检索结果-内蒙古大学图书馆

Classification of Diabetes Types using Machine Learning

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2022年第9期13卷 152-161页

作者： Adigun, Oyeranmi Oyeranm, Folasade Yekini, Nureni Babatunde, Ronke Yaba Coll Technol Dept Comp Sci Lagos Nigeria Yaba Coll Technol Dept Comp Engn Lagos Nigeria Kwara State Univ Dept Comp Sci Malete Kwara Nigeria

learning algorithms have aided health workers (including doctors) in the processing, analysis, and diagnosis of medical problems, as well as the detection of disease patterns and other patient data. Diabetes mellitus (DM), commonly referred to as diabetes, is a gathering of a syndrome issue that is portrayed by high glucose levels in the blood over a drawn-out period. It is a long-term illness that is a great threat to humanity and causes death. Most of the existing machine learning algorithms used for the classification and prediction of diabetes suffer from embodying redundant or inessential medical procedures that cause complications and wastage of time and resources. The absence of a correct diagnosis scheme, deficiency of economic means, and a general lack of awareness represent the main reasons for these negative effects. Hence, preventing the sickness altogether through early detection may doubtless cut back a considerable burden on the economy and aid the patient in diabetes management. This study developed diabetes classification using machine learning techniques that will minimize the aforementioned drawbacks in the prediction of diabetes systems. Decision tree classifiers, logistic regression, random forest, and support vector machines are all examples of predictive algorithms that were tested in this paper. 1009 records of data set were obtained from the Diabetes dataset of Abelvikas, Data World. We used a confusion matrix to visualize the performance evaluation of the classifiers. The experimental result shows that the four machine learning algorithms perform well. However, Random Forest outperforms the other three, with a prediction accuracy of 100% and has a better prediction level when compared with others and existing work.

关键词： -Machine learning diabetes mellitus predictive algorithm correlation map confusion matrix

来源：评论

学校读者我要写书评

暂无评论

Utilising artificial intelligence to determine patients at risk of a rare disease: idiopathic pulmonary arterial hypertension

引用

PULMONARY CIRCULATION 2019年第4期9卷 2045894019890549页

作者： Kiely, David G. Doyle, Orla Drage, Edmund Jenner, Harvey Salvatelli, Valentina Daniels, Flora A. Rigg, John Schmitt, Claude Samyshkin, Yevgeniy Lawrie, Allan Bergemann, Rito Royal Hallamshire Hosp Sheffield Pulm Vasc Dis Unit Sheffield S Yorkshire England Univ Sheffield Dept Infect Immun & Cardiovasc Dis Sheffield S Yorkshire England Univ Sheffield INSIGNEO Sheffield S Yorkshire England IQVIA Real World & Analyt Solut London England GSK Brentford Middx England Evalueserve UK Ltd London England

Idiopathic pulmonary arterial hypertension is a rare and life-shortening condition often diagnosed at an advanced stage. Despite increased awareness, the delay to diagnosis remains unchanged. This study explores whether a predictive model based on healthcare resource utilisation can be used to screen large populations to identify patients at high risk of idiopathic pulmonary arterial hypertension. Hospital Episode Statistics from the National Health Service in England, providing close to full national coverage, were used as a measure of healthcare resource utilisation. Data for patients with idiopathic pulmonary arterial hypertension from the National Pulmonary Hypertension Service in Sheffield were linked to pre-diagnosis Hospital Episode Statistics records. A non-idiopathic pulmonary arterial hypertension control cohort was selected from the Hospital Episode Statistics population. Patient history was limited to <= 5 years pre-diagnosis. Information on demographics, timing/frequency of diagnoses, medical specialities visited and procedures undertaken was captured. For modelling, a bagged gradient boosting trees algorithm was used to discriminate between cohorts. Between 2008 and 2016, 709 patients with idiopathic pulmonary arterial hypertension were identified and compared with a stratified cohort of 2,812,458 patients classified as non-idiopathic pulmonary arterial hypertension with >= 1 ICD-10 coded diagnosis of relevance to idiopathic pulmonary arterial hypertension. A predictive model was developed and validated using cross-validation. The timing and frequency of the clinical speciality seen, secondary diagnoses and age were key variables driving the algorithm's performance. To identify the 100 patients at highest risk of idiopathic pulmonary arterial hypertension, 969 patients would need to be screened with a specificity of 99.99% and sensitivity of 14.10% based on a prevalence of 5.5/million. The positive predictive and negative predictive values were 10.32%

