| 1. |
- Wallert, John, et al.
(författare)
-
Cognitive ability, lifestyle risk factors, and two-year survival in first myocardial infarction men : A Swedish National Registry study
- 2017
-
Ingår i: International Journal of Cardiology. - : Elsevier BV. - 0167-5273 .- 1874-1754. ; 231, s. 13-17
-
Tidskriftsartikel (refereegranskat)abstract
- Background: General cognitive ability (CA) is positively associated with later physical and mental health, health literacy, and longevity. We investigated whether CA estimated approximately 30 years earlier in young adulthood predicted lifestyle-related risk factors and two-year survival in first myocardial infarction (MI) male patients.Methods: Young adulthood CA estimated through psychometric testing at age 18–20 years was obtained from the mandatory military conscript registry (INSARK) and linked to national quality registry SWEDEHEART/RIKS-HIA data on smoking, diabetes, hypertension, obesity (BMI > 30 kg/m2) in 60 years or younger Swedish males with first MI. Patients were followed up in the Cause of Death registry. The 5659 complete cases (deceased = 106, still alive = 5553) were descriptively compared. Crude and adjusted associations were modelled with logistic regression.Results: After multivariable adjustment, one SD increase in CA was associated with a decreased odds ratio of being a current smoker (0.63 [0.59, 0.67], P < 0.001), previous smoker (0.79 [0.73, 0.84], P < 0.001), having diabetes (0.82 [0.74, 0.90], P < 0.001), being obese (0.90 [0.84, 0.95], P < 0.001) at hospital admission, and an increased odds ratio of two-year survival (1.26 [1.02, 1.54], P < 0.001). CA was not associated with hypertension at hospital admission (1.03 [0.97, 1.10], P = 0.283).Conclusions: This study found substantial inverse associations between young adulthood CA, and middle-age lifestyle risk factors smoking, diabetes, and obesity, and two-year survival in first MI male patients. CA assessment might benefit risk stratification and possibly aid further tailoring of secondary preventive strategy.
|
|
| 2. |
|
|
| 3. |
- Wallert, John, 1982-
(författare)
-
Forecasting myocardial infarction and subsequent behavioural outcomes
- 2020
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- This thesis is compiled from four studies dealing with the prediction of myocardial infarction (MI) and some associated risk behaviours post MI.Study 1 extends the field of possible psychosocial stress-triggering of MI to Sweden, and to the phenomenon of temporal crests and troughs in national MI rates. These findings are in the present thesis integrated into a more comprehensive theoretical framework than provided by previous studies. By controlling for different confounders, analysis in subgroups, and more, the probable effect of psychosocial stress on the triggering of MI producing slight oscillations in daily MI rates at different temporal cycles was supported.Study 2 extends the existing literature of cognitive epidemiology to secondary preventive cardiology. Males with higher cognitive ability (CA), as assessed at mandatory military conscription in young adulthood, were found to be more adherent to their statin medication post MI, approximately 30 years later. The association is likely causal, given the fundamental importance of CA as a predictor for our individual ability to understand, plan, and execute everyday behaviour, including such health promoting behaviour as adhering to statin medication after MI.Study 3 continues the thesis thread of predicting clinically relevant health-promoting behaviour. It generated important hypotheses of what predicts adherence to internet-based cognitive behaviour therapy (ICBT) for symptoms of anxiety and/or depression after MI. In particular, the linguistic variables which were derived from what the patients actually wrote online to their ICBT therapist, predicted adherence. Using a flexible random forest model with a moderately sized sample, the aim was to handle a range of predictors and possible higher order effects in the relative strength estimation of these predictors.Study 4 presents the derivation and external validation of a new risk model, STOPSMOKE. Developed as a linear support vector machine with robust resampling, STOPSMOKE proved accurate in the unseen validation cohort for predicting one-year smoking abstinence at the start of cardiac rehabilitation (CR) post MI. STOPSMOKE predictions may inform the targeting of more elaborate interventions to high risk patients. Today, such intervention is not systematic as standard counselling does not account for the individual probability of future smoking abstinence failure. STOPSMOKE thus provides a novel real-world probabilistic basis for the risk of future smoking abstinence failure after MI. This basis may then be used by clinicians, patients, and organisations to tailor smoking intervention as best suited the particular individual or high-risk group. Implemented as part of a spectrum of models in a semi-automatic system, cost-effective tailored risk assessment could allow for augmented CR for future patients.
|
|
| 4. |
- Wallert, John, et al.
