Dieter Mesotten
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
Dieter Mesotten has a total of 1000 co-authors. Here are the top co-authors by number of shared publications:
Ludovic Ernon
Ziekenhuis Oost-Limburg
5 shared publicationsAnouk Lesenne
Department of Anesthesiology, Intensive Care Medicine, Emergency Medicine and Pain Therapy, Ziekenhuis Oost-Limburg Genk, Genk, Belgium
4 shared publications- Cathy De Deyne
Department of Medicine and Life Sciences, Hasselt University, Diepenbeek, Belgium
4 shared publications - Cornelia Genbrugge
Department of Medicine and Life Sciences, Hasselt University, Diepenbeek, Belgium
4 shared publications - Frank Jans
Department of Medicine and Life Sciences, Hasselt University, Diepenbeek, Belgium
4 shared publications - Jo Dens
Department of Medicine and Life Sciences, Hasselt University, Diepenbeek, Belgium
4 shared publications
Latest Publications
- Open Access
- 1 February 2026
- Published by SAGE Publications in Digital Health
- Vol. 12
Artificial intelligence shows comparable or improved performance to traditional risk models in predicting atrial fibrillation after cryptogenic stroke
Background and Aims: Detecting subclinical atrial fibrillation (AF) and initiating anticoagulation therapy are critical for secondary stroke prevention after cryptogenic stroke. This study aimed to evaluate the effectiveness of traditional AF risk scores commonly used in clinical practice and compare with an artificial intelligence (AI)-driven ECG-derived AF prediction score. Methods: A retrospective tertiary care center study identified all cryptogenic stroke/TIA patients admitted between 2017-2023 who received an implantable cardiac monitor (ICM). The European Society of Cardiology (ESC)-recommended risk factors and risk score components (i.e.,CHA 2 DS 2 -VA, Brown ESUS-AF, and HAVOC) from the 2024 guidelines for AF management, were analyzed using multivariate logistic regression to predict AF within one-year post-ICM insertion. The predictive performance of these risk scores and an AI-driven ECG algorithm for AF detection was assessed and compared. Results: 230 cryptogenic stroke/TIA patients underwent ICM insertion. Only age (OR: 1.033, 95%CI 1.002-1.066) was associated with an increased likelihood of AF detection within one-year post-ICM insertion. The ECG-AI score demonstrated higher predictive power over CHA 2 DS 2 -VA and HAVOC (p=.002), and was the only score exceeding an AUROC value of 0.7, but did not outperform Brown ESUS-AF (p=.210). Patients with high scores had a more than two-fold increased likelihood of AF detection (HR: 2.7, 95%CI 1.2-5.8, p=.01). Conclusions: In patients with cryptogenic stroke receiving an ICM, the ECG-AI score showed modest discrimination for AF detection, outperforming CHA 2 DS 2 -VA and HAVOC, but not Brown ESUS-AF. Age was the only significant clinical predictor. These findings indicate a possible role for AI-driven ECG analysis in risk stratification.
- 1 February 2026
- Published by SAGE Publications in Digital Health
- Vol. 12
Open AccessArtificial intelligence shows comparable or improved performance to traditional risk models in predicting atrial fibrillation after cryptogenic stroke
Background and Aims: Detecting subclinical atrial fibrillation (AF) and initiating anticoagulation therapy are critical for secondary stroke prevention after cryptogenic stroke. This study aimed to evaluate the effectiveness of traditional AF risk scores commonly used in clinical practice and compare with an artificial intelligence (AI)-driven ECG-derived AF prediction score. Methods: A retrospective tertiary care center study identified all cryptogenic stroke/TIA patients admitted between 2017-2023 who received an implantable cardiac monitor (ICM). The European Society of Cardiology (ESC)-recommended risk factors and risk score components (i.e.,CHA 2 DS 2 -VA, Brown ESUS-AF, and HAVOC) from the 2024 guidelines for AF management, were analyzed using multivariate logistic regression to predict AF within one-year post-ICM insertion. The predictive performance of these risk scores and an AI-driven ECG algorithm for AF detection was assessed and compared. Results: 230 cryptogenic stroke/TIA patients underwent ICM insertion. Only age (OR: 1.033, 95%CI 1.002-1.066) was associated with an increased likelihood of AF detection within one-year post-ICM insertion. The ECG-AI score demonstrated higher predictive power over CHA 2 DS 2 -VA and HAVOC (p=.002), and was the only score exceeding an AUROC value of 0.7, but did not outperform Brown ESUS-AF (p=.210). Patients with high scores had a more than two-fold increased likelihood of AF detection (HR: 2.7, 95%CI 1.2-5.8, p=.01). Conclusions: In patients with cryptogenic stroke receiving an ICM, the ECG-AI score showed modest discrimination for AF detection, outperforming CHA 2 DS 2 -VA and HAVOC, but not Brown ESUS-AF. Age was the only significant clinical predictor. These findings indicate a possible role for AI-driven ECG analysis in risk stratification.
