Johannes Bickenbach
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Johannes Bickenbach has a total of 76 co-authors. Here are the top co-authors by number of shared publications:
- Gernot Marx
Department of Intensive Care Medicine and Intermediate Care, University Hospital RWTH Aachen, Aachen, Germany
10 shared publications - Sebastian Fritsch
Department of Intensive Care Medicine, University Hospital RWTH Aachen, Aachen, Germany
8 shared publications - Andreas Schuppert
RWTH Aachen University
4 shared publications - Julian Kunze
Department of Intensive Care Medicine, University Hospital RWTH Aachen, Aachen, Germany
4 shared publications - Oliver Maassen
Department of Intensive Care Medicine, University Hospital RWTH Aachen, Aachen, Germany
4 shared publications - Saskia Deffge
Department of Intensive Care Medicine, University Hospital RWTH Aachen, Aachen, Germany
4 shared publications
Latest Publications
- Open Access
- 16 October 2026
- Published by IOP Publishing in Machine Learning: Health
- Vol. 2 (2) , 025021
The evolving drivers of mortality in the ICU: a multicenter validation of phase-specific machine learning models
The evolving drivers of mortality in the ICU: a multicenter validation of phase-specific machine learning models, Meyer, Joana, Polzin, Richard, Bickenbach, Johannes, Marx, Gernot, Schuppert, Andreas The evolving drivers of mortality in the ICU: a multicenter validation of phase-specific machine learning models, Meyer, Joana, Polzin, Richard, Bickenbach, Johannes, Marx, Gernot, Schuppert, Andreas
- 16 October 2026
- Published by IOP Publishing in Machine Learning: Health
- Vol. 2 (2) , 025021
Open AccessThe evolving drivers of mortality in the ICU: a multicenter validation of phase-specific machine learning models
The evolving drivers of mortality in the ICU: a multicenter validation of phase-specific machine learning models, Meyer, Joana, Polzin, Richard, Bickenbach, Johannes, Marx, Gernot, Schuppert, Andreas The evolving drivers of mortality in the ICU: a multicenter validation of phase-specific machine learning models, Meyer, Joana, Polzin, Richard, Bickenbach, Johannes, Marx, Gernot, Schuppert, Andreas
- Open Access
- 11 August 2026
- Published by Springer Nature in BMC Anesthesiology
- Vol. 26 (1) , 498
Effect of intravenously administered norepinephrine on early postoperative tissue perfusion of radial free forearm flaps in the head and neck region – retrospective analysis in the context of continuous flap monitoring
Background: Postoperative flap monitoring following microvascular head and neck reconstruction can be conducted by continuous flap tissue perfusion measurement with an attached surface probe using the Oxygen-to-see (O2C) analysis system. However, intravenously administered norepinephrine may influence flap tissue perfusion and affect the reliability of predefined absolute thresholds used for the detection of vascular flap compromise. This study aimed to evaluate the association between early postoperative flap tissue perfusion and norepinephrine in radial free forearm flaps (RFFF). Methods: Data of patients undergoing head and neck reconstruction with an RFFF from 2020 until 2022 were retrospectively analyzed. Flap tissue perfusion was measured continuously for 8 h postoperatively with an attached surface probe using the O2C analysis system. Intravenously administered norepinephrine dose and blood flow and hemoglobin oxygen saturation as well as flow resistance (ratio of mean arterial blood pressure and flap blood flow) were analyzed for associations. Results: The study included 12 patients (5 men and 7 women). Blood flow and hemoglobin oxygen saturation were not associated with norepinephrine (B=-110.509, p = 0.583 and B=-12.500, p = 0.912). In addition, flow resistance was not associated with norepinephrine (B = 0.292, p = 0.825). Conclusions: Early postoperative tissue perfusion of RFFFs, measured during continuous flap monitoring with attached surface probes for the O2C analysis system, showed no association with norepinephrine with regard for blood flow and hemoglobin oxygen saturation. This supports the reliability of absolute thresholds used to detect vascular flap compromise during continuous postoperative monitoring of RFFFs with the O2C analysis system, albeit additional studies with substantial sample sizes and longer monitoring intervals are required to validate these findings.
