Sven Van Poucke

The authors describe a compartment syndrome progressively developed after a long-term surgical procedure, with a patient positioned in supine position with calf rest, who was successfully treated with hyperbaric oxygenation. This approach saved the patient from a more invasive therapeutic intervention.

Objectives Quantification and early identification of unplanned readmission risk have the potential to improve the quality of care during hospitalization and after discharge. However, high dimensionality, sparsity, and class imbalance of electronic health data and the complexity of risk quantification, challenge the development of accurate predictive models. Predictive models require a certain level of interpretability in order to be applicable in real settings and create actionable insights. This paper aims to develop accurate and interpretable predictive models for readmission in a general pediatric patient population, by integrating a data-driven model (sparse logistic regression) and domain knowledge based on the international classification of diseases 9th-revision clinical modification (ICD-9-CM) hierarchy of diseases. Additionally, we propose a way to quantify the interpretability of a model and inspect the stability of alternative solutions. Materials and methods The analysis was conducted on >66,000 pediatric hospital discharge records from California, State Inpatient Databases, Healthcare Cost and Utilization Project between 2009 and 2011. We incorporated domain knowledge based on the ICD-9-CM hierarchy in a data driven, Tree-Lasso regularized logistic regression model, providing the framework for model interpretation. This approach was compared with traditional Lasso logistic regression resulting in models that are easier to interpret by fewer high-level diagnoses, with comparable prediction accuracy. Results The results revealed that the use of a Tree-Lasso model was as competitive in terms of accuracy (measured by area under the receiver operating characteristic curve-AUC) as the traditional Lasso logistic regression, but integration with the ICD-9-CM hierarchy of diseases provided more interpretable models in terms of high-level diagnoses. Additionally, interpretations of models are in accordance with existing medical understanding of pediatric readmission. Best performing models have similar performances reaching AUC values 0.783 and 0.779 for traditional Lasso and Tree-Lasso, respectfully. However, information loss of Lasso models is 0.35 bits higher compared to Tree-Lasso model.

Platelet function can be quantitatively assessed by specific assays such as light-transmission aggregometry, multiple-electrode aggregometry measuring the response to adenosine diphosphate (ADP), arachidonic acid, collagen, and thrombin-receptor activating peptide and viscoelastic tests such as rotational thromboelastometry (ROTEM). The task of extracting meaningful statistical and clinical information from high-dimensional data spaces in temporal multivariate clinical data represented in multivariate time series is complex. Building insightful visualizations for multivariate time series demands adequate usage of normalization techniques. In this article, various methods for data normalization (z-transformation, range transformation, proportion transformation, and interquartile range) are presented and visualized discussing the most suited approach for platelet function data series. Normalization was calculated per assay (test) for all time points and per time point for all tests. Interquartile range, range transformation, and z-transformation demonstrated the correlation as calculated by the Spearman correlation test, when normalized per assay (test) for all time points. When normalizing per time point for all tests, no correlation could be abstracted from the charts as was the case when using all data as 1 dataset for normalization. Abbreviations: AA = acetylsalicylic acid, ADP = adenosine diphosphate, APT = antiplatelet therapy, CABG = coronary artery bypass grafting, CFT = clot formation time, COL = collagen, CPB = cardiopulmonary bypass, ROTEM = rotational thromboelastometry, CRISP-DM = CRoss-Industry Standard Process for Data Mining, CT = clotting time, Hb = hemoglobin, Hct = hematocrit, K2EDTA = dipotassium ethylenediaminetetraacetate, K-NN = k-Nearest Neighbors, LTA = light transmission aggregometry, MCF = maximum clot firmness, MEIA = multiple electrode impedance aggregometry, ML = maximum lysis, PCA = principal component analysis, PF = platelet function, PlatCt = platelet count, PPP = platelet-poor plasma, PRP = platelet-rich plasma, TRAP thrombin receptor-activating peptide.