关键词： predictive algorithm machine learning idiopathic pulmonary arterial hypertension (PAH) diagnosis

来源：评论

学校读者我要写书评

暂无评论

Predicting misdiagnosed adult-onset type 1 diabetes using machine learning

引用

DIABETES RESEARCH AND CLINICAL PRACTICE 2022年 191卷 110029-110029页

作者： Cheheltani, Rabee King, Nicholas Lee, Suyin North, Benjamin Kovarik, Danny -Molina, Carmella Evans Leavitt, Nadejda Dutta, Sanjoy IQVIA Real World Solut Predict Analyt Wayne PA USA JDRF New York NY USA Indiana Univ Sch Med Ctr Diabet & Metab Dis Indianapolis IN USA 200 Vesey St 28th Floor New York NY 10281 USA

Aims: It is now understood that almost half of newly diagnosed cases of type 1 diabetes are adult-onset. However, type 1 and type 2 diabetes are difficult to initially distinguish clinically in adults, potentially leading to inef-fective care. In this study a machine learning model was developed to identify type 1 diabetes patients mis-diagnosed as type 2 ***: In this retrospective study, a machine learning model was developed to identify misdiagnosed type 1 diabetes patients from a population of patients with a prior type 2 diabetes diagnosis. Using Ambulatory Elec-tronic Medical Records (AEMR), features capturing relevant information on age, demographics, risk factors, symptoms, treatments, procedures, vitals, or lab results were extracted from patients' medical ***: The model identified age, BMI/weight, therapy history, and HbA1c/blood glucose values among top predictors of misdiagnosis. Model precision at low levels of recall (10 %) was 17 %, compared to <1 % incidence rate of misdiagnosis at the time of the first type 2 diabetes encounter in ***: This algorithm shows potential for being translated into screening guidelines or a clinical decision support tool embedded directly in an EMR system to reduce misdiagnosis of adult-onset type 1 diabetes and implement effective care at the outset.

关键词： Adult -onset type 1 diabetes Machine learning Misdiagnosis Clinical decision support tool predictive algorithm AI

来源：评论

学校读者我要写书评

暂无评论

Discovery of novel antimicrobial peptides: A transcriptomic study of the sea anemone Cnidopus japonicus

引用

JOURNAL OF BIOINFORMATICS AND COMPUTATIONAL BIOLOGY 2018年第2期16卷 1840006-1840006页

作者： Grafskaia, Ekaterina N. Polina, Nadezhda F. Babenko, Vladislav V. Kharlampieva, Daria D. Bobrovsky, Pavel A. Manuvera, Valentin A. Farafonova, Tatyana E. Anikanov, Nikolay A. Lazarev, Vassili N. Moscow Inst Phys & Technol Dept Biol & Med Phys Inst Skii 9 Moscow 141700 Russia Fed Med Biol Agcy Fed Res & Clin Ctr Phys Chem Med 1A Malaya Pirogovskaya St Moscow 119435 Russia Russian Acad Sci Inst Biomed Chem Lab Syst Biol Dept Prote Res & Mass Spectrometry 10 Pogodinskaya St Moscow 119121 Russia Russian Acad Sci Dept Peptide & Prot Technol Lab Prote Shemyakin Ovchinnikov Inst Bioorgan Chem 16-10 Miklukho Maklaya St Moscow 117997 Russia

As essential conservative component of the innate immune systems of living organisms, antimicrobial peptides (AMPs) could complement pharmaceuticals that increasingly fail to combat various pathogens exhibiting increased resistance to microbial antibiotics. Among the properties of AMPs that suggest their potential as therapeutic agents, diverse peptides in the venoms of various predators demonstrate antimicrobial activity and kill a wide range of microorganisms. To identify potent AMPs, the study reported here involved a transcriptomic profiling of the tentacle secretion of the sea anemone Cnidopus japonicus. An in silico search algorithm designed to discover toxin-like proteins containing AMPs was developed based on the evaluation of the properties and structural peculiarities of amino acid sequences. The algorithm revealed new proteins of the anemone containing antimicrobial candidate sequences, and 10 AMPs verified using high-throughput proteomics were synthesized. The antimicrobial activity of the candidate molecules was experimentally estimated against Gram-positive and -negative bacteria. Ultimately, three peptides exhibited antimicrobial activity against bacterial strains, which suggests that the method can be applied to reveal new AMPs in the venoms of other predators as well.

