Blinded Clinical Evaluation for Dementia of Alzheimer’s Type Classification Using FDG-PET: A Comparison Between Feature-Engineered and Non-Feature-Engineered Machine Learning Methods

2021 ◽  
Vol 80 (2) ◽  
pp. 715-726
Author(s):  
Da Ma ◽  
Evangeline Yee ◽  
Jane K. Stocks ◽  
Lisanne M. Jenkins ◽  
Karteek Popuri ◽  
...  
Keyword(s):  
Machine Learning ◽  
Fdg Pet ◽  
Clinical Sample ◽  
Normal Subjects ◽  
Learning Methods ◽  
Cognitively Normal ◽  
Machine Learning Methods ◽  
Dementia Of Alzheimer’S Type ◽  
Cognitively Normal Subjects ◽  
Machine Learning Models

Background: Advanced machine learning methods can aid in the identification of dementia risk using neuroimaging-derived features including FDG-PET. However, to enable the translation of these methods and test their usefulness in clinical practice, it is crucial to conduct independent validation on real clinical samples, which has yet to be properly delineated in the current literature. Objective: In this paper, we present our efforts to enable such clinical translational through the evaluation and comparison of two machine-learning methods for discrimination between dementia of Alzheimer’s type (DAT) and Non-DAT controls. Methods: FDG-PET-based dementia scores were generated on an independent clinical sample whose clinical diagnosis was blinded to the algorithm designers. A feature-engineered approach (multi-kernel probability classifier) and a non-feature-engineered approach (3D convolutional neural network) were analyzed. Both classifiers were pre-trained on cognitively normal subjects as well as subjects with DAT. These two methods provided a probabilistic dementia score for this previously unseen clinical data. Performance of the algorithms were compared against ground-truth dementia rating assessed by experienced nuclear physicians. Results: Blinded clinical evaluation on both classifiers showed good separation between the cognitively normal subjects and the patients diagnosed with DAT. The non-feature-engineered dementia score showed higher sensitivity among subjects whose diagnosis was in agreement between the machine-learning models, while the feature-engineered approach showed higher specificity in non-consensus cases. Conclusion: In this study, we demonstrated blinded evaluation using data from an independent clinical sample for assessing the performance in DAT classification models in a clinical setting. Our results showed good generalizability for two machine-learning approaches, marking an important step for the translation of pre-trained machine-learning models into clinical practice.

Analysis of the results of the Russian agricultural census using machine learning methods

2020 ◽  
pp. 41-48
Author(s):  
Anna Evgenievna Kharitonova ◽  
Alina Alekseevna Sundupey ◽  
Svetlana Skachkova
Keyword(s):  
Machine Learning ◽  
Agricultural Land ◽  
High Accuracy ◽  
Learning Methods ◽  
Agricultural Producers ◽  
Machine Learning Methods ◽  
Agricultural Census ◽  
Qualitative Characteristics ◽  
Machine Learning Models ◽  
Crop And Livestock Production

The article provides a comparative analysis of the results of the Russian Agricultural Census of 2006 and 2016. As a result, there is a decrease in the number of agricultural producers, a decrease in the size of agricultural land and equipment in organizations. Against this background, one can see an increase in the concentration of production in both crop and livestock production. Machine learning models have been built to classify subsidy organizations using Python libraries. The accuracy of the constructed models was up to 86 %, which proves the possibility of their use. In the future, the use of machine learning methods will reduce the number of Russian agricultural census indicators and classify organizations with high accuracy according to qualitative characteristics.

Improved Interpretability of Machine Learning Model Using Unsupervised Clustering: Predicting Time to First Treatment in Chronic Lymphocytic Leukemia

2019 ◽  
pp. 1-11 ◽  
Author(s):  
David Chen ◽  
Gaurav Goyal ◽  
Ronald S. Go ◽  
Sameer A. Parikh ◽  
Che G. Ngufor
Keyword(s):  
Machine Learning ◽  
Risk Stratification ◽  
Unsupervised Clustering ◽  
Support Vector ◽  
Learning Models ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Continuous Output ◽  
Time To First Treatment ◽  
Machine Learning Models

PURPOSE Time to event is an important aspect of clinical decision making. This is particularly true when diseases have highly heterogeneous presentations and prognoses, as in chronic lymphocytic lymphoma (CLL). Although machine learning methods can readily learn complex nonlinear relationships, many methods are criticized as inadequate because of limited interpretability. We propose using unsupervised clustering of the continuous output of machine learning models to provide discrete risk stratification for predicting time to first treatment in a cohort of patients with CLL. PATIENTS AND METHODS A total of 737 treatment-naïve patients with CLL diagnosed at Mayo Clinic were included in this study. We compared predictive abilities for two survival models (Cox proportional hazards and random survival forest) and four classification methods (logistic regression, support vector machines, random forest, and gradient boosting machine). Probability of treatment was then stratified. RESULTS Machine learning methods did not yield significantly more accurate predictions of time to first treatment. However, automated risk stratification provided by clustering was able to better differentiate patients who were at risk for treatment within 1 year than models developed using standard survival analysis techniques. CONCLUSION Clustering the posterior probabilities of machine learning models provides a way to better interpret machine learning models.

