LKLorenz Kapral

Lorenz Kapral

*This is an algorithmically generated author record based on publicly available information.

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


Lorenz Kapral has a total of 50 co-authors. Here are the top co-authors by number of shared publications:

  • Oliver Kimberger

    Clinical Division of General Anaesthesia and Intensive Care Medicine, Department of Anaesthesia, Intensive Care Medicine and Pain Medicine, Medical University of Vienna, 1090 Vienna, Austria

    6 shared publications
  • Aylin Albrecht

    Department of Anaesthesia, Intensive Care Medicine and Pain Medicine, Clinical Division of General Anaesthesia and Intensive Care Medicine Medical University of Vienna Vienna Austria

    4 shared publications
  • Christoph Dibiasi

    Department of Anaesthesia, Intensive Care Medicine and Pain Medicine, Medical University of Vienna, 1090 Vienna, Austria

    3 shared publications
  • Sebastian Zeiner

    Department of Anaesthesia, Intensive Care Medicine and Pain Medicine, Clinical Division of General Anaesthesia and Intensive Care Medicine, Medical University of Vienna, Vienna, Austria

    3 shared publications
  • Asan Agibetov

    Institute of Artificial Intelligence Medical University of Vienna Vienna Austria

    2 shared publications
  • Christina Hafner

    Department of Anaesthesia, Intensive Care Medicine and Pain Medicine, Clinical Division of General Anaesthesia and Intensive Care Medicine, Medical University of Vienna, Vienna, Austria

    2 shared publications

Latest Publications

  • Open Access

    Short-Term Prediction of Severe Anemia in Critically Ill Patients Using Machine Learning: Development and External Validation

    by Lorenz Kapral, Aylin Albrecht, Fabian P. Hammerle, Stefan Bartos, Paul Lichtenegger, Sebastian Zeiner, Stefan J. Schaller, Oliver Kimberger, David M. Baron

    Background: Severe anaemia is common in critically ill patients, frequently necessitating urgent diagnostic evaluation, haemodynamic reassessment, and red-blood-cell transfusion. Current ICU practice heavily relies on intermittent haemoglobin (Hb) measurements, which inherently delay recognition of clinically relevant Hb decline. We aimed to develop and externally validate a machine-learning model to predict severe anaemia (Hb <8 g/dL) within the next 6 hours using only routinely collected ICU data.Methods; In this retrospective observational cohort study, we developed an Extreme Gradient Boosting model using the Vienna Anaesthesia and Intensive Care Database (ViennaAIdb; Medical University of Vienna, Austria) for ICU admissions between Jan 1, 2014, and Nov 30, 2021. The primary outcome was severe anaemia within a 6-hour prediction horizon. The cohort was split at the patient level into training and internal test sets. External validation was performed using the MIMIC-IV database (v3.1) via an identical preprocessing pipeline and entirely without model retraining. Model performance was assessed by discrimination, using the area under the receiver operating characteristic curve (AUC), and calibration, using calibration plots and Brier scores. Feature contributions were evaluated with SHapley Additive exPlanations.Findings: The development cohort included 21,731 ICU stays, contributing 3,321,230 hourly prediction samples; the external validation cohort included 821 ICU stays, contributing 11,217 samples. The model demonstrated high discrimination in both cohorts, with an AUC of 0·94 in internal testing and 0·91 in external validation. Calibration was excellent internally and remained robust externally, with close agreement between predicted and observed risks (Brier scores of 0·055 and 0·110, respectively). The most influential predictors of impending anaemia were recent Hb dynamics, cumulative urine output, heart rate, and fluid administration.Interpretation: A machine-learning model based exclusively on routinely available ICU variables accurately predicted severe anaemia within a clinically actionable 6-hour horizon, demonstrating robust discrimination and calibration during external validation without retraining. These findings suggest that automated, near real-time Hb risk stratification could support a shift from reactive laboratory surveillance towards anticipatory monitoring and earlier bedside reassessment. Prospective evaluation is warranted before clinical implementation.FundingNo specific funding was received.

