ObjectiveGuidelines suggest considering antiseizure medication (ASM) discontinuation in seizure-free patients with epilepsy. Past work has poorly explored how discontinuation effects vary between... Show moreObjectiveGuidelines suggest considering antiseizure medication (ASM) discontinuation in seizure-free patients with epilepsy. Past work has poorly explored how discontinuation effects vary between patients. We evaluated (1) what factors modify the influence of discontinuation on seizure risk; and (2) the range of seizure risk increase due to discontinuation across low- versus high-risk patients.MethodsWe pooled three datasets including seizure-free patients who did and did not discontinue ASMs. We conducted time-to-first-seizure analyses. First, we evaluated what individual patient factors modified the relative effect of ASM discontinuation on seizure risk via interaction terms. Then, we assessed the distribution of 2-year risk increase as predicted by our adjusted logistic regressions.ResultsWe included 1626 patients, of whom 678 (42%) planned to discontinue all ASMs. The mean predicted 2-year seizure risk was 43% [95% confidence interval (CI) 39%–46%] for discontinuation versus 21% (95% CI 19%–24%) for continuation. The mean 2-year absolute seizure risk increase was 21% (95% CI 18%–26%). No individual interaction term was significant after correcting for multiple comparisons. The median [interquartile range (IQR)] risk increase across patients was 19% (IQR 14%–24%; range 7%–37%). Results were unchanged when restricting analyses to only the two RCTs.SignificanceNo single patient factor significantly modified the influence of discontinuation on seizure risk, although we captured how absolute risk increases change for patients that are at low versus high risk. Patients should likely continue ASMs if even a 7% 2-year increase in the chance of any more seizures would be too much and should likely discontinue ASMs if even a 37% risk increase would be too little. In between these extremes, individualized risk calculation and a careful understanding of patient preferences are critical. Future work will further develop a two-armed individualized seizure risk calculator and contextualize seizure risk thresholds below which to consider discontinuation.Plain Language SummaryUnderstanding how much antiseizure medications (ASMs) decrease seizure risk is an important part of determining which patients with epilepsy should be treated, especially for patients who have not had a seizure in a while. We found that there was a wide range in the amount that ASM discontinuation increases seizure risk—between 7% and 37%. We found that no single patient factor modified that amount. Understanding what a patient's seizure risk might be if they discontinued versus continued ASM treatment is critical to making informed decisions about whether the benefit of treatment outweighs the downsides. Show less
Feijen, M.C.L.; Egorova, A.D.; Kuijken, T.; Bootsma, M.; Schalij, M.J.; Erven, L. van 2023
Implantable cardioverter defibrillators (ICDs) significantly contribute to the prevention of sudden cardiac death in selected patients. However, it is essential to identify those who are likely to... Show moreImplantable cardioverter defibrillators (ICDs) significantly contribute to the prevention of sudden cardiac death in selected patients. However, it is essential to identify those who are likely to not have benefit from an ICD and to defer a pulse generator exchange. Easily implementable guidelines for individual risk stratification and decision making are lacking. This study investigates the 1-year mortality of patients who underwent an ICD or cardiac resynchronization therapy with defibrillator function (CRT-D) pulse generator replacement in a contemporary real-world tertiary hospital setting. The cause of death and patient- and procedure-related factors are stratified, and predictive values for 1-year mortality are evaluated. Patients with a follow-up of & GE;365 days (or prior mortality) after an ICD or CRT-D exchange at the Leiden University Medical Center from 1 January 2018 until 31 December 2021 were eligible. In total, 588 patients were included (77% male, 69 [60-76] years old, 59% primary prevention, 46% ischemic cardiomyopathy and 37% mildly reduced left ventricular ejection fraction (LVEF)). Patients undergoing a CRT-D replacement or upgrade had a significantly higher 1-year all-cause mortality (10.7% and 11.9%, respectively) compared to patients undergoing ICD (2.8%) exchange (p = 0.002). LVEF & LE; 30%, New York Heart Association class & GE; 3, estimated glomerular filtration rate & LE; 30 mL/min/m2 and haemoglobin & LE; 7 mmol/L were independently associated with mortality within 1 year after pulse generator replacement. There is a growing need for prospectively validated risk scores to weight individualized risk of mortality with the expected ICD therapy benefit and to support a well-informed, shared decision-making process. Show less