- 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
- 20 October 2023
- Published by Springer Nature in European Journal of Medical Research
- Vol. 28 (1) , 1-11
The effect of spinal versus general anaesthesia on perioperative muscle weakness in patients having bilateral total hip arthroplasty: a single center randomized clinical trial
Background: Perioperative neuro-endocrine stress response may contribute to acquired muscle weakness. Regional anaesthesia has been reported to improve the outcome of patients having total hip arthroplasty. In this study, it was hypothesized that spinal anaesthesia (SA) decreases the perioperative neuro-endocrine stress response and perioperatively acquired muscle weakness (PAMW), as compared to general anaesthesia (GA). Methods: Fifty subjects undergoing bilateral total hip arthroplasty (THA) were randomly allocated to receive a standardized SA (n = 25) or GA (n = 25). Handgrip strength was assessed preoperatively, on the first postoperative day (primary endpoint) and on day 7 and 28. Respiratory muscle strength was measured by maximal inspiratory pressure (MIP). Stress response was assessed by measuring levels of Adrenocorticotropic hormone (ACTH), cortisol and interleukin-6 (IL-6). Results: Handgrip strength postoperatively (day 1) decreased by 5.4 ± 15.9% in the SA group, versus 15.2 ± 11.7% in the GA group (p = 0.02). The handgrip strength returned to baseline at day 7 and did not differ between groups at day 28. MIP increased postoperatively in patients randomized to SA by 11.7 ± 48.3%, whereas it decreased in GA by 12.2 ± 19.9% (p = 0.04). On day 7, MIP increased in both groups, but more in the SA (49.0 ± 47.8%) than in the GA group (14.2 ± 32.1%) (p = 0.006). Postoperatively, the levels of ACTH, cortisol and IL-6 increased in the GA, but not in the SA group (p < 0.004). Conclusion: In patients having bilateral THA, SA preserved the postoperative respiratory and peripheral muscle strength and attenuated the neuro-endocrine and inflammatory responses. Trial registration: clinicaltrials.gov NCT03600454.
- 20 October 2023
- Published by Springer Nature in European Journal of Medical Research
- Vol. 28 (1) , 1-11
Open AccessThe effect of spinal versus general anaesthesia on perioperative muscle weakness in patients having bilateral total hip arthroplasty: a single center randomized clinical trial
Background: Perioperative neuro-endocrine stress response may contribute to acquired muscle weakness. Regional anaesthesia has been reported to improve the outcome of patients having total hip arthroplasty. In this study, it was hypothesized that spinal anaesthesia (SA) decreases the perioperative neuro-endocrine stress response and perioperatively acquired muscle weakness (PAMW), as compared to general anaesthesia (GA). Methods: Fifty subjects undergoing bilateral total hip arthroplasty (THA) were randomly allocated to receive a standardized SA (n = 25) or GA (n = 25). Handgrip strength was assessed preoperatively, on the first postoperative day (primary endpoint) and on day 7 and 28. Respiratory muscle strength was measured by maximal inspiratory pressure (MIP). Stress response was assessed by measuring levels of Adrenocorticotropic hormone (ACTH), cortisol and interleukin-6 (IL-6). Results: Handgrip strength postoperatively (day 1) decreased by 5.4 ± 15.9% in the SA group, versus 15.2 ± 11.7% in the GA group (p = 0.02). The handgrip strength returned to baseline at day 7 and did not differ between groups at day 28. MIP increased postoperatively in patients randomized to SA by 11.7 ± 48.3%, whereas it decreased in GA by 12.2 ± 19.9% (p = 0.04). On day 7, MIP increased in both groups, but more in the SA (49.0 ± 47.8%) than in the GA group (14.2 ± 32.1%) (p = 0.006). Postoperatively, the levels of ACTH, cortisol and IL-6 increased in the GA, but not in the SA group (p < 0.004). Conclusion: In patients having bilateral THA, SA preserved the postoperative respiratory and peripheral muscle strength and attenuated the neuro-endocrine and inflammatory responses. Trial registration: clinicaltrials.gov NCT03600454.