  • Open Access

    Prophylactic Enoxaparin Reduces Symptomatic Venous Thromboembolism Compared With No Chemoprophylaxis Within 95 Days After Knee Arthroscopy

    by Aylin Albrecht, Lorenz Kapral, Felix Gruber, Christoph Dibiasi, Oliver Kimberger, Christian Albrecht

    Purpose: To investigate whether prophylactic use of low‐molecular‐weight heparin (enoxaparin) after knee arthroscopy reduces the incidence of symptomatic venous thromboembolism (VTE) compared with no postoperative pharmacological prophylaxis. Methods: We conducted a population‐based cohort study using linked national insurance and hospital data from January 1, 2016, to December 31, 2023. Adults undergoing standard knee arthroscopy were identified and included, and those with prior VTE, coagulation disorders, recent cancer, preoperative anticoagulation, septic arthritis, or extended hospital stay were excluded. Patients filling a prophylactic enoxaparin prescription within 5 days of discharge comprised the enoxaparin group; all others formed the control group. The primary outcome was symptomatic VTE (combined deep vein thrombosis and pulmonary embolism) within 90 days after group allocation. Secondary safety outcomes included wound infection, septic arthritis, heparin‐induced thrombocytopenia, intracranial hemorrhage, gastrointestinal bleeding, epistaxis, and surgery‐related bleeding leading to hospitalization. Results: Of 181,135 knee arthroscopies identified, 99,916 patients met the inclusion criteria. Among them, 67,108 (67%) received enoxaparin and 32,808 (33%) did not. Symptomatic VTE occurred in 380 patients (0.57%) in the enoxaparin group and 293 patients (0.89%) in the control group. Enoxaparin prophylaxis was associated with a significantly lower incidence of symptomatic VTE (hazard ratio: 0.64; 95% confidence interval: 0.55‐0.74; P = .0003), corresponding to a number needed to treat of 310 to prevent 1 symptomatic event. Adverse events were rare in both groups. Conclusions: Prophylactic enoxaparin after knee arthroscopy was associated with a significantly reduced risk of symptomatic VTE within 95 days of discharge compared with no pharmacological prophylaxis. Level of Evidence: Level III, retrospective comparative case series.

  • Open Access

    A serious video game for teaching basic point-of-care echocardiography skills: a non-inferiority trial

    by Josef Michael Lintschinger, Lena Reischmann, Daniel Alexander Klaus, Wolfgang Schaubmayr, Lorenz Kapral, Marc Dunst, Florian Kahlfuss, Alexandra Kaider, Gernot Gerger, Eva Schaden, et al.

    The use of point-of-care ultrasound (POCUS) is expanding, but providing effective training remains challenging. Serious video games offer a promising, acce


  • Open Access

    Trends in Opioid and Non-opioid Prescriptions in Austria (2016–2021): A Nationwide Study on Utilization and Concomitant Benzodiazepine Use

    by Aylin Bilir, Lorenz Kapral, Andrea Michalek-Sauberer, Razvan Bologheanu, Felix Gruber, Oliver Kimberger

    Introduction Although global opioid consumption is decreasing, high-income populations are experiencing an increase. Data on specific opioid-prescribed and at-risk patient groups in Austria are lacking. Methods We performed a retrospective observational population-based study analysing health insurance data between January 2016 and December 2021. The dataset included demographic information; hospital data, including coded primary and secondary discharge diagnoses; and prescription data for all legally available opioids and nonopioid analgesics. The primary objective was to describe trends in opioid and nonopioid analgesic prescriptions. Logistic regression analysis was conducted to identify potential risk factors for receiving an opioid prescription. Results The study cohort included 7,274,651 individuals. During the observation period, the percentage of individuals receiving an opioid prescription decreased by 14.69% (4.22–3.60%). The number of individuals receiving an opioid prescription was consistently greatest for tramadol. A particularly strong positive correlation was observed between opioid prescriptions and the concurrent use of benzodiazepines (odds ratio [OR], 1.45 [95% confidence interval {CI}, 1.43–1.47]). Furthermore, a history of persistent somatoform pain disorder (OR, 1.28 [95% CI, 1.21–1.36]) and a diagnosis of pain disorder (OR, 1.26 [95% CI, 1.25–1.28]) were identified as significant risk factors. In 2021, general practitioners were the predominant initial opioid prescribers, issuing 82.17% of the prescriptions, followed by hospital staff and orthopaedic specialists. Conclusion Prescription opioid use decreased from 2016 to 2021, with tramadol representing the most prevalent opioid. The study revealed a strong link between opioid and benzodiazepine prescriptions and an association with persistent somatoform pain disorder, where opioid use is typically not recommended. Interactive map available for this article.

