Doctoral Thesis
Refine
Document Type
- Doctoral Thesis (3) (remove)
Has Fulltext
- yes (3)
Is part of the Bibliography
- no (3) (remove)
Keywords
- prediction (3) (remove)
Background
Previous work has focused on speckle-tracking echocardiography (STE)-derived global longitudinal and circumferential peak strain as potential superior prognostic metric markers compared with left ventricular ejection fraction (LVEF). However, the value of regional distribution and the respective orientation of left ventricular wall motion (quantified as strain and derived from STE) for survival prediction have not been investigated yet. Moreover, most of the recent studies on risk stratification in primary and secondary prevention do not use neural networks for outcome prediction.
Purpose
To evaluate the performance of neural networks for predicting all cause-mortality with different model inputs in a moderate-sized general population cohort.
Methods
All participants of the second cohort of the population-based Study of Health in Pomerania (SHIP-TREND-0) without prior cardiovascular disease (CVD; acute myocardial infarction, cardiac surgery/intervention, heart failure and stroke) and with transthoracic echocardiography exams were followed for all-cause mortality from baseline examination (2008-2012) until 2019.
A novel deep neural network architecture ‘nnet-Surv-rcsplines’, that extends the Royston-Parmar- cubic splines survival model to neural networks was proposed and applied to predict all-cause mortality from STE-derived global and/or regional myocardial longitudinal, circumferential, transverse, and radial strain in addition to the components of the ESC SCORE model. The models were evaluated by 8.5-year area-under-the-receiver-operating-characteristic (AUROC) and (scaled) Brier score [(S)BS]and compared to the SCORE model adjusted for mortality rates in Germany in 2010.
Results
In total, 3858 participants (53 % female, median age 51 years) were followed for a median time of 8.4 (95 % CI 8.3 – 8.5) years. Application of ‘nnet-Surv-rcsplines’ to the components of the ESC SCORE model alone resulted in the best discriminatory performance (AUROC 0.9 [0.86-0.91]) and lowest prediction error (SBS 21[18-23] %). The latter was significantly lower (p <0.001) than the original SCORE model (SBS 11 [9.5 - 13] %), while discrimination did not differ significantly. There was no difference in (S)BS (p= 0.66) when global circumferential and longitudinal strain were added to the model. Solely including STE-data resulted in an informative (AUROC 0.71 [0.69, 0.74]; SBS 3.6 [2.8-4.6] %) but worse (p<0.001) model performance than when considering the sociodemographic and instrumental biomarkers, too.
Conclusion
Regional myocardial strain distribution contains prognostic information for predicting all-cause mortality in a primary prevention sample of subjects without CVD. Still, the incremental prognostic value of STE parameters was not demonstrated. Application of neural networks on available traditional risk factors in primary prevention may improve outcome prediction compared to standard statistical approaches and lead to better treatment decisions.
Ziel dieser Studie war es, zu untersuchen, wie sich die Mundgesundheit und der zahnmedizinische Therapiebedarf in Deutschland entwickeln werden. In der Arbeit wurden Projektionen zur Entwicklung der Morbidität, der Mundgesundheit und dem Therapiebedarf auf Grundlage der repräsentativen Daten aus den Deutschen Mundgesundheitsstudien III (1997) und IV (2005), den epidemiologischen Begleituntersuchungen zur Gruppenprophylaxe durch die DAJ (2004-2009), den Jahrbüchern der KZBV (2003-2010), den Zahlenberichten der PKV (2006-2011) sowie den Prognosen der Bevölkerungsentwicklung vom Bundesamt für Statistik [2006] vorgenommen. Die Auswertung der Resultate hat ergeben, dass der Trend zur Verbesserung der Mundgesundheit in den nächsten 20 Jahren weiter durch alle Bevölkerungsschichten voranschreiten wird. Am stärksten wird sich die Verbesserung der Mundgesundheit bei Kindern und Jugendlichen (0,3 DMFT bei 12-Jährigen im Jahr 2030) und am schwächsten bei der Risikogruppe der Senioren (22 DMFT) zeigen. Die Anzahl der fehlenden Zähne wird bei Erwachsenen und Senioren stark zurückgehen, besonders in der Basisgruppe der Senioren von 14,1 MT (1997) auf 3,1 (2030). Die Anzahl der gefüllten Zähne wird im Durchschnitt zumeist konstant bleiben. Während Kinder und vor allem die Basisgruppe der Erwachsenen mit 12,3 FT (1997) auf 10,1 (2030) eine Reduktion von Füllungen erleben werden, wird in der Risikogruppe der Erwachsenen und bei Senioren mit deutlich mehr Füllungen gerechnet, insbesondere da hier auch mehr Zähne in Zukunft vorhanden sein werden. Die Verbesserung der Mundgesundheit kann insgesamt zu einem Rückgang des Prothetikbedarfs und zugleich zu einer Verschiebung vom herausnehmbaren zum festsitzenden Zahnersatz führen.
Prediction of high caries increment in adults – a 5-year longitudinal study from North-East Germany
(2013)
The aim of this study is to develop an easily applicable prediction model for high coronal caries increment in adults (20-79 years) from a representative sample (N=2,565) to identify a high risk-group for specific caries prevention. The data from SHIP-0 (1997-2001) and the 5-year follow-up SHIP-1 (2002-2006) is used for analyses. The oral health examination was conducted according to WHO criteria [1997]. The drop-out analysis reveals that drop-outs are significantly older, have a lower school education, are more frequently current smokers, but have a better self-perception of their teeth. The majority of the study-population (76%) has caries incidence in this 5-year period. Caries increment shows a polarized distribution, as the high caries increment group (≥9 surfaces in half-mouth, 11.4% of the sample) comprise 40% of the total increment. The variables male gender, age ≥40 years, lower school education or lower income, current smoking, pain-associated dental visit, baseline caries experience and a non-satisfying self-perception of teeth show a statistically significant influence on high caries increment. The prediction model allows a fair to good prediction on an epidemiological level for men (AUC=0.75). The factors smoking, school education and pain-associated visit only have a significant impact on the prediction of high caries increment in men. Due to very high caries prevalence and increment a population-based prevention in adults should be optimized first, before risk-group specific preventive programmes might be implemented.