Michal Huptych

Open access intrapartum CTG database

BackgroundCardiotocography (CTG) is a monitoring of fetal heart rate and uterine contractions. Since 1960 it is routinely used by obstetricians to assess fetal well-being. Many attempts to introduce methods of automatic signal processing and evaluation have appeared during the last 20 years, however still no significant progress similar to that in the domain of adult heart rate variability, where open access databases are available (e.g. MIT-BIH), is visible. Based on a thorough review of the relevant publications, presented in this paper, the shortcomings of the current state are obvious. A lack of common ground for clinicians and technicians in the field hinders clinically usable progress. Our open access database of digital intrapartum cardiotocographic recordings aims to change that.DescriptionThe intrapartum CTG database consists in total of 552 intrapartum recordings, which were acquired between April 2010 and August 2012 at the obstetrics ward of the University Hospital in Brno, Czech Republic. All recordings were stored in electronic form in the OB TraceVue®;system. The recordings were selected from 9164 intrapartum recordings with clinical as well as technical considerations in mind. All recordings are at most 90 minutes long and start a maximum of 90 minutes before delivery. The time relation of CTG to delivery is known as well as the length of the second stage of labor which does not exceed 30 minutes. The majority of recordings (all but 46 cesarean sections) is – on purpose – from vaginal deliveries. All recordings have available biochemical markers as well as some more general clinical features. Full description of the database and reasoning behind selection of the parameters is presented in the paper.ConclusionA new open-access CTG database is introduced which should give the research community common ground for comparison of results on reasonably large database. We anticipate that after reading the paper, the reader will understand the context of the field from clinical and technical perspectives which will enable him/her to use the database and also understand its limitations.

Using nonlinear features for fetal heart rate classification

Highlights • We analyzed fetal heart rate of normal and acidemic fetuses. • We used conventional and nonlinear features for the signal analysis. • Addition of nonlinear features improves accuracy of classification. • The best nonlinear features are: Lempel Ziv complexity and Sample entropy. • Combination of conventional and nonlinear features provides the best accuracy. Abstract Fetal heart rate (FHR) is used to evaluate fetal well-being and enables clinicians to detect ongoing hypoxia during delivery. Routine clinical evaluation of intrapartum FHR is based on macroscopic morphological features visible to the naked eye. In this paper we evaluated conventional features and compared them to the nonlinear ones in the task of intrapartum FHR classification. The experiments were performed using a database of 217 FHR records with objective annotations, i.e. pH measurement. We have proven that the addition of nonlinear features improves accuracy of classification. The best classification results were achieved using a combination of conventional and nonlinear features with sensitivity of 73.4%, specificity of 76.3%, and F -measure of 71.9%. The best selected nonlinear features were: Lempel Ziv complexity, Sample entropy, and fractal dimension estimated by Higuchi method. Since the results of automatic signal evaluation are easily reproducible, the process of FHR evaluation can become more objective and may enable clinicians to focus on additional non-cardiotocography parameters influencing the fetus during delivery.

Coronary versus carotid blood flow and coronary perfusion pressure in a pig model of prolonged cardiac arrest treated by different modes of venoarterial ECMO and intraaortic balloon counterpulsation

IntroductionExtracorporeal membrane oxygenation (ECMO) is increasingly used in cardiac arrest (CA). Adequacy of carotid and coronary blood flows (CaBF, CoBF) and coronary perfusion pressure (CoPP) in ECMO treated CA is not well established. This study compares femoro-femoral (FF) to femoro-subclavian (FS) ECMO and intraaortic balloon counterpulsation (IABP) contribution based on CaBF, CoBF, CoPP, myocardial and brain oxygenation in experimental CA managed by ECMO.MethodsIn 11 female pigs (50.3 ± 3.4 kg), CA was randomly treated by FF versus FS ECMO ± IABP. Animals under general anesthesia had undergone 15 minutes of ventricular fibrillation (VF) with ECMO flow of 5 to 10 mL/kg/min simulating low-flow CA followed by continued VF with ECMO flow of 100 mL/kg/min. CaBF and CoBF were measured by a Doppler flow wire, cerebral and peripheral oxygenation by near infrared spectroscopy. CoPP, myocardial oxygen metabolism and resuscitability were determined.ResultsCaBF reached values > 80% of baseline in all regimens. CoBF > 80% was reached only by the FF ECMO, 90.0% (66.1, 98.6). Addition of IABP to FF ECMO decreased CoBF to 60.7% (55.1, 86.2) of baseline, P = 0.004. FS ECMO produced 70.0% (49.1, 113.2) of baseline CoBF, significantly lower than FF, P = 0.039. Addition of IABP to FS did not change the CoBF; however, it provided significantly higher flow, 76.7% (71.9, 111.2) of baseline, compared to FF + IABP, P = 0.026. Both brain and peripheral regional oxygen saturations decreased after induction of CA to 23% (15.0, 32.3) and 34% (23.5, 34.0), respectively, and normalized after ECMO institution. For brain saturations, all regimens reached values exceeding 80% of baseline, none of the comparisons between respective treatment approaches differed significantly. After a decline to 15 mmHg (9.5, 20.8) during CA, CoPP gradually rose with time to 68 mmHg (43.3, 84.0), P = 0 .003, with best recovery on FF ECMO. Resuscitability of the animals was high, both 5 and 60 minutes return of spontaneous circulation occured in eight animals (73%).ConclusionsIn a pig model of CA, both FF and FS ECMO assure adequate brain perfusion and oxygenation. FF ECMO offers better CoBF than FS ECMO. Addition of IABP to FF ECMO worsens CoBF. FF ECMO, more than FS ECMO, increases CoPP over time.