- 11 August 2026
- Published by Springer Nature in BMC Anesthesiology
- Vol. 26 (1) , 498
Open AccessEffect of intravenously administered norepinephrine on early postoperative tissue perfusion of radial free forearm flaps in the head and neck region – retrospective analysis in the context of continuous flap monitoring
Background: Postoperative flap monitoring following microvascular head and neck reconstruction can be conducted by continuous flap tissue perfusion measurement with an attached surface probe using the Oxygen-to-see (O2C) analysis system. However, intravenously administered norepinephrine may influence flap tissue perfusion and affect the reliability of predefined absolute thresholds used for the detection of vascular flap compromise. This study aimed to evaluate the association between early postoperative flap tissue perfusion and norepinephrine in radial free forearm flaps (RFFF). Methods: Data of patients undergoing head and neck reconstruction with an RFFF from 2020 until 2022 were retrospectively analyzed. Flap tissue perfusion was measured continuously for 8 h postoperatively with an attached surface probe using the O2C analysis system. Intravenously administered norepinephrine dose and blood flow and hemoglobin oxygen saturation as well as flow resistance (ratio of mean arterial blood pressure and flap blood flow) were analyzed for associations. Results: The study included 12 patients (5 men and 7 women). Blood flow and hemoglobin oxygen saturation were not associated with norepinephrine (B=-110.509, p = 0.583 and B=-12.500, p = 0.912). In addition, flow resistance was not associated with norepinephrine (B = 0.292, p = 0.825). Conclusions: Early postoperative tissue perfusion of RFFFs, measured during continuous flap monitoring with attached surface probes for the O2C analysis system, showed no association with norepinephrine with regard for blood flow and hemoglobin oxygen saturation. This supports the reliability of absolute thresholds used to detect vascular flap compromise during continuous postoperative monitoring of RFFFs with the O2C analysis system, albeit additional studies with substantial sample sizes and longer monitoring intervals are required to validate these findings.
- Open Access
- 15 May 2025
- Published by IOS Press
- Vol. 327, 1001-1002
Intensive Care Patient Usability Assessment in mHealth: A Survey-Study
Patient participation is critical for the success and acceptance of mHealth applications. Many digital health solutions lack sufficient patient input, often resulting in limited use and effectiveness. As part of a project funded by the German Federal Ministry of Education and Research (BMBF), an mHealth app was developed for former intensive care patients at risk for Post Intensive Care Syndrome (PICS). To assess app usage and identify reasons for non-use, a survey was developed using standardized questionnaires, including the German mHealth App Usability Questionnaire (G-MAUQ) and the WHO-5 Well-Being Index. Patients completed the survey during 3 follow-up exams with study nurse support. This method allows for comprehensive feedback to enhance app usability and acceptance. Currently, over 25 patients have completed the survey, with 150 app users set to participate.
- 15 May 2025
- Published by IOS Press
- Vol. 327, 1001-1002
Open AccessIntensive Care Patient Usability Assessment in mHealth: A Survey-Study
Patient participation is critical for the success and acceptance of mHealth applications. Many digital health solutions lack sufficient patient input, often resulting in limited use and effectiveness. As part of a project funded by the German Federal Ministry of Education and Research (BMBF), an mHealth app was developed for former intensive care patients at risk for Post Intensive Care Syndrome (PICS). To assess app usage and identify reasons for non-use, a survey was developed using standardized questionnaires, including the German mHealth App Usability Questionnaire (G-MAUQ) and the WHO-5 Well-Being Index. Patients completed the survey during 3 follow-up exams with study nurse support. This method allows for comprehensive feedback to enhance app usability and acceptance. Currently, over 25 patients have completed the survey, with 150 app users set to participate.
- Open Access
- 21 April 2025
- Published by Springer Nature in Oral and Maxillofacial Surgery
- Vol. 29 (1) , 1-8
Blood pressure and microvascular free flap perfusion in head and neck reconstruction– a retrospective analysis
Purpose: The influence of blood pressure on microvascular free flap perfusion is not fully understood and remains an ongoing topic of debate, as flap perfusion is both a prerequisite for flap viability and a parameter frequently used for postoperative flap monitoring. The aim of this study was to investigate the influence of blood pressure on microvascular free flap perfusion. Methods: Perfusion measurement data obtained with the Oxygen-2-see (O2C) analysis system intraoperatively and postoperatively in 244 patients who underwent microvascular reconstruction of the head and neck region with a fasciocutaneous free flap (FFF) or perforator free flap (PFF) between 2011 and 2020 were analyzed retrospectively. Blood pressure values (i.e., systolic (SBP), diastolic (DBP), and mean arterial blood pressure (MBP)) and perfusion parameters (i.e., flap blood flow, hemoglobin concentration, and hemoglobin oxygen saturation) were evaluated to reveal potential associations. Results: Postoperative flap blood flow was associated with SBP, DBP, and MBP in PFFs ( r = 0.245, p = 0.006; r = 0.239, p = 0.008; r = 0.295, p < 0.001, respectively). These associations also persisted in multivariable analysis ( p = 0.036; p = 0.024; p = 0.004, respectively). Postoperative hemoglobin oxygen saturation was associated with SBP and MBP in PFFs ( r = 0.253, p = 0.005; r = 0.189, p = 0.036, respectively). The association with SBP also persisted in multivariable analysis ( p = 0.005). Conclusion: Microvascular free flap perfusion in PFFs, specifically postoperative flap blood flow and hemoglobin oxygen saturation, is influenced by blood pressure. This suggests that blood pressure might be an adjustable variable for the control of flap perfusion and should be considered as a confounding variable for flap monitoring based on flap perfusion in PFFs.
