1. Artificial intelligence based prediction of diabetic foot risk in patients with diabetes : a literature reviewLucija Gosak, Adrijana Svenšek, Mateja Lorber, Gregor Štiglic, 2023, pregledni znanstveni članek Opis: Diabetic foot is a prevalent chronic complication of diabetes and increases the risk of lower limb amputation, leading to both an economic and a major societal problem. By detecting the risk of developing diabetic foot sufficiently early, it can be prevented or at least postponed. Using artificial intelligence, delayed diagnosis can be prevented, leading to more intensive preventive treatment of patients. Based on a systematic literature review, we analyzed 14 articles that included the use of artificial intelligence to predict the risk of developing diabetic foot. The articles were highly heterogeneous in terms of data use and showed varying degrees of sensitivity, specificity, and accuracy. The most used machine learning techniques were support vector machine (SVM) (n = 6) and K-Nearest Neighbor (KNN) (n = 5). Future research is recommended on larger samples of participants using different techniques to determine the most effective one.
Ključne besede: artificial intelligence, machine learning, thermography, diabetic foot prediction, diabetes, diabetes care, diabetic foot, literature review
Objavljeno v DKUM: 27.11.2023; Ogledov: 76; Prenosov: 4
 Celotno besedilo (654,91 KB)
Gradivo ima več datotek! Več... |
2. Artificial intelligence based prediction models for individuals at risk of multiple diabetic complications : a systematic review of the literatureLucija Gosak, Kristina Martinović, Mateja Lorber, Gregor Štiglic, 2022, pregledni znanstveni članek Opis:
Aim
The aim of this review is to examine the effectiveness of artificial intelligence in predicting multimorbid diabetes-related complications.
Background
In diabetic patients, several complications are often present, which have a significant impact on the quality of life; therefore, it is crucial to predict the level of risk for diabetes and its complications.
Evaluation
International databases PubMed, CINAHL, MEDLINE and Scopus were searched using the terms artificial intelligence, diabetes mellitus and prediction of complications to identify studies on the effectiveness of artificial intelligence for predicting multimorbid diabetes-related complications. The results were organized by outcomes to allow more efficient comparison.
Key issues
Based on the inclusion/exclusion criteria, 11 articles were included in the final analysis. The most frequently predicted complications were diabetic neuropathy (n = 7). Authors included from two to a maximum of 14 complications. The most commonly used prediction models were penalized regression, random forest and Naïve Bayes model neural network.
Conclusion
The use of artificial intelligence can predict the risks of diabetes complications with greater precision based on available multidimensional datasets and provides an important tool for nurses working in preventive health care.
Implications for Nursing Management
Using artificial intelligence contributes to a better quality of care, better autonomy of patients in diabetes management and reduction of complications, costs of medical care and mortality.
Ključne besede: artificial intelligence, prediction models, diabetes, prediction of diabetes complications
Objavljeno v DKUM: 03.10.2023; Ogledov: 107; Prenosov: 20
Celotno besedilo (509,07 KB)
Gradivo ima več datotek! Več... |
3. Protective role of mitochondrial uncoupling proteins against age-related oxidative stress in type 2 diabetes mellitusMaša Čater, Lidija Križančić Bombek, 2022, pregledni znanstveni članek Opis: The accumulation of oxidative damage to DNA and other biomolecules plays an important role in the etiology of aging and age-related diseases such as type 2 diabetes mellitus (T2D), atherosclerosis, and neurodegenerative disorders. Mitochondrial DNA (mtDNA) is especially sensitive to oxidative stress. Mitochondrial dysfunction resulting from the accumulation of mtDNA damage impairs normal cellular function and leads to a bioenergetic crisis that accelerates aging and associated diseases. Age-related mitochondrial dysfunction decreases ATP production, which directly affects insulin secretion by pancreatic beta cells and triggers the gradual development of the chronic metabolic dysfunction that characterizes T2D. At the same time, decreased glucose oxidation in skeletal muscle due to mitochondrial damage leads to prolonged postprandial blood glucose rise, which further worsens glucose homeostasis. ROS are not only highly reactive by-products of mitochondrial respiration capable of oxidizing DNA, proteins, and lipids but can also function as signaling and effector molecules in cell membranes mediating signal transduction and inflammation. Mitochondrial uncoupling proteins (UCPs) located in the inner mitochondrial membrane of various tissues can be activated by ROS to protect cells from mitochondrial damage. Mitochondrial UCPs facilitate the reflux of protons from the mitochondrial intermembrane space into the matrix, thereby dissipating the proton gradient required for oxidative phosphorylation. There are five known isoforms (UCP1-UCP5) of mitochondrial UCPs. UCP1 can indirectly reduce ROS formation by increasing glutathione levels, thermogenesis, and energy expenditure. In contrast, UCP2 and UCP3 regulate fatty acid metabolism and insulin secretion by beta cells and modulate insulin sensitivity. Understanding the functions of UCPs may play a critical role in developing pharmacological strategies to combat T2D. This review summarizes the current knowledge on the protective role of various UCP homologs against age-related oxidative stress in T2D.
