Unsupervised Learning Techniques for the Investigation of Chronic Rhinosinusitis

2019 ◽  
Vol 128 (12) ◽  
pp. 1170-1176
Author(s):  
Abigail Walker ◽  
Pavol Surda
Keyword(s):  
Unsupervised Learning ◽  
Chronic Rhinosinusitis ◽  
Clinical Data ◽  
Traditional Approach ◽  
Health Care Research ◽  
Machine Learning Techniques ◽  
Common Symptom ◽  
Disease Phenotypes ◽  
Learning Techniques ◽  
Investigative Technique

Objectives: This article reviews the principles of unsupervised learning, a novel technique which has increasingly been reported as a tool for the investigation of chronic rhinosinusitis (CRS). It represents a paradigm shift from the traditional approach to investigating CRS based upon the clinically recognized phenotypes of “with polyps” and “without polyps” and instead relies upon the application of complex mathematical models to derive subgroups which can then be further examined. This review article reports on the principles which underlie this investigative technique and some of the published examples in CRS. Methods: This review summarizes the different types of unsupervised learning techniques which have been described and briefly expounds upon their useful applications. A literature review of studies which have unsupervised learning is then presented to provide a practical guide to its uses and some of the new directions of investigations suggested by their findings. Results: The commonest unsupervised learning technique applied to rhinology research is cluster analysis, which can be further subdivided into hierarchical and non-hierarchical approaches. The mathematical principles which underpin these approaches are explained within this article. Studies which have used these techniques can be broadly divided into those which have used clinical data only and that which includes biomarkers. Studies which include biomarkers adhere closely to the established canon of CRS disease phenotypes, while those that use clinical data may diverge from the typical “polyp versus non-polyp” phenotypes and reflect subgroups of patients who share common symptom modifiers. Summary: Artificial intelligence is increasingly influential in health care research and machine learning techniques have been reported in the investigation of CRS, promising several interesting new avenues for research. However, when critically appraising studies which use this technique, the reader needs to be au fait with the limitations and appropriate uses of its application.

scholarly journals Towards Automatic and Interpretable Assignments of Patients Presenting with Pain to the Emergency Department

2021 ◽  
Author(s):  
J.A. Hughes ◽  
N.J. Brown ◽  
Thanh Vu ◽  
Anthony Nguyen
Keyword(s):  
Emergency Department ◽  
Deep Learning ◽  
Quality Of Care ◽  
Machine Learning Techniques ◽  
Initial Assessment ◽  
Common Symptom ◽  
Healthcare Applications ◽  
Learning Techniques ◽  
Real Time Identification

Introduction: Pain is the most common symptom that patients present with to the emergency department. It is hard to identify patients who have presented in pain to the emergency department when compliance with structured pain assessment is low. An ability to identify patients presenting in pain allows further investigation of the quality of care provided. Background: Machine and deep learning techniques are commonly used for text analysis in healthcare. Applications such as the classification of diagnosis and unplanned readmissions from textual medical records have previously been described. In other work, conventional and deep-learning techniques have demonstrated high performance in identifying patients presenting to the emergency department in pain. However, these models have lacked interpretability. Methods: This paper proposes the use of machine learning techniques to identify patients who present in pain based upon their initial assessment using interpretable deep learning models. Results: The interpretable deep learning model of pain identification was shown to have more accuracy and precision than other machine and deep learning techniques. This technique has significant application to large datasets for the identification of the quality of care and real-time identification of patients presenting in pain to improve their care.

Machine Learning Techniques for Corneal Diseases Diagnosis: A Survey

2020 ◽  
pp. 2150016
Author(s):  
Samer Kais Jameel ◽  
Sezgin Aydin ◽  
Nebras H. Ghaeb
Keyword(s):  
Machine Learning ◽  
Decision Making ◽  
Clinical Data ◽  
Medical Images ◽  
Diagnostic Techniques ◽  
Machine Learning Techniques ◽  
Corneal Disease ◽  
Automated Learning ◽  
Learning Techniques ◽  
The Way

Machine learning techniques become more related to medical researches by using medical images as a dataset. It is categorized and analyzed for ultimate effectiveness in diagnosis or decision-making for diseases. Machine learning techniques have been exploited in numerous researches related to corneal diseases, contribution to ophthalmologists for diagnosing the diseases and comprehending the way automated learning techniques act. Nevertheless, confusion still exists in the type of data used, whether it is images, data extracted from images or clinical data, the course reliant on the type of device for obtaining them. In this study, the researches that used machine learning were reviewed and classified in terms of the kind of utilized machine for capturing data, along with the latest updates in sophisticated approaches for corneal disease diagnostic techniques.