- 21 April 2025
- Published by Springer Nature in Oral and Maxillofacial Surgery
- Vol. 29 (1) , 1-8
Open AccessBlood pressure and microvascular free flap perfusion in head and neck reconstruction– a retrospective analysis
Purpose: The influence of blood pressure on microvascular free flap perfusion is not fully understood and remains an ongoing topic of debate, as flap perfusion is both a prerequisite for flap viability and a parameter frequently used for postoperative flap monitoring. The aim of this study was to investigate the influence of blood pressure on microvascular free flap perfusion. Methods: Perfusion measurement data obtained with the Oxygen-2-see (O2C) analysis system intraoperatively and postoperatively in 244 patients who underwent microvascular reconstruction of the head and neck region with a fasciocutaneous free flap (FFF) or perforator free flap (PFF) between 2011 and 2020 were analyzed retrospectively. Blood pressure values (i.e., systolic (SBP), diastolic (DBP), and mean arterial blood pressure (MBP)) and perfusion parameters (i.e., flap blood flow, hemoglobin concentration, and hemoglobin oxygen saturation) were evaluated to reveal potential associations. Results: Postoperative flap blood flow was associated with SBP, DBP, and MBP in PFFs ( r = 0.245, p = 0.006; r = 0.239, p = 0.008; r = 0.295, p < 0.001, respectively). These associations also persisted in multivariable analysis ( p = 0.036; p = 0.024; p = 0.004, respectively). Postoperative hemoglobin oxygen saturation was associated with SBP and MBP in PFFs ( r = 0.253, p = 0.005; r = 0.189, p = 0.036, respectively). The association with SBP also persisted in multivariable analysis ( p = 0.005). Conclusion: Microvascular free flap perfusion in PFFs, specifically postoperative flap blood flow and hemoglobin oxygen saturation, is influenced by blood pressure. This suggests that blood pressure might be an adjustable variable for the control of flap perfusion and should be considered as a confounding variable for flap monitoring based on flap perfusion in PFFs.
- Open Access
- 1 November 2024
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-11
Boosting the accuracy of existing models by updating and extending: using a multicenter COVID-19 ICU cohort as a proxy
Most published prediction models for Coronavirus Disease 2019 (COVID-19) were poorly reported, at high risk of bias, and heterogeneous in model performance. To tackle methodological challenges faced in previous prediction studies, we investigated whether model updating and extending improves mortality prediction, using the Intensive Care Unit (ICU) as a proxy. All COVID-19 patients admitted to seven ICUs in the Euregio-Meuse Rhine during the first pandemic wave were included. The 4C Mortality and SEIMC scores were selected as promising prognostic models from an external validation study. Five predictors could be estimated based on cohort size. TRIPOD guidelines were followed and logistic regression analyses with the linear predictor, APACHE II score, and country were performed. Bootstrapping with backward selection was applied to select variables for the final model. Additionally, shrinkage was performed. Model discrimination was displayed as optimism-corrected areas under the ROC curve and calibration by calibration slopes and plots. The mortality rate of the 551 included patients was 36%. Discrimination of the 4C Mortality and SEIMC scores increased from 0.70 to 0.74 and 0.70 to 0.73 and calibration plots improved compared to the original models after updating and extending. Mortality prediction can be improved after updating and extending of promising models.
- 1 November 2024
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-11
Open AccessBoosting the accuracy of existing models by updating and extending: using a multicenter COVID-19 ICU cohort as a proxy
Most published prediction models for Coronavirus Disease 2019 (COVID-19) were poorly reported, at high risk of bias, and heterogeneous in model performance. To tackle methodological challenges faced in previous prediction studies, we investigated whether model updating and extending improves mortality prediction, using the Intensive Care Unit (ICU) as a proxy. All COVID-19 patients admitted to seven ICUs in the Euregio-Meuse Rhine during the first pandemic wave were included. The 4C Mortality and SEIMC scores were selected as promising prognostic models from an external validation study. Five predictors could be estimated based on cohort size. TRIPOD guidelines were followed and logistic regression analyses with the linear predictor, APACHE II score, and country were performed. Bootstrapping with backward selection was applied to select variables for the final model. Additionally, shrinkage was performed. Model discrimination was displayed as optimism-corrected areas under the ROC curve and calibration by calibration slopes and plots. The mortality rate of the 551 included patients was 36%. Discrimination of the 4C Mortality and SEIMC scores increased from 0.70 to 0.74 and 0.70 to 0.73 and calibration plots improved compared to the original models after updating and extending. Mortality prediction can be improved after updating and extending of promising models.
