scholarly journals A Machine Learning Approach to Predicting Diabetes Complications

Healthcare ◽  
2021 ◽  
Vol 9 (12) ◽  
pp. 1712
Author(s):  
Yazan Jian ◽  
Michel Pasquier ◽  
Assim Sagahyroon ◽  
Fadi Aloul
Keyword(s):  
Metabolic Syndrome ◽  
Diabetic Foot ◽  
Missing Values ◽  
Diabetes Complications ◽  
The Body ◽  
Performance Accuracy ◽  
Machine Learning Approach ◽  
Life Threatening ◽  
Binary Classifiers ◽  
Fold Cross Validation

Diabetes mellitus (DM) is a chronic disease that is considered to be life-threatening. It can affect any part of the body over time, resulting in serious complications such as nephropathy, neuropathy, and retinopathy. In this work, several supervised classification algorithms were applied for building different models to predict and classify eight diabetes complications. The complications include metabolic syndrome, dyslipidemia, neuropathy, nephropathy, diabetic foot, hypertension, obesity, and retinopathy. For this study, a dataset collected by the Rashid Center for Diabetes and Research (RCDR) located in Ajman, UAE, was utilized. The dataset consists of 884 records with 79 features. Some essential preprocessing steps were applied to handle the missing values and unbalanced data problems. Furthermore, feature selection was performed to select the top five and ten features for each complication. The final number of records used to train and build the binary classifiers for each complication was as follows: 428—metabolic syndrome, 836—dyslipidemia, 223—neuropathy, 233—nephropathy, 240—diabetic foot, 586—hypertension, 498—obesity, 228—retinopathy. Repeated stratified k-fold cross-validation (with k = 10 and a total of 10 repetitions) was employed for a better estimation of the performance. Accuracy and F1-score were used to evaluate the models’ performance reaching a maximum of 97.8% and 97.7% for accuracy and F1-scores, respectively. Moreover, by comparing the performance achieved using different attributes’ sets, it was found that by using a selected number of features, we can still build adequate classifiers.

scholarly journals The Complexity of Diabetic Foot Management: From Common Care to Best Practice. The Italian Expert Opinion by Delphi Survey

2019 ◽  
Vol 19 (1) ◽  
pp. 34-43 ◽  
Author(s):  
Elisabetta Salutini ◽  
Enrico Brocco ◽  
Roberto Da Ros ◽  
Luca Monge ◽  
Luigi Uccioli ◽  
...  
Keyword(s):  
Clinical Judgment ◽  
Diabetic Foot ◽  
Best Practice ◽  
Diabetes Complications ◽  
Public Health Issue ◽  
Life Threatening ◽  
Foot Lesions ◽  
Diabetic Foot Lesions ◽  
Wound Bed Preparation ◽  
Leg Amputation

Diabetic foot is a major public health issue, driven by diabetes complications (neuropathy, peripheral vascular disease, foot deformity, and abnormal leucocyte function), which may lead to leg amputation, thus resulting in severe disability, reduced quality of life, and high health costs. The prevention of diabetes complications and the early detection and proper management of diabetic foot wounds are the milestones to avoid major amputations. Unfortunately, in many areas, the prevention of diabetic foot lesions is inadequate and wounds may proceed toward infection and chronicity, with limb- and life-threatening results. Using the Delphi method, we conducted a survey on diabetic foot among Italian experts, selected across different Italian clinical centers. This method was used to achieve a consensus on current opinion and clinical leanings on the diagnosis and management of diabetic foot ulcers. Specifically, the aim of the survey was to evaluate the current management of the diabetic foot syndrome; highlight the differences in the approach among a group of experts; evaluate the role of wound bed preparation and antisepsis; and discuss any areas of disagreement in which evidences are sparse and the clinical judgment plays a crucial role in the decision-making process.