Application of Machine Learning Algorithms in Stock Market Prediction

2020 ◽  
pp. 153-180
Author(s):  
Sumit Kumar ◽  
Sanlap Acharya
Keyword(s):  
Machine Learning ◽  
Unsupervised Learning ◽  
Supervised Learning ◽  
Stock Prices ◽  
Stock Price ◽  
Short Term Memory ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Learning Techniques ◽  
Better Than

The prediction of stock prices has always been a very challenging problem for investors. Using machine learning techniques to predict stock prices is also one of the favourite topics for academics working in this domain. This chapter discusses five supervised learning techniques and two unsupervised learning techniques to solve the problem of stock price prediction and has compared the performances of all the algorithms. Among the supervised learning techniques, Long Short-Term Memory (LSTM) algorithm performed better than the others whereas, among the unsupervised learning techniques, Restricted Boltzmann Machine (RBM) performed better. RBM is found to be performing even better than LSTM.

Clinical Decision Support Systems

2021 ◽  
pp. 268-280
Author(s):  
Diviya Prabha V. ◽  
Rathipriya R.
Keyword(s):  
Clinical Data ◽  
Personal Data ◽  
Clinical Decision Support Systems ◽  
Clinical Decision ◽  
Machine Learning Techniques ◽  
Health Issues ◽  
Minimum Entropy ◽  
Readmission Rates ◽  
Learning Techniques ◽  
Number Of Patients

Clinical data is increasing day-by-day mainly in hospitals by an ageing of the human population. Patients discharged from hospitals are readmitted due to health issues. As the number of patients increases, there are a smaller number of hospitals and an increase in healthcare costs. This results in ineffective decision making that minimizes the healthcare. Machine learning techniques score better for solving this kind of problem. The proposed work, minimum entropy feature selection with logistic regression (MELR), is performing better for the readmission rates. Decision cannot be based on the clinical knowledge and personal data about the patient. It must be precise in choosing the future patient outcomes. This chapter produces promising results for clinical data.

Machine Learning for Predicting Motor Improvement After Acute Subcortical Infarction Using Baseline Whole Brain Volumes

2021 ◽  
pp. 154596832110541
Author(s):  
Gang Liu ◽  
Jiewei Wu ◽  
Chao Dang ◽  
Shuangquan Tan ◽  
Kangqiang Peng ◽  
...  
Keyword(s):  
Machine Learning ◽  
Clinical Data ◽  
Machine Learning Techniques ◽  
Whole Brain ◽  
Brain Volumes ◽  
Poor Recovery ◽  
Learning Scheme ◽  
Learning Techniques ◽  
Motor Improvement ◽  
Subcortical Infarction

Background. Neuroimaging biomarkers are valuable predictors of motor improvement after stroke, but there is a gap between published evidence and clinical usage. Objective. In this work, we aimed to investigate whether machine learning techniques, when applied to a combination of baseline whole brain volumes and clinical data, can accurately predict individual motor outcome after stroke. Methods. Upper extremity Fugl-Meyer Assessments (FMA-UE) were conducted 1 week and 12 weeks, and structural MRI was performed 1 week, after onset in 56 patients with subcortical infarction. Proportional recovery model residuals were employed to assign patients to proportional and poor recovery groups (34 vs 22). A sophisticated machine learning scheme, consisting of conditional infomax feature extraction, synthetic minority over-sampling technique for nominal and continuous, and bagging classification, was employed to predict motor outcomes, with the input features being a combination of baseline whole brain volumes and clinical data (FMA-UE scores). Results. The proposed machine learning scheme yielded an overall balanced accuracy of 87.71% in predicting proportional vs poor recovery outcomes, a sensitivity of 93.77% in correctly identifying poor recovery outcomes, and a ROC AUC of 89.74%. Compared with only using clinical data, adding whole brain volumes can significantly improve the classification performance, especially in terms of the overall balanced accuracy (from 80.88% to 87.71%) and the sensitivity (from 92.23% to 93.77%). Conclusions. Experimental results suggest that a combination of baseline whole brain volumes and clinical data, when equipped with appropriate machine learning techniques, may provide valuable information for personalized rehabilitation planning after subcortical infarction.

scholarly journals Making Money from What You Know - How to Sell Information?