(författare)
-
Predicting Adherence to Internet-Delivered Psychotherapy for Symptoms of Depression and Anxiety After Myocardial Infarction : Machine Learning Insights From the U-CARE Heart Randomized Controlled Trial
- 2018
-
Ingår i: Journal of Medical Internet Research. - : Air University Press. - 1438-8871. ; 20:10
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Low adherence to recommended treatments is a multifactorial problem for patients in rehabilitation after myocardial infarction (MI). In a nationwide trial of internet-delivered cognitive behavior therapy (iCBT) for the high-risk subgroup of patients with MI also reporting symptoms of anxiety, depression, or both (MI-ANXDEP), adherence was low. Since low adherence to psychotherapy leads to a waste of therapeutic resources and risky treatment abortion in MI-ANXDEP patients, identifying early predictors for adherence is potentially valuable for effective targeted care.Objectives: The goal of the research was to use supervised machine learning to investigate both established and novel predictors for iCBT adherence in MI-ANXDEP patients.Methods: Data were from 90 MI-ANXDEP patients recruited from 25 hospitals in Sweden and randomized to treatment in the iCBT trial Uppsala University Psychosocial Care Programme (U-CARE) Heart study. Time point of prediction was at completion of the first homework assignment. Adherence was defined as having completed more than 2 homework assignments within the 14-week treatment period. A supervised machine learning procedure was applied to identify the most potent predictors for adherence available at the first treatment session from a range of demographic, clinical, psychometric, and linguistic predictors. The internal binary classifier was a random forest model within a 3×10–fold cross-validated recursive feature elimination (RFE) resampling which selected the final predictor subset that best differentiated adherers versus nonadherers.Results: Patient mean age was 58.4 years (SD 9.4), 62% (56/90) were men, and 48% (43/90) were adherent. Out of the 34 potential predictors for adherence, RFE selected an optimal subset of 56% (19/34; Accuracy 0.64, 95% CI 0.61-0.68, P<.001). The strongest predictors for adherence were, in order of importance, (1) self-assessed cardiac-related fear, (2) sex, and (3) the number of words the patient used to answer the first homework assignment.Conclusions: For developing and testing effective iCBT interventions, investigating factors that predict adherence is important. Adherence to iCBT for MI-ANXDEP patients in the U-CARE Heart trial was best predicted by cardiac-related fear and sex, consistent with previous research, but also by novel linguistic predictors from written patient behavior which conceivably indicate verbal ability or therapeutic alliance. Future research should investigate potential causal mechanisms and seek to determine what underlying constructs the linguistic predictors tap into. Whether these findings replicate for other interventions outside of Sweden, in larger samples, and for patients with other conditions who are offered iCBT should also be investigated.
|
|
| 5. |
- Wallert, John, et al.
(författare)
-
Predicting two-year survival versus non-survival after first myocardial infarction using machine learning and Swedish national register data
- 2017
-
Ingår i: BMC Medical Informatics and Decision Making. - : BioMed Central. - 1472-6947. ; 17
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Machine learning algorithms hold potential for improved prediction of all-cause mortality in cardiovascular patients, yet have not previously been developed with high-quality population data. This study compared four popular machine learning algorithms trained on unselected, nation-wide population data from Sweden to solve the binary classification problem of predicting survival versus non-survival 2 years after first myocardial infarction (MI).Methods: This prospective national registry study for prognostic accuracy validation of predictive models used data from 51,943 complete first MI cases as registered during 6 years (2006-2011) in the national quality register SWEDEHEART/RIKS-HIA (90% coverage of all MIs in Sweden) with follow-up in the Cause of Death register (> 99% coverage). Primary outcome was AUROC (C-statistic) performance of each model on the untouched test set (40% of cases) after model development on the training set (60% of cases) with the full (39) predictor set. Model AUROCs were bootstrapped and compared, correcting the P-values for multiple comparisons with the Bonferroni method. Secondary outcomes were derived when varying sample size (1-100% of total) and predictor sets (39, 10, and 5) for each model. Analyses were repeated on 79,869 completed cases after multivariable imputation of predictors.Results: A Support Vector Machine with a radial basis kernel developed on 39 predictors had the highest complete cases performance on the test set (AUROC = 0.845, PPV = 0.280, NPV = 0.966) outperforming Boosted C5.0 (0.845 vs. 0. 841, P = 0.028) but not significantly higher than Logistic Regression or Random Forest. Models converged to the point of algorithm indifference with increased sample size and predictors. Using the top five predictors also produced good classifiers. Imputed analyses had slightly higher performance.Conclusions: Improved mortality prediction at hospital discharge after first MI is important for identifying high-risk individuals eligible for intensified treatment and care. All models performed accurately and similarly and because of the superior national coverage, the best model can potentially be used to better differentiate new patients, allowing for improved targeting of limited resources. Future research should focus on further model development and investigate possibilities for implementation.
|
|
| 6. |
|
|
| 7. |
- Wallert, John, et al.
(författare)
-
Temporal changes in myocardial infarction incidence rates are associated with periods of perceived psychosocial stress : a SWEDEHEART national registry study
- 2017
-
Ingår i: American Heart Journal. - New York : Elsevier. - 0002-8703 .- 1097-6744. ; 191, s. 12-20
-
Tidskriftsartikel (refereegranskat)abstract
- Background Psychosocial stress might trigger myocardial infarction (MI). Increased MI incidence coincides with recurrent time periods during the year perceived as particularly stressful in the population.Methods A stress-triggering hypothesis on the risk of MI onset was investigated with Swedish population data on MI hospital admission date and symptom onset date (N = 156,690; 148,176) as registered from 2006 through 2013 in the national quality registry database Swedish Web-system for Enhancement and Development of Evidence-based care in Heart disease Evaluated According to Recommended Therapies (SWEDEHEART). Poisson regression was applied to analyze daily MI rates during days belonging to the Christmas and New Year holidays, turns of the month, Mondays, weekends, and summer vacation in July compared with remaining control days.Results Adjusted incidence rate ratios (IRRs) for MI rates were higher during Christmas and New Year holidays (IRR = 1.07 [1.04-1.09], P < .001) and on Mondays (IRR = 1.11 [1.09-1.13], P < .001) and lower in July (IRR = 0.92 [0.90-0.94], P < .001) and over weekends (IRR = 0.88 [0.87-0.89], P < .001), yet not during the turns of the month (IRR = 1.01 [1.00–1.02], P = .891). These findings were also predominantly robust with symptom onset as alternative outcome, when adjusting for both established and some suggested-but-untested confounders, and in 8 subgroups.Conclusions Fluctuations in daily MI incidence rates are systematically related to time periods of presumed psychosocial stress. Further research might clarify mechanisms that are amenable to clinical alteration.
|
|