  • Open Access

    Optimized Renal Replacement Therapy Decisions in Intensive Care: A Reinforcement Learning Approach

    by Lorenz Kapral, Razvan Bologheanu, Mohammad Mahdi Azarbeik, Aylin Bilir, Richard Weiss, Stefan Bartos, Stefan Schaller, Clemens Heitzinger, Eva Schaden, Oliver Kimberger

    Purpose Acute kidney injury (AKI) is highly prevalent in intensive care units (ICUs) and often requires renal replacement therapy (RRT). However, the optimal timing for initiating RRT remains controversial. The aim of this study was to develop a reinforcement learning (RL) model to support individualized RRT decision-making for critically ill AKI patients. Methods We trained and validated our RL model using ICU data from two cohorts: the publicly available MIMIC-IV database and a dataset from the Medical University of Vienna (MUW). Patients with AKI of stage I or higher were included, and those with chronic kidney disease or prior kidney transplantation were excluded. We extracted 88 features, employing weighted K-means clustering for state definition. A Q-learning–based RL approach was applied, with off-policy evaluation to assess the policy’s performance versus clinician decisions. Results In both the MIMIC and MUW cohorts, the RL model demonstrated a high level of concordance (up to 98.5%) with clinicians but exhibited superior performance on key metrics. Notably, the model identified a reproducible patient subgroup with greater illness severity for whom earlier or more frequent RRT could improve outcomes, suggesting a beneficial role for AI-driven decision support. Conclusions Our RL model provides dynamic, data-driven recommendations for initiating and ceasing RRT, closely aligning with clinical practice and identifying high-risk patients who may benefit from earlier intervention.

  • Open Access

    Development and external validation of temporal fusion transformer models for continuous intraoperative blood pressure forecasting

    by Lorenz Kapral, Christoph Dibiasi, Natasa Jeremic, Stefan Bartos, Sybille Behrens, Aylin Bilir, Clemens Heitzinger, Oliver Kimberger


  • Open Access

    A retrospective analysis of the need for on-site emergency physician presence and mission characteristics of a rural ground-based emergency medical service

    by Josef Michael Lintschinger, Daniel Laxar, Lorenz Kapral, Stefan Ulbing, Thomas Glock, Sybille Behrens, Christoph Frimmel, Reinhold Renner, Daniel Alexander Klaus, Harald Willschke, et al.

    This study aimed to address the challenges faced by rural emergency medical services in Europe, due to an increasing number of missions and limited human resources. The primary objective was to determine the necessity of having an on-site emergency physician (EP), while the secondary objectives included analyzing the characteristics of rural EP missions. A retrospective study was conducted, examining rural EP missions carried out between January 1st, 2017, and December 2nd, 2021 in Burgenland, Austria. The need for physical presence of an EP was classified based on the National Advisory Committee for Aeronautics (NACA) score into three categories; category A: no need for an EP (NACA 1–3); category B: need for an EP (NACA 1–3 along with additional medical interventions beyond the capabilities of emergency medical technicians); and category C: definite need for an EP (NACA 4–7). Descriptive statistics were used for analysis. Out of 16,971 recorded missions, 15,591 were included in the study. Approximately 32.3% of missions fell into category A, indicating that an EP’s physical presence was unnecessary. The diagnoses made by telecommunicators matched those of the EPs in only 52.8% of cases. The study suggests that about a third of EP missions carried out in rural areas might not have a solid medical rationale. This underscores the importance of developing an alternative care approach for these missions. Failing to address this could put additional pressure on already stretched EMS systems, risking their collapse.