2019 ◽  
Vol 33 ◽  
pp. 2421-2428
Author(s):  
Shani Alkoby ◽  
Zihe Wang ◽  
David Sarne ◽  
Pingzhong Tang
Keyword(s):  
Traditional Approach ◽  
Human Subjects ◽  
Communication Technologies ◽  
Expected Profit ◽  
Machine Learning Techniques ◽  
Strategic Information ◽  
Information Provider ◽  
World State ◽  
Learning Techniques ◽  
Information Providers

Information plays a key role in many decision situations. The rapid advancement in communication technologies makes information providers more accessible, and various information providing platforms can be found nowadays, most of which are strategic in the sense that their goal is to maximize the providers’ expected profit. In this paper, we consider the common problem of a strategic information provider offering prospective buyers information which can disambiguate uncertainties the buyers have, which can be valuable for their decision making. Unlike prior work, we do not limit the information provider’s strategy to price setting but rather enable her flexibility over the way information is sold, specifically enabling querying about specific outcomes and the elimination of a subset of non-true world states alongside the traditional approach of disclosing the true world state. We prove that for the case where the buyer is self-interested (and the information provider does not know the true world state beforehand) all three methods (i.e., disclosing the true worldstate value, offering to check a specific value, and eliminating a random value) are equivalent, yielding the same expected profit to the information provider. For the case where buyers are human subjects, using an extensive set of experiments we show that the methods result in substantially different outcomes. Furthermore, using standard machine learning techniques the information provider can rather accurately predict the performance of the different methods for new problem settings, hence substantially increase profit.

scholarly journals The Machines Aren’t Taking Over (Yet): An Empirical Comparison of Traditional, Profiling, and Machine Learning Approaches to Criterion-Related Validation

2020 ◽  
Vol 6 (3) ◽  
Author(s):  
Kristin Allen ◽  
Mathijs Affourtit ◽  
Craig Reddock
Keyword(s):  
Machine Learning ◽  
Traditional Approach ◽  
Machine Learning Techniques ◽  
Group Differences ◽  
Learning Approaches ◽  
New Techniques ◽  
Selection Procedures ◽  
Predicting Performance ◽  
Learning Techniques ◽  
Efficient Alternative

Criterion-related validation (CRV) studies are used to demonstrate the effectiveness of selection procedures. However, traditional CRV studies require significant investment of time and resources, as well as large sample sizes, which often create practical challenges. New techniques, which use machine learning to develop classification models from limited amounts of data, have emerged as a more efficient alternative. This study empirically investigates the effectiveness of traditional CRV with a variety of profiling approaches and machine learning techniques using repeated cross-validation. Results show that the traditional approach generally performs best both in terms of predicting performance and larger group differences between candidates identified as top or non-top performers. In addition to empirical effectiveness, other practical implications are discussed.

Recognition on Images From Internet Street View Based on Hierarchical Features Learning With CNNs

2019 ◽  
pp. 1411-1424
Author(s):  
Jian-min Liu ◽  
Min-hua Yang
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Unsupervised Learning ◽  
Convolutional Neural Networks ◽  
Error Rates ◽  
Machine Learning Techniques ◽  
Street View ◽  
Learning Techniques ◽  
Similarities And Differences ◽  
Hierarchical Features

This article describes hierarchical features with unsupervised learning on images from internet street view images. This is due to the time spent by trained researchers on feature construction steps with traditional methods. This article focuses on the activation of each layer of with convolutional neural networks (CNNs) on Internet street view images detection and compared similarities and differences among them on each layer. The experiment results achieved error rates of 21% on recognition which work went relatively well than the traditional machine learning techniques, such as Parallel SVM.

Sign in / Sign up

Export Citation Format

Share Document