Ključne besede: uncoupling proteins, reactive oxygen species, aging, age-related diseases, diabetes
Objavljeno v DKUM: 23.08.2023; Ogledov: 171; Prenosov: 13
Celotno besedilo (1,14 MB)
Gradivo ima več datotek! Več... |
4. Skeletal muscle uncoupling proteins in mice models of obesityLidija Križančić Bombek, Maša Čater, 2022, pregledni znanstveni članek Opis: Obesity and accompanying type 2 diabetes are among major and increasing worldwide problems that occur fundamentally due to excessive energy intake during its expenditure. Endotherms continuously consume a certain amount of energy to maintain core body temperature via thermogenic processes, mainly in brown adipose tissue and skeletal muscle. Skeletal muscle glucose utilization and heat production are significant and directly linked to body glucose homeostasis at rest, and especially during physical activity. However, this glucose balance is impaired in diabetic and obese states in humans and mice, and manifests as glucose resistance and altered muscle cell metabolism. Uncoupling proteins have a significant role in converting electrochemical energy into thermal energy without ATP generation. Different homologs of uncoupling proteins were identified, and their roles were linked to antioxidative activity and boosting glucose and lipid metabolism. From this perspective, uncoupling proteins were studied in correlation to the pathogenesis of diabetes and obesity and their possible treatments. Mice were extensively used as model organisms to study the physiology and pathophysiology of energy homeostasis. However, we should be aware of interstrain differences in mice models of obesity regarding thermogenesis and insulin resistance in skeletal muscles. Therefore, in this review, we gathered up-to-date knowledge on skeletal muscle uncoupling proteins and their effect on insulin sensitivity in mouse models of obesity and diabetes.
Ključne besede: uncoupling protein, skeletal muscle, insulin, diabetes, obesity
Objavljeno v DKUM: 10.08.2023; Ogledov: 234; Prenosov: 13
Celotno besedilo (1,36 MB)
Gradivo ima več datotek! Več... |
5. Alpha cell stimulus-sehttps://dk.um.si/teme/dkumDev2/img/NovoOkno.pngcretion coupling and intercellular interactions in health and type 2 diabetesViljem Pohorec, Nika Zadravec, Marko Turk, Jurij Dolenšek, Andraž Stožer, 2023, pregledni znanstveni članek Ključne besede: Alpha cell, calcium imaging, epinephrine, physiology, type 2 diabetes mellitus
Objavljeno v DKUM: 18.07.2023; Ogledov: 155; Prenosov: 17
Celotno besedilo (268,08 KB)
Gradivo ima več datotek! Več...