Coronary artery bypass grafting (CABG) with cardiopulmonary bypass (CPB) is frequently associated with low platelet count (PC) and disturbed platelet function (PF). While PC is easy to measure, PF is more difficult to assess. Moreover, the time-related platelet dysfunction and recovery after CPB is not fully elucidated. Platelet dysfunction could lead to bleeding but also to coronary graft failure. Laboratory tests could provide more insights into PF after CABG. The aim of the current study was to investigate the time-related PF induced by CPB. Blood samples of 20 patients with a preoperative PC of more than 250 × 10(9)/L were collected before incision, after weaning from CPB, and 24 h postoperative. Platelet contribution to coagulation was quantified by PLTEM (calculated by means of EXTEM and FIBTEM results). PF was assessed by multiple electrode impedance aggregometry (MEIA) in whole blood and by light transmission aggregometry (LTA) in platelet-rich plasma after stimulation with arachidonic acid (AA), adenosine diphosphate, collagen, and thrombin-receptor-activating peptide. LTA and MEIA analysis demonstrated significant platelet dysfunction after CPB, with partial recovery within 24 h after surgery. AA-induced platelet aggregation increased to higher levels within 24 h after surgery compared to baseline values as measured by LTA. PLTEM maximum clot firmness remained unchanged throughout the study. Correlation analyses revealed that MEIA and rotational thromboelastometry (ROTEM), but not LTA, were dependent on PC and hematocrit. No correlations were found between LTA, MEIA, ROTEM, PC, and clinical outcome parameters. Our results demonstrate a reversible platelet dysfunction recovering within 24 h after CPB. Interestingly, AA-induced platelet aggregation increases to higher levels during the first 24 h postoperatively, which might be important for early initiation of antiplatelet therapy after CABG. MEIA as POC test is able to detect platelet dysfunction during cardiac surgery with a PC of ≥150 × 10(9)/L.

Despite the accelerating pace of scientific discovery, the current clinical research enterprise does not sufficiently address pressing clinical questions. Given the constraints on clinical trials, for a majority of clinical questions, the only relevant data available to aid in decision making are based on observation and experience. Our purpose here is 3-fold. First, we describe the classic context of medical research guided by Poppers' scientific epistemology of "falsificationism." Second, we discuss challenges and shortcomings of randomized controlled trials and present the potential of observational studies based on big data. Third, we cover several obstacles related to the use of observational (retrospective) data in clinical studies. We conclude that randomized controlled trials are not at risk for extinction, but innovations in statistics, machine learning, and big data analytics may generate a completely new ecosystem for exploration and validation.

The eye lens is one of the most sensitive organs for radiation injury and exposure might lead to radiation induced cataract. Eye lens dosimetry in anesthesiology has been published in few clinical trials and an active debate about the causality of radiation induced cataract is still ongoing. Recently, the International Commission on Radiological Protection (ICRP) recommended a reduction in the annual dose limit for occupational exposure for the lens of the eye from 150 to 20 mSv, averaged over a period of 5 years, with the dose in a single year not exceeding 50 mSv. This prospective study investigated eye lens dosimetry in anesthesiology practice during a routine year of professional activity. The radiation exposure measured represented the exposure in a normal working schedule of a random anesthesiologist during 1 month and this cumulative eye lens dose was extrapolated to 1 year. Next, eye lens doses were measured in anesthesiology during neuro-embolisation procedures, radiofrequency ablations or vertebroplasty/kyphoplasty procedures. The eye lens doses are measured in terms of the dose equivalent H p(3) with the Eye-D dosimeter (Radcard, Poland) close to the right eye (on the temple). In 16 anesthesiologists, the estimated annual eye lens doses range from a minimum of 0.4 mSv to a maximum of 3.5 mSv with an average dose of 1.33 mSv. Next, eye lens doses were measured for nine neuro-embolisation procedures, ten radiofrequency ablations and six vertebroplasty/kyphoplasty procedures. Average eye lens doses of 77 ± 76 µSv for neuro-embolisations, 38 ± 34 µSv for cardiac ablations and 40 ± 44 µSv for vertebro-/kyphoplasty procedures were recorded. The maximum doses were respectively 264, 97 and 122 µSv. This study demonstrated that the estimated annual eye lens dose is well below the revised ICRP's limit of 20 mSv/year. However, we demonstrated high maximum and average doses during neuro-embolisation, cardiac ablation and vertebro-/kyphoplasty procedures. With radiation induced cataract being explained as a possible stochastic effect, without a threshold dose, anesthesiologists who regularly work in a radiological environment should remain vigilant and maintain radiation safety standards at all times. This includes adequately protective equipment (protection shields, apron, thyroid shield and leaded eye wear), keeping distance, routine monitoring and appropriate education.