- Open Access
- 1 May 2024
- Published by AME Publishing Company in Quantitative Imaging in Medicine and Surgery
- Vol. 14 (5) , 3248-3263
Diaphragm ultrasound in patients with prolonged weaning from mechanical ventilation
Background: Several publications have examined diaphragmatic ultrasound using two-dimensional (2D) parameters in the context of weaning from mechanical ventilation (MV) and extubation. However, the studied cohorts had rather short duration of ventilation. Examinations on patients with prolonged weaning after long-term ventilation were missing. It was the aim of this study to assess of the diaphragm and peripheral musculature of patients undergoing prolonged weaning creating a chronological sequence of ultrasonic parameters during the course of weaning. Methods: This study was carried out as a monocentric, prospective observational cross-sectional study. Patients in prolonged weaning who were transferred to a specialized weaning unit were eligible for inclusion if they were ventilated invasively by means of an endotracheal tube or tracheal cannula and if their expected treatment period was at least 5 days. Diaphragmatic function and one representative peripheral muscle were examined in 50 patients between March 2020 and April 2021. The 2D sonographic parameters of diaphragm and diaphragmatic function consisted of diaphragmatic thickness (Tdi) at the end of inspiration and expiration, the fractional thickening (FT) and the diaphragmatic excursion. Additionally, the M. quadriceps femoris was sonographically assessed at two locations. The difference of measurements between the first and the last measuring timepoint were examined using the Wilcoxon signed-rank test. For a longer chronological sequence, the Friedman’s rank sum test with subsequent Wilcoxon-Nemenyi-McDonald-Thompson test for multiple comparisons was carried out. Results: Fifty patients with prolonged weaning were included. The median duration of MV before transfer to the weaning unit was 11.5 [interquartile range (IQR) 10] days. Forty-one patients could be assessed over the full course of weaning, with 38 successfully weaned. Within these 41 patients, the sonographic parameters of the diaphragm slightly increased over the course of weaning indicating an increase in thickness and mobility. Especially parameters which represented an active movement reached statistical significance, i.e., inspiratory Tdi when assessed under spontaneous breathing [begin 3.41 (0.99) vs. end 3.43 (1.31) mm; P=0.01] and diaphragmatic excursion [begin 0.7 (0.8) vs. end 0.9 (0.6) cm; P=0.01]. The presence of positive end-expiratory pressure (PEEP) and pressure support did not influence the sonographic parameters significantly. The M. quadriceps femoris, in contrast, decreased slightly but constantly over the time [lower third: begin 1.36 (0.48) vs. end 1.28 (0.36) cm; P=0.054]. Conclusions: The present study is the first one to longitudinally analyse diaphragmatic ultrasound in patients with prolonged weaning. Sonographic assessment showed that Tdi and excursion increased over the course of prolonged weaning, while the diameter of a representative peripheral muscle decreased. However, the changes are rather small, and data show a wide dispersion. To allow a potential, standardized use of diaphragm ultrasound for diagnostic decision support in prolonged weaning, further studies in this specific patient group are required.
