scholarly journals Application of a time-series deep learning model to predict cardiac dysrhythmias in electronic health records

PLoS ONE ◽  
2021 ◽  
Vol 16 (9) ◽  
pp. e0239007
Author(s):  
Aixia Guo ◽  
Sakima Smith ◽  
Yosef M. Khan ◽  
James R. Langabeer II ◽  
Randi E. Foraker
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Logistic Regression ◽  
Deep Learning ◽  
Random Forest ◽  
Deep Neural Networks ◽  
Naive Bayes ◽  
Naïve Bayes ◽  
Cardiac Dysrhythmias ◽  
Electronic Health

Background Cardiac dysrhythmias (CD) affect millions of Americans in the United States (US), and are associated with considerable morbidity and mortality. New strategies to combat this growing problem are urgently needed. Objectives Predicting CD using electronic health record (EHR) data would allow for earlier diagnosis and treatment of the condition, thus improving overall cardiovascular outcomes. The Guideline Advantage (TGA) is an American Heart Association ambulatory quality clinical data registry of EHR data representing 70 clinics distributed throughout the US, and has been used to monitor outpatient prevention and disease management outcome measures across populations and for longitudinal research on the impact of preventative care. Methods For this study, we represented all time-series cardiovascular health (CVH) measures and the corresponding data collection time points for each patient by numerical embedding vectors. We then employed a deep learning technique–long-short term memory (LSTM) model–to predict CD from the vector of time-series CVH measures by 5-fold cross validation and compared the performance of this model to the results of deep neural networks, logistic regression, random forest, and Naïve Bayes models. Results We demonstrated that the LSTM model outperformed other traditional machine learning models and achieved the best prediction performance as measured by the average area under the receiver operator curve (AUROC): 0.76 for LSTM, 0.71 for deep neural networks, 0.66 for logistic regression, 0.67 for random forest, and 0.59 for Naïve Bayes. The most influential feature from the LSTM model were blood pressure. Conclusions These findings may be used to prevent CD in the outpatient setting by encouraging appropriate surveillance and management of CVH.

scholarly journals Komparasi Tujuh Algoritma Identifikasi Fraud ATM Pada PT. Bank Central Asia Tbk

2020 ◽  
Vol 7 (3) ◽  
pp. 441-450
Author(s):  
Haliem Sunata
Keyword(s):  
Logistic Regression ◽  
Random Forest ◽  
Decision Tree ◽  
Central Asia ◽  
Naive Bayes ◽  
Naïve Bayes ◽  
Random Tree

Tingginya penggunaan mesin ATM, sehingga menimbulkan celah fraud yang dapat dilakukan oleh pihak ketiga dalam membantu PT. Bank Central Asia Tbk untuk menjaga mesin ATM agar selalu siap digunakan oleh nasabah. Lambat dan sulitnya mengidentifikasi fraud mesin ATM menjadi salah satu kendala yang dihadapi PT. Bank Central Asia Tbk. Dengan adanya permasalahan tersebut maka peneliti mengumpulkan 5 dataset dan melakukan pre-processing dataset sehingga dapat digunakan untuk pemodelan dan pengujian algoritma, guna menjawab permasalahan yang terjadi. Dilakukan 7 perbandingan algoritma diantaranya decision tree, gradient boosted trees, logistic regression, naive bayes ( kernel ), naive bayes, random forest dan random tree. Setelah dilakukan pemodelan dan pengujian didapatkan hasil bahwa algoritma gradient boosted trees merupakan algoritma terbaik dengan hasil akurasi sebesar 99.85% dan nilai AUC sebesar 1, tingginya hasil algoritma ini disebabkan karena kecocokan setiap attribut yang diuji dengan karakter gradient boosted trees dimana algoritma ini menyimpan dan mengevaluasi hasil yang ada. Maka algoritma gradient boosted trees merupakan penyelesaian dari permasalahan yang dihadapi oleh PT. Bank Central Asia Tbk.