With the accumulation of large amounts of health related data, predictive analytics could stimulate the transformation of reactive medicine towards Predictive, Preventive and Personalized (PPPM) Medicine, ultimately affecting both cost and quality of care. However, high-dimensionality and high-complexity of the data involved, prevents data-driven methods from easy translation into clinically relevant models. Additionally, the application of cutting edge predictive methods and data manipulation require substantial programming skills, limiting its direct exploitation by medical domain experts. This leaves a gap between potential and actual data usage. In this study, the authors address this problem by focusing on open, visual environments, suited to be applied by the medical community. Moreover, we review code free applications of big data technologies. As a showcase, a framework was developed for the meaningful use of data from critical care patients by integrating the MIMIC-II database in a data mining environment (RapidMiner) supporting scalable predictive analytics using visual tools (RapidMiner's Radoop extension). Guided by the CRoss-Industry Standard Process for Data Mining (CRISP-DM), the ETL process (Extract, Transform, Load) was initiated by retrieving data from the MIMIC-II tables of interest. As use case, correlation of platelet count and ICU survival was quantitatively assessed. Using visual tools for ETL on Hadoop and predictive modeling in RapidMiner, we developed robust processes for automatic building, parameter optimization and evaluation of various predictive models, under different feature selection schemes. Because these processes can be easily adopted in other projects, this environment is attractive for scalable predictive analytics in health research.

Alterations in platelet function are a common finding in surgical procedures involving cardiopulmonary bypass and hypothermia. Although the combined impact of hypothermia and artificial circulation on platelets has been studied before, the ultimate strategy to safely minimize the risk for bleeding and thrombosis is yet unknown. The aim of this study was to evaluate the use of a mock circulation loop to study the impact of hypothermia for platelet-related hemostatic changes. Venous blood was collected from healthy adult humans (n = 3). Closed mock circulation loops were assembled, each consisting of a centrifugal pump, an oxygenator with integrated heat exchanger, and a hardshell venous reservoir. The experiment started with the mock circulation temperature set at 37°C (T0 [0 h]). Cooling was then initiated at T1 (+2 h), where temperature was adjusted from 37°C to 32°C. Hypothermia was maintained from T2 (+4 h) to T3 (+28 h). From that point in time, rewarming from 32°C to 37°C was initiated with similar speed as cooling. From time point T4 (+30 h), normothermia (37°C) was maintained until the experiment ended at T5 (+32 h). Blood samples were analyzed in standard hematological tests: light transmission aggregometry (LTA) (arachidonic acid [AA], adenosine diphosphate [ADP], collagen [COL], thrombin-receptor-activating-peptide-14 [TRAP]), multiple electrode aggregometry (MEA) (AA, ADP, COL, TRAP), and rotational thromboelastometry (ROTEM) (EXTEM, FIBTEM, PLTEM). Hemoglobin, hematocrit, and platelet count decrease more substantially during temperature drop (37-32°C) than during hypothermia maintenance. Hb and Hct continue to follow this trend during active rewarming (32-37°C). PC increase from the moment active rewarming was initiated. None of the values return to the initial values. LTA values demonstrate a similar decrease in aggregation after stimulation with the platelet agonists between the start of the mock circulation and the start of cooling. Except for platelet stimulation using COL, this trend continues during temperature drop from 37°C to 32°C. LTA values using AA and TRAP demonstrate a considerable decline in platelet function throughout the experiment that was most pronounced after 24 h of circulation at 32°C. LTA values using ADP and COL further decline after rewarming. MEA ADP, ASPI, and COL identify platelet dysfunction patterns analogous with LTA, between the start of the mock circulation and the start of cooling. Except for MEA TRAP, this trend continues during temperature drop from 37°C to 32°C. MEA ASPI and ADP demonstrate a considerable decline in platelet function throughout the experiment, which was most pronounced after 24 h of circulation at 32°C. For MEA COL and TRAP, further decline in platelet function is observed after rewarming. This study quantitatively assessed the effect of temperature changes on platelet function during experimental mock circulation demonstrating a considerable decline in platelet function during hypothermia without uniform recovery of platelet function observed after rewarming.

The authors describe a compartment syndrome progressively developed after a long-term surgical procedure, with a patient positioned in supine position with calf rest, who was successfully treated with hyperbaric oxygenation. This approach saved the patient from a more invasive therapeutic intervention.