scholarly journals Diabetic Retinopathy Prediction by Ensemble Learning Based on Biochemical and Physical Data

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3663
Author(s):  
Zun Shen ◽  
Qingfeng Wu ◽  
Zhi Wang ◽  
Guoyi Chen ◽  
Bin Lin
Keyword(s):  
Diabetic Retinopathy ◽  
Prediction Model ◽  
Ensemble Learning ◽  
Positive Impact ◽  
Reduction Rate ◽  
Developed Countries ◽  
Small Sample ◽  
Feature Reduction ◽  
Physical Data ◽  
Diabetes Retinopathy

(1) Background: Diabetic retinopathy, one of the most serious complications of diabetes, is the primary cause of blindness in developed countries. Therefore, the prediction of diabetic retinopathy has a positive impact on its early detection and treatment. The prediction of diabetic retinopathy based on high-dimensional and small-sample-structured datasets (such as biochemical data and physical data) was the problem to be solved in this study. (2) Methods: This study proposed the XGB-Stacking model with the foundation of XGBoost and stacking. First, a wrapped feature selection algorithm, XGBIBS (Improved Backward Search Based on XGBoost), was used to reduce data feature redundancy and improve the effect of a single ensemble learning classifier. Second, in view of the slight limitation of a single classifier, a stacking model fusion method, Sel-Stacking (Select-Stacking), which keeps Label-Proba as the input matrix of meta-classifier and determines the optimal combination of learners by a global search, was used in the XGB-Stacking model. (3) Results: XGBIBS greatly improved the prediction accuracy and the feature reduction rate of a single classifier. Compared to a single classifier, the accuracy of the Sel-Stacking model was improved to varying degrees. Experiments proved that the prediction model of XGB-Stacking based on the XGBIBS algorithm and the Sel-Stacking method made effective predictions on diabetes retinopathy. (4) Conclusion: The XGB-Stacking prediction model of diabetic retinopathy based on biochemical and physical data had outstanding performance. This is highly significant to improve the screening efficiency of diabetes retinopathy and reduce the cost of diagnosis.

scholarly journals Association of Diabetic Retinopathy with Diabetic Foot in a Tertiary Care Centre

2019 ◽  
Vol 46 (3) ◽  
pp. 90-93
Author(s):  
Purabi Rani Debnath ◽  
Mohammuddunnobi
Keyword(s):  
Diabetic Retinopathy ◽  
Tertiary Care ◽  
Foot Ulcer ◽  
Developed Countries ◽  
Cross Sectional Study ◽  
Tertiary Care Centre ◽  
Cross Sectional ◽  
Diabetes Retinopathy ◽  
Department Of Ophthalmology ◽  
Common Causes

Diabetic retinopathy (DR) is one of the most common causes of blindness in developed countries. Early detection of diabetic retinopathy (DR) is crucial for preventing irreversible blindness. To measure the association of diabetic retinopathy with dabetic foot a cross-sectional study was carried out at Department of Ophthalmology and Surgery, BIRDEM General Hospital, Dhaka from January 2017 to September 2017. Patients were included, who were known diabetic. New cases of type-2 diabetes were also included because they might have complications at the time of diagnosis because of the nature of disease. Mean duration of diabetes was significantly higher in DFU with DR group. BUN and diabetes retinopathy were statistically significant (p<0.05) between two groups. Mean HbA1c, pre-prandial glucose, C-peptide, cholesterol, triglyceride, HDL, LDL, hematocrit, creatinine, ABI, TBI and DM foot ulcer were not statistically significant (p>0.05) between two groups. Most patients (33.3%) had a grade I ulcer in DF with DR group and 33.3% in DF without DR group. Medication taking was significantly high patients who were DF without DR. Combined agents was 11(36.7%) and 11(36.7%) in DF with DR and DF without DR group respectively. Insulin was taken 16(53.3%) in DF with DR group and 19(63.3%) in DF without DR group. Maximum patients had a grade I ulcer in diabetes foot ulcer. Medication taking was significantly high patients who were diabetes foot ulcer than without diabetes foot ulcer. Mean insulin, BUN and diabetes retinopathy was found significantly higher in diabetes with diabetes foot ulcer. Mean insulin BUN and diabetic retinopathy was was significantly higher in diabetes with diabetes foot ulcer. Bangladesh Med J. 2017 Sep; 46 (3): 90-93

scholarly journals Weighted Hybrid Feature Reduction Embedded with Ensemble Learning for Speech Data of Parkinson’s Disease

