<p>The purpose of this study was to develop a recursive algorithm for computing a maximum a posteriori (MAP) estimate of a binary Markov random field (MRF) by using the MAP-MRF framework. We also discuss how to include an approximation in the recursive scheme, so that the algorithm becomes computationally feasible also for larger problems. In particular, we discuss how our algorithm can be used in an image analysis setting. We consider a situation where an unobserved latent field is assumed to follow a Markov random field prior model, a Gaussian noise-corrupted version of the latent field is observed, and we estimate the unobserved field by the MAP estimator.</p>

<p>Based on the tumor growth model of Harald Weedon-Fekjær et al.'s paper "Breast cancer tumor growth estimated through mammography screening data", a simulation of breast cancer occurrence and tumor growth in a large population of women was made. The simulation was made realistic by starting tumor growth according to a Poisson process, including a distribution for clinical detection size and a screening test sensitivity function, and using an individual growth rate, based on estimates of Weedon-Fekjær et al. After running the full simulation, parts of the simulation outcomes were compared to known data of breast cancer and the model was found to give realistic and expected results. The simulation was then used to look for other interesting results such as expected reduction in time to tumor detection due to screening and finding the size distribution of tumors before and after screening. For the age group 50 - 69 years, it was found that screening every year allows a reduction of 19.1 months, while screening every two, three, five and ten years allows for reductions of, respectively, 9.5, 8.3, 6.1 and 3.4 months. These results are based on the assumption that tumors are actually found at screening, i.e. the tumors are not found clinically before they are found on screening. When clinical findings are included, different results are obtained. For the age group 50 - 69 years, it was found that screening every year allows a reduction of 15 months, while screening every two, three, five and ten years allows for reductions of, respectively, 4.8, 1.4, -5.6 and -21.5 months. Negative numbers indicate that a tumor is found earlier clinically than at screening.</p>

Based on the tumor growth model of Harald Weedon-Fekjær et al.'s paper "Breast cancer tumor growth estimated through mammography screening data", a simulation of breast cancer occurrence and tumor growth in a large population of women was made. The simulation was made realistic by starting tumor growth according to a Poisson process, including a distribution for clinical detection size and a screening test sensitivity function, and using an individual growth rate, based on estimates of Weedon-Fekjær et al. After running the full simulation, parts of the simulation outcomes were compared to known data of breast cancer and the model was found to give realistic and expected results. The simulation was then used to look for other interesting results such as expected reduction in time to tumor detection due to screening and finding the size distribution of tumors before and after screening. For the age group 50 - 69 years, it was found that screening every year allows a reduction of 19.1 months, while screening every two, three, five and ten years allows for reductions of, respectively, 9.5, 8.3, 6.1 and 3.4 months. These results are based on the assumption that tumors are actually found at screening, i.e. the tumors are not found clinically before they are found on screening. When clinical findings are included, different results are obtained. For the age group 50 - 69 years, it was found that screening every year allows a reduction of 15 months, while screening every two, three, five and ten years allows for reductions of, respectively, 4.8, 1.4, -5.6 and -21.5 months. Negative numbers indicate that a tumor is found earlier clinically than at screening.

The purpose of this study was to develop a recursive algorithm for computing a maximum a posteriori (MAP) estimate of a binary Markov random field (MRF) by using the MAP-MRF framework. We also discuss how to include an approximation in the recursive scheme, so that the algorithm becomes computationally feasible also for larger problems. In particular, we discuss how our algorithm can be used in an image analysis setting. We consider a situation where an unobserved latent field is assumed to follow a Markov random field prior model, a Gaussian noise-corrupted version of the latent field is observed, and we estimate the unobserved field by the MAP estimator.

With the first generation of microarray experiments there were discussions and important arguments on how the samples should be treated. This included what kind of transformation and normalization procedures that the data should be subjected to before the actual analysis. With the new generation of microarray experiments, genome wide association studies, and more complicated experiments, new questions and standards arises. An important question is the appropriate use of controls, and what effect these controls have on the assessed behaviour of the genes.The main objective in this thesis was to analyse a data set and experimental procedure from an experiment done at IKM (NTNU, 2009), where the effect of a gastrin treatment was measured on a set of genes along with an unstimulated control sample over a time interval. The experiment was replicated once, giving two independent experiments. A natural extension of this is then; what is the gain in precision by adding additional replicas to the experiment? And what additional information is given in an unstimulated control sample?Our approach was to use the Linear Mixed Effects (LME) framework to fit a regression curve to each gene, for both the treated time series itself, and the treated adjusted for by the unstimulated control sample. Each replication was assumed to have a random offset from the common mean. The mean was modelled using basis expansion with the Legendre polynomials, thus allowing it to vary as a smooth function over the time interval.A computer simulation showed that an increase in the number of independent time series sampled would decrease the error in the estimated expression profile. Even when this causes the number of time points (measurements) within the time series to decrease.The analysis of the data showed that not using an unstimulated control gave many false positive results, however, always using such a control will also cause an increase in both false negative and false positive results, due to increase in stochastisity. However, having an unstimulated control sample will give the researcher an increased control when assessing the effect of the treatment.

