ABSTRACT
BACKGROUND: An inherent difference exists between male and female bodies, the historical under-representation of females in clinical trials widened this gap in existing healthcare data. The fairness of clinical decision-support tools is at risk when developed based on biased data. This paper aims to quantitatively assess the gender bias in risk prediction models. We aim to generalize our findings by performing this investigation on multiple use cases at different hospitals. METHODS: First, we conduct a thorough analysis of the source data to find gender-based disparities. Secondly, we assess the model performance on different gender groups at different hospitals and on different use cases. Performance evaluation is quantified using the area under the receiver-operating characteristic curve (AUROC). Lastly, we investigate the clinical implications of these biases by analyzing the underdiagnosis and overdiagnosis rate, and the decision curve analysis (DCA). We also investigate the influence of model calibration on mitigating gender-related disparities in decision-making processes. RESULTS: Our data analysis reveals notable variations in incidence rates, AUROC, and over-diagnosis rates across different genders, hospitals and clinical use cases. However, it is also observed the underdiagnosis rate is consistently higher in the female population. In general, the female population exhibits lower incidence rates and the models perform worse when applied to this group. Furthermore, the decision curve analysis demonstrates there is no statistically significant difference between the model's clinical utility across gender groups within the interested range of thresholds. CONCLUSION: The presence of gender bias within risk prediction models varies across different clinical use cases and healthcare institutions. Although inherent difference is observed between male and female populations at the data source level, this variance does not affect the parity of clinical utility. In conclusion, the evaluations conducted in this study highlight the significance of continuous monitoring of gender-based disparities in various perspectives for clinical risk prediction models.
ABSTRACT
In 873 propensity score-matched pairs of patients undergoing valvular heart surgery, we compared a "moderate dose" of tranexamic acid (TXA) protocol (group 1; median TXA dose: 24 mg/kg body weight) with a 1.5-g "bolus-only" protocol (group 2; median TXA dose: 19 mg/kg body weight). The number of transfused patients was higher in group 2 than in group 1 (74.5 vs 66.0%, p < 0.001), as was the number of transfused red blood cell concentrates (p = 0.001). The risks of re-exploration and convulsive seizures were similar between groups (p > 0.50). Data indicate an impaired efficacy following the "bolus-only" protocol, without a significant safety improvement.
Subject(s)
Antifibrinolytic Agents , Cardiac Surgical Procedures , Tranexamic Acid , Humans , Tranexamic Acid/adverse effects , Antifibrinolytic Agents/adverse effects , Treatment Outcome , Cardiac Surgical Procedures/adverse effects , Cardiac Surgical Procedures/methods , Body Weight , Blood Loss, SurgicalABSTRACT
Lung transplantation is the only therapy for patients with end-stage lung disease. In advanced lung diseases such as cystic fibrosis (CF), life expectancy increases, and it is important to recognize extrapulmonary comorbidities. Cardiovascular involvement, including pulmonary hypertension, right-heart failure, and myocardial dysfunction, are manifest in the late stages of CF disease. Besides right-heart failure, left-heart dysfunction seems to be underestimated. Therefore, an optimal anesthesia and surgical management risk evaluation in this high-risk patient population is mandatory, especially concerning the perioperative use of mechanical circulatory support. The use of an index case of an older patient with the diagnosis of cystic fibrosis demonstrates the importance of early risk stratification and strategy planning in a multidisciplinary team approach to guarantee successful lung transplantation.