关键词： Antimicrobial peptides sea anemone toxin transcriptome predictive algorithm

来源：评论

学校读者我要写书评

暂无评论

Structure-based prediction of binding peptides to MHC class I molecules: Application to a broad range of MHC alleles

引用

PROTEIN SCIENCE 2000年第9期9卷 1838-1846页

作者： Schueler-Furman, O Altuvia, Y Sette, A Margalit, H Hebrew Univ Jerusalem Hadassah Med Sch Dept Mol Genet & Biotechnol IL-91120 Jerusalem Israel Epimmune Inc San Diego CA 92121 USA

Specific binding of antigenic peptides to major histocompatibility complex (MHC) class I molecules is a prerequisite for their recognition by cytotoxic T-cells. Prediction of MHC-binding peptides must therefore be incorporated in any predictive algorithm attempting to identify immunodominant T-cell epitopes, based on the amino acid sequence of the protein antigen. Development of predictive algorithms based on experimental binding data requires experimental testing of a very large number of peptides. A complementary approach relies on the structural conservation observed in crystallographically solved peptide-MHC complexes. By this approach, the peptide structure in the MHC groove is used as a template upon which peptide candidates are threaded, and their compatibility to bind is evaluated by statistical pairwise potentials. Our original algorithm based on this approach used the pairwise potential table of Miyazawa and Jernigan (Miyazawa S, Jernigan RL, 1996, J Mol Biol 256:623-644) and succeeded to correctly identify good binders only for MHC molecules with hydrophobic binding pockets, probably because of the high emphasis of hydrophobic interactions in this table. A recently developed pairwise potential table by Betancourt and Thirumalai (Betancourt MR, Thirumalai D, 1999, Protein Sci 8:361-369) that is based on the Miyazawa and Jernigan table describes the hydrophilic interactions more appropriately. In this paper, we demonstrate how the use of this table, together with a new definition of MHC contact residues by which only residues that contribute exclusively to sequence specific binding are included, allows the development of an improved algorithm that can be applied to a wide range of MHC class I alleles.

关键词： knowledge-based prediction MHC class I pairwise potential peptide-protein binding predictive algorithm

来源：评论

学校读者我要写书评

暂无评论

Prediction Aided Tapering In rheumatoid arthritis patients treated with biOlogicals (PATIO): protocol for a randomized controlled trial

引用

TRIALS 2022年第1期23卷 494-494页

作者： Messelink, Marianne A. van der Leeuw, Matthijs S. den Broeder, Alfons A. Tekstra, Janneke van der Goes, Marlies C. Heijstek, Marloes W. Lafeber, Floris Welsing, Paco M. J. Univ Utrecht Univ Med Ctr Utrecht Dept Rheumatol & Clin Immunol Heidelberglaan 100 NL-3508 GA Utrecht Netherlands Sint Maartensklin Dept Rheumatol Hengstdal 3 NL-3508 GA Ubbergen Netherlands Meander Med Ctr Dept Rheumatol Maatweg 3 NL-3813 TZ Amersfoort Netherlands