P1925Machine learning versus classic electrocardiographic criteria for left ventricular hypertrophy in a young pre-participation cohort: results from the SAFE protocol study

2019 ◽  
Vol 40 (Supplement_1) ◽  
Author(s):  
G Sng ◽  
D Y Z Lim ◽  
C H Sia ◽  
J S W Lee ◽  
X Y Shen ◽  
...  
Keyword(s):  
Machine Learning ◽  
Left Ventricular Hypertrophy ◽  
Ventricular Hypertrophy ◽  
Left Ventricular ◽  
Superior Performance ◽  
Learning Models ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Ecg Criteria ◽  
Machine Learning Models

Abstract Background/Introduction Classic electrocardiographic (ECG) criteria for left ventricular hypertrophy (LVH) have been well studied in Western populations, particularly in hypertensive patients. However, their utility in Asian populations is not well studied, and their applicability to young pre-participation cohorts is unclear. We sought to evaluate the performance of classical criteria against that of machine learning models. Aims We sought to evaluate the performance of classical criteria against the performance of novel machine learning models in the identification of LVH. Methodology Between November 2009 and December 2014, pre-participation screening ECG and subsequent echocardiographic data was collected from 13,954 males aged 16 to 22, who reported for medical screening prior to military conscription. Final diagnosis of LVH was made on echocardiography, with LVH defined as a left ventricular mass index >115g/m2. The continuous and binary forms of classical criteria were compared against machine learning models using receiver-operating characteristics (ROC) curve analysis. An 80:20 split was used to divide the data into training and test sets for the machine learning models, and three fold cross validation was used in training the models. We also compared the important variables identified by machine learning models with the input variables of classical criteria. Results Prevalence of echocardiographic LVH in this population was 0.91% (127 cases). Classical ECG criteria had poor performance in predicting LVH, with the best predictions achieved by the continuous Sokolow-Lyon (AUC = 0.63, 95% CI = 0.58–0.68) and the continuous Modified Cornell (AUC = 0.63, 95% CI = 0.58–0.68). Machine learning methods achieved superior performance – Random Forest (AUC = 0.74, 95% CI = 0.66–0.82), Gradient Boosting Machines (AUC = 0.70, 95% CI = 0.61–0.79), GLMNet (AUC = 0.78, 95% CI = 0.70–0.86). Novel and less recognized ECG parameters identified by the machine learning models as being predictive of LVH included mean QT interval, mean QRS interval, R in V4, and R in I. ROC curves of models studies Conclusion The prevalence of LVH in our population is lower than that previously reported in other similar populations. Classical ECG criteria perform poorly in this context. Machine learning methods show superior predictive performance and demonstrate non-traditional predictors of LVH from ECG data. Further research is required to improve the predictive ability of machine learning models, and to understand the underlying pathology of the novel ECG predictors identified.

scholarly journals Empirical asset pricing via machine learning: evidence from the European stock market

2021 ◽  
Author(s):  
Wolfgang Drobetz ◽  
Tizian Otto
Keyword(s):  
Machine Learning ◽  
Stock Returns ◽  
Network Architecture ◽  
Risk Measures ◽  
Predictive Performance ◽  
Support Vector ◽  
Learning Models ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Machine Learning Models

AbstractThis paper evaluates the predictive performance of machine learning methods in forecasting European stock returns. Compared to a linear benchmark model, interactions and nonlinear effects help improve the predictive performance. But machine learning models must be adequately trained and tuned to overcome the high dimensionality problem and to avoid overfitting. Across all machine learning methods, the most important predictors are based on price trends and fundamental signals from valuation ratios. However, the models exhibit substantial variation in statistical predictive performance that translate into pronounced differences in economic profitability. The return and risk measures of long-only trading strategies indicate that machine learning models produce sizeable gains relative to our benchmark. Neural networks perform best, also after accounting for transaction costs. A classification-based portfolio formation, utilizing a support vector machine that avoids estimating stock-level expected returns, performs even better than the neural network architecture.