- Open Access
- 22 December 2022
- Published by Springer Nature in BMC Research Notes
- Vol. 15 (1) , 1-7
A comparative study of patient satisfaction about anesthesia with dexmedetomidine for ambulatory dental surgery
Objective: Intranasal administration of dexmedetomidine for monitored anesthesia care (MAC) appears to be an effective, safe, and appropriate alternative to general anesthesia (GA) for ambulatory dental surgery. Based on the available evidence we evaluated a new MAC protocol with intranasal dexmedetomidine as the primary choice. To assess a difference in patient satisfaction and anesthesia-related discomfort between GA and MAC in ambulatory dental surgery, a study was conducted among patients undergoing various dental procedures. Patient satisfaction and anesthesia-related discomfort were assessed on the first postoperative day using the Bauer patient satisfaction questionnaire. Results: Although the differences were small, patients in the MAC group were overall more satisfied with the general care compared to the GA group (p < 0.02). Patients in the MAC group reported more postoperative drowsiness compared to the GA group (p < 0.05), but less postoperative hoarseness and sore throat (p = 0.005 and p < 0.001, respectively). Moreover, postoperative thirst was more common in the GA group (p = 0.002). In conclusion, the differences in patient satisfaction and anesthesia-related discomfort between GA and MAC in this implementation study were small but appeared to favor MAC with intranasal dexmedetomidine over GA as anesthesia method during dental ambulatory surgery.
- 22 December 2022
- Published by Springer Nature in BMC Research Notes
- Vol. 15 (1) , 1-7
Open AccessA comparative study of patient satisfaction about anesthesia with dexmedetomidine for ambulatory dental surgery
Objective: Intranasal administration of dexmedetomidine for monitored anesthesia care (MAC) appears to be an effective, safe, and appropriate alternative to general anesthesia (GA) for ambulatory dental surgery. Based on the available evidence we evaluated a new MAC protocol with intranasal dexmedetomidine as the primary choice. To assess a difference in patient satisfaction and anesthesia-related discomfort between GA and MAC in ambulatory dental surgery, a study was conducted among patients undergoing various dental procedures. Patient satisfaction and anesthesia-related discomfort were assessed on the first postoperative day using the Bauer patient satisfaction questionnaire. Results: Although the differences were small, patients in the MAC group were overall more satisfied with the general care compared to the GA group (p < 0.02). Patients in the MAC group reported more postoperative drowsiness compared to the GA group (p < 0.05), but less postoperative hoarseness and sore throat (p = 0.005 and p < 0.001, respectively). Moreover, postoperative thirst was more common in the GA group (p = 0.002). In conclusion, the differences in patient satisfaction and anesthesia-related discomfort between GA and MAC in this implementation study were small but appeared to favor MAC with intranasal dexmedetomidine over GA as anesthesia method during dental ambulatory surgery.
- 21 November 2022
- Published by Springer Nature in Acta Neurologica Belgica
- Vol. 123 (2) , 545-551
Multicentric validation of a reduced features case-mix set for predicting functional outcome after ischemic stroke in Belgium
Introduction Ischemic stroke is the second cause of death and leading cause of severe disability worldwide. A reduced features set of CT-DRAGON (age, NIHSS on admission and pre-stroke mRS) predicts 90-day functional outcome after stroke in a single center. The current study was designed to validate this adapted CT-DRAGON score in three major Belgian hospitals, in the framework of future case-mix adjustment. Methods This retrospective study included stroke patients, treated by thrombolysis, thrombectomy, a combination of both or neither thrombolysis or thrombectomy (conservative treatment) in 2019. Patient characteristics and 90-day mRS were collected. Multivariable logistic regression analysis of 90-day mRS 0–2 vs. 3–6 and 0–5 vs. 6 with the reduced features set was performed. Discriminative performance was assessed by the area under the receiver operating characteristic curve (AUROC). Results Thirty-three percent of patients (413/1243) underwent treatment. Majority of strokes was treated conservatively (n = 830, 67%), 18% (n = 225) was treated by thrombolysis, 7% (n = 88) by thrombectomy and 8% (n = 100) by thrombolysis and thrombectomy. Age, NIHSS and pre-stroke mRS were independently associated with 90-day mRS 0–2 (all p ≤ 0.0001, AUROC 0.88). When treatment modality was added in the model, age, NIHSS, pre-stroke mRS and treatment modality were independently associated with 90-day mRS 0–2 (p < 0.0001, p < 0.0001, p < 0.0001 and p = 0.0001) AUROC 0.89). Age, NIHSS, pre-stroke mRS and treatment modality were independently associated with 90-day survival (p = 0.0001, p < 0.0001, p < 0.0001 and p = 0.008, AUROC 0.86). Discussion The reduced features set (age, NIHSS and pre-mRS) was independently associated with long-term functional outcome in a Belgian multicentric cohort, making it useful for case-mix adjustments in Belgian stroke centers. Treatment modality was associated with long-term outcome.