Gradivo je zbirka in zajema 1 gradivo! |
6. Strojno učenje za podporo bolj učinkovitega postopka diagnoze bolezni : magistrsko deloJure Kučer, 2020, magistrsko delo Opis: Razširjenost trenda masovnega hranjenja podatkov na različnih področjih znanosti omogoča vse naprednejšo uporabo metod strojnega učenja za iskanje novega znanja. Magistrsko delo zajema predstavitev osnovnih konceptov in tehnik za obdelavo podatkov, obravnavo manjkajočih vrednosti in končno uporabo pri učenju popularnejših algoritmov strojnega učenja z namenom klasifikacije laboratorijskih meritev pacientov. Primerjani sta uspešnost klasifikacijskih modelov naivni Bayes,
k-najbližjih sosedov, odločitveno drevo, metoda podpornih vektorjev, naključni gozd, nevronska mreža, Adaboost in Adabagg ter vpliv metod podvzorčenja, nadvzorčenja in SMOTE za balansiranje učnih podatkov. Implementiran je tudi grafični vmesnik za vnos meritev, klasifikacijo, pregled rezultatov in pomembnosti lastnosti.
Ključne besede: strojno učenje, diagnoza bolezni, klasifikacija, diabetes
Objavljeno v DKUM: 04.01.2021; Ogledov: 690; Prenosov: 83
Celotno besedilo (2,18 MB) |
7. Aplikacija android za pomoč bolnikom z diabetesomSimon Muršič, 2018, diplomsko delo Opis: V diplomskem delu smo najprej opisali bolezen diabetes in predstavili platformo Android. Nato smo pregledali uporabo in razširjenost aplikacij za zdravje ter njihovo deljenje v različnih segmentih. Ugotovili smo, da imajo aplikacije za nadzorovanje kroničnih bolezni največji tržni potencial. Zato smo se odločili, da izdelamo Android aplikacijo za pomoč bolnikom z diabetesom. V aplikacijo smo vključili funkcionalnosti, kot so beleženje obrokov, aktivnosti in krvnega sladkorja. Implementirali smo tudi nastavljanje opomnika za uporabo zdravil in obveščanje oseb po elektronski pošti.
Ključne besede: diabetes, Android, sladkorna bolezen, aplikacije za zdravje, mZdravje
Objavljeno v DKUM: 16.07.2018; Ogledov: 1738; Prenosov: 249
Celotno besedilo (1,40 MB) |
8. Uravnotežena prehrana nosečnice z gestacijskim diabetesomNataša Zupanič, 2017, diplomsko delo Opis: Izhodišča: Gestacijski diabetes je sodobna bolezen nosečnic. Vedno pogosteje se pojavlja pri nosečnicah, ki imajo povišano telesno težo in nezdrav življenjski slog. Pomembno je, da se nosečnice zavedajo vpliva gestacijskega diabetesa na svojega otroka. Zato je potrebno spremeniti življenjski slog. Prva sprememba v življenjskem slogu je uravnotežena zdrava prehrana. Namen diplomskega dela je predstaviti zdravo uravnoteženo prehrano nosečnice z gestacijskim diabetesom in vlogo medicinske sestre pri tem.
Raziskovalne metode: V diplomskem delu smo uporabili deskriptivno metodo dela ter kvantitativno metodologijo raziskovanja. Za zbiranje podatkov smo kot raziskovalni inštrument uporabili anonimni anketni vprašalnik. V raziskavi je sodelovalo 50 nosečnic z gestacijskim diabetesom, ki so obiskovale diabetološko ambulanto.
Rezultati: Analiza anketnih odgovorov je pokazala, da so anketiranke največ informacij o uravnoteženi prehrani nosečnice z gestacijskim diabetesom dobile od medicinske sestre. Odgovori na vprašanja, ki se nanašajo na raznolikost prehrane nam povedo, da več kot polovica vprašanih uživa sadje in zelenjavo vsak dvakrat na dan, polovica vprašanih anketirank je pozorna na kalorično vrednost živil in 38 % jih je pozornih na glikemični indeks živil. Iz podanih odgovorov je razvidno, da 18 % anketirank ne upošteva vseh navodil glede zdrave uravnotežene prehrane.
Diskusija in zaključek: Medicinska sestra ima pomembno funkcijo pri poučevanju o zdravi uravnoteženi prehrani nosečnice z gestacijskim diabetesom. Vendar je z raziskavo ugotovljeno, da se kljub dovolj informacijam o zdravi uravnoteženi prehrani anketiranke ne držijo vseh navodil, kar lahko privede do težav v zdravju nosečnice in ploda. Zato je potrebno nosečnice z gestacijskim diabetesom kontinuirano osveščat o zdravi uravnoteženi prehrani.