Automatic evaluation of intrapartum fetal heart rate recordings: a comprehensive analysis of useful features

Cardiotocography is the monitoring of fetal heart rate (FHR) and uterine contractions (TOCO), used routinely since the 1960s by obstetricians to detect fetal hypoxia. The evaluation of the FHR in clinical settings is based on an evaluation of macroscopic morphological features and so far has managed to avoid adopting any achievements from the HRV research field. In this work, most of the features utilized for FHR characterization, including FIGO, HRV, nonlinear, wavelet, and time and frequency domain features, are investigated and assessed based on their statistical significance in the task of distinguishing the FHR into three FIGO classes. We assess the features on a large data set (552 records) and unlike in other published papers we use three-class expert evaluation of the records instead of the pH values. We conclude the paper by presenting the best uncorrelated features and their individual rank of importance according to the meta-analysis of three different ranking methods. The number of accelerations and decelerations, interval index, as well as Lempel-Ziv complexity and Higuchis fractal dimension are among the top five features.

Assessment of features for automatic CTG analysis based on expert annotation

Cardiotocography (CTG) is the monitoring of fetal heart rate (FHR) and uterine contractions (TOCO) since 1960s used routinely by obstetricians to detect fetal hypoxia. The evaluation of the FHR in clinical settings is based on an evaluation of macroscopic morphological features and so far has managed to avoid adopting any achievements from the HRV research field. In this work, most of the ever-used features utilized for FHR characterization, including FIGO, HRV, nonlinear, wavelet, and time and frequency domain features, are investigated and the features are assessed based on their statistical significance in the task of distinguishing the FHR into three FIGO classes. Annotation derived from the panel of experts instead of the commonly utilized pH values was used for evaluation of the features on a large data set (552 records). We conclude the paper by presenting the best uncorrelated features and their individual rank of importance according to the meta-analysis of three different ranking methods. Number of acceleration and deceleration, interval index, as well as Lempel-Ziv complexity and Higuchis fractal dimension are among the top five features.

Standardization and Interoperability: Basic Conditions for Efficient Solutions

Information and communication technologies have already become inseparable part of healthcare sector activities. In the paper we discuss the issues of standardization and interoperability that are crucial for correct interconnection of medical and other devices and information systems. Our previous work in the area has led us to the conclusion that successful integration of partial solutions will be strongly dependent on the issue of interoperability of medical devices and information systems. It comprises problems of standardization of data acquisition, communication, processing, and storage; and connected problem: correct data mapping between different ICT applications. We present several examples of partial solutions of communication and data format definition in dedicated areas.

Early vancomycin, amikacin and gentamicin concentrations in pulmonary artery and pulmonary tissue are not affected by VA ECMO (venoarterial extracorporeal membrane oxygenation) in a pig model of prolonged cardiac arrest