- 21 November 2022
- Published by Springer Nature in Acta Neurologica Belgica
- Vol. 123 (2) , 545-551
Multicentric validation of a reduced features case-mix set for predicting functional outcome after ischemic stroke in Belgium
Introduction Ischemic stroke is the second cause of death and leading cause of severe disability worldwide. A reduced features set of CT-DRAGON (age, NIHSS on admission and pre-stroke mRS) predicts 90-day functional outcome after stroke in a single center. The current study was designed to validate this adapted CT-DRAGON score in three major Belgian hospitals, in the framework of future case-mix adjustment. Methods This retrospective study included stroke patients, treated by thrombolysis, thrombectomy, a combination of both or neither thrombolysis or thrombectomy (conservative treatment) in 2019. Patient characteristics and 90-day mRS were collected. Multivariable logistic regression analysis of 90-day mRS 0–2 vs. 3–6 and 0–5 vs. 6 with the reduced features set was performed. Discriminative performance was assessed by the area under the receiver operating characteristic curve (AUROC). Results Thirty-three percent of patients (413/1243) underwent treatment. Majority of strokes was treated conservatively (n = 830, 67%), 18% (n = 225) was treated by thrombolysis, 7% (n = 88) by thrombectomy and 8% (n = 100) by thrombolysis and thrombectomy. Age, NIHSS and pre-stroke mRS were independently associated with 90-day mRS 0–2 (all p ≤ 0.0001, AUROC 0.88). When treatment modality was added in the model, age, NIHSS, pre-stroke mRS and treatment modality were independently associated with 90-day mRS 0–2 (p < 0.0001, p < 0.0001, p < 0.0001 and p = 0.0001) AUROC 0.89). Age, NIHSS, pre-stroke mRS and treatment modality were independently associated with 90-day survival (p = 0.0001, p < 0.0001, p < 0.0001 and p = 0.008, AUROC 0.86). Discussion The reduced features set (age, NIHSS and pre-mRS) was independently associated with long-term functional outcome in a Belgian multicentric cohort, making it useful for case-mix adjustments in Belgian stroke centers. Treatment modality was associated with long-term outcome.
- Open Access
- 25 July 2022
- Published by Springer Nature in Critical Care
- Vol. 26 (1) , 1-15
Acute kidney injury in critical COVID-19: a multicenter cohort analysis in seven large hospitals in Belgium
Background: Acute kidney injury (AKI) has been reported as a frequent complication of critical COVID-19. We aimed to evaluate the occurrence of AKI and use of kidney replacement therapy (KRT) in critical COVID-19, to assess patient and kidney outcomes and risk factors for AKI and differences in outcome when the diagnosis of AKI is based on urine output (UO) or on serum creatinine (sCr). Methods: Multicenter, retrospective cohort analysis of patients with critical COVID-19 in seven large hospitals in Belgium. AKI was defined according to KDIGO within 21 days after ICU admission. Multivariable logistic regression analysis was used to explore the risk factors for developing AKI and to assess the association between AKI and ICU mortality. Results: Of 1286 patients, 85.1% had AKI, and KRT was used in 9.8%. Older age, obesity, a higher APACHE II score and use of mechanical ventilation at day 1 of ICU stay were associated with an increased risk for AKI. After multivariable adjustment, all AKI stages were associated with ICU mortality. AKI was based on sCr in 40.1% and UO in 81.5% of patients. All AKI stages based on sCr and AKI stage 3 based on UO were associated with ICU mortality. Persistent AKI was present in 88.6% and acute kidney disease (AKD) in 87.6%. Rapid reversal of AKI yielded a better prognosis compared to persistent AKI and AKD. Kidney recovery was observed in 47.4% of surviving AKI patients. Conclusions: Over 80% of critically ill COVID-19 patients had AKI. This was driven by the high occurrence rate of AKI defined by UO criteria. All AKI stages were associated with mortality (NCT04997915).
