On the Use of Hemadsorption with CytoSorb in Patients with Septic Shock. Comment on Kogelmann et al. First Evaluation of a New Dynamic Scoring System Intended to Support Prescription of Adjuvant CytoSorb Hemoadsorption Therapy in Patients with Septic Shock. J. Clin. Med. 2021, 10, 2939

With great interest we read the article by Klaus Kogelmann and co-authors on the “First Evaluation of a New Dynamic Scoring System Intended to Support Prescription of Adjuvant CytoSorb Hemoadsorption Therapy in Patients with Septic Shock” [...]

A Novel Machine Learning-Derived Dynamic Scoring System Predicts Risk of Thrombosis in Polycythemia Vera (PV) Patients

Introduction: Thrombosis remains a leading cause of morbidity and early mortality in PV. The European LeukemiaNet (ELN) classifies patients (pts) at diagnosis as high-risk according to age ≥60 years (yr) and/ or prior thrombosis, but dynamic models predicting short-term risk of initial or recurrent thrombosis are unavailable. We utilized machine learning (ML) to develop a dynamic scoring system that predicts thrombosis in PV pts using the most important of 60 clinicopathologic features. Methods: A Random Forests ML model was trained to classify instances (3-month follow-up intervals of PV pts) as predictive or non-predictive of thrombosis, arterial or venous, in subsequent 3-6 months based on 60 features: 4 demographic, 11 history & physical, 13 treatments, 18 laboratory, and 14 pathology and molecular. The dataset was derived from Weill Cornell Medicine (WCM) Research Database Repository as previously described (Abu-Zeinah et al. Leukemia 2021) and split into training (75%) and testing (25%) sets. Hyperparameter tuning was performed to optimize model training. Synthetic minority oversampling technique (SMOTE) was implemented to reduce class imbalance since instances predictive of thrombosis were a minority. Missing data were imputed using multiple imputation by chained equations (MICE). The scoring system was developed based on ML-derived features of highest importance and confirmed by logistic regression multivariable analysis (MVA). Cumulative incidence (CI) of thrombosis was compared between risk groups using Fine-Gray model. External validation of the ML model and scoring system is underway using the Mount Sinai School of Medicine (MSSM) PV dataset. Statistical analyses and plots were performed in RStudio software v 1.4.1106. Results: 470 PV pts at WCM were included with baseline features shown in Fig 1A. During follow-up, 159 thromboses (88 venous, 71 arterial) occurred in 115 pts. CI of thrombosis was significantly higher shortly after diagnosis, as previously appreciated (Hulcrantz et al. Ann Intern Med. 2018), and following a thrombotic event (Fig 1B-C). Bilinear fitting to CI curves identified a 2-yr breakpoint that marked the transition from a high to a much lower long-term risk after diagnosis (incidence rate (IR), per year, of 4.4% vs 1%, respectively) and after thrombosis (IR of 9.7% vs 1.8%). Of the ML model's top 10 features, 5 that independently predicted thrombosis in MVA were selected for a clinically convenient scoring system to estimate thrombosis risk (Fig 1D-E). One point was assigned for each of age ≥60 yr, prior thrombosis, WBC ≥12 x 10 9/L, peri-diagnosis (<2 yr from diagnosis), and peri-thrombosis (<2 yr from last thrombosis). Using this scoring system, we found that high-risk (Hi) and intermediate-risk (Int) pts (score ≥2 and =1) were 6.5 and 2.3 times more likely to have thrombosis, respectively, than low-risk (Lo) pts (score = 0) (p<0.001 and p=0.014). Probability of thrombosis was significantly different for Lo, Int, and Hi at 1 yr (0%, 1%, and 6%), 2 yrs (1%, 3%, and 10%), and 5 yr (2%, 9% and 21%) (Fig 1F & 1H). In contrast, ELN high-risk pts were only 2.2 times more likely to have thrombosis than ELN low-risk pts (Fig 1G-H). The concordance (C-index) of the ML-derived model (0.7± se 0.02) was higher than ELN (0.59 ± se 0.03). External validation using the MSSM PV data (Fig 1A) is ongoing. Discussion: We applied ML to our large PV-WCM dataset to identify most important clinicopathologic features predicting thrombosis. In contrast to linear models, ML has little penalty for increasing number of parameters tested and can easily accommodate high-dimensional data to improve predictions. Because "big data" is not routinely available to caregivers, we developed a simple, dynamic scoring system predicting the risk of thrombosis in PV based on 5 most important features identified by ML. This new and dynamic scoring system outperformed ELN stratification and may prove useful in guiding treatment and improving selection of pts for clinical trials aimed at preventing thrombosis in PV pts. Conclusion: The risk of thrombosis in PV pts is temporally non-linear and strongly influenced by proximity to diagnosis and recent thrombosis. A simple ML-derived dynamic scoring system is presented that better classifies pts into distinct Lo, Int, and Hi thrombosis risk groups based on age, prior thrombosis, WBC, peri-diagnosis, and peri-thrombosis. Figure 1 Figure 1. Disclosures Abu-Zeinah: PharmaEssentia: Consultancy. Silver: Abbvie: Consultancy; PharamEssentia: Consultancy, Speakers Bureau. Mascarenhas: Merck: Consultancy, Membership on an entity's Board of Directors or advisory committees, Research Funding; CTI Biopharm: Consultancy, Membership on an entity's Board of Directors or advisory committees, Research Funding; Galecto: Consultancy; Geron: Consultancy; PharmaEssentia: Consultancy, Membership on an entity's Board of Directors or advisory committees, Research Funding; Genentech/Roche: Consultancy, Membership on an entity's Board of Directors or advisory committees; Sierra Oncology: Consultancy, Membership on an entity's Board of Directors or advisory committees; Prelude: Consultancy; Celgene/BMS: Consultancy, Membership on an entity's Board of Directors or advisory committees; Merus: Research Funding; AbbVie: Consultancy, Membership on an entity's Board of Directors or advisory committees, Research Funding; Promedior: Consultancy, Membership on an entity's Board of Directors or advisory committees; Roche: Consultancy, Membership on an entity's Board of Directors or advisory committees, Research Funding; Incyte: Consultancy, Membership on an entity's Board of Directors or advisory committees, Research Funding; Kartos: Consultancy, Membership on an entity's Board of Directors or advisory committees, Research Funding; Constellation: Consultancy, Membership on an entity's Board of Directors or advisory committees; Gilead: Consultancy, Membership on an entity's Board of Directors or advisory committees; Forbius: Research Funding; Geron: Consultancy, Research Funding; Novartis: Consultancy, Membership on an entity's Board of Directors or advisory committees, Research Funding. Scandura: MPN-RF (Foundation): Research Funding; CR&T (Foudation): Research Funding; European Leukemia net: Honoraria, Other: travel fees ; Abbvie: Consultancy, Honoraria, Membership on an entity's Board of Directors or advisory committees, Research Funding; Constellation: Research Funding.