Subject(s)
Cystic Fibrosis , Heart Failure , Lung Transplantation , Humans , Comorbidity , Cystic Fibrosis/complications , Cystic Fibrosis/surgery , Heart Failure/epidemiology , Risk FactorsABSTRACT
OBJECTIVES: There is accumulating evidence that blood pressure management might be associated with end-organ dysfunction after cardiac surgery. This study aimed to investigate the impact of intraoperative hypotension (IOH) on adverse neurologic outcomes and mortality. DESIGN: A single-center retrospective cohort study. SETTING: The Heart and Diabetes Centre Bad Oeynhausen NRW, Ruhr-University Bochum. PARTICIPANTS: This retrospective cohort study included 31,315 adult patients who underwent elective cardiac surgery at the authors' institution between January 2009 and December 2018. INTERVENTIONS: All cardiac surgery procedures except assist device implantation, organ transplantation, and emergency surgery. MEASUREMENTS AND MAIN RESULTS: Adverse neurologic outcomes were defined as postoperative delirium and stroke. IOH was defined as mean arterial pressure below 60 mmHg for >2 minutes. The frequency of IOH episodes and the cumulative IOH duration were recorded. The association between IOH and adverse neurologic outcomes was examined with unadjusted statistical analysis and multiple logistic regression analysis. Eight hundred forty-nine (2.9%) patients developed postoperative stroke, and 2,401 (7.7%) patients developed postoperative delirium. The frequency of IOH episodes was independently associated with postoperative delirium in the multiple logistic regression analysis (odds ratio 1.02, 95% CI 1.003-1.03, p < 0.001), whereas there was no association between it and stroke. CONCLUSION: This large retrospective monocentric cohort study revealed that increased episodes of IOH were associated with the risk of developing postoperative delirium after cardiac surgery. This might have important clinical implications with respect to careful and precise hemodynamic monitoring and proactive treatment, especially in patients with increased risk for postoperative delirium.
Subject(s)
Cardiac Surgical Procedures , Emergence Delirium , Hypotension , Stroke , Adult , Humans , Blood Pressure , Retrospective Studies , Cohort Studies , Postoperative Complications/diagnosis , Postoperative Complications/epidemiology , Postoperative Complications/etiology , Intraoperative Complications , Cardiac Surgical Procedures/adverse effects , Hypotension/diagnosis , Hypotension/epidemiology , Hypotension/etiology , Stroke/complicationsABSTRACT
The Pediatric Cardiac Anesthesia (PCA) fellowship is a demanding training program in Europe and the United States. Successful completion of the program requires years of training in anesthesiology, a thorough understanding of cardiovascular anatomy and physiology, and extensive experience in the perioperative management of neonates and children with heart disease. In the context of the first candidate to successfully complete the PCA program in Europe, this article presents excerpts from the design and structure of the European PCA program. The PCA program is evaluated critically by both external and internal reviewers, and points are highlighted that could be included in the next version of the program.
Subject(s)
Anesthesia, Cardiac Procedures , Anesthesiology , Infant, Newborn , Humans , Child , United States , Fellowships and Scholarships , Anesthesiology/education , Education, Medical, Graduate , Pediatric AnesthesiaABSTRACT
OBJECTIVE: To comprehensively assess relevant institutional variations in anesthesia and intensive care management during left ventricular assist device (LVAD) implantation. DESIGN: The authors used a prospective data analysis. SETTING: This was an online survey. PARTICIPANTS: Participants were from LVAD centers in Europe and the US. INTERVENTIONS: After investigating initial interest, 91 of 202 European and 93 of 195 US centers received a link to the survey targeting institutional organization and experience, perioperative hemodynamic monitoring, medical management, and postoperative intensive care aspects. MEASUREMENTS AND MAIN RESULTS: The survey was completed by 73 (36.1%) European and 60 (30.8%) US centers. Although most LVAD implantations were performed in university hospitals (>5 years of experience), significant differences were observed in the composition of the preoperative multidisciplinary team and provision of intraoperative care. No significant differences in monitoring or induction agents were observed. Propofol was used more often for maintenance in Europe (p < 0.001). The choice for inotropes changed significantly from preoperatively (more levosimendan in Europe) to intraoperatively (more use of epinephrine in both Europe and the US). The use of quantitative methods for defining right ventricular (RV) function was reported more often from European centers than from US centers (p < 0.05). Temporary mechanical circulatory support for the treatment of RV failure was more often used in Europe. Nitric oxide appeared to play a major role only intraoperatively. There were no significant differences in early postoperative complications reported from European versus US centers. CONCLUSIONS: Although the perioperative practice of care for patients undergoing LVAD implantation differs in several aspects between Europe and the US, there were no perceived differences in early postoperative complications.