Mathematics ◽  
2021 ◽  
Vol 9 (24) ◽  
pp. 3172
Author(s):  
Zeeshan Hameed ◽  
Waheed Ur Rehman ◽  
Wakeel Khan ◽  
Nasim Ullah ◽  
Fahad R. Albogamy
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Ensemble Learning ◽  
Neurodegenerative Disorder ◽  
Small Sample Size ◽  
Small Sample ◽  
Feature Reduction ◽  
Speech Data ◽  
Boosting Method ◽  
The Stability

Parkinson’s disease (PD) is a progressive and long-term neurodegenerative disorder of the central nervous system. It has been studied that 90% of the PD subjects have voice impairments which are some of the vital characteristics of PD patients and have been widely used for diagnostic purposes. However, the curse of dimensionality, high aliasing, redundancy, and small sample size in PD speech data bring great challenges to classify PD objects. Feature reduction can efficiently solve these issues. However, existing feature reduction algorithms ignore high aliasing, noise, and the stability of algorithms, and thus fail to give substantial classification accuracy. To mitigate these problems, this study proposes a weighted hybrid feature reduction embedded with ensemble learning technique which comprises (1) hybrid feature reduction technique that increases inter-class variance, reduces intra-class variance, preserves the neighborhood structure of data, and remove co-related features that causes high aliasing and noise in classification. (2) Weighted-boosting method to train the model precisely. (3) Furthermore, the stability of the algorithm is enhanced by introducing a bagging strategy. The experiments were performed on three different datasets including two widely used datasets and a dataset provided by Southwest Hospital (Army Military Medical University) Chongqing, China. The experimental results indicated that compared with existing feature reduction methods, the proposed algorithm always shows the highest accuracy, precision, recall, and G-mean for speech data of PD. Moreover, the proposed algorithm not only shows excellent performance for classification but also deals with imbalanced data precisely and achieved the highest AUC in most of the cases. In addition, compared with state-of-the-art algorithms, the proposed method shows improvement up to 4.53%. In the future, this algorithm can be used for early and differential diagnoses, which are rated as challenging tasks.

The Worrying Trend of Diabetes Mellitus in Saudi Arabia: An Urgent Call to Action

2020 ◽  
Vol 16 (3) ◽  
pp. 204-210 ◽  
Author(s):  
Asirvatham A. Robert ◽  
Mohamed A. Al Dawish
Keyword(s):  
Diabetes Mellitus ◽  
Saudi Arabia ◽  
Present Report ◽  
Adult Population ◽  
Current Trend ◽  
Fold Increase ◽  
Developed Countries ◽  
Evidence Base ◽  
Small Sample ◽  
Cross Sectional

From last few years, the pervasiveness of diabetes mellitus (DM), in Saudi Arabia, is growing at a frightening rate. Overall, one-fourth of the adult population is affected by DM, which is further predicted to rise to more than double by the year 2030. The most alarming is possibly the escalation propensity of diabetes, in recent years, where a nearly ten-fold increase has been witnessed over the past thirty years in Saudi Arabia. However, the number of research arbitrations on the prevalence and incidence of DM is woefully inadequate, as compared to developed countries. Apart from this, most of the existing research data carried out in Saudi Arabia is cross-sectional, with small sample sizes, which most often involve only certain parts of the country. Consequently, the present scenario demands more multidimensional and multisectoral research to strengthen the evidence base and to accumulate greater knowledge as a basis for measures and programmes to confront diabetes and its complications. Thus, the present report makes an attempt to depict the current trend of diabetes as well as intends to put forward essential measures for controlling diabetes in Saudi Arabia.

scholarly journals The analgesic efficacy of extracorporeal shock wave combined with percutaneous vertebroplasty in the treatment of osteoporotic thoracolumbar compression fractures in postmenopausal women

2021 ◽  
Vol 20 (1) ◽  
Author(s):  
Xiaowei Liu ◽  
Hui Wang ◽  
Yang Zhang ◽  
Mingling Wang ◽  
Yujin Qiu ◽  
...  
Keyword(s):  
Shock Wave ◽  
Postmenopausal Women ◽  
Percutaneous Vertebroplasty ◽  
Reduction Rate ◽  
Compression Fracture ◽  
Analgesic Efficacy ◽  
Small Sample ◽  
Compression Fractures ◽  
Extracorporeal Shock Wave ◽  
Post Operation