- 25 July 2022
- Published by Springer Nature in Critical Care
- Vol. 26 (1) , 1-15
Open AccessAcute kidney injury in critical COVID-19: a multicenter cohort analysis in seven large hospitals in Belgium
Background: Acute kidney injury (AKI) has been reported as a frequent complication of critical COVID-19. We aimed to evaluate the occurrence of AKI and use of kidney replacement therapy (KRT) in critical COVID-19, to assess patient and kidney outcomes and risk factors for AKI and differences in outcome when the diagnosis of AKI is based on urine output (UO) or on serum creatinine (sCr). Methods: Multicenter, retrospective cohort analysis of patients with critical COVID-19 in seven large hospitals in Belgium. AKI was defined according to KDIGO within 21 days after ICU admission. Multivariable logistic regression analysis was used to explore the risk factors for developing AKI and to assess the association between AKI and ICU mortality. Results: Of 1286 patients, 85.1% had AKI, and KRT was used in 9.8%. Older age, obesity, a higher APACHE II score and use of mechanical ventilation at day 1 of ICU stay were associated with an increased risk for AKI. After multivariable adjustment, all AKI stages were associated with ICU mortality. AKI was based on sCr in 40.1% and UO in 81.5% of patients. All AKI stages based on sCr and AKI stage 3 based on UO were associated with ICU mortality. Persistent AKI was present in 88.6% and acute kidney disease (AKD) in 87.6%. Rapid reversal of AKI yielded a better prognosis compared to persistent AKI and AKD. Kidney recovery was observed in 47.4% of surviving AKI patients. Conclusions: Over 80% of critically ill COVID-19 patients had AKI. This was driven by the high occurrence rate of AKI defined by UO criteria. All AKI stages were associated with mortality (NCT04997915).
- 30 June 2022
- Published by Springer Nature in Acta Neurologica Belgica
- Vol. 122 (5) , 1281-1287
Hospital-acquired infections after acute ischaemic stroke and its association with healthcare-related costs and functional outcome
Introduction Acute ischaemic stroke is associated with important mortality, morbidity, and healthcare-related costs. Age, pre-stroke functionality and stroke severity are important contributors to functional outcome. Stroke patients also risk developing infections during hospitalization. We sought to explore possible predictors of post-stroke infections and the relationship of post-stroke infection with healthcare-related costs and functional outcome. Methods This single-centre retrospective study included 530 patients treated for ischaemic stroke between January 2017 and February 2019. Antibiotics’ administration was used as a proxy for post-stroke infection. Functional outcome at 90 days was assessed by the modified Rankin Scale (mRS). Total healthcare-related costs were recorded for the index hospital stay. Multivariable analysis for post-stroke infection was done with the independent factors sex, age, pre-stroke mRS, National Institutes of Health Stroke Scale (NIHSS) and diabetes mellitus. Results Twenty percent of patients had a post-stroke infection. NIHSS (OR 1.10, 95%CI 1.06–1.13, p < 0.0001) and diabetes mellitus (OR 2.18, 95%CI 1.28–3.71, p = 0.0042) were independent predictors for post-stroke infection. Mean total healthcare-related costs were 15,374 euro (SD 19,968; IQR 3,380–18,165), with a mean of 31,061 euro (SD 29,995; IQR 12,584–42,843) in patients with infection, compared to 11,406 euro (SD 13,987; IQR 3,083–12,726) in patients without (p < 0.0001). Median 90-days mRS was 5 (IQR 3–6) in patients with infection versus 1 (IQR 0–3.5) in patients without (p < 0.0001). Conclusions In patients, admitted for acute ischaemic stroke, stroke severity and diabetes mellitus were identified as the main predictors for post-stroke infection. Hospital-acquired infections were associated with increased costs and worse functional outcome.