BACKGROUND ECMO (extracorporeal membrane oxygenation) is increasingly used in severe hemodynamic compromise and cardiac arrest (CA). Pulmonary infections are frequent in these patients. Venoarterial (VA) ECMO decreases pulmonary blood flow and antibiotic availability in lungs during VA ECMO treated CA is not known. We aimed to assess early vancomycin, amikacin and gentamicin concentrations in the pulmonary artery as well as tracheal aspirate and to determine penetration ratios of these antibiotics to lung tissue in a pig model of VA ECMO treated CA. METHODS Twelve female pigs, body weight 51.5 ± 3.5 kg, were subjected to prolonged CA managed by different modes of VA ECMO. Anesthetized animals underwent 15 min of ventricular fibrillation (VF) followed by continued VF with ECMO flow of 100 mL/kg/min. Immediately after institution of ECMO, a 30 min vancomycin infusion (10 mg/kg) was started and amikacin and gentamicin boluses (7.5 and 3 mg/kg, respectively) were administered. ECMO circuit, aortic, pulmonary arterial, and tracheal aspirate concentrations of antibiotics were measured at 30 and 60 min after administration; penetration ratios were calculated. RESULTS All 30 min antibiotic concentrations and 60 min concentration for gentamicin in the pulmonary artery were no different than the aorta. However, the 60 min pulmonary artery vancomycin and amikacin values were significantly higher than aortic, 19.8 (14.3-21.6) vs. 17.6 (14.2-19.0) mg/L, p = 0.009, and 15.6 mg/L (11.0-18.6) vs. 11.2 (10.4-17.2) mg/L, p = 0.036, respectively. One hour penetration ratios were 18.5% for vancomycin, 34.9% for gentamicin and 38.8% for amikacin. CONCLUSION In a pig model of VA ECMO treated prolonged CA, despite diminished pulmonary flow, VA ECMO does not decrease early vancomycin, gentamicin, and amikacin concentrations in pulmonary artery. Within 1 h post administration, antibiotics can be detected in tracheal aspirate in adequate concentrations.

Ant inspired techniques in textual information retrieval from a hospital information system

In this work we have studied, evaluated and proposed different swarm intelligence techniques for mining information from loosely structured medical textual records with no apriori knowledge. In the paper we depict the process of mining a large dataset of ∼50,000–120,000 records × 20 attributes in database tables, originating from the hospital information system (thanks go to the University Hospital in Brno, Czech Republic) recording over 10 years. This paper concerns only textual attributes with free text input, that means 613,000 text fields in 16 attributes. Each attribute item contains ∼800–1,500 characters (diagnoses, medications, etc.). The output of this task is a set of ordered/nominal attributes suitable for rule discovery mining and automated processing.

Effect of Pulsatility on Microcirculation in Patients Treated with Extracorporeal Cardiopulmonary Resuscitation: A Pilot Study

The effect of pulsatile blood flow on microcirculation during extracorporeal cardiopulmonary resuscitation (ECPR) is not elucidated; therefore, we designed an observational study comparing sublingual microcirculation in patients with refractory cardiac arrest (CA) with spontaneously pulsatile or low/nonpulsatile blood flow after treatment with ECPR. Microcirculation was assessed with Sidestream Dark Field technology in 12 patients with CA who were treated with ECPR and 12 healthy control subjects. Microcirculatory images were analyzed offline in a blinded fashion, and consensual parameters were determined for the vessels ⩽20 &mgr;m. The patients’ data, including actual hemodynamic parameters, were documented. Pulsatile blood flow was defined by a pulse pressure (PP) ≥ 15 mm Hg. Compared with the healthy volunteers, the patients who were treated with ECPR exhibited a significantly lower proportion of perfused capillaries (PPC); other microcirculatory parameters did not differ. The groups of patients with pulsatile (n = 7) versus low/nonpulsatile (n = 5) blood flow did not differ in regards to the collected data and hemodynamic variables (except for the PP and ejection fraction of the left ventricle) as well as microcirculatory parameters. In conclusion, microcirculation appeared to be effectively supported by ECPR in our group of patients with CA with the exception of the PPC. We found only nonsignificant contribution of spontaneous pulsatility to extracorporeal membrane oxygenation-generated microcirculatory blood flow.

Intrapartum Fetal Heart Rate Classification: Cross-Database Evaluation

Fetal Heart Rate (FHR) provides obstetricians with essential information about fetal reactions to stress events during delivery. Early detection of fetal acidosis, enabling timely interventions and prevention of adverse consequences of acidosis for fetuses, remains a challenging task. In particular, the use of different, proprietary and small databases in various published works hinders meaningful comparisons of achieved results. This work relies on the the use of two independent databases in order to asses relevantly acidosis detection performance and to address important issues of knowledge transfer (features, classification model) from one database to the other. Using a large set of features, supervised classification is performed with state-of-the-art sparse support vector machines. It shows that selected features and classification performance are consistent for both databases. Further it quantifies the level of generalization of the achieved results, by making use of one database for learning and the other one for testing.