scholarly journals IDENTIFIKASI JENIS IKAN MENGGUNAKAN MODEL HYBRID DEEP LEARNING DAN ALGORITMA KLASIFIKASI

Sebatik ◽  
2020 ◽  
Vol 24 (2) ◽  
Author(s):  
Anifuddin Azis
Keyword(s):  
Neural Networks ◽  
Support Vector Machine ◽  
Logistic Regression ◽  
Deep Learning ◽  
Random Forest ◽  
Decision Tree ◽  
Nearest Neighbor ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Data Output

Indonesia merupakan negara dengan keanekaragaman hayati terbesar kedua di dunia setelah Brazil. Indonesia memiliki sekitar 25.000 spesies tumbuhan dan 400.000 jenis hewan dan ikan. Diperkirakan 8.500 spesies ikan hidup di perairan Indonesia atau merupakan 45% dari jumlah spesies yang ada di dunia, dengan sekitar 7.000an adalah spesies ikan laut. Untuk menentukan berapa jumlah spesies tersebut dibutuhkan suatu keahlian di bidang taksonomi. Dalam pelaksanaannya mengidentifikasi suatu jenis ikan bukanlah hal yang mudah karena memerlukan suatu metode dan peralatan tertentu, juga pustaka mengenai taksonomi. Pemrosesan video atau citra pada data ekosistem perairan yang dilakukan secara otomatis mulai dikembangkan. Dalam pengembangannya, proses deteksi dan identifikasi spesies ikan menjadi suatu tantangan dibandingkan dengan deteksi dan identifikasi pada objek yang lain. Metode deep learning yang berhasil dalam melakukan klasifikasi objek pada citra mampu untuk menganalisa data secara langsung tanpa adanya ekstraksi fitur pada data secara khusus. Sistem tersebut memiliki parameter atau bobot yang berfungsi sebagai ektraksi fitur maupun sebagai pengklasifikasi. Data yang diproses menghasilkan output yang diharapkan semirip mungkin dengan data output yang sesungguhnya.  CNN merupakan arsitektur deep learning yang mampu mereduksi dimensi pada data tanpa menghilangkan ciri atau fitur pada data tersebut. Pada penelitian ini akan dikembangkan model hybrid CNN (Convolutional Neural Networks) untuk mengekstraksi fitur dan beberapa algoritma klasifikasi untuk mengidentifikasi spesies ikan. Algoritma klasifikasi yang digunakan pada penelitian ini adalah : Logistic Regression (LR), Support Vector Machine (SVM), Decision Tree, K-Nearest Neighbor (KNN),  Random Forest, Backpropagation.

P1923Deep and machine learning models to improve risk prediction of cardiovascular disease using data extraction from electronic health records

2019 ◽  
Vol 40 (Supplement_1) ◽  
Author(s):  
I Korsakov ◽  
A Gusev ◽  
T Kuznetsova ◽  
D Gavrilov ◽  
R Novitskiy
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Cardiovascular Disease ◽  
Logistic Regression ◽  
Deep Learning ◽  
Risk Prediction ◽  
Learning Algorithm ◽  
Learning Models ◽  
Electronic Health ◽  
Machine Learning Models

