cCOG: A web-based cognitive test tool for detecting neurodegenerative disorders.

INTRODUCTION: Web-based cognitive tests have potential for standardized screening in neurodegenerative disorders. We examined accuracy and consistency of cCOG, a computerized cognitive tool, in detecting mild cognitive impairment (MCI) and dementia. METHODS: Clinical data of 306 cognitively normal, 120 mild cognitive impairment (MCI), and 69 dementia subjects from three European cohorts were analyzed. Global cognitive score was defined from standard neuropsychological tests and compared to the corresponding estimated score from the cCOG tool containing seven subtasks. The consistency of cCOG was assessed comparing measurements administered in clinical settings and in the home environment. RESULTS: cCOG produced accuracies (receiver operating characteristic-area under the curve [ROC-AUC]) between 0.71 and 0.84 in detecting MCI and 0.86 and 0.94 in detecting dementia when administered at the clinic and at home. The accuracy was comparable to the results of standard neuropsychological tests (AUC 0.69-0.77 MCI/0.91-0.92 dementia). DISCUSSION: cCOG provides a promising tool for detecting MCI and dementia with potential for a cost-effective approach including home-based cognitive assessments.

The association between charlson comorbidity index and mortality in acute coronary syndrome - the MADDEC study.

Objectives. Acute coronary syndrome (ACS) is associated with high mortality. Charlson comorbidity index (CCI) was designed over 30 years ago to measure the impact of pre-existing comorbidities on long-term survival of the patient. We wanted to re-evaluate the performance of CCI and its components in modern setting. Design. This is a retrospective study of 1576 consecutive patients undergoing invasive evaluation and treated for ACS in single tertiary center between 2015-2016. Mortality was analyzed in timeframes of 1, 6 and 24 months. CCI-scores were retrieved from written medical records and complimented with data from electronic sources. The performance of CCI and its components was compared to the GRACE-score measuring patients' status upon hospital admission. Results. Population mean age at baseline was 69.3 (SD 11.8) years and 69.1% of the patients were male (n = 1089). Most of the components of CCI associated significantly with mortality at all timeframes despite adjusting for age but only diabetes and congestive heart failure associated with mortality at all time points after adjusting for GRACE-score. CCI associated with mortality [GRACE adjusted HR-values of single unit increase of CCI after 1, 6 and 24-month follow-up: 1.12(95% CI:1.00-1.25), 1.17(1.07-1.29) and 1.24(1.16-1.33)]. CCI performed modestly with its AUC-values ranging between 0.755 and 0.784, with prognostic performance increasing with longer follow-up. Adding components of CCI did not significantly improve risk prediction over GRACE-score. Conclusions. In conclusion, CCI or its individual components measuring the impact of comorbidities on overall mortality does not provide any significant value compared to GRACE-score during up to 2 years of follow-up.

Left ventricular ejection fraction adds value over the GRACE score in prediction of 6-month mortality after ACS: the MADDEC study.

Background: Reduced left ventricular ejection fraction (LVEF) is a risk marker for mortality after an acute coronary syndrome (ACS). Global Registry of Acute Coronary Events (GRACE) risk score, developed almost two decades ago, is the preferred scoring system for risk stratification in ACS. The aim of this study was to validate the GRACE score and evaluate whether LVEF has incremental predictive value over the GRACE in predicting 6-month mortality after ACS in a contemporary setting. Methods: A retrospective analysis of all 1576 consecutive patients who were admitted to Tays Heart Hospital and underwent coronary angiography for a first episode of ACS (2015-2016). Clinical risk factors were extensively recorded. Adjusted Cox regression analysis was used to analyse the associations between LVEF and the GRACE score with 6-month all-cause mortality. The incremental predictive value was assessed by the change in C-statistic by Delong's method for paired samples and by index of discrimination improvement (IDI). Results: In univariable analysis, both LVEF and the GRACE were associated with 6-month mortality, and after applying both variables into the same model, the results remained significant (GRACE score: HR: 1.036, 95% CI 1.030 to 1.042; LVEF: HR: 0.965, 95% CI 0.948 to 0.982, both HRs corresponding to a one unit change in the exposure variable). The GRACE score demonstrated good discrimination for mortality (C-statistic: 0.833, 95% CI 0.795 to 0.871). Adding LVEF to the model with the GRACE score improved model performance significantly (C-statistic: 0.848, 95% CI 0.813 to 0.883, p=0.029 for the improvement and IDI 0.0171, 95% CI 0.0016 to 0.0327, p=0.031). Conclusions: Adding LVEF to the GRACE score significantly improves risk prediction of 6-month mortality after ACS.