A MACHINE LEARNING APPROACH BASED ON SVM FOR CLASSIFICATION OF LIVER DISEASES

2020 ◽  
Vol 32 (03) ◽  
pp. 2050018
Author(s):  
Mohammad Fathi ◽  
Mohammadreza Nemati ◽  
Seyed Mohsen Mohammadi ◽  
Reza Abbasi-Kesbi
Keyword(s):  
Cross Validation ◽  
The Body ◽  
Support Vector ◽  
Classification Algorithms ◽  
Data Partition ◽  
Linear Quadratic ◽  
Machine Learning Approach ◽  
And Performance ◽  
Fold Cross Validation

The liver is an organ in the body that plays an important role in the production and secretion of the bile. Recently, the number of liver patients are increasing because of the inhalation of harmful gases, the consumption of contaminated foods, herbs, and narcotics. Today, classification algorithms are widely used in diverse medical applications. In this paper, the classification of the liver, and non-liver patients is performed based on a support vector machine (SVM) on two datasets. To this end, the dataset is normalized and then sorted based on a proposed algorithm. After that, the feature selection is performed in order to remove the outliers and missing data. Then, 10-fold cross-validation is used for the data partition. In the end, the classification models of Linear, Quadratic and Gaussian SVM are defined and performance evaluation of the proposed method is investigated by calculation of F1-score, accuracy, and sensitivity. The results show that ILPD data have maximum accuracy, sensitivity, and F1-score of 90.9%, 89.2%, and 94%, respectively, so that a minimum improvement of 17.9% is obtained in accuracy than previous works. Additionally, the highest accuracy, sensitivity, and F1-score of BUPA data is 92.2%, 89%, and 94.3%, separately.

scholarly journals Using Different Combinations of Body-Mounted IMU Sensors to Estimate Speed of Horses—A Machine Learning Approach

Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 798
Author(s):  
Hamed Darbandi ◽  
Filipe Serra Bragança ◽  
Berend Jan van der Zwaag ◽  
John Voskamp ◽  
Annik Imogen Gmel ◽  
...  
Keyword(s):  
Machine Learning ◽  
The Body ◽  
Biomechanical Analysis ◽  
Estimation Accuracy ◽  
Speed Estimation ◽  
Motion Patterns ◽  
Positioning Systems ◽  
Machine Learning Approach ◽  
Global Positioning ◽  
Measurement Units

Speed is an essential parameter in biomechanical analysis and general locomotion research. It is possible to estimate the speed using global positioning systems (GPS) or inertial measurement units (IMUs). However, GPS requires a consistent signal connection to satellites, and errors accumulate during IMU signals integration. In an attempt to overcome these issues, we have investigated the possibility of estimating the horse speed by developing machine learning (ML) models using the signals from seven body-mounted IMUs. Since motion patterns extracted from IMU signals are different between breeds and gaits, we trained the models based on data from 40 Icelandic and Franches-Montagnes horses during walk, trot, tölt, pace, and canter. In addition, we studied the estimation accuracy between IMU locations on the body (sacrum, withers, head, and limbs). The models were evaluated per gait and were compared between ML algorithms and IMU location. The model yielded the highest estimation accuracy of speed (RMSE = 0.25 m/s) within equine and most of human speed estimation literature. In conclusion, highly accurate horse speed estimation models, independent of IMU(s) location on-body and gait, were developed using ML.

Association between muscle strength and risk factors for metabolic syndrome in children and adolescents: a systematic review

2020 ◽  
Vol 0 (0) ◽  
Author(s):  
Tiago R. de Lima ◽  
Priscila C. Martins ◽  
Giuseppe L. Torre ◽  
Alice Mannocci ◽  
Kelly S. Silva ◽  
...  
Keyword(s):  
Risk Factors ◽  
Systematic Review ◽  
Metabolic Syndrome ◽  
Muscle Strength ◽  
Children And Adolescents ◽  
Lower Risk ◽  
Preliminary Evidence ◽  
Risk Of Bias ◽  
The Body ◽  
Reference List

AbstractThe aim of this systematic review was to identify and summarize evidence for the association between muscle strength (MS) and metabolic syndrome (MetS), and MS and combinations of risk factors for MetS in children and adolescents. Five databases (Medline/PubMed, EBSCO, Scielo, Scopus, and Web of Knowledge) were searched up to November 2019 with complementary reference list searches. Inclusion criteria were studies that investigated the relationship between MS and MetS or MS and combinations of risk factors for MetS in children and adolescents (≤19 years of age). Risk of bias was assessed using standard procedures. From the total of 15,599 articles initially identified, 13 articles were included, representing 11,641 children and adolescents. Higher MS values were associated with lower risk for MetS or combinations of risk factors for MetS (n=11/13 studies). Of the total of included studies, about 23.1% (03/13) were longitudinal and all included studies were classified as having a moderate risk of bias. This review provides preliminary evidence for a beneficial relationship between MS and MetS among children and adolescents. Additionally, although the body of evidence points to the beneficial relationship between higher MS and lower risk for combination of factors for MetS in children and adolescents, this relationship is inconclusive.