- 30 June 2022
- Published by Springer Nature in Acta Neurologica Belgica
- Vol. 122 (5) , 1281-1287
Hospital-acquired infections after acute ischaemic stroke and its association with healthcare-related costs and functional outcome
Introduction Acute ischaemic stroke is associated with important mortality, morbidity, and healthcare-related costs. Age, pre-stroke functionality and stroke severity are important contributors to functional outcome. Stroke patients also risk developing infections during hospitalization. We sought to explore possible predictors of post-stroke infections and the relationship of post-stroke infection with healthcare-related costs and functional outcome. Methods This single-centre retrospective study included 530 patients treated for ischaemic stroke between January 2017 and February 2019. Antibiotics’ administration was used as a proxy for post-stroke infection. Functional outcome at 90 days was assessed by the modified Rankin Scale (mRS). Total healthcare-related costs were recorded for the index hospital stay. Multivariable analysis for post-stroke infection was done with the independent factors sex, age, pre-stroke mRS, National Institutes of Health Stroke Scale (NIHSS) and diabetes mellitus. Results Twenty percent of patients had a post-stroke infection. NIHSS (OR 1.10, 95%CI 1.06–1.13, p < 0.0001) and diabetes mellitus (OR 2.18, 95%CI 1.28–3.71, p = 0.0042) were independent predictors for post-stroke infection. Mean total healthcare-related costs were 15,374 euro (SD 19,968; IQR 3,380–18,165), with a mean of 31,061 euro (SD 29,995; IQR 12,584–42,843) in patients with infection, compared to 11,406 euro (SD 13,987; IQR 3,083–12,726) in patients without (p < 0.0001). Median 90-days mRS was 5 (IQR 3–6) in patients with infection versus 1 (IQR 0–3.5) in patients without (p < 0.0001). Conclusions In patients, admitted for acute ischaemic stroke, stroke severity and diabetes mellitus were identified as the main predictors for post-stroke infection. Hospital-acquired infections were associated with increased costs and worse functional outcome.
- Open Access
Vital Signs Prediction for COVID-19 Patients in ICU
This study introduces machine learning predictive models to predict the future values of the monitored vital signs of COVID-19 ICU patients. The main vital sign predictors include heart rate, respiration rate, and oxygen saturation. We investigated the performances of the developed predictive models by considering different approaches. The first predictive model was developed by considering the following vital signs: heart rate, blood pressure (systolic, diastolic and mean arterial, pulse pressure), respiration rate, and oxygen saturation. Similar to the first approach, the second model was developed using the same vital signs, but it was trained and tested based on a leave-one-subject-out approach. The third predictive model was developed by considering three vital signs: heart rate (HR), respiration rate (RR), and oxygen saturation (SpO). The fourth model was a leave-one-subject-out model for the three vital signs. Finally, the fifth predictive model was developed based on the same three vital signs, but with a five-minute observation rate, in contrast with the aforementioned four models, where the observation rate was hourly to bi-hourly. For the five models, the predicted measurements were those of the three upcoming observations (on average, three hours ahead). Based on the obtained results, we observed that by limiting the number of vital sign predictors (i.e., three vital signs), the prediction performance was still acceptable, with the average mean absolute percentage error (MAPE) being , and for heart rate, oxygen saturation, and respiration rate, respectively. Moreover, increasing the observation rate could enhance the prediction performance to be, on average, , and for heart rate, oxygen saturation, and respiration rate, respectively. It is envisioned that such models could be integrated with monitoring systems that could, using a limited number of vital signs, predict the health conditions of COVID-19 ICU patients in real-time.Open AccessVital Signs Prediction for COVID-19 Patients in ICU
This study introduces machine learning predictive models to predict the future values of the monitored vital signs of COVID-19 ICU patients. The main vital sign predictors include heart rate, respiration rate, and oxygen saturation. We investigated the performances of the developed predictive models by considering different approaches. The first predictive model was developed by considering the following vital signs: heart rate, blood pressure (systolic, diastolic and mean arterial, pulse pressure), respiration rate, and oxygen saturation. Similar to the first approach, the second model was developed using the same vital signs, but it was trained and tested based on a leave-one-subject-out approach. The third predictive model was developed by considering three vital signs: heart rate (HR), respiration rate (RR), and oxygen saturation (SpO). The fourth model was a leave-one-subject-out model for the three vital signs. Finally, the fifth predictive model was developed based on the same three