First Evaluation of a New Dynamic Scoring System Intended to Support Prescription of Adjuvant CytoSorb Hemoadsorption Therapy in Patients with Septic Shock

Introduction: Despite advances in critical care medicine, adjunctive approaches in sepsis therapy have failed to prove their efficacy. Notwithstanding promising results using hemoadsorption (CytoSorb), questions remain concerning timing and dosing. We created a dynamic scoring system (DSS) to assess patients with early septic shock and performed a first evaluation of the system in this patient population. Methods: Data from 502 patients with septic shock according to Sepsis-3 criteria were retrospectively analyzed. Score parameters were documented at the time of diagnosis (T0) and 6 h later (T6) to calculate a dynamic score. Survival on day 7 and 56 as well as ICU and hospital mortality were analyzed in regard to the score as well as the delay of hemoadsorption therapy. Results: Of the 502 patients analyzed, 198 received adjunctive CytoSorb treatment and 304 received standard therapy. Septic shock was typically represented by 5 points, while >6 points indicated a situation refractory to standard therapy with the worst outcome in patients shown by >8 points. The differences in mortality between the score groups (<6, 6–8, >8 points) were significant. Analysis further showed a significant 56-day, ICU and hospital survival advantage in CytoSorb patients when therapy was started early. Conclusion: We created a scoring system allowing for the assessment of the clinical development of patients in the early phase of septic shock. Applying this approach, we were able to detect populations with a distinct mortality pattern. The data also showed that an early start of CytoSorb therapy was associated with significantly improved survival. As a next step, this easy-to-apply scoring system would require validation in a prospective manner to learn whether patients to be treated with hemoadsorption therapy in the course of septic shock could thereby be identified.

