Browsing by Subject "risk prediction"

Sort by: Order: Results:

Now showing items 1-6 of 6
  • Johnson, Linda S. B.; Salonen, Minna; Kajantie, Eero; Conen, David; Healey, Jeff S.; Osmond, Clive; Eriksson, Johan G. (2017)
    Background-Early life risk factors are associated with cardiometabolic disease, but have not been fully studied in atrial fibrillation (AF). There are discordant results from existing studies of birth weight and AF, and the impact of maternal body size, gestational age, placental size, and birth length is unknown. Methods and Results-The Helsinki Birth Cohort Study includes 13 345 people born as singletons in Helsinki in the years 1934-1944. Follow-up was through national registries, and ended on December 31, 2013, with 907 incident cases. Cox regression analyses stratified on year of birth were constructed for perinatal variables and incident AF, adjusting for offspring sex, gestational age, and socioeconomic status at birth. There was a significant U-shaped association between birth weight and AF (P for quadratic term = 0.01). The lowest risk of AF was found among those with a birth weight of 3.4 kg (3.8 kg for women [85th percentile] and 3.0 kg for men [17th percentile]). High maternal body mass index (>= 30 kg/m(2)) predicted offspring AF; hazard ratio 1.36 (95% CI 1.07-1.74, P = 0.01) compared with normal body mass index ( Conclusions-High maternal body mass index during pregnancy and maternal height are previously undescribed predictors of offspring AF. Efforts to prevent maternal obesity might reduce later AF in offspring. Birth weight has a U-shaped relation to incident AF independent of other perinatal variables.
  • Passos, Ives C.; Ballester, Pedro L.; Barros, Rodrigo C.; Librenza-Garcia, Diego; Mwangi, Benson; Birmaher, Boris; Brietzke, Elisa; Hajek, Tomas; Lopez Jaramillo, Carlos; Mansur, Rodrigo B.; Alda, Martin; Haarman, Bartholomeus C. M.; Isometsa, Erkki; Lam, Raymond W.; McIntyre, Roger S.; Minuzzi, Luciano; Kessing, Lars V.; Yatham, Lakshmi N.; Duffy, Anne; Kapczinski, Flavio (2019)
    Objectives The International Society for Bipolar Disorders Big Data Task Force assembled leading researchers in the field of bipolar disorder (BD), machine learning, and big data with extensive experience to evaluate the rationale of machine learning and big data analytics strategies for BD. Method A task force was convened to examine and integrate findings from the scientific literature related to machine learning and big data based studies to clarify terminology and to describe challenges and potential applications in the field of BD. We also systematically searched PubMed, Embase, and Web of Science for articles published up to January 2019 that used machine learning in BD. Results The results suggested that big data analytics has the potential to provide risk calculators to aid in treatment decisions and predict clinical prognosis, including suicidality, for individual patients. This approach can advance diagnosis by enabling discovery of more relevant data-driven phenotypes, as well as by predicting transition to the disorder in high-risk unaffected subjects. We also discuss the most frequent challenges that big data analytics applications can face, such as heterogeneity, lack of external validation and replication of some studies, cost and non-stationary distribution of the data, and lack of appropriate funding. Conclusion Machine learning-based studies, including atheoretical data-driven big data approaches, provide an opportunity to more accurately detect those who are at risk, parse-relevant phenotypes as well as inform treatment selection and prognosis. However, several methodological challenges need to be addressed in order to translate research findings to clinical settings.
  • HEALICS Consortium; Keuning, Britt E.; Kaufmann, Thomas; Wiersema, Renske; Pettilä, Ville; van der Horst, Iwan C. C. (2020)
    Background Mortality prediction models are applied in the intensive care unit (ICU) to stratify patients into different risk categories and to facilitate benchmarking. To ensure that the correct prediction models are applied for these purposes, the best performing models must be identified. As a first step, we aimed to establish a systematic review of mortality prediction models in critically ill patients. Methods Mortality prediction models were searched in four databases using the following criteria: developed for use in adult ICU patients in high-income countries, with mortality as primary or secondary outcome. Characteristics and performance measures of the models were summarized. Performance was presented in terms of discrimination, calibration and overall performance measures presented in the original publication. Results In total, 43 mortality prediction models were included in the final analysis. In all, 15 models were only internally validated (35%), 13 externally (30%) and 10 (23%) were both internally and externally validated by the original researchers. Discrimination was assessed in 42 models (98%). Commonly used calibration measures were the Hosmer-Lemeshow test (60%) and the calibration plot (28%). Calibration was not assessed in 11 models (26%). Overall performance was assessed in the Brier score (19%) and the Nagelkerke's R-2 (4.7%). Conclusions Mortality prediction models have varying methodology, and validation and performance of individual models differ. External validation by the original researchers is often lacking and head-to-head comparisons are urgently needed to identify the best performing mortality prediction models for guiding clinical care and research in different settings and populations.
