SLO | ENG | Piškotki in zasebnost

Večja pisava | Manjša pisava

Iskanje po katalogu digitalne knjižnice Pomoč

Iskalni niz: išči po
išči po
išči po
išči po
* po starem in bolonjskem študiju


1 - 10 / 14
Na začetekNa prejšnjo stran12Na naslednjo stranNa konec
Machine learning helps physicians in diagnosing of mitral valve prolapse
Petra Povalej, Mitja Lenič, Milan Zorman, Peter Kokol, Lenka Lhotska, Rado Pišot, 2003, izvirni znanstveni članek

Opis: In this paper we present a multimethod approach for induction of a specific class of classifiers, which can assist physicians in medical diagnosing in the case of mitral valve prolapse. Mitral valve prolapse is one of the most controversial prevalent cardiac condition and may affect up to ten percent of the population and in the worst case results in sudden death. MultiVeDec is a general framework enabling researchers to generate various intelligent tools based on machine learning. In this paper we focused on various decision tree methods, which are capable of extracting knowledge in a form closer to human perception, a feature that is very important in medical field. The experiment included classifiers with various classical single method approaches, evolutionary approaches, hybrid approaches and also our newest multimethod approach. The main concern of the latest approach is to find a way to enable dynamic combination of methodologies to the somehow quasi unified knowledge representation. The proposed multimethod approach was capable to outperform all other tested approaches by producing classifier for diagnosing mitral valve prolapse with the highest overall and average class accuracy. More importantly, it was also capable to find some new knowledge important in diagnosing of mitral valve prolapse.
Objavljeno: 01.06.2012; Ogledov: 905; Prenosov: 23
URL Celotno besedilo (0,00 KB)

Non-invasive methods for children's cholesterol level determination
Petra Povalej, Peter Kokol, Jernej Završnik, 2003, strokovni članek

Opis: Today, there is a controversy about the role of cholesterol in infants and the measurement and management of blood cholesterol in children. Several scientific evidences are supporting relationship between elevated blood cholesterol in children and high cholesterol in adults and development of adult arteriosclerotic diseases such as cardiovascular and cerebrovascular disease. Therefore controlling the level of blood cholesterol in children is very important for the health of the whole population. Non-invasive methods are much more convenient for the children because of their anxieties about blood examinations. In this paper we will present a new try to find non-invasive methods for determining the level of blood cholesterol in children with the use of intelligent system.
Ključne besede: cholesterol level determination, noninvasive method
Objavljeno: 01.06.2012; Ogledov: 907; Prenosov: 4
URL Celotno besedilo (0,00 KB)

Improving medical decision making by self organizing intelligent systems
Peter Kokol, Petra Povalej, Gregor Štiglic, Dejan Dinevski, 2008, objavljeni znanstveni prispevek na konferenci

Ključne besede: cellular automata, classification, machine learning
Objavljeno: 05.06.2012; Ogledov: 1205; Prenosov: 18
URL Celotno besedilo (0,00 KB)

Erythropoietic protoporphyria patients in Slovenia
Maksimiljan Gorenjak, Petra Povalej, Jovan Miljković, Aleksej Kansky, Pij B. Marko, 2007, izvirni znanstveni članek

Opis: Background: There are only scarce epidemiological data on the prevalence of erythropoietic protoporphyria (EPP) in a given population. The aim of this study was to assess the prevalence of EPP within the Slovenian population. Materials and methods: The patients were selected by routine examination of photosensitive patients and by studying hospital records. A quantitative method was used to assess protoporphyrin, with values larger than 530 nm/l considered elevated. Results: 32 EPP patients were detected, which allows us to estimate the prevalence of EPP in Slovenia at 1.75 per 100,000 inhabitants.
Objavljeno: 21.12.2015; Ogledov: 270; Prenosov: 9
URL Celotno besedilo (0,00 KB)

