Does COVID-19 Clinical Status Associate with Outcome Severity? An Unsupervised Machine Learning Approach for Knowledge Extraction

Since the beginning of the COVID-19 pandemic, 195 million people have been infected and 4.2 million have died from the disease or its side effects. Physicians, healthcare scientists and medical staff continuously try to deal with overloaded hospital admissions, while in parallel, they try to identify meaningful correlations between the severity of infected patients with their symptoms, comorbidities and biomarkers. Artificial intelligence (AI) and machine learning (ML) have been used recently in many areas related to COVID-19 healthcare. The main goal is to manage effectively the wide variety of issues related to COVID-19 and its consequences. The existing applications of ML to COVID-19 healthcare are based on supervised classifications which require a labeled training dataset, serving as reference point for learning, as well as predefined classes. However, the existing knowledge about COVID-19 and its consequences is still not solid and the points of common agreement among different scientific communities are still unclear. Therefore, this study aimed to follow an unsupervised clustering approach, where prior knowledge is not required (tabula rasa). More specifically, 268 hospitalized patients at the First Propaedeutic Department of Internal Medicine of AHEPA University Hospital of Thessaloniki were assessed in terms of 40 clinical variables (numerical and categorical), leading to a high-dimensionality dataset. Dimensionality reduction was performed by applying a principal component analysis (PCA) on the numerical part of the dataset and a multiple correspondence analysis (MCA) on the categorical part of the dataset. Then, the Bayesian information criterion (BIC) was applied to Gaussian mixture models (GMM) in order to identify the optimal number of clusters under which the best grouping of patients occurs. The proposed methodology identified four clusters of patients with similar clinical characteristics. The analysis revealed a cluster of asymptomatic patients that resulted in death at a rate of 23.8%. This striking result forces us to reconsider the relationship between the severity of COVID-19 clinical symptoms and the patient’s mortality.

Download Full-text

Four Machine Learning Algorithms for Biometrics Fusion: A Comparative Study

Applied Computational Intelligence and Soft Computing ◽

10.1155/2012/242401 ◽

2012 ◽

Vol 2012 ◽

pp. 1-7 ◽

Cited By ~ 11

Author(s):

I. G. Damousis ◽

S. Argyropoulos

Keyword(s):

Machine Learning ◽

Learning Algorithms ◽

Gaussian Mixture Models ◽

Gaussian Mixture ◽

Machine Learning Algorithms ◽

Training Dataset ◽

Support Vector ◽

False Alarms ◽

Security Systems ◽

Vector Machines

We examine the efficiency of four machine learning algorithms for the fusion of several biometrics modalities to create a multimodal biometrics security system. The algorithms examined are Gaussian Mixture Models (GMMs), Artificial Neural Networks (ANNs), Fuzzy Expert Systems (FESs), and Support Vector Machines (SVMs). The fusion of biometrics leads to security systems that exhibit higher recognition rates and lower false alarms compared to unimodal biometric security systems. Supervised learning was carried out using a number of patterns from a well-known benchmark biometrics database, and the validation/testing took place with patterns from the same database which were not included in the training dataset. The comparison of the algorithms reveals that the biometrics fusion system is superior to the original unimodal systems and also other fusion schemes found in the literature.

Download Full-text

Case Example: Adjacent Segment Disease: What Is It, and How Is It Rated?

Guides Newsletter ◽

10.1001/amaguidesnewsletters.2011.marapr02 ◽

2011 ◽

Vol 16 (2) ◽

pp. 8-9

Author(s):

Marjorie Eskay-Auerbach

Keyword(s):

Clinical Symptoms ◽

Lumbar Fusion ◽

Adjacent Segment Degeneration ◽

Adjacent Segment Disease ◽

Adjacent Segment ◽

Disc Space Narrowing ◽

Disc Disease ◽

Disc Space ◽

Radiographic Findings ◽

Asymptomatic Patients

Abstract The incidence of cervical and lumbar fusion surgery has increased in the past twenty years, and during follow-up some of these patients develop changes at the adjacent segment. Recognizing that adjacent segment degeneration and disease may occur in the future does not alter the rating for a cervical or lumbar fusion at the time the patient's condition is determined to be at maximum medical improvement (MMI). The term adjacent segment degeneration refers to the presence of radiographic findings of degenerative disc disease, including disc space narrowing, instability, and so on at the motion segment above or below a cervical or lumbar fusion. Adjacent segment disease refers to the development of new clinical symptoms that correspond to these changes on imaging. The biomechanics of adjacent segment degeneration have been studied, and, although the exact mechanism is uncertain, genetics may play a role. Findings associated with adjacent segment degeneration include degeneration of the facet joints with hypertrophy and thickening of the ligamentum flavum, disc space collapse, and translation—but the clinical significance of these radiographic degenerative changes remains unclear, particularly in light of the known presence of abnormal findings in asymptomatic patients. Evaluators should not rate an individual in anticipation of the development of changes at the level above a fusion, although such a development is a recognized possibility.