  • Open Access

    Predicting Intraoperative Hypothermia Burden during Non-Cardiac Surgery: A Retrospective Study Comparing Regression to Six Machine Learning Algorithms

    by Christoph Dibiasi, Asan Agibetov, Lorenz Kapral, Sebastian Zeiner, Oliver Kimberger

    Background: Inadvertent intraoperative hypothermia is a common complication that affects patient comfort and morbidity. As the development of hypothermia is a complex phenomenon, predicting it using machine learning (ML) algorithms may be superior to logistic regression. Methods: We performed a single-center retrospective study and assembled a feature set comprised of 71 variables. The primary outcome was hypothermia burden, defined as the area under the intraoperative temperature curve below 37 °C over time. We built seven prediction models (logistic regression, extreme gradient boosting (XGBoost), random forest (RF), multi-layer perceptron neural network (MLP), linear discriminant analysis (LDA), k-nearest neighbor (KNN), and Gaussian naïve Bayes (GNB)) to predict whether patients would not develop hypothermia or would develop mild, moderate, or severe hypothermia. For each model, we assessed discrimination (F1 score, area under the receiver operating curve, precision, recall) and calibration (calibration-in-the-large, calibration intercept, calibration slope). Results: We included data from 87,116 anesthesia cases. Predicting the hypothermia burden group using logistic regression yielded a weighted F1 score of 0.397. Ranked from highest to lowest weighted F1 score, the ML algorithms performed as follows: XGBoost (0.44), RF (0.418), LDA (0.406), LDA (0.4), KNN (0.362), and GNB (0.32). Conclusions: ML is suitable for predicting intraoperative hypothermia and could be applied in clinical practice.


  • Open Access

    Development of a Reinforcement Learning Algorithm to Optimize Corticosteroid Therapy in Critically Ill Patients with Sepsis

    by Razvan Bologheanu, Lorenz Kapral, Daniel Laxar, Mathias Maleczek, Christoph Dibiasi, Sebastian Zeiner, Asan Agibetov, Ari Ercole, Patrick Thoral, Paul Elbers, et al.

    Background: The optimal indication, dose, and timing of corticosteroids in sepsis is controversial. Here, we used reinforcement learning to derive the optimal steroid policy in septic patients based on data on 3051 ICU admissions from the AmsterdamUMCdb intensive care database. Methods: We identified septic patients according to the 2016 consensus definition. An actor-critic RL algorithm using ICU mortality as a reward signal was developed to determine the optimal treatment policy from time-series data on 277 clinical parameters. We performed off-policy evaluation and testing in independent subsets to assess the algorithm’s performance. Results: Agreement between the RL agent’s policy and the actual documented treatment reached 59%. Our RL agent’s treatment policy was more restrictive compared to the actual clinician behavior: our algorithm suggested withholding corticosteroids in 62% of the patient states, versus 52% according to the physicians’ policy. The 95% lower bound of the expected reward was higher for the RL agent than clinicians’ historical decisions. ICU mortality after concordant action in the testing dataset was lower both when corticosteroids had been withheld and when corticosteroids had been prescribed by the virtual agent. The most relevant variables were vital parameters and laboratory values, such as blood pressure, heart rate, leucocyte count, and glycemia. Conclusions: Individualized use of corticosteroids in sepsis may result in a mortality benefit, but optimal treatment policy may be more restrictive than the routine clinical practice. Whilst external validation is needed, our study motivates a ‘precision-medicine’ approach to future prospective controlled trials and practice.


  • Open Access

    Neutron Radiography and Tomography of the Drying Process of Screed Samples

    by Lorenz Kapral, Michael Zawisky, Hartmut Abele

    The moisture content of screed samples is an essential parameter in the construction industry, since the screed must dry to a certain level of moisture content to be ready for covering. This paper introduces neutron radiography (NR) and neutron tomography (NT) as new, non-destructive techniques for analysing the drying characteristics of screed. Our NR analyses evaluate the results of the established methods while offering much higher spatial resolution of 200 μm, thereby facilitating a two- and three-dimensional understanding of screed’s drying behaviour. Because of NR’s exceptionally high sensitivity regarding the total cross section of hydrogen the precise moisture content of screed samples is obtainable, resulting in new observations. The current methods to measure moisture content comprise the ‘calcium carbide method’, the ‘Darr method’, and electrical sensor systems.