Comprehensible predictive modeling using regularized logistic regression and comorbidity based features
Gregor Štiglic, Nino Fijačko, Petra Povalej, Fei Wang, Alexandros Kalousis, Boris Delibašić, Zoran Obradović, 2015, izvirni znanstveni članek

Opis: Different studies have demonstrated the importance of comorbidities to better understand the origin and evolution of medical complications. This study focuses on improvement of the predictive model interpretability based on simple logical features representing comorbidities. We use group lasso based feature interaction discovery followed by a post-processing step, where simple logic terms are added. In the final step, we reduce the feature set by applying lasso logistic regression to obtain a compact set of non-zero coefficients that represent a more comprehensible predictive model. The effectiveness of the proposed approach was demonstrated on a pediatric hospital discharge dataset that was used to build a readmission risk estimation model. The evaluation of the proposed method demonstrates a reduction of the initial set of features in a regression model by 72%, with a slight improvement in the Area Under the ROC Curve metric from 0.763 (95% CI: 0.755%0.771) to 0.769 (95% CI: 0.761%0.777). Additionally, our results show improvement in comprehensibility of the final predictive model using simple comorbidity based terms for logistic regression.
Ključne besede: predictive models, logistic regression, readmission classification, comorbidities
Objavljeno: 19.06.2017; Ogledov: 170; Prenosov: 38
.pdf Celotno besedilo (1,13 MB)

Book of Abstracts International Scientific Conference »Research and Education in Nursing«
2017, druge monografije in druga zaključena dela

Opis: University of Maribor Faculty of Health Sciences is organizing an International Scientific Conference »Research and Education in Nursing«. It will be held on June 15th 2017 at the faculty and will include most recent findings of domestic and foreign researchers and students in nursing and health sciences. All abstracts are included in the International Scientific Conference Proceedings. The conference aims to explore advances in nursing research and education and it is intended for knowledge and experience exchange of participants about the impact of research on health care in Slovenian and international arena. It will provide an opportunity to promote the development, dissemination and use of knowledge in the field of nursing and health sciences for nursing practitioners and educators, furthermore they can exchange research evidence, models of best practice and innovative ideas.
Objavljeno: 19.07.2017; Ogledov: 152; Prenosov: 15

Contribution of temporal data to predictive performance in 30-day readmission of morbidly obese patients
Petra Povalej, Zoran Obradović, Gregor Štiglic, 2017, izvirni znanstveni članek

Opis: Background: Reduction of readmissions after discharge represents an important challenge for many hospitals and has attracted the interest of many researchers in the past few years. Most of the studies in this field focus on building cross-sectional predictive models that aim to predict the occurrence of readmission within 30-days based on information from the current hospitalization. The aim of this study is demonstration of predictive performance gain obtained by inclusion of information from historical hospitalization records among morbidly obese patients. Methods: The California Statewide inpatient database was used to build regularized logistic regression models for prediction of readmission in morbidly obese patients (n = 18,881). Temporal features were extracted from historical patient hospitalization records in a one-year timeframe. Five different datasets of patients were prepared based on the number of available hospitalizations per patient. Sample size of the five datasets ranged from 4,787 patients with more than five hospitalizations to 20,521 patients with at least two hospitalization records in one year. A 10-fold cross validation was repeted 100 times to assess the variability of the results. Additionally, random forest and extreme gradient boosting were used to confirm the results. Results: Area under the ROC curve increased significantly when including information from up to three historical records on all datasets. The inclusion of more than three historical records was not efficient. Similar results can be observed for Brier score and PPV value. The number of selected predictors corresponded to the complexity of the dataset ranging from an average of 29.50 selected features on the smallest dataset to 184.96 on the largest dataset based on 100 repetitions of 10-fold cross-validation. Discussion: The results show positive influence of adding information from historical hospitalization records on predictive performance using all predictive modeling techniques used in this study. We can conclude that it is advantageous to build separate readmission prediction models in subgroups of patients with more hospital admissions by aggregating information from up to three previous hospitalizations.
Ključne besede: readmission prediction, predictive modelling, temporal data
Objavljeno: 02.08.2017; Ogledov: 237; Prenosov: 29
.pdf Celotno besedilo (1,10 MB)