Download Full-text

Multiple vehicles detection and tracking for intelligent transport systems using machine learning approaches

Transport and Communication Science Journal ◽

10.25073/tcsj.70.3.7 ◽

2019 ◽

Vol 70 (3) ◽

pp. 214-224

Author(s):

Bui Ngoc Dung ◽

Manh Dzung Lai ◽

Tran Vu Hieu ◽

Nguyen Binh T. H.

Keyword(s):

Machine Learning ◽

Gaussian Mixture ◽

Research Field ◽

Transport Systems ◽

Learning Approaches ◽

Subtraction Method ◽

Intelligent Transport Systems ◽

Intelligent Transport ◽

Detection And Tracking ◽

Multiple Vehicles

Video surveillance is emerging research field of intelligent transport systems. This paper presents some techniques which use machine learning and computer vision in vehicles detection and tracking. Firstly the machine learning approaches using Haar-like features and Ada-Boost algorithm for vehicle detection are presented. Secondly approaches to detect vehicles using the background subtraction method based on Gaussian Mixture Model and to track vehicles using optical flow and multiple Kalman filters were given. The method takes advantages of distinguish and tracking multiple vehicles individually. The experimental results demonstrate high accurately of the method.

Download Full-text

CLINICAL SYMPTOMS, ULTRASOUND AND HISTOPATHOLOGY OF TUMORLIKE LESIONS OF THE BLADDER.

Journal of Medicine and Pharmacy ◽

10.34071/jmp.2017.1.6 ◽

2017 ◽

pp. 41-46

Author(s):

Van Mao Nguyen ◽

Thi Bich Chi Nguyen

Keyword(s):

Bladder Cancer ◽

Bladder Tumor ◽

Clinical Symptoms ◽

Bladder Wall ◽

Lower Abdominal Pain ◽

University Hospital ◽

Wall Thickening ◽

Health Examination ◽

Ultrasound Images ◽

Key Words Bladder Cancer

Background: Bladder cancer is one of the most frequent type of urinary cancer which has been ever increasing. For the better treatment, the early discovery and definite diagnosis of this disease played an important role. Objective: To describe some clinical symptoms and ultrasound features of tumorlike lesions of the bladder. To diagnose and classify the histopathology of tumorlike lesions of the bladder. Materials, method: cross - sectional study on 64 cases in Hue University Hospital and Hue central hospital from April, 2016 to February, 2017. Results: Hematuria was the most common reason that patients went to hospital (79.7%). Lower abdominal pain and irritation during urination accounting for 9.4% and 6.2% respectively. Only 3 patients with bladder cancer were accidentally discovered through periodic health examination (4.7%). The characteristics of hematuria in bladder tumor was flesh red urine (62.5%) and total hematuria (60.7%). With ultrasonography, the results of 64 patients were divided in 3 groups as follow: bladder tumor, which was the highest rate 87.5%, bladder polyp was 3.1% and focal bladder wall thickening was 9.4%. Of which, the vast majority of these ultrasound images was tumor - like lesions protruding in the lumen of the bladder (75%), the rest was wall thickening lesions (25%). Tumors were different in size, the biggest tumor was 7cm in diameter and the smallest was 0.6cm. Those with the diameter 3cm or bigger accounting for 42.2%, the smaller was 57.8%. Most cases have only one lesion (62.5%) and at lateral wall (46.6%). Histopathologically, cancer was 59/64 case (92.2%): urothelial carcinoma was 98.3 %, squamous cell carcinomawas 1.7% and 5 cases (7.8%) were benign. Most cancerous cases were poorly differentiated, grade II (50.9%) and grade III (32.2%). The stage T1NxMx was 20.3% and worse than T2MxNx was 79.7%. Conclusion: hematuria was the most popular symptom, suggesting bladder cancer. Clinical diagnosing bladder cancer was not high sensitive (61.01%). Ultrasound could detect bladder tumor with high sensitive (89.8%). These patients also needed histopathology classification to diagnose and finally choose the best method for the appropriate treatment. Key words: bladder cancer, histopathology, ultrasound, uroepithelial carcinoma, hematuria