- 1 May 2024
- Published by AME Publishing Company in Quantitative Imaging in Medicine and Surgery
- Vol. 14 (5) , 3248-3263
Open AccessDiaphragm ultrasound in patients with prolonged weaning from mechanical ventilation
Background: Several publications have examined diaphragmatic ultrasound using two-dimensional (2D) parameters in the context of weaning from mechanical ventilation (MV) and extubation. However, the studied cohorts had rather short duration of ventilation. Examinations on patients with prolonged weaning after long-term ventilation were missing. It was the aim of this study to assess of the diaphragm and peripheral musculature of patients undergoing prolonged weaning creating a chronological sequence of ultrasonic parameters during the course of weaning. Methods: This study was carried out as a monocentric, prospective observational cross-sectional study. Patients in prolonged weaning who were transferred to a specialized weaning unit were eligible for inclusion if they were ventilated invasively by means of an endotracheal tube or tracheal cannula and if their expected treatment period was at least 5 days. Diaphragmatic function and one representative peripheral muscle were examined in 50 patients between March 2020 and April 2021. The 2D sonographic parameters of diaphragm and diaphragmatic function consisted of diaphragmatic thickness (Tdi) at the end of inspiration and expiration, the fractional thickening (FT) and the diaphragmatic excursion. Additionally, the M. quadriceps femoris was sonographically assessed at two locations. The difference of measurements between the first and the last measuring timepoint were examined using the Wilcoxon signed-rank test. For a longer chronological sequence, the Friedman’s rank sum test with subsequent Wilcoxon-Nemenyi-McDonald-Thompson test for multiple comparisons was carried out. Results: Fifty patients with prolonged weaning were included. The median duration of MV before transfer to the weaning unit was 11.5 [interquartile range (IQR) 10] days. Forty-one patients could be assessed over the full course of weaning, with 38 successfully weaned. Within these 41 patients, the sonographic parameters of the diaphragm slightly increased over the course of weaning indicating an increase in thickness and mobility. Especially parameters which represented an active movement reached statistical significance, i.e., inspiratory Tdi when assessed under spontaneous breathing [begin 3.41 (0.99) vs. end 3.43 (1.31) mm; P=0.01] and diaphragmatic excursion [begin 0.7 (0.8) vs. end 0.9 (0.6) cm; P=0.01]. The presence of positive end-expiratory pressure (PEEP) and pressure support did not influence the sonographic parameters significantly. The M. quadriceps femoris, in contrast, decreased slightly but constantly over the time [lower third: begin 1.36 (0.48) vs. end 1.28 (0.36) cm; P=0.054]. Conclusions: The present study is the first one to longitudinally analyse diaphragmatic ultrasound in patients with prolonged weaning. Sonographic assessment showed that Tdi and excursion increased over the course of prolonged weaning, while the diameter of a representative peripheral muscle decreased. However, the changes are rather small, and data show a wide dispersion. To allow a potential, standardized use of diaphragm ultrasound for diagnostic decision support in prolonged weaning, further studies in this specific patient group are required.
- Open Access
- 10 March 2023
- Published by Springer Nature in European Archives of Oto-Rhino-Laryngology
- Vol. 280 (7) , 3375-3382
Impacts of vascular comorbidities on free flap perfusion in microvascular head and neck reconstruction
Purpose: Arterial hypertension (AHTN), type 2 diabetes mellitus (DM), and atherosclerotic vascular disease (ASVD) are common vascular comorbidities in patients undergoing reconstruction of the head and neck region with a microvascular free flap. These conditions may affect flap perfusion (microvascular blood flow and tissue oxygenation), which is a prerequisite for flap survival and thus reconstruction success. This study aimed to investigate the impacts of AHTN, DM, and ASVD on flap perfusion. Methods: Data from 308 patients who underwent successful reconstruction of the head and neck region with radial free forearm flaps, anterolateral thigh flaps, or fibula free flaps between 2011 and 2020 were retrospectively analyzed. Flap perfusion was measured intraoperatively and postoperatively with the O2C tissue oxygen analysis system. Flap blood flow, hemoglobin concentration, and hemoglobin oxygen saturation were compared between patients with and without AHTN, DM, and ASVD. Results: Intraoperative hemoglobin oxygen saturation and postoperative blood flow were lower in patients with ASVD than in patients without ASVD (63.3% vs. 69.5%, p = 0.046; 67.5 arbitrary units [AU] vs. 85.0 AU, p = 0.036; respectively). These differences did not persist in the multivariable analysis (all p > 0.05). No difference was found in intraoperative or postoperative blood flow or hemoglobin oxygen saturation between patients with and without AHTN or DM (all p > 0.05). Conclusion: Perfusion of microvascular free flaps used for head and neck reconstruction is not impaired in patients with AHTN, DM, or ASVD. Unrestricted flap perfusion may contribute to the observed successful use of microvascular free flaps in patients with these comorbidities.