Abstract Background To explore the analgesic efficacy of extracorporeal shock wave (ESW) combined with percutaneous vertebroplasty (PVP) after reduction in overextension position in the treatment of osteoporotic thoracolumbar compression fractures in postmenopausal women. Methods The data of postmenopausal women with osteoporotic thoracolumbar compression fracture admitted in our department from January 2017 to October 2019 were analyzed retrospectively. They were divided into groups of unipedicular percutaneous kyphoplasty (U-PKP n = 21), bipedicular PKP (B-PKP n = 20), and ESW combined with PVP after reduction in overextension position (EP-PVP n = 18). The improvement of pain and vertebral height in three groups was compared. Results Postoperative compression rate and Cobb angle of vertebral fractures in the three groups were all lower than those before surgery, and the differences between pre-operation and post-operation were statistically significant (P < 0.05). The visual analog scale (VAS) and Oswestry dysfunction index (ODI) scores of the three groups decreased significantly after the operation (P < 0.05). The ODI scores of the EP-PVP group in the third months after the operation were significantly improved compared with the other two groups, and the difference was statistically significant (P < 0.05). Conclusions In our small-sample study, all three treatment schemes can treat osteoporotic compression fracture of thoracolumbar vertebrae in postmenopausal women, relieve pain, and improve quality of life. ESW combined with PVP after reduction in overextension position could achieve a good vertebral reduction rate and improve kyphosis, and may reduce the application of analgesic drugs.

Perceptions and Understanding of Diabetes Mellitus Technology in Adults with Type 1 or Type 2 DM: A Pilot Survey from Pakistan

2021 ◽  
pp. 193229682110111
Author(s):  
Sarah Nadeem ◽  
Uswah Siddiqi ◽  
Russell Seth Martins ◽  
Kaleemullah Badini
Keyword(s):  
Diabetes Mellitus ◽  
Pilot Study ◽  
Diabetes Care ◽  
Online Survey ◽  
Small Sample Size ◽  
Developed Countries ◽  
Small Sample ◽  
Cost Of Care ◽  
Cross Sectional ◽  
Specific Patient

Introduction: Diabetes mellitus technology (DMT) is increasingly used for routine management in developed countries, yet its uptake in developing countries is not as consistent. Multiple factors may influence this, including country specific patient perception regarding DMT. We conducted a pilot study in Pakistan to understand this important question which has not been studied yet. Methods: A cross-sectional pilot study was conducted in Pakistan. An anonymous survey exploring perceptions of diabetes technology was circulated on social media platforms, collecting responses over 2 weeks. Target population included adults (≥18 years) living in Pakistan, with DM1 or 2. Results: A total of 40 responses were received. The majority (36/40) reported using conventional glucometers. Nine used continuous glucose monitoring (CGM). Thirty-two of 40 patients believed DMT improved diabetes care, 22 felt it helped decreased risk of Diabetes-related complications. 15/40 stated that DMT results in increased cost of care. Sixteen reported their diabetes care teams had never discussed wearable DMT options whereas 11 disliked them because they did not want a device on their self. Conclusion: In our pilot study we have identified broad themes of opportunity and challenges to DMT use in Pakistan. Patients’ perceptions regarding DMT were generally positive but significant barriers to its acceptance included high cost, lack of discussion between doctor and patient about available technology and personal hesitation. Limitations of our study include sampling bias (online survey) and small sample size, but this data can help inform larger studies, to look at this important topic in greater detail.

scholarly journals Trends and Opportunities of Tertiary Education in Safety Engineering Moving towards Safety 4.0

2021 ◽  
Vol 13 (2) ◽  
pp. 524
Author(s):  
Vendula Laciok ◽  
Katerina Sikorova ◽  
Bruno Fabiano ◽  
Ales Bernatik
Keyword(s):  
Occupational Safety ◽  
New Technologies ◽  
Positive Impact ◽  
Tertiary Education ◽  
Small Sample Size ◽  
Work Organization ◽  
Small Sample ◽  
Occupational Safety And Health ◽  
Safety Engineering ◽  
Safety And Health

Industry and related work and workplaces are constantly changing as a result of the implementation of new technologies, substances and work processes, changes in the composition of the workforce and the labor market, and new forms of employment and work organization. The implementation of new technologies represents certain ambivalence. Next to the positive impact on workers’ health, new risks and challenges can arise in the area of process and occupational safety and health of people at work. On these bases, it follows the need for predicting and handling the new risks, in order to ensure safe and healthy workplaces in the future. The aim of most forecasting studies is not only to identify new emerging risks, but also to foresee changes that could affect occupational safety and health. However, a number of questions still require proper investigation, i.e., “What impact do new emerging risks have on tertiary education in the area of Safety engineering? Has tertiary education already reacted to progress in science and research and does it have these innovations in its syllabus? How are tertiary graduates prepared for the real world of new technologies?” This paper represents a first attempt in the literature to provide answers to the raised questions, by a survey approach involving academics, Health Safety and Environment (HSE) industrial experts and university students in the Czech Republic. Even if statistical evaluation is limited to a single Country and to a small sample size, the obtained results allow suggesting practical recommendations that can contribute to ensuring new challenges in the area of education by addressing relevant culture issues needed to support new workplace realities according to the newly defined Safety 4.0.