  • Fernandez, C.; Rysä, J.; Almgren, P.; Nilsson, J.; Engström, G.; Orho-Melander, M.; Ruskoaho, H.; Melander, O. (2018)
    Background. Diabetes mellitus is linked to premature mortality of virtually all causes. Furin is a proprotein convertase broadly involved in the maintenance of cellular homeostasis; however, little is known about its role in the development of diabetes mellitus and risk of premature mortality. Objectives. To test if fasting plasma concentration of furin is associated with the development of diabetes mellitus and mortality. Methods. Overnight fasted plasma furin levels were measured at baseline examination in 4678 individuals from the population-based prospective Malmo Diet and Cancer Study. We studied the relation of plasma furin levels with metabolic and hemodynamic traits. We used multivariable Cox proportional hazards models to investigate the association between baseline plasma furin levels and incidence of diabetes mellitus and mortality during 21.3-21.7 years follow-up. Results. An association was observed between quartiles of furin concentration at baseline and body mass index, blood pressure and plasma concentration of glucose, insulin, LDL and HDL cholesterol (vertical bar 0.11 vertical bar Conclusion. Individuals with high plasma furin concentration have a pronounced dysmetabolic phenotype and elevated risk of diabetes mellitus and premature mortality.
  • Kowlessur, Sudhirsen; Hu, Zhibin; Heecharan, Jaysing; Wang, Jianming; Dai, Juncheng; Tuomilehto, Jaakko O.; Soderberg, Stefan; Zimmet, Paul; Barengo, Noel C. (2018)
    Information on the predictors of future hypertension in Mauritians with prehypertension is scant. The aim of this study was to analyze the 5-year and 11-year risk of hypertension and its predictors in people with normotension and prehypertension at baseline in Mauritius in 1987. This was a retrospective cohort study of 883 men and 1194 women of Mauritian Indian and Mauritian Creole ethnicity, aged 25-74 years old, free of hypertension at baseline in 1987 with follow-up examinations in 1992 and 1998 using the same methodology. The main outcome was 5- and 11-year risk of hypertension. Odds ratios (OR) and corresponding 95% confidence intervals (CI) were calculated. The 5-year risk of hypertension was 5.4-times higher in people with prehypertension compared with normotensive individuals at baseline. The corresponding odds for prehypertensive people at baseline regarding 11-year hypertension risk was 3.39 (95% CI 2.67-4.29) in the adjusted logistic regression models. Being of Creole ethnicity (OR 1.42; 95% CI 1.09-1.86) increased the 11-year odds of hypertension compared with the Indian population. It is of importance to screen for people with prehypertension and implement strategies to reduce their systolic blood pressure levels to the recommended levels of 120/80 mmHg. Special attention needs to be given to Mauritians of Creole ethnicity.
  • Paige, Ellie; Barrett, Jessica; Pennells, Lisa; Sweeting, Michael; Willeit, Peter; Di Angelantonio, Emanuele; Gudnason, Vilmundur; Nordestgaard, Borge G.; Psaty, Bruce M.; Goldbourt, Uri; Best, Lyle G.; Assmann, Gerd; Salonen, Jukka T.; Nietert, Paul J.; Verschuren, W. M. Monique; Brunner, Eric J.; Kronmal, Richard A.; Salomaa, Veikko; Bakker, Stephan J. L.; Dagenais, Gilles R.; Sato, Shinichi; Jansson, Jan-Hakan; Willeit, Johann; Onat, Altan; de la Camara, Agustin Gomez; Roussel, Ronan; Volzke, Henry; Dankner, Rachel; Tipping, Robert W.; Meade, Tom W.; Donfrancesco, Chiara; Kuller, Lewis H.; Peters, Annette; Gallacher, John; Kromhout, Daan; Iso, Hiroyasu; Knuiman, Matthew; Casiglia, Edoardo; Kavousi, Maryam; Palmieri, Luigi; Sundstrom, Johan; Davis, Barry R.; Njolstad, Inger; Couper, David; Danesh, John; Thompson, Simon G.; Wood, Angela (2017)
    The added value of incorporating information from repeated blood pressure and cholesterol measurements to predict cardiovascular disease (CVD) risk has not been rigorously assessed. We used data on 191,445 adults from the Emerging Risk Factors Collaboration (38 cohorts from 17 countries with data encompassing 1962-2014) with more than 1 million measurements of systolic blood pressure, total cholesterol, and high-density lipoprotein cholesterol. Over a median 12 years of follow-up, 21,170 CVD events occurred. Risk prediction models using cumulative mean values of repeated measurements and summary measures from longitudinal modeling of the repeated measurements were compared with models using measurements from a single time point. Risk discrimination (C-index) and net reclassification were calculated, and changes in C-indices were meta-analyzed across studies. Compared with the single-time-point model, the cumulative means and longitudinal models increased the C-index by 0.0040 (95% confidence interval (CI): 0.0023, 0.0057) and 0.0023 (95% CI: 0.0005, 0.0042), respectively. Reclassification was also improved in both models; compared with the single-time-point model, overall net reclassification improvements were 0.0369 (95% CI: 0.0303, 0.0436) for the cumulative-means model and 0.0177 (95% CI: 0.0110, 0.0243) for the longitudinal model. In conclusion, incorporating repeated measurements of blood pressure and cholesterol into CVD risk prediction models slightly improves risk prediction.