Ključne besede: nosečnost, gestacijski diabetes, sladkorna bolezen, zdrava prehrana, medicinska sestra.
Objavljeno v DKUM: 28.11.2017; Ogledov: 2935; Prenosov: 387
Celotno besedilo (2,43 MB) |
9. Implementing quality indicators for diabetes and hypertension in family medicine in SloveniaZalika Klemenc-Ketiš, Igor Švab, Tonka Poplas-Susič, 2017, izvirni znanstveni članek Opis: Introduction: A new form of family practices was introduced in 2011 through a pilot project introducing nurse practitioners as members of team and determining a set of quality indicators. The aim of this article was to assess the quality of diabetes and hypertension management.
Methods: We included all family medicine practices that were participating in the project in December 2015 (N=584). The following data were extracted from automatic electronic reports on quality indicators: gender and specialisation of the family physician, status (public servant/self-contracted), duration of participation in the project, region of Slovenia, the number of inhabitants covered by a family medicine practice, the name of IT provider, and levels of selected quality indicators.
Results: Out of 584 family medicine practices that were included in this project at the end of 2015, 568 (97.3%) had complete data and could be included in this analysis. The highest values were observed for structure quality indicator (list of diabetics) and the lowest for process and outcome quality indicators. The values of the selected quality indicators were independently associated with the duration of participation in the project, some regions of Slovenia where practices were located, and some IT providers of the practices.
Conclusion: First, the analysis of data on quality indicators for diabetes and hypertension in this primary care project pointed out the problems which are currently preventing higher quality of chronic patient management at the primary health care level.
Ključne besede: family practices, healthcare quality indicator, diabetes mellitus, hypertension, Slovenia
Objavljeno v DKUM: 03.11.2017; Ogledov: 1320; Prenosov: 333
Celotno besedilo (424,82 KB)
Gradivo ima več datotek! Več... |
10. Razvoj spletne aplikacije in napovednega modela za napoved nediagnosticirane sladkorne bolezni tipa 2Andrej Fajfar, 2017, magistrsko delo Opis: V magistrski nalogi smo s pomočjo metode strojnega učenja »Random Forest« skušali napovedati stopnjo tveganja za nastanek sladkorne bolezni oz. verjetnost prisotnosti nediagnosticirane sladkorne bolezni na podlagi podatkov iz Slovenije. Za izbrano metodo smo določili optimalno število in vrsto spremenljivk za posamezni model. Za evalvacijo modela smo uporabili povprečno območje pod krivuljo (AUC), točnost in F-mero. Za model populacije s povečanim tveganjem smo dosegli povprečno AUC 0,823, točnost 0,824 in F-mero 0,804. V modelu za napoved nediagnostirane sladkorne bolezni smo dosegli povprečno AUC in točnost 0,749 in F-mero 0,654. Na podlagi podatkov smo pokazali, da je možno z veliko uspešnostjo določiti osebe z visokim tveganjem, ki predstavljajo preddiabetike in nediagnostirane diabetike oz. skupino s tveganjem za nastanek sladkorne bolezni tipa 2. Pokazali smo uporabo tehnik uravnoteženja odločitvenega razreda in rezultate primerjali z neuravnoteženim razredom. Uravnoteženje razreda zviša klasifikacijsko uspešnost modela. Rezultate smo primerjali z rezultati drugih znanstvenih objav in zasledili podobnost med rezultati. Tuje raziskave navajajo, da je klasifikator Random Forest najpogosteje izbran model, v primerjavi z drugimi modeli za napovedovanje kroničnih bolezni. S korelacijskim testom smo pokazali, da napovedna uspešnost modela ne korelira s številom dreves v ansamblu (p = 0,00015).
Ključne besede: strojno učenje, Random Forest, neuravnoteženi podatki, diabetes mellitus
Objavljeno v DKUM: 19.10.2017; Ogledov: 1180; Prenosov: 159
Celotno besedilo (1,38 MB) |