- 10 March 2023
- Published by Springer Nature in European Archives of Oto-Rhino-Laryngology
- Vol. 280 (7) , 3375-3382
Open AccessImpacts of vascular comorbidities on free flap perfusion in microvascular head and neck reconstruction
Purpose: Arterial hypertension (AHTN), type 2 diabetes mellitus (DM), and atherosclerotic vascular disease (ASVD) are common vascular comorbidities in patients undergoing reconstruction of the head and neck region with a microvascular free flap. These conditions may affect flap perfusion (microvascular blood flow and tissue oxygenation), which is a prerequisite for flap survival and thus reconstruction success. This study aimed to investigate the impacts of AHTN, DM, and ASVD on flap perfusion. Methods: Data from 308 patients who underwent successful reconstruction of the head and neck region with radial free forearm flaps, anterolateral thigh flaps, or fibula free flaps between 2011 and 2020 were retrospectively analyzed. Flap perfusion was measured intraoperatively and postoperatively with the O2C tissue oxygen analysis system. Flap blood flow, hemoglobin concentration, and hemoglobin oxygen saturation were compared between patients with and without AHTN, DM, and ASVD. Results: Intraoperative hemoglobin oxygen saturation and postoperative blood flow were lower in patients with ASVD than in patients without ASVD (63.3% vs. 69.5%, p = 0.046; 67.5 arbitrary units [AU] vs. 85.0 AU, p = 0.036; respectively). These differences did not persist in the multivariable analysis (all p > 0.05). No difference was found in intraoperative or postoperative blood flow or hemoglobin oxygen saturation between patients with and without AHTN or DM (all p > 0.05). Conclusion: Perfusion of microvascular free flaps used for head and neck reconstruction is not impaired in patients with AHTN, DM, or ASVD. Unrestricted flap perfusion may contribute to the observed successful use of microvascular free flaps in patients with these comorbidities.
- Open Access
- 1 April 2022
- Published by Korean Society of Ultrasound in Medicine in Ultrasonography
- Vol. 41 (2) , 403-415
Speckle tracking ultrasonography as a new tool to assess diaphragmatic function: a feasibility study
A reliable method of measuring diaphragmatic function at the bedside is still lacking. Widely used two-dimensional (2D) ultrasonographic measurements, such as diaphragm excursion, diaphragm thickness, and fractional thickening (FT) have failed to show clear correlations with diaphragmatic function. A reason for this is that 2D ultrasonographic measurements, like FT, are merely able to measure the deformation of muscular diaphragmatic tissue in the transverse direction, while longitudinal measurements in the direction of contracting muscle fibres are not possible. Speckle tracking ultrasonography, which is widely used in cardiac imaging, overcomes this disadvantage and allows observations of movement in the direction of the contracting muscle fibres, approximating muscle deformation and the deformation velocity. Several studies have evaluated speckle tracking as a promising method to assess diaphragm contractility in healthy subjects. This technical note demonstrates the feasibility of speckle tracking ultrasonography of the diaphragm in a group of 20 patients after an aortocoronary bypass graft procedure. The results presented herein suggest that speckle tracking ultrasonography is able to depict alterations in diaphragmatic function after surgery better than 2D ultrasonographic measurements.
- 1 April 2022
- Published by Korean Society of Ultrasound in Medicine in Ultrasonography
- Vol. 41 (2) , 403-415
Open AccessSpeckle tracking ultrasonography as a new tool to assess diaphragmatic function: a feasibility study
A reliable method of measuring diaphragmatic function at the bedside is still lacking. Widely used two-dimensional (2D) ultrasonographic measurements, such as diaphragm excursion, diaphragm thickness, and fractional thickening (FT) have failed to show clear correlations with diaphragmatic function. A reason for this is that 2D ultrasonographic measurements, like FT, are merely able to measure the deformation of muscular diaphragmatic tissue in the transverse direction, while longitudinal measurements in the direction of contracting muscle fibres are not possible. Speckle tracking ultrasonography, which is widely used in cardiac imaging, overcomes this disadvantage and allows observations of movement in the direction of the contracting muscle fibres, approximating muscle deformation and the deformation velocity. Several studies have evaluated speckle tracking as a promising method to assess diaphragm contractility in healthy subjects. This technical note demonstrates the feasibility of speckle tracking ultrasonography of the diaphragm in a group of 20 patients after an aortocoronary bypass graft procedure. The results presented herein suggest that speckle tracking ultrasonography is able to depict alterations in diaphragmatic function after surgery better than 2D ultrasonographic measurements.