Risk prediction for meningioma tumors was until recently almost exclusively based on morphological features of the tumor. To improve risk prediction, multiple models have been established that... Show moreRisk prediction for meningioma tumors was until recently almost exclusively based on morphological features of the tumor. To improve risk prediction, multiple models have been established that incorporate morphological and molecular features for an integrated risk prediction score. One such model is the integrated molecular-morphologic meningioma integrated score (IntS), which allocates points to the histological grade, epigenetic methylation family and specific copy-number variations. After publication of the IntS, questions arose in the neuropathological community about the practical and clinical implementation of the IntS, specifically regarding the calling of CNVs, the applicability of the newly available version (v12.5) of the brain tumor classifier and the need for incorporation of TERT-promoter and CDKN2A/B status analysis in the IntS calculation. To investigate and validate these questions additional analyses of the discovery (n = 514), retrospective validation (n = 184) and prospective validation (n = 287) cohorts used for IntS discovery and validation were performed. Our findings suggest that any loss over 5% of the chromosomal arm suffices for the calling of a CNV, that input from the v12.5 classifier is as good or better than the dedicated meningioma classifier (v2.4) and that there is most likely no need for additional testing for TERT-promoter mutations and/or homozygous losses of CDKN2A/B when defining the IntS for an individual patient. The findings from this study help facilitate the clinical implementation of IntS-based risk prediction for meningioma patients. Show less
Velickovic, V.M.; Spelman, T.; Clark, M.; Probst, S.; Armstrong, D.G.; Steyerberg, E. 2022
Significance: Chronic wounds are associated with significant morbidity, marked loss of quality of life, and considerable economic burden. Evidence-based risk prediction to guide improved wound... Show moreSignificance: Chronic wounds are associated with significant morbidity, marked loss of quality of life, and considerable economic burden. Evidence-based risk prediction to guide improved wound prevention and treatment is limited by the complexity in their etiology, clinical underreporting, and a lack of studies using large high-quality datasets. Recent Advancements: The objective of this review is to summarize key components and challenges in the development of personalized risk prediction tools for both prevention and management of chronic wounds, while highlighting several innovations in the development of better risk stratification. Critical Issues: Regression-based risk prediction approaches remain important for assessment of prognosis and risk stratification in chronic wound management. Advances in statistical computing have boosted the development of several promising machine learning (ML) and other semiautomated classification tools. These methods may be better placed to handle large number of wound healing risk factors from large datasets, potentially resulting in better risk prediction when combined with conventional methods and clinical experience and expertise. Future Directions: Where the number of predictors is large and heterogenous, the correlations between various risk factors complex, and very large data sets are available, ML may prove a powerful adjuvant for risk stratifying patients predisposed to chronic wounds. Conventional regression-based approaches remain important, particularly where the number of predictors is relatively small. Translating estimated risk derived from ML algorithms into practical prediction tools for use in clinical practice remains challenging. Show less
Barbour, S.J.; Coppo, R.; Zhang, H.; Liu, Z.H.; Suzuki, Y.; Matsuzaki, K.; ... ; Int IgA Nephropathy Network 2022
The International IgA Nephropathy (IgAN) Prediction Tool is the preferred method in the 2021 KDIGO guidelines to predict, at the time of kidney biopsy, the risk of a 50% drop in estimated... Show moreThe International IgA Nephropathy (IgAN) Prediction Tool is the preferred method in the 2021 KDIGO guidelines to predict, at the time of kidney biopsy, the risk of a 50% drop in estimated glomerular filtration rate or kidney failure. However, it is not known if the Prediction Tool can be accurately applied after a period of observation post-biopsy. Using an international multi-ethnic derivation cohort of 2,507 adults with IgAN, we updated the Prediction Tool for use one year after biopsy, and externally validated this in a cohort of 722 adults. The original Prediction Tool applied at one-year without modification had a coefficient of variation (R-2) of 55% and 54% and four-year concordance (C statistic) of 0.82 but poor calibration with under-prediction of risk (integrated calibration index (ICI) 1.54 and 2.11, with and without race, respectively). Our updated Prediction Tool had a better model fit with higher R2 (61% and 60%), significant increase in four-year C-statistic (0.87 and 0.86) and better four-year calibration with lower ICI (0.75 and 0.35). On external validation, the updated Prediction Tool had similar R-2 (60% and 58%) and four-year C-statistics (both 0.85) compared to the derivation analysis, with excellent four-year calibration (ICI 0.62 and 0.56). This updated Prediction Tool had similar prediction performance when used two years after biopsy. Thus, the original Prediction Tool should be used only at the time of biopsy whereas our updated Prediction Tool can be used for risk stratification one or two years post-biopsy. Show less