In this thesis we have explored the very high prices that sometimes occurs in the Nord Pool electricity market Elspot. By applying AR-GARCH time series models, extreme value theory, and ACER estimation techniques, we have sought to estimate the probabilities of threshold exceedances related to electricity prices. Of particular concern was the heavy-tailed Fr&#233;chet distribution, which was the asymptotic distribution assumed in the ACER estimation.We have found that with extreme value theory we are better equipped to deal with the very high quantiles in the time series we have analyzed. We have also described a method that can give an assessment of the probability of exceeding a selected level in the electricity price.

Det overordnede målet med denne avhandling var å få en oversikt over ulike forstyrrelser i de nedre urinveier hos gamle. Dernest var målet å beskrive oppfatninger og barrierer som influerte på personalets muligheter for å gi riktig inkontinenspleie til beboere i sykehjem. Avhandlingen består av en kvantitativ studie (artikkel I, II, III), og en kvalitativ studie (artikkel IV). Artikkel I var en tverrsnittstudie. Artikkel II og III var en prospektiv tidsdesignstudie med en oppfølgingsperiode på ett år. 183 beboere fra seks sykehjem deltok i den kvantitative studien. I artikkel I ble prevalensen av urininkontinens hos norske sykehjembeboere evaluert. I tillegg ble det forsøkt å identifisere faktorer som var assosiert med urininkontinens i denne populasjonen. I artikkel II ble det undersøkt om residualurin var en risiko for å utvikle urinveisinfeksjon hos gamle på sykehjem. I artikkel III ble det undersøkt om bleiebruk per døgn er en pålitelig metode for å kvantifisere urininkontinens hos sykehjemsbeboere. Det ble også studert om det var sammenheng mellom urinveisinfeksjon, bleiebruk per døgn og væskeinntak. I den kvalitative studien var målet å identifisere oppfatninger og barrierer som influerte på pleiernes muligheter for å gi riktig inkontinenspleie. Fem avdelingsledere, fem sykepleiere og fem hjelpepleiere ble intervjuet i til sammen tre fokusgruppeintervjuer.Analysen i artikkel I viste at 122 beboere (69 %) var inkontinent for urin og 144 (83 %) brukte bleier. 14 % brukte bleier for sikkerhets skyld. Lav ADL-skår, demens og urinveisinfeksjon var assosiert med urininkontinens (P = &lt;0.01). I artikkel II hadde 98 beboere (63.3 %) residualurin mindre enn 100 ml, og 52 (34.7 %) hadde residualurin på 100 ml eller større. I løpet av oppfølgingsperioden hadde 51 beboere (34 %) utviklet en eller flere urinveisinfeksjoner. Forekomsten av urinveisinfeksjon var høyere hos kvinnene enn hos mennene (40.4 % versus 19.6 %; P = 0.02). Det ble ikke funnet noen signifikant forskjell i gjennomsnittlig residualurin mellom beboere som utviklet og som ikke utviklet urinveisinfeksjon (79 versus 97 ml, P = 0.26). Residualurin på 100 ml eller større var ikke assosiert med større risiko for utvikling av urinveisinfeksjon.I artikkel III brukte 118 (77 %) av beboerne bleier. Bleiebruk per døgn er et upålitelig mål på urininkontinens hos beboere i sykehjem. Beboere som brukte bleier hadde en økende risiko for å utvikle urinveisinfeksjon sammenlignet medvibeboere som ikke brukte bleier (41 versus 11 %; P = 0.001). Daglig væskeinntak var ikke assosiert med urinveisinfeksjoner (P = 0.46). Antall bleieskift viste ingen korrelasjon med risikoen for utvikling av urinveisinfeksjon (P = 0.62). Bleiene som beboerne brukte per døgn, viste stor variasjon i inkontinensvolum. I den kvalitative studien ledet innholdsanalysen fram til tre emner og åtte kategorier. Det første emnet, Oppfatninger og barrierer assosiert med beboerne, inneholdt en kategori ”fysiske og kognitive problemer”. Det andre emnet, Oppfatninger og barrierer assosiert med personalet, inneholdt tre kategorier: ”manglende kunnskaper”, ”holdninger og tro” og ”manglende tilgjengelighet”. Det tredje emnet, Oppfatninger og barrierer assosiert med den organisatoriske kulturen, inneholdt fire kategorier: ”rigide rutiner”, manglende ressurser”, ”manglede dokumentasjon” og ”svakt lederskap”. Resultatene i denne avhandlingen viser at forekomsten av urininkontinens i sykehjem er høy. Absorberende produkter er hyppig brukt uten en kjent historie av urininkontinens. Fysisk svekkelse, demens og urinveisinfeksjon er assosiert med urininkontinens. Residualurin er vanlig hos beboere i sykehjem. Det ble ikke funnet noen sammenheng mellom residualurin og urinveisinfeksjon. Bruk av absorberende bleier er assosiert med økt risiko for utvikling av urinveisinfeksjon. Bleiebruk per døgn og væskeinntak var ikke korrelert med økt risiko for utvikling av urinveisinfeksjon. Bleiebruk per døgn er et upålitelig mål på urininkontinens hos