Download Full-text

AN EFFICIENT MACHINE LEARNING MODEL FOR PREDICTION OF ACUTE MYOCARDIAL INFARCTION

Recent Advances in Computer Science and Communications ◽

10.2174/2666255813666200325104317 ◽

2020 ◽

Vol 13 ◽

Author(s):

Dhilsath Fathima.M ◽

S. Justin Samuel ◽

R. Hari Haran

Keyword(s):

Machine Learning ◽

Myocardial Infarction ◽

Acute Myocardial Infarction ◽

Logistic Regression ◽

Decision Tree ◽

Learning Model ◽

Training Dataset ◽

Data Set ◽

Machine Learning Model ◽

Proposed Model

Aim: This proposed work is used to develop an improved and robust machine learning model for predicting Myocardial Infarction (MI) could have substantial clinical impact. Objectives: This paper explains how to build machine learning based computer-aided analysis system for an early and accurate prediction of Myocardial Infarction (MI) which utilizes framingham heart study dataset for validation and evaluation. This proposed computer-aided analysis model will support medical professionals to predict myocardial infarction proficiently. Methods: The proposed model utilize the mean imputation to remove the missing values from the data set, then applied principal component analysis to extract the optimal features from the data set to enhance the performance of the classifiers. After PCA, the reduced features are partitioned into training dataset and testing dataset where 70% of the training dataset are given as an input to the four well-liked classifiers as support vector machine, k-nearest neighbor, logistic regression and decision tree to train the classifiers and 30% of test dataset is used to evaluate an output of machine learning model using performance metrics as confusion matrix, classifier accuracy, precision, sensitivity, F1-score, AUC-ROC curve. Results: Output of the classifiers are evaluated using performance measures and we observed that logistic regression provides high accuracy than K-NN, SVM, decision tree classifiers and PCA performs sound as a good feature extraction method to enhance the performance of proposed model. From these analyses, we conclude that logistic regression having good mean accuracy level and standard deviation accuracy compared with the other three algorithms. AUC-ROC curve of the proposed classifiers is analyzed from the output figure.4, figure.5 that logistic regression exhibits good AUC-ROC score, i.e. around 70% compared to k-NN and decision tree algorithm. Conclusion: From the result analysis, we infer that this proposed machine learning model will act as an optimal decision making system to predict the acute myocardial infarction at an early stage than an existing machine learning based prediction models and it is capable to predict the presence of an acute myocardial Infarction with human using the heart disease risk factors, in order to decide when to start lifestyle modification and medical treatment to prevent the heart disease.

Download Full-text

Derivation of Respiratory Metrics in Health and Asthma; Machine Learning Methodology (Preprint)

10.2196/preprints.25178 ◽

2020 ◽

Author(s):

Joseph Prinable ◽

Peter Jones ◽

David Boland ◽

Alistair McEwan ◽

Cindy Thamrin

Keyword(s):

Machine Learning ◽

Short Term Memory ◽

Reference Signal ◽

Machine Learning Algorithms ◽

Training Dataset ◽

Local Health ◽

Strongly Correlated ◽

Human Research Ethics ◽

Expiration Time ◽

Wide Variability

BACKGROUND The ability to continuously monitor breathing metrics may have indications for general health as well as respiratory conditions such as asthma. However, few studies have focused on breathing due to a lack of available wearable technologies. OBJECTIVE Examine the performance of two machine learning algorithms in extracting breathing metrics from a finger-based pulse oximeter, which is amenable to long-term monitoring. METHODS Pulse oximetry data was collected from 11 healthy and 11 asthma subjects who breathed at a range of controlled respiratory rates. UNET and Long Short-Term memory (LSTM) algorithms were applied to the data, and results compared against breathing metrics derived from respiratory inductance plethysmography measured simultaneously as a reference. RESULTS The UNET vs LSTM model provided breathing metrics which were strongly correlated with those from the reference signal (all p<0.001, except for inspiratory:expiratory ratio). The following relative mean bias(95% confidence interval) were observed: inspiration time 1.89(-52.95, 56.74)% vs 1.30(-52.15, 54.74)%, expiration time -3.70(-55.21, 47.80)% vs -4.97(-56.84, 46.89)%, inspiratory:expiratory ratio -4.65(-87.18, 77.88)% vs -5.30(-87.07, 76.47)%, inter-breath intervals -2.39(-32.76, 27.97)% vs -3.16(-33.69, 27.36)%, and respiratory rate 2.99(-27.04 to 33.02)% vs 3.69(-27.17 to 34.56)%. CONCLUSIONS Both machine learning models show strongly correlation and good comparability with reference, with low bias though wide variability for deriving breathing metrics in asthma and health cohorts. Future efforts should focus on improvement of performance of these models, e.g. by increasing the size of the training dataset at the lower breathing rates. CLINICALTRIAL Sydney Local Health District Human Research Ethics Committee (#LNR\16\HAWKE99 ethics approval).