scholarly journals Loss of Smell and Taste Can Accurately Predict COVID-19 Infection: A Machine-Learning Approach

2021 ◽  
Vol 10 (4) ◽  
pp. 570
Author(s):  
María A Callejon-Leblic ◽  
Ramon Moreno-Luna ◽  
Alfonso Del Cuvillo ◽  
Isabel M Reyes-Tejero ◽  
Miguel A Garcia-Villaran ◽  
...  
Keyword(s):  
Machine Learning ◽  
Modelling Framework ◽  
Visual Analog Scales ◽  
Average Accuracy ◽  
Machine Learning Approach ◽  
Taste Disorders ◽  
Polymerase Chain ◽  
Fold Cross Validation ◽  
Validation Scheme ◽  
Control Study

The COVID-19 outbreak has spread extensively around the world. Loss of smell and taste have emerged as main predictors for COVID-19. The objective of our study is to develop a comprehensive machine learning (ML) modelling framework to assess the predictive value of smell and taste disorders, along with other symptoms, in COVID-19 infection. A multicenter case-control study was performed, in which suspected cases for COVID-19, who were tested by real-time reverse-transcription polymerase chain reaction (RT-PCR), informed about the presence and severity of their symptoms using visual analog scales (VAS). ML algorithms were applied to the collected data to predict a COVID-19 diagnosis using a 50-fold cross-validation scheme by randomly splitting the patients in training (75%) and testing datasets (25%). A total of 777 patients were included. Loss of smell and taste were found to be the symptoms with higher odds ratios of 6.21 and 2.42 for COVID-19 positivity. The ML algorithms applied reached an average accuracy of 80%, a sensitivity of 82%, and a specificity of 78% when using VAS to predict a COVID-19 diagnosis. This study concludes that smell and taste disorders are accurate predictors, with ML algorithms constituting helpful tools for COVID-19 diagnostic prediction.

scholarly journals Interclass Interference Suppression in Multi-Class Problems

2021 ◽  
Vol 11 (1) ◽  
pp. 450
Author(s):  
Jinfu Liu ◽  
Mingliang Bai ◽  
Na Jiang ◽  
Ran Cheng ◽  
Xianling Li ◽  
...  
Keyword(s):  
Classification Accuracy ◽  
Cross Validation ◽  
Selection Process ◽  
Interference Suppression ◽  
Generalization Ability ◽  
Suppression Effect ◽  
Binary Classifiers ◽  
The One ◽  
Fold Cross Validation ◽  
Validation Experiments

Multi-classifiers are widely applied in many practical problems. But the features that can significantly discriminate a certain class from others are often deleted in the feature selection process of multi-classifiers, which seriously decreases the generalization ability. This paper refers to this phenomenon as interclass interference in multi-class problems and analyzes its reason in detail. Then, this paper summarizes three interclass interference suppression methods including the method based on all-features, one-class classifiers and binary classifiers and compares their effects on interclass interference via the 10-fold cross-validation experiments in 14 UCI datasets. Experiments show that the method based on binary classifiers can suppress the interclass interference efficiently and obtain the best classification accuracy among the three methods. Further experiments were done to compare the suppression effect of two methods based on binary classifiers including the one-versus-one method and one-versus-all method. Results show that the one-versus-one method can obtain a better suppression effect on interclass interference and obtain better classification accuracy. By proposing the concept of interclass inference and studying its suppression methods, this paper significantly improves the generalization ability of multi-classifiers.

From strongyloidiasis to disseminated mucormycosis: the story of an HTLV-1-infected migrant

2020 ◽  
Author(s):  
Brice Autier ◽  
Adélaïde Chesnay ◽  
Claire Mayence ◽  
Stéphanie Houcke ◽  
Hélène Guégan ◽  
...  
Keyword(s):  
Immune Deficiency ◽  
Strongyloides Stercoralis ◽  
The Body ◽  
Life Threatening ◽  
Disseminated Strongyloidiasis ◽  
Disseminated Mucormycosis

Strongyloidiasis manifestations range from asymptomatic cases to the life-threatening disseminated strongyloidiasis in case of immune deficiency: larvae migrate throughout the body, disseminating germs from the digestive flora to various organs. Here, we described a case of disseminated mucormycosis consecutive to Strongyloides stercoralis hyperinfestation in a Surinamese migrant infected with HTLV-1.