Early detection of breast cancer through screening reduces breast cancer mortality. The benefits of screening must also be considered within the context of potential harms (e.g., false positives,... Show moreEarly detection of breast cancer through screening reduces breast cancer mortality. The benefits of screening must also be considered within the context of potential harms (e.g., false positives, overdiagnosis). Furthermore, while breast cancer risk is highly variable within the population, most screening programs use age to determine eligibility. A risk-based approach is expected to improve the benefit-harm ratio of breast cancer screening programs. The PERSPECTIVE I&I (Personalized Risk Assessment for Prevention and Early Detection of Breast Cancer: Integration and Implementation) project seeks to improve personalized risk assessment to allow for a cost-effective, population-based approach to risk-based screening and determine best practices for implementation in Canada. This commentary describes the four inter-related activities that comprise the PERSPECTIVE I&I project. 1: Identification and validation of novel moderate to high-risk susceptibility genes. 2: Improvement, validation, and adaptation of a risk prediction web-tool for the Canadian context. 3: Development and piloting of a socio-ethical framework to support implementation of risk-based breast cancer screening. 4: Economic analysis to optimize the implementation of risk-based screening. Risk-based screening and prevention is expected to benefit all women, empowering them to work with their healthcare provider to make informed decisions about screening and prevention. Show less
Vanier, A.; Smolen, J.S.; Allaart, C.F.; Vollenhoven, R. van; Verschueren, P.; Vastesaeger, N.; ... ; Fautrel, B. 2020
Objective. In early RA, some patients exhibit rapid radiographic progression (RRP) after one year, associated with poor functional prognosis. Matrices predicting this risk have been proposed,... Show moreObjective. In early RA, some patients exhibit rapid radiographic progression (RRP) after one year, associated with poor functional prognosis. Matrices predicting this risk have been proposed, lacking precision or inadequately calibrated. We developed a matrix to predict RRP with high precision and adequate calibration.Methods. Post-hoc analysis by pooling individual data from cohorts (ESPOIR and Leuven cohorts) and clinical trials (ASPIRE, BeSt and SWEFOT trials). Adult DMARD-naive patients with active early RA for which the first therapeutic strategy after inclusion was to prescribe methotrexate or leflunomide were included. A logistic regression model to predict RRP was built. The best model was selected by 10-fold stratified cross-validation by maximizing the Area Under the Curve. Calibration and discriminatory power of the model were checked. The probabilities of RRP for each combination of levels of baseline characteristics were estimated.Results. 1306 patients were pooled. 20.6% exhibited RRP. Four predictors were retained: rheumatoid factor positivity, presence of at least one RA erosion on X-rays, CRP>30mg/l, number of swollen joints. The matrix estimates RRP probability for 36 combinations of level of baseline characteristics with a greatly enhanced precision compared with previously published matrices (95% CI: from +/- 0.02 minimum to +/- 0.08 maximum) and model calibration is excellent (P = 0.79).Conclusion. A matrix proposing RRP probability with high precision and excellent calibration in early RA was built. Although the matrix has moderate sensitivity and specificity, it is easily usable and may help physicians and patients to make treatment decisions in daily clinical practice. Show less
Background Rapid coronary plaque progression (RPP) is associated with incident cardiovascular events. To date, no method exists for the identification of individuals at risk of RPP at a single... Show moreBackground Rapid coronary plaque progression (RPP) is associated with incident cardiovascular events. To date, no method exists for the identification of individuals at risk of RPP at a single point in time. This study integrated coronary computed tomography angiography-determined qualitative and quantitative plaque features within a machine learning (ML) framework to determine its performance for predicting RPP.Methods and Results Qualitative and quantitative coronary computed tomography angiography plaque characterization was performed in 1083 patients who underwent serial coronary computed tomography angiography from the PARADIGM (Progression of Atherosclerotic Plaque Determined by Computed Tomographic Angiography Imaging) registry. RPP was defined as an annual progression of percentage atheroma volume >= 1.0%. We employed the following ML models: model 1, clinical variables; model 2, model 1 plus qualitative plaque features; model 3, model 2 plus quantitative plaque features. ML models were compared with the atherosclerotic cardiovascular disease risk score, Duke coronary artery disease score, and a logistic regression statistical model. 224 patients (21%) were identified as RPP. Feature selection in ML identifies that quantitative computed tomography variables were higher-ranking features, followed by qualitative computed tomography variables and clinical/laboratory variables. ML model 3 exhibited the highest discriminatory performance to identify individuals who would experience RPP when compared with atherosclerotic cardiovascular disease risk score, the other ML models, and the statistical model (area under the receiver operating characteristic curve in ML model 3, 0.83 [95% CI 0.78-0.89], versus atherosclerotic cardiovascular disease risk score, 0.60 [0.52-0.67]; Duke coronary artery disease score, 0.74 [0.68-0.79]; ML model 1, 0.62 [0.55-0.69]; ML model 2, 0.73 [0.67-0.80]; all P<0.001; statistical model, 0.81 [0.75-0.87], P=0.128).Conclusions Based on a ML framework, quantitative atherosclerosis characterization has been shown to be the most important feature when compared with clinical, laboratory, and qualitative measures in identifying patients at risk of RPP. Show less