Field Development Optimization Using Machine Learning Methods to Identify the Optimal Water Flooding Regime

2021 ◽  
Author(s):  
Alexey Vasilievich Timonov ◽  
Arturas Rimo Shabonas ◽  
Sergey Alexandrovich Schmidt
Keyword(s):  
Machine Learning ◽  
Optimization Algorithms ◽  
Machine Learning Algorithms ◽  
Water Flooding ◽  
Learning Models ◽  
Learning Methods ◽  
Injection Wells ◽  
Field Development ◽  
Machine Learning Methods ◽  
Machine Learning Models

Abstract The main technology used to optimize field development is hydrodynamic modeling, which is very costly in terms of computing resources and expert time to configure the model. And in the case of brownfields, the complexity increases exponentially. The paper describes the stages of developing a hybrid geological-physical-mathematical proxy model using machine learning methods, which allows performing multivariate calculations and predicting production including various injection well operating regimes. Based on the calculations, we search for the optimal ratio of injection volume distribution to injection wells under given infrastructural constraints. The approach implemented in this work takes into account many factors (some features of the geological structure, history of field development, mutual influence of wells, etc.) and can offer optimal options for distribution of injection volumes of injection wells without performing full-scale or sector hydrodynamic simulation. To predict production, we use machine learning methods (based on decision trees and neural networks) and methods for optimizing the target functions. As a result of this research, a unified algorithm for data verification and preprocessing has been developed for feature extraction tasks and the use of deep machine learning models as input data. Various machine learning algorithms were tested and it was determined that the highest prediction accuracy is achieved by building machine learning models based on Temporal Convolutional Networks (TCN) and gradient boosting. Developed and tested an algorithm for finding the optimal allocation of injection volumes, taking into account the existing infrastructure constraints. Different optimization algorithms are tested. It is determined that the choice and setting of boundary conditions is critical for optimization algorithms in this problem. An integrated approach was tested on terrigenous formations of the West Siberian field, where the developed algorithm showed effectiveness.

Comparative Analysis of Random Forests with Statistical and Machine Learning Methods in Predicting Fault-Prone Classes

2012 ◽  
pp. 428-449 ◽  
Author(s):  
Ruchika Malhotra ◽  
Arvinder Kaur ◽  
Yogesh Singh
Keyword(s):  
Machine Learning ◽  
Random Forests ◽  
Data Sets ◽  
Classification Problems ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Code Metrics ◽  
Machine Learning Models ◽  
Better Than

There are available metrics for predicting fault prone classes, which may help software organizations for planning and performing testing activities. This may be possible due to proper allocation of resources on fault prone parts of the design and code of the software. Hence, importance and usefulness of such metrics is understandable, but empirical validation of these metrics is always a great challenge. Random Forest (RF) algorithm has been successfully applied for solving regression and classification problems in many applications. In this work, the authors predict faulty classes/modules using object oriented metrics and static code metrics. This chapter evaluates the capability of RF algorithm and compares its performance with nine statistical and machine learning methods in predicting fault prone software classes. The authors applied RF on six case studies based on open source, commercial software and NASA data sets. The results indicate that the prediction performance of RF is generally better than statistical and machine learning models. Further, the classification of faulty classes/modules using the RF method is better than the other methods in most of the data sets.

Combining electronic and structural features in machine learning models to predict organic solar cells properties

2019 ◽  
Vol 6 (2) ◽  
pp. 343-349 ◽  
Author(s):  
Daniele Padula ◽  
Jack D. Simpson ◽  
Alessandro Troisi
Keyword(s):  
Machine Learning ◽  
Solar Cells ◽  
Organic Solar Cells ◽  
Structural Similarity ◽  
Structural Features ◽  
Learning Models ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Machine Learning Models

Combining electronic and structural similarity between organic donors in kernel based machine learning methods allows to predict photovoltaic efficiencies reliably.

Exploring machine learning methods for absolute configuration determination with vibrational circular dichroism

2021 ◽  
Vol 23 (35) ◽  
pp. 19781-19789
Author(s):  
Tom Vermeyen ◽  
Jure Brence ◽  
Robin Van Echelpoel ◽  
Roy Aerts ◽  
Guillaume Acke ◽  
...  
Keyword(s):  
Machine Learning ◽  
Circular Dichroism ◽  
Absolute Configuration ◽  
Vibrational Circular Dichroism ◽  
Learning Models ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
The Absolute ◽  
Circular Dichroïsm ◽  
Machine Learning Models

The capabilities of machine learning models to extract the absolute configuration of a series of compounds from their vibrational circular dichroism spectra have been demonstrated. The important spectral areas are identified.

Sign in / Sign up

Export Citation Format

Share Document