scholarly journals Melatonin and diet-induced metabolic syndrome in rats: impact on the hypophysial-testicular axis

2013 ◽  
Vol 16 (2) ◽  
Author(s):  
Pablo A. Scacchi Bernasconi ◽  
Nancy P. Cardoso ◽  
Roxana Reynoso ◽  
Pablo Scacchi ◽  
Daniel P. Cardinali
Keyword(s):  
Metabolic Syndrome ◽  
Body Weight ◽  
Uric Acid ◽  
Plasma Levels ◽  
Density Lipoprotein ◽  
The Body ◽  
High Fat ◽  
Testosterone Secretion ◽  
Diet Manipulation ◽  
The Impact

AbstractCombinations of fructose- and fat-rich diets in experimental animals can model the human metabolic syndrome (MS). In rats, the increase in blood pressure (BP) after diet manipulation is sex related and highly dependent on testosterone secretion. However, the extent of the impact of diet on rodent hypophysial-testicular axis remains undefined. In the present study, rats drinking a 10% fructose solution or fed a high-fat (35%) diet for 10 weeks had higher plasma levels of luteinizing hormone (LH) and lower plasma levels of testosterone, without significant changes in circulating follicle-stimulating hormone or the weight of most reproductive organs. Diet manipulation brought about a significant increase in body weight, systolic BP, area under the curve (AUC) of glycemia after an intraperitoneal glucose tolerance test (IPGTT), and plasma low-density lipoprotein cholesterol, cholesterol, triglycerides, and uric acid levels. The concomitant administration of melatonin (25 μg/mL of drinking water) normalized the abnormally high LH levels but did not affect the inhibited testosterone secretion found in fructose- or high-fat-fed rats. Rather, melatonin per se inhibited testosterone secretion. Melatonin significantly blunted the body weight and systolic BP increase, the increase in the AUC of glycemia after an IPGTT, and the changes in circulating lipid profile and uric acid found in both MS models. The results are compatible with a primary inhibition of testicular function in diet-induced MS in rats and with the partial effectiveness of melatonin to counteract the metabolic but not the testicular sequelae of rodent MS.

scholarly journals Adipokines, Myokines, and Hepatokines: Crosstalk and Metabolic Repercussions

2021 ◽  
Vol 22 (5) ◽  
pp. 2639
Author(s):  
Ana Rita de Oliveira dos Santos ◽  
Bárbara de Oliveira Zanuso ◽  
Vitor Fernando Bordin Miola ◽  
Sandra Maria Barbalho ◽  
Patrícia C. Santos Bueno ◽  
...  
Keyword(s):  
Metabolic Syndrome ◽  
Interleukin 1 ◽  
The Body ◽  
Healthy Weight ◽  
Beta Oxidation ◽  
Necrosis Factor Alpha ◽  
Beneficial Effects ◽  
Muscle Tissues ◽  
Endocrine Organs ◽  
Sharing Space

Adipose, skeletal, and hepatic muscle tissues are the main endocrine organs that produce adipokines, myokines, and hepatokines. These biomarkers can be harmful or beneficial to an organism and still perform crosstalk, acting through the endocrine, paracrine, and autocrine pathways. This study aims to review the crosstalk between adipokines, myokines, and hepatokines. Far beyond understanding the actions of each biomarker alone, it is important to underline that these cytokines act together in the body, resulting in a complex network of actions in different tissues, which may have beneficial or non-beneficial effects on the genesis of various physiological disorders and their respective outcomes, such as type 2 diabetes mellitus (DM2), obesity, metabolic syndrome, and cardiovascular diseases (CVD). Overweight individuals secrete more pro-inflammatory adipokines than those of a healthy weight, leading to an impaired immune response and greater susceptibility to inflammatory and infectious diseases. Myostatin is elevated in pro-inflammatory environments, sharing space with pro-inflammatory organokines, such as tumor necrosis factor-alpha (TNF-α), interleukin-1 (IL-1), resistin, and chemerin. Fibroblast growth factor FGF21 acts as a beta-oxidation regulator and decreases lipogenesis in the liver. The crosstalk mentioned above can interfere with homeostatic disorders and can play a role as a potential therapeutic target that can assist in the methods of diagnosing metabolic syndrome and CVD.

Sign in / Sign up

Export Citation Format

Share Document