Extensive phenotype data and machine learning in prediction of mortality in acute coronary syndrome - the MADDEC study.

Objective: Investigation of the clinical potential of extensive phenotype data and machine learning (ML) in the prediction of mortality in acute coronary syndrome (ACS). Methods: The value of ML and extensive clinical data was analyzed in a retrospective registry study of 9066 consecutive ACS patients (January 2007 to October 2017). Main outcome was six-month mortality. Prediction models were developed using two ML methods, logistic regression and extreme gradient boosting (xgboost). The models were fitted in training set of patients treated in 2007-2014 and 2017 (81%, n = 7344) and validated in a separate validation set of patients treated in 2015-2016 with full GRACE score data available for comparison of model accuracy (19%, n = 1722). Results: Overall, six-month mortality was 7.3% (n = 660). Several variables were found to be significantly associated with six-month mortality by both ML methods. The xgboost scored the best performance: AUC 0.890 (0.864-0.916). The AUC values for logistic regression and GRACE score were 0.867(0.837-0.897) and 0.822 (0.785-0.859), respectively. The AUC value of xgboost was better when compared to logistic regression (p = .012) and GRACE score (p < .00001). Conclusions: The use of extensive phenotype data and novel machine learning improves prediction of mortality in ACS over traditional GRACE score. KEY MESSAGES The collection of extensive cardiovascular phenotype data from electronic health records as well as from data recorded by physicians can be used highly effectively in prediction of mortality after acute coronary syndrome. Supervised machine learning methods such as logistic regression and extreme gradient boosting using extensive phenotype data significantly outperform conventional risk assessment by the current golden standard GRACE score. Integration of electronic health records and the use of supervised machine learning methods can be easily applied in a single centre level to model the risk of mortality.

Is 50 Hz high enough ECG sampling frequency for accurate HRV analysis?

With the worldwide growth of mobile wireless technologies, healthcare services can be provided at anytime and anywhere. Usage of wearable wireless physiological monitoring system has been extensively increasing during the last decade. These mobile devices can continuously measure e.g. the heart activity and wirelessly transfer the data to the mobile phone of the patient. One of the significant restrictions for these devices is usage of energy, which leads to requiring low sampling rate. This article is presented in order to investigate the lowest adequate sampling frequency of ECG signal, for achieving accurate enough time domain heart rate variability (HRV) parameters. For this purpose the ECG signals originally measured with high 5 kHz sampling rate were down-sampled to simulate the measurement with lower sampling rate. Down-sampling loses information, decreases temporal accuracy, which was then restored by interpolating the signals to their original sampling rates. The HRV parameters obtained from the ECG signals with lower sampling rates were compared. The results represent that even when the sampling rate of ECG signal is equal to 50 Hz, the HRV parameters are almost accurate with a reasonable error.

Comparison of HRV parameters derived from photoplethysmography and electrocardiography signals.

Heart rate variability (HRV) has become a useful tool in analysis of cardiovascular system in both research and clinical fields. HRV has been also used in other applications such as stress level estimation in wearable devices. HRV is normally obtained from ECG as the time interval of two successive R waves. Recently PPG has been proposed as an alternative for ECG in HRV analysis to overcome some difficulties in measurement of ECG. In addition, PPG-HRV is also used in some commercial devices such as modern optical wrist-worn heart rate monitors. However, some researches have shown that PPG is not a surrogate for heart rate variability analysis. In this work, HRV analysis was applied on beat-to-beat intervals obtained from ECG and PPG in 19 healthy male subjects. Some important HRV parameters were calculated from PPG-HRV and ECG-HRV. Maximum of PPG and its second derivative were considered as two methods for obtaining the beat-to-beat signals from PPG and the results were compared with those achieved from ECG-HRV. Our results show that the smallest error happens in SDNN and SD2 with relative error of 2.46% and 2%, respectively. The most affected parameter is pNN50 with relative error of 29.89%. In addition, in our trial, using the maximum of PPG gave better results than its second derivative.