scholarly journals Electrical activity in rat retina in a streptozotocin-induced diabetes model

2018 ◽  
Vol 21 (5) ◽  
pp. 356-363
Author(s):  
Ekaterina M. Klochihina ◽  
Aleksey K. Erdyakov ◽  
Maria P. Morozova ◽  
Svetlana A. Gavrilova ◽  
Elena S. Akhapkina ◽  
...  
Keyword(s):  
Diabetic Retinopathy ◽  
Wave Amplitude ◽  
Developed Countries ◽  
Laboratory Animals ◽  
Control Group ◽  
Oscillatory Potential ◽  
Ischaemic Injury ◽  
Rhythmic Stimulation ◽  
Potential Test ◽  
Wave Latency

Objectives: Diabetic retinopathy remains the major cause of blindness among the working-age population of developed countries. Considering this, experimental models of diabetes involving laboratory animals are important for assessing clinically significant methods to determine early pathologic alterations of the retina. The early detection of diabetic retinopathy in combination with a search for new pathogenetic targets will enable focusing on new strategies to limit the development of critical changes in the retina and to prolong retinal functioning during the development of diabetes mellitus. Aim: This study aimed to define parameters of electroretinography test that identifies changes due to retinal impairment in diabetes. Methods: Experimental diabetes was induced in Wistar rats by intraperitoneally injecting streptozocin (65 mg/kg; group DM). The control group (CB) received intraperitoneal injections of the vehicle, i.e. citric buffer. On each consecutive day of the experiment, all rats received insulin detemir (2 u/kg). Ophthalmoscopy and electroretinography were conducted before initiating the experiment and after 50, 58 and 66 days of injectin sptreptozocin. Results: Amid 2u\kg insulin injection the glucose level in venous blood in DM group amounted to 30-40 mM. The ophthalmoscopy showed that the optic nerve disk paled by the 50th day, with its line erasing. During electroretinography, wave amplitude in oscillatory potential test tended to decrease. -wave latency of photopic system increased with -wave latency of photopic system and - and -waves latency of scotopic system not altering. In addition, the amplitude of rhythmic stimulation of 8 and 12 Hz decreased. Conclusion: The most apparent parameters of electroretinography for modelling streptozocin-induced diabetes are wave amplitude during the oscillatory potential test, photopic B-wave latency and the amplitude of rhythmic stimulation. These results suggest that in diabetes, ischaemic injury is an important cause of early dysfunction of inner retinal layers.

scholarly journals Spectral Minutiae Fingerprint Recognition System

2014 ◽  
pp. 103-108
Author(s):  
S. Shanawaz Basha ◽  
N. Musrat Sultana
Keyword(s):  
Large Scale ◽  
Reduction Rate ◽  
Principal Component ◽  
Rejection Rate ◽  
Recognition System ◽  
Feature Reduction ◽  
Fingerprint Recognition ◽  
Identification System ◽  
Behavioral Characteristics ◽  
Template Size

Biometrics refers to the automatic recognition of individuals based on their physiological and/or behavioral characteristics, such as faces, finger prints, iris, and gait. In this paper, we focus on the application of finger print recognition system. The spectral minutiae fingerprint recognition is a method to represent a minutiae set as a fixedlength feature vector, which is invariant to translation, and in which rotation and scaling become translations, so that they can be easily compensated for. Based on the spectral minutiae features, this paper introduces two feature reduction algorithms: the Column Principal Component Analysis and the Line Discrete Fourier Transform feature reductions, which can efficiently compress the template size with a reduction rate of 94%.With reduced features, we can also achieve a fast minutiae-based matching algorithm. This paper presents the performance of the spectral minutiae fingerprint recognition system, this fast operation renders our system suitable for a large-scale fingerprint identification system, thus significantly reducing the time to perform matching, especially in systems like, police patrolling, airports etc,. The spectral minutiae representation system tends to significantly reduce the false acceptance rate with a marginal increase in the false rejection rate.

Sign in / Sign up

Export Citation Format

Share Document