Josef Škola
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Josef Škola has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Jan Benes
Department of Anesthesiology and Intensive Care Medicine, Faculty of Medicine in Plzen, Charles University, Plzen, Czech Republic -
1 shared publication - Lenka Horakova
Czech Technical University in Prague
1 shared publication - Marcela Bílská
Charles University, Faculty of Medicine in Hradec Králové, Czech Republic
1 shared publication - Martin Rožánek
Department of Biomedical Technology, Faculty of Biomedical Engineering, Czech Technical University in Prague, Kladno, Czech Republic
1 shared publication Michal Soukup
Department of Informatics, Faculty of Science, Jan Evangelista Purkyně University, Ústí nad Labem, Czechia
1 shared publication- Michala Horáková
Department of Anaesthesiology, Resuscitation and Intensive Care, Faculty of Medicine in Pilsen, Charles University, Alej Svobody 80, 304 60 Plzen-Lochotin, Czech Republic
1 shared publication
Latest Publications
- Open Access
- 30 September 2026
- Published by Springer Nature in Neurocritical Care
- p. 1-13
Data for Machine Learning Models: Clinical Experience Determines Interrater Reliability in Waveform Anomaly Detection
Background: High-frequency intracranial pressure (ICP) and arterial blood pressure (ABP) waveforms are increasingly utilized for advanced physiological monitoring and as inputs for machine learning (ML) models. The accuracy of derived parameters relies on input data quality, and anomaly contaminated signals may impair model performance. Reliable anomaly annotation is therefore essential. Despite progress in automated labeling, human annotations remain the “ground truth” for ML training approaches. Human labeling is subjective and may vary depending on the signal type and the annotator’s experience. This study aimed to quantify the interrater reliability of anomaly annotations in ICP and ABP waveforms. Methods: Anonymized, synchronized ICP and ABP waveforms were analyzed retrospectively. From a single-center neurocritical care database, 100 h of recordings (32,760 10 s segments) were selected using predefined criteria. Six annotators (three neurocritical care consultants, two residents, one medical student) annotated anomalies under identical conditions. Interrater reliability was assessed for ICP and ABP using multiple metrics [Gwet’s AC2, Fleiss’ κ , prevalence- and bias-adjusted kappa (PABAK), positive/negative agreement, and intraclass correlation coefficient, ICC(2, k )], with segment-level and patient-level cluster-robust 95% confidence intervals. A broader anomaly definition, rather than artifact-based labeling, was used to capture variability in judgments of signal fidelity. Results: Anomaly prevalence was low (3.99% for ICP, 5.83% for ABP). Overall agreement was high for both signals (Gwet’s AC2 ≥ 0.98). However, anomaly specific agreement differed by modality and experience. For ICP, senior annotators achieved higher positive agreement than mixed-experience teams (+ 12.8%), whereas ABP annotation showed no significant experience effect. Across all annotators, ABP exhibited higher anomaly specific concordance, with similar overall agreement. Conclusions: Robust interrater reliability in waveform anomaly annotation is achievable in routine neurocritical care; however, reliability remained signal- and experience-dependent. ICP annotation benefits from expert training and supervision, while ABP can be reliably annotated by mixed-experience teams. These findings support signal-specific annotation strategies and provide an empirical basis for developing ML-based anomaly detection systems.
- 30 September 2026
- Published by Springer Nature in Neurocritical Care
- p. 1-13
Open AccessData for Machine Learning Models: Clinical Experience Determines Interrater Reliability in Waveform Anomaly Detection
Background: High-frequency intracranial pressure (ICP) and arterial blood pressure (ABP) waveforms are increasingly utilized for advanced physiological monitoring and as inputs for machine learning (ML) models. The accuracy of derived parameters relies on input data quality, and anomaly contaminated signals may impair model performance. Reliable anomaly annotation is therefore essential. Despite progress in automated labeling, human annotations remain the “ground truth” for ML training approaches. Human labeling is subjective and may vary depending on the signal type and the annotator’s experience. This study aimed to quantify the interrater reliability of anomaly annotations in ICP and ABP waveforms. Methods: Anonymized, synchronized ICP and ABP waveforms were analyzed retrospectively. From a single-center neurocritical care database, 100 h of recordings (32,760 10 s segments) were selected using predefined criteria. Six annotators (three neurocritical care consultants, two residents, one medical student) annotated anomalies under identical conditions. Interrater reliability was assessed for ICP and ABP using multiple metrics [Gwet’s AC2, Fleiss’ κ , prevalence- and bias-adjusted kappa (PABAK), positive/negative agreement, and intraclass correlation coefficient, ICC(2, k )], with segment-level and patient-level cluster-robust 95% confidence intervals. A broader anomaly definition, rather than artifact-based labeling, was used to capture variability in judgments of signal fidelity. Results: Anomaly prevalence was low (3.99% for ICP, 5.83% for ABP). Overall agreement was high for both signals (Gwet’s AC2 ≥ 0.98). However, anomaly specific agreement differed by modality and experience. For ICP, senior annotators achieved higher positive agreement than mixed-experience teams (+ 12.8%), whereas ABP annotation showed no significant experience effect. Across all annotators, ABP exhibited higher anomaly specific concordance, with similar overall agreement. Conclusions: Robust interrater reliability in waveform anomaly annotation is achievable in routine neurocritical care; however, reliability remained signal- and experience-dependent. ICP annotation benefits from expert training and supervision, while ABP can be reliably annotated by mixed-experience teams. These findings support signal-specific annotation strategies and provide an empirical basis for developing ML-based anomaly detection systems.