Subject(s)
Anesthesia , Heart Failure , Heart-Assist Devices , Ventricular Dysfunction, Right , Humans , United States/epidemiology , Prospective Studies , Heart-Assist Devices/adverse effects , Postoperative Complications , Anesthesia/adverse effects , Europe/epidemiology , Retrospective Studies , Treatment OutcomeABSTRACT
BACKGROUND: Increasing regulations and requirements of advisory bodies, in particular the Joint Federal Committee and the Medical Service of the health insurance funds, make it necessary to employ only demonstrably well-trained perfusionists. The minimum requirement for this staff is EBCP certification. Currently there is limited availability of such specialists on the German market. Therefore, the qualification of young people in this area is of central importance. The aim of this paper is to strengthen the training of perfusionists at our centre, to standardise the process and to provide the respective student with a "roadmap" to their internship. MATERIAL & METHODS: The structure is based on a rough division of the 24 weeks of internship. This is described in detail in the following and is backed up with the learning objectives for the respective time periods. RESULTS: At our centre, practical training has been standardized and clear responsibilities have been defined. Furthermore, as a centre of maximum care in the field of cardiac surgery, we can offer students the necessary number of perfusions in just six months to meet the requirements of the ECBP for practical training. According to this concept, 20 perfusionists have been successfully trained in the last 8 years. All of them have passed the exams and have been certified according to EBCP. CONCLUSION: The aim of the practical semester is for the student to be in a position at the end of the semester to independently supervise simple cardiac surgery procedures with the aid of the Extra- Corporal Circulation (ECC) and to carry this out in accordance with the currently valid guidelines and directives (1-8) and the departmental procedural instructions based on them. Great emphasis is placed to the students becoming aware of their competence to act, knowing their limits and being able to assess when these limits have been reached and the involvement of experienced colleagues is necessary to ensure patient safety.
ABSTRACT
BACKGROUND: In valvular open-heart surgery, data regarding the effect of a moderate dose of tranexamic acid (TXA) on clinical outcomes are limited. METHODS: Out of a cohort of 13,293 patients, we performed a propensity-score-matched analysis in 6,106 patients and assessed the risk of convulsive seizures (CS, primary endpoint), stroke, renal replacement therapy, and mortality (secondary endpoints). In the entire study cohort of 13,293 patients, we also assessed the multivariable-adjusted association of CS with postoperative outcomes. RESULTS: The risk of CS was significantly higher in the TXA group (2.4%; n = 72) than in the non-TXA group (1.0%; n = 32), with a relative risk ratio (RR) of 2.28 (95% confidence interval [CI]: 1.50-3.47; p < 0.001). The risk of CS was also higher in patients receiving TXA doses ≥25 mg/kg body weight (3.7%; n = 40) than in patients receiving <25 mg/kg body weight (1.6%; n = 32; p < 0.001). Perioperative secondary clinical endpoints and 1-year mortality did not differ significantly between study groups (p-value > 0.05). Compared with non-CS patients (n = 13,000), patients with nonhemorrhagic, nonembolic CS (n = 253) revealed higher multivariable-adjusted in-hospital risks of stroke (RR: 3.82 [95% CI: 2.44-5.60; p < 0.001]) and mortality (RR: 2.07 [95% CI: 1.23-3.48; p = 0.006]), and a higher 1-year mortality risk (RR: 1.85 [95% CI: 1.42-2.41; p < 0.001]). CONCLUSION: A moderate TXA dose was associated with a significantly higher risk of seizure, but not with other clinical complications such as stroke, renal replacement therapy, and mortality. However, in the small group of patients experiencing a seizure, the risks of stroke and short- and mid-term mortality were substantially higher than in patients not experiencing a seizure, indicating that the use of a low-dose TXA protocol (<25 mg/kg body weight) should be considered.
Subject(s)
Antifibrinolytic Agents , Cardiac Surgical Procedures , Stroke , Tranexamic Acid , Humans , Treatment Outcome , Seizures/chemically induced , Seizures/drug therapy , Body Weight , Blood Loss, SurgicalABSTRACT
BACKGROUND: Increasing evidence from randomised controlled trials supports the implementation of a six-measure care bundle proposed by the Kidney Disease Improving Global Outcomes (KDIGO) guidelines in patients at high risk for acute kidney injury (AKI) to reduce its incidence after cardiac surgery. OBJECTIVE: To assess compliance with the KDIGO bundle in clinical practice. DESIGN: Prospective observational multinational study. SETTING: Six international tertiary care centres, from February 2021 to November 2021. PATIENTS: Five hundred and thirty-seven consecutive patients undergoing cardiac surgery during a 1-month observational period. INTERVENTIONS: All patients were assessed for the postoperative implementation of the following measures: avoidance of nephrotoxic medication and radiocontrast agents whenever possible, strict glycaemic control, close monitoring of renal function, optimisation of haemodynamic and volume status and functional monitoring of haemodynamic status. MAIN OUTCOME MEASURES: The primary endpoint was the proportion of patients receiving fully compliant care. Secondary outcomes were occurrence of AKI and major adverse kidney event rate at day 30. RESULTS: The full care bundle was applied to 0.4% of patients. There was avoidance of nephrotoxic drugs in 15.6%, radiocontrast agents in 95.3% and hyperglycaemia in 39.6%. Close monitoring of urine output and serum creatinine was achieved in 6.3%, 57.4% underwent optimisation of volume and haemodynamic status, and 43.9% received functional haemodynamic monitoring. 27.2% developed AKI within 72âh after surgery. The average number of implemented measures was 2.6â±â1.0 and did not differ between AKI or non-AKI patients ( P â=â0.854). CONCLUSION: Adherence with the KDIGO bundle was very low in cardiac surgery patients. Initiatives to improve guideline compliance might provide a strategy to mitigate the burden of AKI. TRIAL REGISTRATION: www.drks.de DRKS00024204.
