validated a robust deep neural network–based prediction model that identifies patients at high risk for intraoperative CSF. Machine learning algorithms may predict outcomes and adverse events that were previously nearly unpredictable, thus enabling safer and improved patient care and better patient counseling.

Download Full-text