- Open Access
- 15 December 2023
- Published by Solen s.r.o. in Anesteziologie a intenzivní medicína
- Vol. 34 (4) , 157-164
Trauma-induced coagulopathy - pathophysiology, diagnostics and treatment
?l?nek formou p?ehledu shrnuje soudob? pohled na z?kladn? principy patofyziologie, diagnostiky a l??by traumatem indukovan? koagulopatie u pacient? se z?va?n?m ?razem. ?l?nek formou p?ehledu shrnuje soudob? pohled na z?kladn? principy patofyziologie, diagnostiky a l??by traumatem indukovan? koagulopatie u pacient? se z?va?n?m ?razem.
- 15 December 2023
- Published by Solen s.r.o. in Anesteziologie a intenzivní medicína
- Vol. 34 (4) , 157-164
Open AccessTrauma-induced coagulopathy - pathophysiology, diagnostics and treatment
?l?nek formou p?ehledu shrnuje soudob? pohled na z?kladn? principy patofyziologie, diagnostiky a l??by traumatem indukovan? koagulopatie u pacient? se z?va?n?m ?razem. ?l?nek formou p?ehledu shrnuje soudob? pohled na z?kladn? principy patofyziologie, diagnostiky a l??by traumatem indukovan? koagulopatie u pacient? se z?va?n?m ?razem.
- Open Access
- 20 February 2023
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 12 (4) , 1707
Shock Index for Early Detection of Low Plasma Fibrinogen in Trauma: A Prospective Observational Cohort Pilot Study
Shock index (a ratio between heart rate and systolic blood pressure) predicts transfusion requirements and the need for haemostatic resuscitation in severe trauma patients. In the present study, we aimed to determine whether prehospital and on-admission shock index values can be used to predict low plasma fibrinogen in trauma patients. Between January 2016 and February 2017, trauma patients admitted from the helicopter emergency medical service into two large trauma centres in the Czech Republic were prospectively assessed for demographic, laboratory and trauma-associated variables and shock index at scene, during transport and at admission to the emergency department. Hypofibrinogenemia defined as fibrinogen plasma level of 1.5 g·L−l was deemed as a cut-off for further analysis. Three hundred and twenty-two patients were screened for eligibility. Of these, 264 (83%) were included for further analysis. The hypofibrinogenemia was predicted by the worst prehospital shock index with the area under the receiver operating characteristics curve (AUROC) of 0.79 (95% CI 0.64–0.91) and by the admission shock index with AUROC of 0.79 (95% CI 0.66–0.91). For predicting hypofibrinogenemia, the prehospital shock index ≥ 1 has 0.5 sensitivity (95% CI 0.19–0.81), 0.88 specificity (95% CI 0.83–0.92) and a negative predictive value of 0.98 (0.96–0.99). The shock index may help to identify trauma patients at risk of hypofibrinogenemia early in the prehospital course.
- 20 February 2023
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 12 (4) , 1707
Open AccessShock Index for Early Detection of Low Plasma Fibrinogen in Trauma: A Prospective Observational Cohort Pilot Study
Shock index (a ratio between heart rate and systolic blood pressure) predicts transfusion requirements and the need for haemostatic resuscitation in severe trauma patients. In the present study, we aimed to determine whether prehospital and on-admission shock index values can be used to predict low plasma fibrinogen in trauma patients. Between January 2016 and February 2017, trauma patients admitted from the helicopter emergency medical service into two large trauma centres in the Czech Republic were prospectively assessed for demographic, laboratory and trauma-associated variables and shock index at scene, during transport and at admission to the emergency department. Hypofibrinogenemia defined as fibrinogen plasma level of 1.5 g·L−l was deemed as a cut-off for further analysis. Three hundred and twenty-two patients were screened for eligibility. Of these, 264 (83%) were included for further analysis. The hypofibrinogenemia was predicted by the worst prehospital shock index with the area under the receiver operating characteristics curve (AUROC) of 0.79 (95% CI 0.64–0.91) and by the admission shock index with AUROC of 0.79 (95% CI 0.66–0.91). For predicting hypofibrinogenemia, the prehospital shock index ≥ 1 has 0.5 sensitivity (95% CI 0.19–0.81), 0.88 specificity (95% CI 0.83–0.92) and a negative predictive value of 0.98 (0.96–0.99). The shock index may help to identify trauma patients at risk of hypofibrinogenemia early in the prehospital course.