- Open Access
- 24 June 2021
- Published by JMIR Publications Inc. in JMIR Preprints
The Influence of Inhomogeneous Input Data from Different Waves on Predictive Model Development for COVID-19 ICU Patients (Preprint)
BACKGROUND During the course of the COVID-19 pandemic, a variety of machine learning models were developed to predict different aspects of the disease, such as long-term causes, organ dysfunction or ICU mortality. The number of training datasets used has increased significantly over time. However, these data now come from different waves of the pandemic, not always addressing the same therapeutic approaches over time as well as changing outcomes between two waves. The impact of these changes on model development has not yet been studied. OBJECTIVE The aim of the investigation was to examine the predictive performance of several models trained with data from one wave predicting the second wave´s data and the impact of a pooling of these data sets. Finally, a method for comparison of different datasets for heterogeneity is introduced. METHODS We used two datasets from wave one and two to develop several predictive models for mortality of the patients. Four classification algorithms were used: logistic regression (LR), support vector machine (SVM), random forest classifier (RF) and AdaBoost classifier (ADA). We also performed a mutual prediction on the data of that wave which was not used for training. Then, we compared the performance of models when a pooled dataset from two waves was used. The populations from the different waves were checked for heterogeneity using a convex hull analysis. RESULTS 63 patients from wave one (03-06/2020) and 54 from wave two (08/2020-01/2021) were evaluated. For both waves separately, we found models reaching sufficient accuracies up to 0.79 AUROC (95%-CI 0.76-0.81) for SVM on the first wave and up 0.88 AUROC (95%-CI 0.86-0.89) for RF on the second wave. After the pooling of the data, the AUROC decreased relevantly. In the mutual prediction, models trained on second wave´s data showed, when applied on first wave´s data, a good prediction for non-survivors but an insufficient classification for survivors. The opposite situation (training: first wave, test: second wave) revealed the inverse behaviour with models correctly classifying survivors and incorrectly predicting non-survivors. The convex hull analysis for the first and second wave populations showed a more inhomogeneous distribution of underlying data when compared to randomly selected sets of patients of the same size. CONCLUSIONS Our work demonstrates that a larger dataset is not a universal solution to all machine learning problems in clinical settings. Rather, it shows that inhomogeneous data used to develop models can lead to serious problems. With the convex hull analysis, we offer a solution for this problem. The outcome of such an analysis can raise concerns if the pooling of different datasets would cause inhomogeneous patterns preventing a better predictive performance.
- 24 June 2021
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessThe Influence of Inhomogeneous Input Data from Different Waves on Predictive Model Development for COVID-19 ICU Patients (Preprint)
BACKGROUND During the course of the COVID-19 pandemic, a variety of machine learning models were developed to predict different aspects of the disease, such as long-term causes, organ dysfunction or ICU mortality. The number of training datasets used has increased significantly over time. However, these data now come from different waves of the pandemic, not always addressing the same therapeutic approaches over time as well as changing outcomes between two waves. The impact of these changes on model development has not yet been studied. OBJECTIVE The aim of the investigation was to examine the predictive performance of several models trained with data from one wave predicting the second wave´s data and the impact of a pooling of these data sets. Finally, a method for comparison of different datasets for heterogeneity is introduced. METHODS We used two datasets from wave one and two to develop several predictive models for mortality of the patients. Four classification algorithms were used: logistic regression (LR), support vector machine (SVM), random forest classifier (RF) and AdaBoost classifier (ADA). We also performed a mutual prediction on the data of that wave which was not used for training. Then, we compared the performance of models when a pooled dataset from two waves was used. The populations from the different waves were checked for heterogeneity using a convex hull analysis. RESULTS 63 patients from wave one (03-06/2020) and 54 from wave two (08/2020-01/2021) were evaluated. For both waves separately, we found models reaching sufficient accuracies up to 0.79 AUROC (95%-CI 0.76-0.81) for SVM on the first wave and up 0.88 AUROC (95%-CI 0.86-0.89) for RF on the second wave. After the pooling of the data, the AUROC decreased relevantly. In the mutual prediction, models trained on second wave´s data showed, when applied on first wave´s data, a good prediction for non-survivors but an insufficient classification for survivors. The opposite situation (training: first wave, test: second wave) revealed the inverse behaviour with models correctly classifying survivors and incorrectly predicting non-survivors. The convex hull analysis for the first and second wave populations showed a more inhomogeneous distribution of underlying data when compared to randomly selected sets of patients of the same size. CONCLUSIONS Our work demonstrates that a larger dataset is not a universal solution to all machine learning problems in clinical settings. Rather, it shows that inhomogeneous data used to develop models can lead to serious problems. With the convex hull analysis, we offer a solution for this problem. The outcome of such an analysis can raise concerns if the pooling of different datasets would cause inhomogeneous patterns preventing a better predictive performance.