Abstract Abstract Background Advances in precision medicine will require an increasingly individualized prognostic evaluation of patients in order to provide the patient with appropriate therapy. The traditional statistical methods of predictive modeling, such as SCORE, PROCAM, and Framingham, according to the European guidelines for the prevention of cardiovascular disease, not adapted for all patients and require significant human involvement in the selection of predictive variables, transformation and imputation of variables. In ROC-analysis for prediction of significant cardiovascular disease (CVD), the areas under the curve for Framingham: 0.62–0.72, for SCORE: 0.66–0.73 and for PROCAM: 0.60–0.69. To improve it, we apply for approaches to predict a CVD event rely on conventional risk factors by machine learning and deep learning models to 10-year CVD event prediction by using longitudinal electronic health record (EHR). Methods For machine learning, we applied logistic regression (LR) and recurrent neural networks with long short-term memory (LSTM) units as a deep learning algorithm. We extract from longitudinal EHR the following features: demographic, vital signs, diagnoses (ICD-10-cm: I21-I22.9: I61-I63.9) and medication. The problem in this step, that near 80 percent of clinical information in EHR is “unstructured” and contains errors and typos. Missing data are important for the correct training process using by deep learning & machine learning algorithm. The study cohort included patients between the ages of 21 to 75 with a dynamic observation window. In total, we got 31517 individuals in the dataset, but only 3652 individuals have all features or missing features values can be easy to impute. Among these 3652 individuals, 29.4% has a CVD, mean age 49.4 years, 68,2% female. Evaluation We randomly divided the dataset into a training and a test set with an 80/20 split. The LR was implemented with Python Scikit-Learn and the LSTM model was implemented with Keras using Tensorflow as the backend. Results We applied machine learning and deep learning models using the same features as traditional risk scale and longitudinal EHR features for CVD prediction, respectively. Machine learning model (LR) achieved an AUROC of 0.74–0.76 and deep learning (LSTM) 0.75–0.76. By using features from EHR logistic regression and deep learning models improved the AUROC to 0.78–0.79. Conclusion The machine learning models outperformed a traditional clinically-used predictive model for CVD risk prediction (i.e. SCORE, PROCAM, and Framingham equations). This approach was used to create a clinical decision support system (CDSS). It uses both traditional risk scales and models based on neural networks. Especially important is the fact that the system can calculate the risks of cardiovascular disease automatically and recalculate immediately after adding new information to the EHR. The results are delivered to the user's personal account.

scholarly journals Identifying undetected dementia in UK primary care patients: a retrospective case-control study comparing machine-learning and standard epidemiological approaches

2019 ◽  
Vol 19 (1) ◽  
Author(s):  
Elizabeth Ford ◽  
Philip Rooney ◽  
Seb Oliver ◽  
Richard Hoile ◽  
Peter Hurley ◽  
...  
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Random Forest ◽  
Health Service ◽  
Naive Bayes ◽  
Case Control ◽  
Naïve Bayes ◽  
Support Vector ◽  
Clinical Practice Research Datalink ◽  
Patient Records

Abstract Background Identifying dementia early in time, using real world data, is a public health challenge. As only two-thirds of people with dementia now ultimately receive a formal diagnosis in United Kingdom health systems and many receive it late in the disease process, there is ample room for improvement. The policy of the UK government and National Health Service (NHS) is to increase rates of timely dementia diagnosis. We used data from general practice (GP) patient records to create a machine-learning model to identify patients who have or who are developing dementia, but are currently undetected as having the condition by the GP. Methods We used electronic patient records from Clinical Practice Research Datalink (CPRD). Using a case-control design, we selected patients aged >65y with a diagnosis of dementia (cases) and matched them 1:1 by sex and age to patients with no evidence of dementia (controls). We developed a list of 70 clinical entities related to the onset of dementia and recorded in the 5 years before diagnosis. After creating binary features, we trialled machine learning classifiers to discriminate between cases and controls (logistic regression, naïve Bayes, support vector machines, random forest and neural networks). We examined the most important features contributing to discrimination. Results The final analysis included data on 93,120 patients, with a median age of 82.6 years; 64.8% were female. The naïve Bayes model performed least well. The logistic regression, support vector machine, neural network and random forest performed very similarly with an AUROC of 0.74. The top features retained in the logistic regression model were disorientation and wandering, behaviour change, schizophrenia, self-neglect, and difficulty managing. Conclusions Our model could aid GPs or health service planners with the early detection of dementia. Future work could improve the model by exploring the longitudinal nature of patient data and modelling decline in function over time.

