Doctoral Thesis
Refine
Document Type
- Doctoral Thesis (2) (remove)
Language
- English (2)
Has Fulltext
- yes (2)
Is part of the Bibliography
- no (2) (remove)
Keywords
- general population (2) (remove)
Institute
Our study examined whether potentially critical indications from depression questionnaires, interviews, and single items on suicidal ideation among partici-pants in a large prospective population-based study are related to short-term sui-cides within one year. For this purpose, we studied the association between (a) the severity of depressive symptoms according to the M-CIDI and the PHQ-9, BDI-II, and CID-S depression screening and (b) elevated scores on single sui-cidal ideation items and mortality according to claims databases.
In the baseline cohort, the frequency of depressive symptoms measured by CID-S was 12.90% (SHIP-START-0). The frequency for “Moderate” to “Severe de-pression” measured by the PHQ-9 (≥ 10 points) and BDI-II (≥ 20 points) ques-tionnaires ranged from 5.40% (SHIP-LEGENDE) to 8.80% (SHIP-TREND Morbid-ity follow-up). The 1-month prevalence of unipolar depression, measured by the M-CIDI in SHIP LEGENDE, was 2.31%.
Between 5.90% (SHIP-TREND Morbidity follow-up) and 6.60% (SHIP-LEGENDE) of respondents showed a certain degree of suicidal ideation in the two weeks preceding the assessment, according to BDI-II and PHQ-9.
Our results show the high frequency of depressive symptoms in the study region, with women being affected more frequently than men, especially in the higher categories. Furthermore, women were more frequently affected by suicidal idea-tion, although this difference was not evident in the highest categories.
There was one potential suicide in the year after a SHIP examination.
From our results, we cannot conclude that severe self-reported symptoms from depression questionnaires should be reported back to participants of an obser-vational population-based study to prevent suicide deaths within one year.
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.