Background: Biological disease-modifying anti-rheumatic drugs (bDMARDs) are effective in the treatment of rheumatoid arthritis (RA) but are expensive and increase the risk of infection. Therefore, in patients with a stable low level of disease activity or remission, tapering bDMARDs should be considered. Although tapering does not seem to affect long-term disease control, (short-lived) flares are frequent during the tapering process. We have previously developed and externally validated a dynamic flare prediction model for use as a decision aid during stepwise tapering of bDMARDs to reduce the risk of a flare during this process. Methods: In this investigator-initiated, multicenter, open-label, randomized (1:1) controlled trial, we will assess the effect of incorporating flare risk predictions into a bDMARD tapering strategy. One hundred sixty RA patients treated with a bDMARD with stable low disease activity will be recruited. In the control group, the bDMARD will be tapered according to "disease activity guided dose optimization" (DGDO). In the intervention group, the bDMARD will be tapered according to a strategy that combines DGDO with the dynamic flare prediction model, where the next bDMARD tapering step is not taken in case of a high risk of flare. Patients will be randomized 1:1 to the control or intervention group. The primary outcome is the number of flares per patient (DAS28-CRP increase > 1.2, or DAS28-CRP increase > 0.6 with a current DAS28-CRP >= 2.9) during the 18-month follow-up period. Secondary outcomes include the number of patients with a major flare (flare duration >= 12 weeks), bDMARD dose reduction, adverse events, disease activity (DAS28-CRP) and patient-reported outcomes such as quality of life and functional disability. Health Care Utilization and Work Productivity will also be assessed. Discussion: This will be the first clinical trial to evaluate the benefit of applying a dynamic flare prediction model as a decision aid during bDMARD tape

关键词： Rheumatoid arthritis Dose reduction Tapering bDMARD Biological Clinical decision aid Prediction model Randomized controlled trial Study protocol predictive algorithm

来源：评论

学校读者我要写书评

暂无评论

Data Sources for Signature Discovery in Toxicology

Data Sources for Signature Discovery in Toxicology

引用

作者： Dragana Mitic Potkrajac Branka Rakic Gordana Apic Robert B. Russell

From a systems biology point of view, signature of a chemical can be defined as a collection of data or a measure of cellular response to a certain chemical, where biomarkers are often the best characteristics objectively measured and evaluated as an indicator of the biological processes. Chemical profiles (signatures) related to chemical-induced gene expression and gene changes coupled to particular pathologies require additional interpretation and processing to identify true biomarker candidates and together with the mechanistic hypothesis underlying biological effects of that chemical enable comprehensive knowledge about chemical toxic effect. Knowledge bases such as ToxWiz capture a broad spectrum of mechanistic hypothesis and pathways for toxic effects derived from precise expert analysis of millions of scientific articles, establishing connections between mechanism of disease, pathology, and toxic endpoints, and representing them in a form of biological pathways for underlying toxic endpoints. A unique module connected to ToxWiz knowledge base represents a hand-curated database of gene expression signatures. This module contains a good size collection of 1000 unique toxicity signatures related to chemical-induced toxicities in human, rat, mouse, and several nonmammalian species covering studies with 297 compounds, known to induce major toxicities in liver, kidney, and most other major organ systems. Implemented software tools based on systems biology principles allow analysis of novel compounds for toxic effects and allows the analysis of your own data in order to identify new biomarker candidates by interrogating your -omics data with gene signatures module. By describing biological pathways underlying the toxic effects, and discovering and exploring related biomarkers, these tools promise to help design safer chemicals. Furthermore, we describe here an example exercise on annotated public data, using ToxWiz knowledge base and tools, which confirm and expand

关键词： Systems biology Biomarkers Molecular mechanism Manual curation Data extraction ToxWiz Toxic endpoint Chemical signature predictive algorithm Gene expression data

来源：评论

学校读者我要写书评

暂无评论

A Single-Phase Power Factor Correction with Current Control

A Single-Phase Power Factor Correction with Current Control

引用

2012 International Conference on Power Electronics Engineering and Computer Technology(PEECT 2012)

作者： Zezhong Xia Xuebei Ren Rongde Yang Automation College Wuhan University of Technology

In this paper a new current control strategy based on DSP for power factor correction is presented. Boost converter controlled by DSC can achieve sinusoidal current, but we have to compromise between the switching frequency and the executing speed. With the help of predictive algorithm, DSP can efficiently compute the duty cycle needed for the next period, and less instruction cycles is needed to complete the current calculation. A 400 W experiment prototype is built using the ds PIC33 F digital signal controller. Experiment and simulation show that the predictive current control algorithm can achieve high power factor and low ripple of output voltage. And the algorithm can produce less THD of input current and has better dynamic response, compared with the traditional current PI control strategy.