scholarly journals IProCAD: Intelligent Prognosis of Coronary Artery Disease Excluding Angiogram in Patient with Stable Angina

2020 ◽  
Vol 9 (5) ◽  
pp. 2032-2040
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Heart Disease ◽  
Random Forest ◽  
Decision Tree ◽  
Stable Angina ◽  
Naive Bayes ◽  
Feature Vector ◽  
Naïve Bayes ◽  
The Other

Cardiovascular diseases are one of the main causes of mortality in the world. A proper prediction mechanism system with reasonable cost can significantly reduce this death toll in the low-income countries like Bangladesh. For those countries we propose machine learning backed embedded system that can predict possible cardiac attack effectively by excluding the high cost angiogram and incorporating only twelve (12) low cost features which are age, sex, chest pain, blood pressure, cholesterol, blood sugar, ECG results, heart rate, exercise induced angina, old peak, slope, and history of heart disease. Here, two heart disease datasets of own built NICVD (National Institute of Cardiovascular Disease, Bangladesh) patients’, and UCI (University of California Irvin) are used. The overall process comprises into four phases: Comprehensive literature review, collection of stable angina patients’ data through survey questionnaires from NICVD, feature vector dimensionality is reduced manually (from 14 to 12 dimensions), and the reduced feature vector is fed to machine learning based classifiers to obtain a prediction model for the heart disease. From the experiments, it is observed that the proposed investigation using NICVD patient’s data with 12 features without incorporating angiographic disease status to Artificial Neural Network (ANN) shows better classification accuracy of 92.80% compared to the other classifiers Decision Tree (82.50%), Naïve Bayes (85%), Support Vector Machine (SVM) (75%), Logistic Regression (77.50%), and Random Forest (75%) using the 10-fold cross validation. To accommodate small scale training and test data in our experimental environment we have observed the accuracy of ANN, Decision Tree, Naïve Bayes, SVM, Logistic Regression and Random Forest using Jackknife method, which are 84.80%, 71%, 75.10%, 75%, 75.33% and 71.42% respectively. On the other hand, the classification accuracies of the corresponding classifiers are 91.7%, 76.90%, 86.50%, 76.3%, 67.0% and 67.3%, respectively for the UCI dataset with 12 attributes. Whereas the same dataset with 14 attributes including angiographic status shows the accuracies 93.5%, 76.7%, 86.50%, 76.8%, 67.7% and 69.6% for the respective classifiers

scholarly journals Benchmarking Attention-Based Interpretability of Deep Learning in Multivariate Time Series Predictions

Entropy ◽  
2021 ◽  
Vol 23 (2) ◽  
pp. 143
Author(s):  
Domjan Barić ◽  
Petar Fumić ◽  
Davor Horvatić ◽  
Tomislav Lipic
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Deep Learning ◽  
Deep Neural Networks ◽  
Prediction Performance ◽  
Good Prediction ◽  
Multiple Time ◽  
Multiple Time Series ◽  
Learning Models ◽  
Performance Score

The adaptation of deep learning models within safety-critical systems cannot rely only on good prediction performance but needs to provide interpretable and robust explanations for their decisions. When modeling complex sequences, attention mechanisms are regarded as the established approach to support deep neural networks with intrinsic interpretability. This paper focuses on the emerging trend of specifically designing diagnostic datasets for understanding the inner workings of attention mechanism based deep learning models for multivariate forecasting tasks. We design a novel benchmark of synthetically designed datasets with the transparent underlying generating process of multiple time series interactions with increasing complexity. The benchmark enables empirical evaluation of the performance of attention based deep neural networks in three different aspects: (i) prediction performance score, (ii) interpretability correctness, (iii) sensitivity analysis. Our analysis shows that although most models have satisfying and stable prediction performance results, they often fail to give correct interpretability. The only model with both a satisfying performance score and correct interpretability is IMV-LSTM, capturing both autocorrelations and crosscorrelations between multiple time series. Interestingly, while evaluating IMV-LSTM on simulated data from statistical and mechanistic models, the correctness of interpretability increases with more complex datasets.