vital signs, but with a five-minute observation rate, in contrast with the aforementioned four models, where the observation rate was hourly to bi-hourly. For the five models, the predicted measurements were those of the three upcoming observations (on average, three hours ahead). Based on the obtained results, we observed that by limiting the number of vital sign predictors (i.e., three vital signs), the prediction performance was still acceptable, with the average mean absolute percentage error (MAPE) being , and for heart rate, oxygen saturation, and respiration rate, respectively. Moreover, increasing the observation rate could enhance the prediction performance to be, on average, , and for heart rate, oxygen saturation, and respiration rate, respectively. It is envisioned that such models could be integrated with monitoring systems that could, using a limited number of vital signs, predict the health conditions of COVID-19 ICU patients in real-time. - 3 October 2021
- Published by Springer Nature in Acta Neurologica Belgica
- Vol. 122 (1) , 173-180
Interaction between stroke severity and quality indicators of acute stroke care: a single-center retrospective analysis
Ischemic stroke leads to substantial mortality and morbidity worldwide. Door-to-CT time, door-to-needle time (DNT), and door-to-groin time (DGT) are important quality indicators of stroke care. However, patient characteristics remain important determinants of outcome as well. In this single-center study, we investigated the interaction between these quality indicators and stroke severity regarding long-term functional outcome. All consecutive stroke patients treated at the ZOL stroke center, Genk, Belgium, between 2017 and 2020 were included in this retrospective observational study. Stroke severity was graded as “mild” if National Institutes of Health Stroke Scale (NIHSS) was equal to or lower than 8, “moderate” if NIHSS was between 9 and 15, and “severe” if NIHSS was higher than 16. Modified Rankin Scale (mRS) scores were collected before and 3 months after stroke. Ordinal regression analysis with correction for patient characteristics of functional outcome was done. A total of 1255 patients were included, of which 84% suffered an ischemic CVA (n = 1052) and 16% a TIA (n = 203). The proportion of patients treated conservatively or with thrombolysis, thrombectomy, or the combination of both differed according to stroke severity (p < 0.0001). Door-to-CT time was longer in mild and moderate stroke (p < 0.0001). Median DNT also differed between stroke categories: 46 (IQR 31–70) min for mild vs. 36 (25–56) min for moderate vs. 30 (21–45) min for severe stroke (p = 0.0002). Median DGT did not differ between stroke severity categories (p = 0.15). NIHSS on admission and pre-stroke mRS were independently associated with mRS at 90 days. Operational performance, reflected in door-to-CT time and DNT, was worse in patients with mild and moderate stroke severity. DNT was also associated with functional outcome in our center, along with pre-stroke mRS, NIHSS on admission and age.
- 3 October 2021
- Published by Springer Nature in Acta Neurologica Belgica
- Vol. 122 (1) , 173-180
Interaction between stroke severity and quality indicators of acute stroke care: a single-center retrospective analysis
Ischemic stroke leads to substantial mortality and morbidity worldwide. Door-to-CT time, door-to-needle time (DNT), and door-to-groin time (DGT) are important quality indicators of stroke care. However, patient characteristics remain important determinants of outcome as well. In this single-center study, we investigated the interaction between these quality indicators and stroke severity regarding long-term functional outcome. All consecutive stroke patients treated at the ZOL stroke center, Genk, Belgium, between 2017 and 2020 were included in this retrospective observational study. Stroke severity was graded as “mild” if National Institutes of Health Stroke Scale (NIHSS) was equal to or lower than 8, “moderate” if NIHSS was between 9 and 15, and “severe” if NIHSS was higher than 16. Modified Rankin Scale (mRS) scores were collected before and 3 months after stroke. Ordinal regression analysis with correction for patient characteristics of functional outcome was done. A total of 1255 patients were included, of which 84% suffered an ischemic CVA (n = 1052) and 16% a TIA (n = 203). The proportion of patients treated conservatively or with thrombolysis, thrombectomy, or the combination of both differed according to stroke severity (p < 0.0001). Door-to-CT time was longer in mild and moderate stroke (p < 0.0001). Median DNT also differed between stroke categories: 46 (IQR 31–70) min for mild vs. 36 (25–56) min for moderate vs. 30 (21–45) min for severe stroke (p = 0.0002). Median DGT did not differ between stroke severity categories (p = 0.15). NIHSS on admission and pre-stroke mRS were independently associated with mRS at 90 days. Operational performance, reflected in door-to-CT time and DNT, was worse in patients with mild and moderate stroke severity. DNT was also associated with functional outcome in our center, along with pre-stroke mRS, NIHSS on admission and age.