关键词： PFC Digital control predictive algorithm

来源：评论

学校读者我要写书评

暂无评论

Prediction of stroke using an algorithm to estimate arterial stiffness

引用

INTERNATIONAL JOURNAL OF CARDIOLOGY CARDIOVASCULAR RISK AND PREVENTION 2021年 11卷 200114-200114页

作者： Kostis, John B. Lin, Chun Pang Dobrzynski, Jeanne M. Kostis, William J. Ambrosio, Matthew Cabrera, Javier Rutgers Robert Wood Johnson Med Sch Cardiovasc Inst New Brunswick NJ USA City Univ Hong Kong Hong Kong Peoples R China Rutgers State Univ New Brunswick NJ USA

Background: Arterial stiffness is important because it is associated with adverse cardiovascular events including stroke. Methods that are based on pulse wave velocity have significant limitations in estimating arterial stiffness. The purpose of this paper is to present a novel easy to apply non-invasive method to estimate arterial stiffness that is based on pulse pressure. Methods: Two indices to estimate arterial stiffness, (1) arterial stiffness 1 (AS1) and (2) arterial stiffness 2 (AS2) were developed and applied in two National Institutes of Health funded clinical trials, the Systolic Hypertension in the Elderly Program and the Systolic Blood Pressure Intervention Trial. These indices were developed by fitting individual survival models for selected predictor variables to the response, i.e. time to stroke, by selecting the coefficients that were statistically significant at the 0.05 a level after adjusting the variable weights. The indices were derived as the weighted linear combination of the coefficients. Results: AS1 and AS2 performed well in two goodness of fit criteria i.e. overall model p-value and concordance correlation. Comparison of Cox models using indices AS1 and AS2 and chronological age indicated that AS1 and AS2 independently predicted the occurrence of stroke at five years better than chronological age. Nearly identical effects were observed when the analyses were limited to Black participants in SPRINT with a concordance correlation of 0.80 and log rank test p-value of 0.007. Conclusion: These indices that are derived from pulse pressure predict the occurrence of stroke better than either pulse pressure or chronological age alone and may be used in designing new randomized clinical trials, and possibly incorporated in hypertension and stroke guidelines.

关键词： Arterial stiffness Stroke Pulse pressure predictive algorithm

来源：评论

学校读者我要写书评

暂无评论

Predicting TMS-induced activation in human neocortex using concurrent TMS/PET, finite element analysis and computational modeling

引用

BIOMEDICAL PHYSICS & ENGINEERING EXPRESS 2019年第2期5卷

作者： Arabkheradmand, Ghazaleh Krieg, Todd D. Salinas, Felipe S. Fox, Peter T. Mogul, David J. IIT Biomed Engn Dept Chicago IL 60616 USA Univ Texas Hlth Sci Ctr San Antonio Res Imaging Inst San Antonio TX 78229 USA

Transcranial magnetic stimulation (TMS) is a powerful technique to noninvasively activate neurons in the brain. However, the relationship between TMS-generated electric fields (E-fields) and specific cortical responses is not well understood. The goal of this study was to investigate the relationship between induced E-fields and neocortical activation measured by metabolic responses. Human subject-specific detailed finite element models (FEM) of the head were constructed to calculate the distribution of induced cortical E-field vectors. Positron emission tomography (PET) recordings were made during concurrent TMS application as a measure of cortical activation. A functional model of local circuit connections was developed to study the relationship between applied magnetic fields and neocortical activation and was fitted to experimental data. Sensitivity of interneurons to induced tangential E-fields was over twice as strong as pyramidal neuron sensitivity to induced normal E-fields which may help explain why cortical electrophysiological responses to TMS have specific sensitivities to coil orientation. Furthermore, this study produced an algorithm for predicting electrophysiological responses in human neocortex with high accuracy (> 95%) that could provide an invaluable tool for planning of specific regional cortical activation critical in both research and clinical applications.

关键词： transcranial magnetic stimulation pet cortical activation predictive algorithm finite element modeling

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：