Download Full-text

Digging for the truth: the case for active annotation in evaluating the credibility of online medical information (Preprint)

10.2196/preprints.25920 ◽

2020 ◽

Author(s):

Mikołaj Morzy ◽

Bartłomiej Balcerzak ◽

Adam Wierzbicki ◽

Adam Wierzbicki

Keyword(s):

Machine Learning ◽

Medical Information ◽

Representation Learning ◽

Training Dataset ◽

Highly Qualified ◽

Human In The Loop ◽

Annotation Process ◽

Comprehensive Framework ◽

Online Sources ◽

The Web

BACKGROUND With the rapidly accelerating spread of dissemination of false medical information on the Web, the task of establishing the credibility of online sources of medical information becomes a pressing necessity. The sheer number of websites offering questionable medical information presented as reliable and actionable suggestions with possibly harmful effects poses an additional requirement for potential solutions, as they have to scale to the size of the problem. Machine learning is one such solution which, when properly deployed, can be an effective tool in fighting medical disinformation on the Web. OBJECTIVE We present a comprehensive framework for designing and curating of machine learning training datasets for online medical information credibility assessment. We show how the annotation process should be constructed and what pitfalls should be avoided. Our main objective is to provide researchers from medical and computer science communities with guidelines on how to construct datasets for machine learning models for various areas of medical information wars. METHODS The key component of our approach is the active annotation process. We begin by outlining the annotation protocol for the curation of high-quality training dataset, which then can be augmented and rapidly extended by employing the human-in-the-loop paradigm to machine learning training. To circumvent the cold start problem of insufficient gold standard annotations, we propose a pre-processing pipeline consisting of representation learning, clustering, and re-ranking of sentences for the acceleration of the training process and the optimization of human resources involved in the annotation. RESULTS We collect over 10 000 annotations of sentences related to selected subjects (psychiatry, cholesterol, autism, antibiotics, vaccines, steroids, birth methods, food allergy testing) for less than $7 000 employing 9 highly qualified annotators (certified medical professionals) and we release this dataset to the general public. We develop an active annotation framework for more efficient annotation of non-credible medical statements. The results of the qualitative analysis support our claims of the efficacy of the presented method. CONCLUSIONS A set of very diverse incentives is driving the widespread dissemination of medical disinformation on the Web. An effective strategy of countering this spread is to use machine learning for automatically establishing the credibility of online medical information. This, however, requires a thoughtful design of the training pipeline. In this paper we present a comprehensive framework of active annotation. In addition, we publish a large curated dataset of medical statements labelled as credible, non-credible, or neutral.

Download Full-text

The use of Lactobacillus casei DG® prevents symptomatic episodes and reduces the antibiotic use in patients affected by chronic bacterial prostatitis: results from a phase IV study

World Journal of Urology ◽

10.1007/s00345-020-03580-7 ◽

2021 ◽

Author(s):

Tommaso Cai ◽

Luca Gallelli ◽

Erika Cione ◽

Gianpaolo Perletti ◽

Francesco Ciarleglio ◽

...

Keyword(s):