- Open Access
- 31 July 2020
- Published by Frontiers Media SA in Frontiers in Neurology
- Vol. 11, 718
Prediction of Functional Outcome After Acute Ischemic Stroke: Comparison of the CT-DRAGON Score and a Reduced Features Set
Background and Purpose: The CT-DRAGON score was developed to predict long-term functional outcome after acute stroke in the anterior circulation treated by thrombolysis. Its implementation in clinical practice may be hampered by its plethora of variables. The current study was designed to develop and evaluate an alternative score, as a reduced set of features, derived from the original CT-DRAGON score. Methods: This single-center retrospective study included 564 patients treated for stroke, in the anterior and the posterior circulation. At 90 days, favorable [modified Rankin Scale score (mRS) of 0–2] and miserable outcome (mRS of 5–6) were predicted by the CT-DRAGON in 427 patients. Bootstrap forests selected the most relevant parameters of the CT-DRAGON, in order to develop a reduced set of features. Discrimination, calibration and misclassification of both models were tested. Results: The area under the receiver operating characteristic curve (AUROC) for the CT-DRAGON was 0.78 (95% CI 0.74–0.81) for favorable and 0.78 (95% CI 0.72-0.83) for miserable outcome. Misclassification was 29% for favorable and 13.5% for miserable outcome, with a 100% specificity for the latter. National Institutes of Health Stroke Scale (NIHSS), pre-stroke mRS and age were identified as the strongest contributors to favorable and miserable outcome and named the reduced features set. While CT-DRAGON was only available in 323 patients (57%), the reduced features set could be calculated in 515 patients (91%) (p < 0.001). Misclassification was 25.8% for favorable and 14.4% for miserable outcome, with a 97% specificity for miserable outcome. The reduced features set had better discriminative power than CT-DRAGON for both outcomes (both p < 0.005), with an AUROC of 0.82 (95% CI 0.79–0.86) and 0.83 (95% CI 0.77–0.87) for favorable and miserable outcome, respectively. Conclusions: The CT-DRAGON score revealed acceptable discrimination in our cohort of both anterior and posterior circulation strokes, receiving all treatment modalities. The reduced features set could be measured in a larger cohort and with better discrimination. However, the reduced features set needs further validation in a prospective, multicentre study. Clinical Trial Registration: http://www.clinicaltrials.gov. Identifiers: NCT03355690, NCT04092543.
- 31 July 2020
- Published by Frontiers Media SA in Frontiers in Neurology
- Vol. 11, 718
Open AccessPrediction of Functional Outcome After Acute Ischemic Stroke: Comparison of the CT-DRAGON Score and a Reduced Features Set
Background and Purpose: The CT-DRAGON score was developed to predict long-term functional outcome after acute stroke in the anterior circulation treated by thrombolysis. Its implementation in clinical practice may be hampered by its plethora of variables. The current study was designed to develop and evaluate an alternative score, as a reduced set of features, derived from the original CT-DRAGON score. Methods: This single-center retrospective study included 564 patients treated for stroke, in the anterior and the posterior circulation. At 90 days, favorable [modified Rankin Scale score (mRS) of 0–2] and miserable outcome (mRS of 5–6) were predicted by the CT-DRAGON in 427 patients. Bootstrap forests selected the most relevant parameters of the CT-DRAGON, in order to develop a reduced set of features. Discrimination, calibration and misclassification of both models were tested. Results: The area under the receiver operating characteristic curve (AUROC) for the CT-DRAGON was 0.78 (95% CI 0.74–0.81) for favorable and 0.78 (95% CI 0.72-0.83) for miserable outcome. Misclassification was 29% for favorable and 13.5% for miserable outcome, with a 100% specificity for the latter. National Institutes of Health Stroke Scale (NIHSS), pre-stroke mRS and age were identified as the strongest contributors to favorable and miserable outcome and named the reduced features set. While CT-DRAGON was only available in 323 patients (57%), the reduced features set could be calculated in 515 patients (91%) (p < 0.001). Misclassification was 25.8% for favorable and 14.4% for miserable outcome, with a 97% specificity for miserable outcome. The reduced features set had better discriminative power than CT-DRAGON for both outcomes (both p < 0.005), with an AUROC of 0.82 (95% CI 0.79–0.86) and 0.83 (95% CI 0.77–0.87) for favorable and miserable outcome, respectively. Conclusions: The CT-DRAGON score revealed acceptable discrimination in our cohort of both anterior and posterior circulation strokes, receiving all treatment modalities. The reduced features set could be measured in a larger cohort and with better discrimination. However, the reduced features set needs further validation in a prospective, multicentre study. Clinical Trial Registration: http://www.clinicaltrials.gov. Identifiers: NCT03355690, NCT04092543.