beboere i sykehjem. Funnene fra den kvalitative studien viser at det er mange barrierer som influerer på personalets evne til å gi riktig inkontinenspleie til beboere i sykehjem. Det kan likevel se ut som om personalets oppfatninger og holdninger, samt manglende kunnskaper om urininkontinens, er de viktigste barrierene for å gi riktig inkontinenspleie. / The overall aim of this thesis was to get an overview over different dysfunction in the lower urinary tract in the elderly. Also, we wanted to describe the perceptions and barriers that influence the nursing staff`’s ability to provide appropriate incontinence care in nursing home residents. The thesis includes one quantitative study (paper I, II, III), and one qualitative study (paper IV). Paper I was a cross-sectional study. Paper II and III were a prospective surveillance with a follow-up period of 1 year. 183 residents from six Norwegian nursing homes participated. In paper I, the prevalence of urinary incontinence in Norwegian nursing home residents was evaluated. The factors possibly associated with urinary incontinence were also studied. In paper II, we investigated whether residual urine was a risk factor for developing urinary tract infections in the elderly in nursing homes. In paper III, the objective was to determine whether pads per day usage is a reliable measure of urinary incontinence in nursing home residents. Furthermore, we wanted to study the association between urinary tract infections, pads per day usage and fluid intake. In the qualitative study, the aim was to identify perceptions and barriers that influence the ability of nursing staff to provide appropriate incontinence care. Five charge nurses, five registered nurses and five certified nursing assistants participated in the focus group interviews.The analysis in paper I, showed that 122 (69 %) of the resident were incontinent for urine and 144 used absorbent pads (83 %). 14 % of residents used absorbent pads ‘just to make sure’. They did not have a history of urinary incontinence. Low ADL score, dementia and urinary tract infection were significantly associated with incontinence for urine (P = &lt;0.01). In paper II, 93 of the residents (65.3 %) had postvoid residual urine (PVR) &lt; 100 mL and 52 residents (34.7 %) had a PVR 100 mL. During the follow-up period, 51 residents (34.0 %) had one or more urinary tract infections (UTI). The prevalence of UTI among females was higher than among men (40.4 % versus. 19.6 %; P = 0.015). There was no significant difference in mean PVR among residents that did or did not develop UTI (79 mL versus 97mL; P = 0.26). A PVR 100 mL was not associated with an increased risk of developing UTI`s (P = 0.59).In paper III, 118 (77 %) used absorbent pads. Residents that used absorbent pads were at increased risk of developing UTIs compared to residents that did notviiiuse pads (41 % versus 11 %; P = 0.001). Daily fluid intake was not associated with UTIs (P = 0.46). The number of pad shifts had no relation with the risk of developing UTIs (P = 0.62). Residents with a given pad per day (PPD) presented a wide range of incontinence volumes.In paper IV, three topics and eight categories were identified. The first topic, Perceptions and barriers associated with residents, consisted of one category: ‘physical and cognitive problems’. The second topic, Perceptions and barriers associated with nursing staff, consisted of three categories: ‘lack of knowledge’, ‘attitudes and beliefs’ and ‘lack of accessibility’. The third topic, Perceptions and barriers associated with organizational culture, consisted of four categories: ‘rigid routines’, ‘lack of resource’, ‘lack of documentation’ and ‘lack of leadership’.The results of the thesis show that the prevalence of urinary incontinence in nursing homes is high. Absorbent products are frequently used without a history of urinary incontinence. Physical impairment, dementia and urinary tract infections are associated with urinary incontinence. is common in nursing home residents. No association between PVR and UTI was found. The use of absorbent pads is associated with an increased risk of developing UTIs. PPD and daily fluid intake are not correlated with the risk of developing UTIs. PPD is an unreliable measure of urinary incontinence in nursing home residents. The findings from the qualitative study shows that there are many barriers that might influence the possibilities of nursing staff to provide appropriate incontinence care to residents in nursing homes. However, it can nevertheless seem like opinions and the attitude of nursing staff, together with a lack of knowledge about urinary incontince, are the most important barriers to provide appropriate incontinence care.