scholarly journals ANALISIS PERBANDINGAN KORELASI SPEARMAN DAN MAXIMAL INFORMATION COEFFICIENT DALAM SELEKSI FITUR WEBSITE PHISHING MENGGUNAKAN ALGORITMA MACHINE LEARNING

2021 ◽  
Vol 12 (2) ◽  
pp. 107
Author(s):  
Jimmy H. Moedjahedy ◽  
Arief Setyanto ◽  
Komang Aryasa
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Random Forest ◽  
Naive Bayes ◽  
Naïve Bayes ◽  
Total Information ◽  
Information Coefficient ◽  
Maximal Information Coefficient

<p><em>aan yang menipu maupun secara teknis untuk mencuri data identitas pribadi konsumen dan kredensial akun keuangan. Phishing dirancang untuk mengarahkan konsumen ke website phishing yang menipu penerima untuk membocorkan data keuangan seperti nama pengguna dan kata sandi. Dalam dataset phishing, terdapat fitur-fitur yang bisa mengkategorikan apakah sebuah website adalah website phishing atau bukan. Tujuan dari penelitian ini adalah untuk membandingkan hasil seleksi fitur-fitur yang ada dengan menggunakan dua metode yaitu metode gabungan Maximal Information coefficient dan Total Information Coefficient dengan metode korelasi Spearman. Hasil seleksi diuji dengan lima algoritma machine learning yaitu, Logistic Regression, Naïve Bayes, J48, AdaBoost MI</em> dan <em>Random Forest. Hasil dari penelitian ini adalah metode gabungan Maximal Information coefficent dan Total Information Coefficient memiliki nilai akurasi 97.25 % dengan menggunakan Random Forest mengungguli metode korelasi Spearman dengan nilai akurasi 95,33%.</em></p>

scholarly journals Impact of the COVID-19 pandemic on the expression of emotions in social media

2020 ◽  
Vol 15 ◽  
pp. 23-35
Author(s):  
Debabrata Ghosh ◽  
Keyword(s):  
Social Media ◽  
Logistic Regression ◽  
Random Forest ◽  
Naive Bayes ◽  
Naïve Bayes ◽  
Support Vector ◽  
Emotion Classification ◽  
Machine Learning Classification ◽  
Expression Of Emotions ◽  
The Mind

In the age of social media, every second thousands of messages are exchanged. Analyzing those unstructured data to find out specific emotions is a challenging task. Analysis of emotions involves evaluation and classification of text into emotion classes such as Happy, Sad, Anger, Disgust, Fear, Surprise, as defined by emotion dimensional models which are described in the theory of psychology (www 1; Russell, 2005). The main goal of this paper is to cover the COVID-19 pandemic situation in India and its impact on human emotions. As people very often express their state of the mind through social media, analyzing and tracking their emotions can be very effective for government and local authorities to take required measures. We have analyzed different machine learning classification models, such as Naïve Bayes, Support Vector Machine, Random Forest Classifier, Decision Tree and Logistic Regression with 10-fold cross validation to find out top ML models for emotion classification. After tuning the Hyperparameter, we got Logistic regression as the best suited model with accuracy 77% with the given datasets. We worked on algorithm based supervised ML technique to get the expected result. Although multiple studies were conducted earlier along the same lines, none of them performed comparative study among different ML techniques or hyperparameter tuning to optimize the results. Besides, this study has been done on the dataset of the most recent COVID-19 pandemic situation, which is itself unique. We captured Twitter data for a duration of 45 days with hashtag #COVID19India OR #COVID19 and analyzed the data using Logistic Regression to find out how the emotion changed over time based on certain social factors. Keywords: classification, COVID-19, emotion, emotion analysis, Naïve Bayes, Pandemic, Random Forest, SVM.

Sign in / Sign up

Export Citation Format

Share Document