Dynamic Predictive Scores for Cardiac Surgery-Associated Agitated Delirium: a single-center retrospective observational study

Background Prevention, screening, and early treatment are the mainstays of postoperative delirium management. Score system is an objective and effective tool to stratify potential delirium risk for patients undergoing cardiac surgery Methods Patients undergoing cardiac surgery from January 1, 2012, to January 1, 2019, were enrolled in our retrospective study. The patients were divided into a derivation cohort (n = 45,744) and a validation cohort (n = 11,436). The agitated delirium (AD) predictive systems were formulated using multivariate logistic regression analysis at three time points: preoperation, ICU admittance, and 24 hours after ICU admittance. Results The prevalence of AD after cardiac surgery in the whole cohort was 3.6% (2,085/57,180). The dynamic scoring system included preoperative LVEF ≤ 45%, serum creatinine > 100 umol/L, emergency surgery, coronary artery disease, hemorrhage volume > 600 mL, intraoperative platelet or plasma use, and postoperative LVEF ≤ 45%. The area under the receiver operating characteristic curve (AUC) values for AD prediction of 0.68 (preoperative), 0.74 (on the day of ICU admission), and 0.75 (postoperative). The Hosmer-Lemeshow test indicated that the calibration of the preoperative prediction model was poor (P = 0.01), whereas that of the pre- and intraoperative prediction model (P = 0.49) and the pre-, intra- and postoperative prediction model (P = 0.35) was good. Conclusions Using perioperative data, we developed a dynamic scoring system for predicting the risk of AD following cardiac surgery. The dynamic scoring system may improve early recognition of and interventions for AD.

Taxation and growth: Why does it matter and how can it be analysed?

The growth impact of tax reforms is probably one of the most controversial issues in economic policy discussions, reflecting deep beliefs in the way economic agents are expected to react to policy changes. The optimal tax theory literature provides a wide array of arguments to identify the mechanisms through which tax reforms might influence growth, depending on the tax category considered and the circumstances under which tax reforms are implemented. The empirical literature has relied on the use of cross-country growth regressions and provided general results leading to normative conclusions on the desirability of specific tax reform options. However, recent research has shown that this approach yields inconclusive results, notably due to identification and endogeneity issues, and the difficulty to account for the true determinants of governments' actions. The dynamic scoring approach combining microsimulation and macro models proves more useful in this respect, especially in order to draw policy recommendations while accounting for the second-round effects of tax reforms. I illustrate these arguments by analysing the growth impact of a hypothetical change from the current flat personal income tax (PIT) rates to progressive taxes in Central and Eastern European (CEE) countries. I find that the estimated impact of such a reform would be rather small but positive when using the dynamic scoring method, while the less-reliable traditional growth regressions would suggest adverse growth effects.

A New Scoring Procedure in Assessment Centers: Insights from Interaction Analysis

This paper proposes interaction analysis as an alternative scoring procedure in assessment centers (ACs). Interaction analysis allows for a more fine-grained scoring approach by which candidate behaviors are captured as they actually happen, thus avoiding judgment errors typically associated with traditional scoring procedures. We describe interaction analysis and explain how this procedure can improve the validity of ACs. In a short research example, we showcase how interaction analysis can be implemented in AC settings. Finally, we integrate our arguments in terms of three key propositions which we hope will inspire future research on more dynamic scoring procedures.