New perspectives for computer-aided discrimination of Parkinson's disease and essential tremor
Petra Povalej, J.A. Gallego, J. P. Romero, Vojko Glaser, E. Rocon, Julián Benito-León, Félix Bermejo-Pareja, Ignacio Posada, Aleš Holobar, 2017, izvirni znanstveni članek

Opis: Pathological tremor is a common but highly complex movement disorder, affecting ~5% of population older than 65 years. Different methodologies have been proposed for its quantification. Nevertheless, the discrimination between Parkinson's disease tremor and essential tremor remains a daunting clinical challenge, greatly impacting patient treatment and basic research. Here, we propose and compare several movement-based and electromyography-based tremor quantification metrics. For the latter, we identified individual motor unit discharge patterns from high-density surface electromyograms and characterized the neural drive to a single muscle and how it relates to other affected muscles in 27 Parkinson's disease and 27 essential tremor patients. We also computed several metrics from the literature. The most discriminative metrics were the symmetry of the neural drive to muscles, motor unit synchronization, and the mean log power of the tremor harmonics in movement recordings. Noteworthily, the first two most discriminative metrics were proposed in this study. We then used decision tree modelling to find the most discriminative combinations of individual metrics, which increased the accuracy of tremor type discrimination to 94%. In summary, the proposed neural drive-based metrics were the most accurate at discriminating and characterizing the two most common pathological tremor types.
Ključne besede: Parkinson's disease, essential tremor, electromyography, wrist movements, motor units, muscular excitation, decision tree
Objavljeno: 03.11.2017; Ogledov: 198; Prenosov: 19
.pdf Celotno besedilo (3,31 MB)

Vesna Kondić, 2015, magistrsko delo/naloga

Opis: Varnost in zdravje pri delu sta ključna elementa pri zagotavljanju bolj zdravega in daljšega poklicnega življenja. Problem: Delo neposredno vpliva na zdravje, saj ljudje na delovnem mestu preživijo veliko časa, zato je zagotavljanje varnosti in zdravja delavcev pri delu zelo pomemben člen, ki ga mora delodajalec tudi zakonsko upoštevati. Namen: Namen magistrskega dela je proučiti učinkovitost promocije zdravja na delovnem mestu z vidika varovanja zdravja zaposlenih in ozaveščanja zaposlenih o pomembnosti promocije zdravja na delovnem mestu. Cilji: Cilja sta bila ugotoviti, ali zaposleni prepoznajo promocijo zdravja na delovnem mestu in kakšno je njihovo mnenje glede učinkovitosti promocije zdravja na delovnem mestu. Proučili smo tudi razlike v počutju zaposlenih v organizaciji, kjer se izvaja promocija zdravja na delovnem mestu. Metodologija: Uporabili smo kvalitativne (intervju z delodajalci oz. z njihovimi predstavniki) in kvantitativne metode (vprašalnik za zaposlene). Kvalitativni del raziskave je bil narejen v sedmih različnih podjetjih, kjer smo delodajalcem oz. njihovim predstavnikom postavili vnaprej pripravljena vprašanja. Za kvantitativni del so bili podatki zbrani s spletnim vprašalnikom, in sicer na podlagi metode snežne kepe. Populacijo so predstavljali vsi zaposleni v RS. Rezultati so bili obdelani s statističnim programskim paketom SPSS, verzija 22.0. Raziskovalni vzorec pa je bil predstavljen na podlagi frekvenc, pripadajočih odstotkov in na podlagi povprečnih vrednosti in standardnih odklonov. Primerjava je bila narejena na podlagi hi-kvadrat testa. Bistvene ugotovitve: Tako delavci kot tudi delodajalci se zavedajo, da je promocija zdravja na delovnem mestu koristna, a se očitno izvaja bolje v organizacijah, ki so v tuji lasti. Zaposleni v organizacijah s tujim lastništvom menijo, da so njihova delovna mesta bolj zdravo oblikovana, preprečujejo poškodbe na delovnem mestu, zmanjšujejo izpostavljenost škodljivim kemijskim snovem, imajo poskrbljeno za topel obrok, v primerjavi s tistimi zaposlenimi, ki delajo v organizacijah, kjer je lastništvo domače. Tako lahko tudi s to raziskavo potrdimo, da bi bilo v Sloveniji treba še dosti narediti na ukrepih, ki so bili do sedaj precej zanemarjeni. Vpliva promocije zdravja na delovnem mestu na zmanjšanje števila bolniških odsotnosti in število fluktuacij na delovnem mestu nismo dokazali.
Ključne besede: - promocija zdravja, - varnost in zdravje pri delu, - promocija zdravja na delovnem mestu, - absentizem.
Objavljeno: 19.02.2015; Ogledov: 1676; Prenosov: 856
.pdf Celotno besedilo (738,10 KB)