- Top Cited PapersOpen Access
- 5 March 2021
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 23 (3) , e26646
Future Medical Artificial Intelligence Application Requirements and Expectations of Physicians in German University Hospitals: Web-Based Survey
Background: The increasing development of artificial intelligence (AI) systems in medicine driven by researchers and entrepreneurs goes along with enormous expectations for medical care advancement. AI might change the clinical practice of physicians from almost all medical disciplines and in most areas of health care. While expectations for AI in medicine are high, practical implementations of AI for clinical practice are still scarce in Germany. Moreover, physicians’ requirements and expectations of AI in medicine and their opinion on the usage of anonymized patient data for clinical and biomedical research have not been investigated widely in German university hospitals. Objective: This study aimed to evaluate physicians’ requirements and expectations of AI in medicine and their opinion on the secondary usage of patient data for (bio)medical research (eg, for the development of machine learning algorithms) in university hospitals in Germany. Methods: A web-based survey was conducted addressing physicians of all medical disciplines in 8 German university hospitals. Answers were given using Likert scales and general demographic responses. Physicians were asked to participate locally via email in the respective hospitals. Results: The online survey was completed by 303 physicians (female: 121/303, 39.9%; male: 173/303, 57.1%; no response: 9/303, 3.0%) from a wide range of medical disciplines and work experience levels. Most respondents either had a positive (130/303, 42.9%) or a very positive attitude (82/303, 27.1%) towards AI in medicine. There was a significant association between the personal rating of AI in medicine and the self-reported technical affinity level (H4=48.3, P<.001). A vast majority of physicians expected the future of medicine to be a mix of human and artificial intelligence (273/303, 90.1%) but also requested a scientific evaluation before the routine implementation of AI-based systems (276/303, 91.1%). Physicians were most optimistic that AI applications would identify drug interactions (280/303, 92.4%) to improve patient care substantially but were quite reserved regarding AI-supported diagnosis of psychiatric diseases (62/303, 20.5%). Of the respondents, 82.5% (250/303) agreed that there should be open access to anonymized patient databases for medical and biomedical research. Conclusions: Physicians in stationary patient care in German university hospitals show a generally positive attitude towards using most AI applications in medicine. Along with this optimism comes several expectations and hopes that AI will assist physicians in clinical decision making. Especially in fields of medicine where huge amounts of data are processed (eg, imaging procedures in radiology and pathology) or data are collected continuously (eg, cardiology and intensive care medicine), physicians’ expectations of AI to substantially improve future patient care are high. In the study, the greatest potential was seen in the application of AI for the identification of drug interactions, assumedly due to the rising complexity of drug administration to polymorbid, polypharmacy patients. However, for the practical usage of AI in health care, regulatory and organizational challenges still have to be mastered.
- 5 March 2021
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 23 (3) , e26646
Top Cited PapersOpen AccessFuture Medical Artificial Intelligence Application Requirements and Expectations of Physicians in German University Hospitals: Web-Based Survey
Background: The increasing development of artificial intelligence (AI) systems in medicine driven by researchers and entrepreneurs goes along with enormous expectations for medical care advancement. AI might change the clinical practice of physicians from almost all medical disciplines and in most areas of health care. While expectations for AI in medicine are high, practical implementations of AI for clinical practice are still scarce in Germany. Moreover, physicians’ requirements and expectations of AI in medicine and their opinion on the usage of anonymized patient data for clinical and biomedical research have not been investigated widely in German university hospitals. Objective: This study aimed to evaluate physicians’ requirements and expectations of AI in medicine and their opinion on the secondary usage of patient data for (bio)medical research (eg, for the development of machine learning algorithms) in university hospitals in Germany. Methods: A web-based survey was conducted addressing physicians of all medical disciplines in 8 German university hospitals. Answers were given using Likert scales and general demographic responses. Physicians were asked to participate locally via email in the respective hospitals. Results: The online survey was completed by 303 physicians (female: 121/303, 39.9%; male: 173/303, 57.1%; no response: 9/303, 3.0%) from a wide range of medical disciplines and work experience levels. Most respondents either had a positive (130/303, 42.9%) or a very positive attitude (82/303, 27.1%) towards AI in medicine. There was a significant association between the personal rating of AI in medicine and the self-reported technical affinity level (H4=48.3, P<.001). A vast majority of physicians expected the future of medicine to be a mix of human and artificial intelligence (273/303, 90.1%) but also requested a scientific evaluation before the routine implementation of AI-based systems (276/303, 91.1%). Physicians were most optimistic that AI applications would identify drug interactions (280/303, 92.4%) to improve patient care substantially but were quite reserved regarding AI-supported diagnosis of psychiatric diseases (62/303, 20.5%). Of the respondents, 82.5% (250/303) agreed that there should be open access to anonymized patient databases for medical and biomedical research. Conclusions: Physicians in stationary patient care in German university hospitals show a generally positive attitude towards using most AI applications in medicine. Along with this optimism comes several expectations and hopes that AI will assist physicians in clinical decision making. Especially in fields of medicine where huge amounts of data are processed (eg, imaging procedures in radiology and pathology) or data are collected continuously (eg, cardiology and intensive care medicine), physicians’ expectations of AI to substantially improve future patient care are high. In the study, the greatest potential was seen in the application of AI for the identification of drug interactions, assumedly due to the rising complexity of drug administration to polymorbid, polypharmacy patients. However, for the practical usage of AI in health care, regulatory and organizational challenges still have to be mastered.