Quality Of Life ◽

Clinical Symptoms ◽

Clinical Status ◽

Well Being ◽

Antibiotic Use ◽

Chronic Bacterial Prostatitis ◽

Symptomatic Recurrence ◽

Bacterial Prostatitis ◽

Phase Iv

Abstract Purpose To evaluate the efficacy of Lactobacillus paracasei CNCM I-1572 (L. casei DG®) in both prevention of symptomatic recurrences and improvement of quality of life in patients with chronic bacterial prostatitis (CBP). Methods Patients with CBP attending a single Urological Institution were enrolled in this phase IV study. At enrollment, all patients were treated with antibiotics in agreement with EAU guidelines and then were treated with L. casei DG® (2 capsules/day for 3 months). Clinical and microbiological analyses were carried out before (enrollment, T0) and 6 months (T2) after the treatment. Both safety and adherence to the treatment were evaluated 3 months (T1) after the enrollment. NIH Chronic Prostatitis Symptom Index (CPSI), International Prostate Symptom Score (IPSS) and Quality of Well-Being (QoL) questionnaires were used. The outcome measures were the rate of symptomatic recurrence, changes in questionnaire symptom scores and the reduction of antibiotic use. Results Eighty-four patients were included. At T2, 61 patients (72.6%) reported a clinical improvement of symptoms with a return to their clinical status before symptoms. A time dependent improvement in clinical symptoms with significant changes in NIH-CPSI, IPSS and QoL (mean difference T2 vs T0: 16.5 ± 3.58; − 11.0 ± 4.32; + 0.3 ± 0.09; p < 0.001), was reported. We recorded that L. casei DG® treatment induced a statistically significant decrease in both (p < 0.001) symptomatic recurrence [1.9/3 months vs 0.5/3 months] and antibiotic use [− 7938 UDD]. No clinically relevant adverse effects were reported. Conclusions L. casei DG® prevents symptomatic recurrences and improves the quality of life in patients with CBP, reducing the antibiotic use.

Download Full-text

A Comparative Survey of Feature Extraction and Machine Learning Methods in Diverse Acoustic Environments

Sensors ◽

10.3390/s21041274 ◽

2021 ◽

Vol 21 (4) ◽

pp. 1274

Author(s):

Daniel Bonet-Solà ◽

Rosa Ma Alsina-Pagès

Keyword(s):

Machine Learning ◽

Feature Extraction ◽

Best Practice ◽

Nearest Neighbor ◽

Gaussian Mixture ◽

Machine Learning Algorithms ◽

Multimedia Retrieval ◽

Natural Environments ◽

K Nearest Neighbor ◽

Acoustic Environments

Acoustic event detection and analysis has been widely developed in the last few years for its valuable application in monitoring elderly or dependant people, for surveillance issues, for multimedia retrieval, or even for biodiversity metrics in natural environments. For this purpose, sound source identification is a key issue to give a smart technological answer to all the aforementioned applications. Diverse types of sounds and variate environments, together with a number of challenges in terms of application, widen the choice of artificial intelligence algorithm proposal. This paper presents a comparative study on combining several feature extraction algorithms (Mel Frequency Cepstrum Coefficients (MFCC), Gammatone Cepstrum Coefficients (GTCC), and Narrow Band (NB)) with a group of machine learning algorithms (k-Nearest Neighbor (kNN), Neural Networks (NN), and Gaussian Mixture Model (GMM)), tested over five different acoustic environments. This work has the goal of detailing a best practice method and evaluate the reliability of this general-purpose algorithm for all the classes. Preliminary results show that most of the combinations of feature extraction and machine learning present acceptable results in most of the described corpora. Nevertheless, there is a combination that outperforms the others: the use of GTCC together with kNN, and its results are further analyzed for all the corpora.

Download Full-text

Exploratory Analysis of Driving Force of Wildfires in Australia: An Application of Machine Learning within Google Earth Engine

Remote Sensing ◽

10.3390/rs13010010 ◽

2020 ◽

Vol 13 (1) ◽

pp. 10

Author(s):

Andrea Sulova ◽

Jamal Jokar Arsanjani

Keyword(s):

Climate Change ◽

Machine Learning ◽

Random Forest ◽

Google Earth ◽

Summer Season ◽

Driving Factors ◽

Machine Learning Algorithms ◽

Classification And Regression Tree ◽

Training Dataset ◽

Google Earth Engine

Recent studies have suggested that due to climate change, the number of wildfires across the globe have been increasing and continue to grow even more. The recent massive wildfires, which hit Australia during the 2019–2020 summer season, raised questions to what extent the risk of wildfires can be linked to various climate, environmental, topographical, and social factors and how to predict fire occurrences to take preventive measures. Hence, the main objective of this study was to develop an automatized and cloud-based workflow for generating a training dataset of fire events at a continental level using freely available remote sensing data with a reasonable computational expense for injecting into machine learning models. As a result, a data-driven model was set up in Google Earth Engine platform, which is publicly accessible and open for further adjustments. The training dataset was applied to different machine learning algorithms, i.e., Random Forest, Naïve Bayes, and Classification and Regression Tree. The findings show that Random Forest outperformed other algorithms and hence it was used further to explore the driving factors using variable importance analysis. The study indicates the probability of fire occurrences across Australia as well as identifies the potential driving factors of Australian wildfires for the 2019–2020 summer season. The methodical approach and achieved results and drawn conclusions can be of great importance to policymakers, environmentalists, and climate change researchers, among others.

Download Full-text