Napovedovanje rehospitalizacij za paciente z multiplo sklerozo
Sanja Rikanović, 2016, magistrsko delo

Opis: V magistrskem delu smo raziskovali nenačrtovane ponovne sprejeme pri pacientih z multiplo sklerozo (MS). Cilj našega raziskovalnega dela je bil sestaviti model, ki bo pri napovedovanju nenačrtovanih ponovnih sprejemov uspešnejši od modelov, ki niso vezani na posamezno diagnozo. Pri pisanju teoretičnega dela naloge smo se opirali na strokovno literaturo o multipli sklerozi ter na raziskave o modelih za napovedovanje nenačrtovanih ponovnih sprejemov. Za empirični del naloge smo uporabili podatke iz podatkovne baze SID (State Inpatient Database) za Kalifornijo, ki je del skupine podatkovnih baz, razvitih v okviru projekta HCUP (Healthcare Cost and Utilization Project). Specializiran napovedni model, zgrajen na osnovi podatkov o pacientih z multiplo sklerozo, se je pri napovedovanju ponovnega sprejema bolnikov z MS v manj kot 30 dneh izkazal kot uspešnejši od globalnega modela, ki je bil zgrajen na osnovi podatkov o vseh pacientih ne glede na diagnozo. Povprečna AUC-vrednost specializiranega modela je znašala 0,708, kar je za 0,042 višje od povprečne AUC-vrednosti globalnega modela (AUC = 0,666). Prav tako smo pri specializiranem modelu zaznali višje povprečne vrednosti diagnostične natančnosti, senzitivnosti, specifičnosti in NPV. Dodaten prispevek specializiranega modela v primerjavi z globalnim modelom se kaže tudi v nižji Brierjevi oceni ter v manjšem številu uporabljenih vhodnih spremenljivk in posledično v manj kompleksnem modelu. Vse našteto govori v prid specializiranemu napovednemu modelu za paciente z MS, zato smo v naslednjem koraku temu modelu dodali še podatke o predhodnih hospitalizacijah in ugotovili, da vključitev zgodovinskih podatkov o hospitalizacijah prav tako pozitivno vpliva na napovedovanje nenačrtovanih ponovnih sprejemov. Za napovedovanje nenačrtovanih ponovnih sprejemov pri pacientih z MS je bolje uporabiti specializiran model kot splošnega. Rezultati magistrskega dela so primerni za nadaljnje proučevanje rehospitalizacij pri pacientih z MS.
Ključne besede: multipla skleroza, rehospitalizacija, bolnišnična odpustna pisma, napovedni model, Lasso regresija, ansambelske metode, odločitvena drevesa.
Objavljeno: 01.09.2016; Ogledov: 551; Prenosov: 82
.pdf Celotno besedilo (888,29 KB)

Iskanje izvedeno v 0.05 sek.
Na vrh
Logotipi partnerjev Univerza v Mariboru Univerza v Ljubljani Univerza na Primorskem Univerza v Novi Gorici