Subject(s)
Acute Kidney Injury , Cardiac Surgical Procedures , Humans , Acute Kidney Injury/diagnosis , Acute Kidney Injury/epidemiology , Acute Kidney Injury/etiology , Cardiac Surgical Procedures/adverse effects , Contrast Media , Kidney/physiology , Postoperative Complications/diagnosis , Postoperative Complications/epidemiology , Postoperative Complications/etiology , Prospective StudiesABSTRACT
INTRODUCTION: No antidote or established extracorporeal elimination strategy is available for argatroban. Hemadsorption facilitates elimination of smaller drugs. CASE REPORT: A 34-year-old patient underwent urgent heart transplantation. Because of a history of heparin-induced thrombocytopenia, preoperative anticoagulation was performed with argatroban. Despite ceasing of the continuous infusion of argatroban 2 h before surgery, concentration only declined from 0.60 µg/ml to 0.58 µg/ml before surgery, and the activated clotting time (ACT) value shortly was 223 s. Microvascular bleeding had been observed when starting surgery. A CytoSorb® absorption column was integrated into the system of the heparin-anticoagulated cardiopulmonary bypass (CPB) circuit and a flow of 400 mL/min provided during the 2 h of extracorporeal circulation. The argatroban concentration after weaning from CPB was 0.04 µg/ml and satisfying hemostasis had been achieved after protamine administration. CONCLUSION: Data indicate that the CytoSorb® absorption column might be an effective tool for quick extracorporeal removal of therapeutic concentrations of argatroban.
Subject(s)
Anticoagulants , Heart Transplantation , Humans , Adult , Anticoagulants/therapeutic use , Cardiopulmonary Bypass , Heparin/therapeutic use , ArginineABSTRACT
BACKGROUND: Compared with coronary artery bypass grafting surgery, data regarding postoperative delirium are scant in valvular open-heart surgery. Therefore, the goal of this retrospective study was to investigate the incidence, preoperative risk factors, and early outcomes of delirium in a large group of patients undergoing valvular open-heart surgery. METHODS: In 13,229 patients with isolated valvular or combined valvular and bypass surgery, the incidence of postoperative delirium was assessed until discharge. Independent risk factors of delirium were evaluated by multivariable logistic regression analysis. Moreover, we assessed the multivariable-adjusted risk of prolonged intensive care unit (ICU) stay (>48 hours) and in-hospital mortality in patients with delirium. RESULTS: Overall, the incidence of postoperative delirium was 8.4%. The incidence in patients experiencing a postoperative stroke or seizure was 23.1 and 29.7%, respectively. Twelve preoperative risk factors, mostly nonmodifiable, were independently associated with the risk of delirium, including advanced age, renal impairment, stroke, the need for emergency surgery, and severe preoperative anemia (hemoglobin < 9 g/dL). Postoperative delirium was associated with an adjusted odds ratio (OR) of prolonged ICU stay of 9.48 (95% confidence interval [CI]: 7.96-11.30). Adjusted in-hospital mortality was, however, significantly lower in patients with delirium versus patients without delirium (OR, 0.56; 95% CI: 0.38-0.83). CONCLUSION: In valvular open-heart surgery, postoperative delirium is a frequent neurological complication that is associated with other postoperative neurological complications and several, mostly nonmodifiable, preoperative risk factors. Although postoperative delirium was associated with a significantly increased risk of prolonged ICU stay, this did not translate into an increased short-term mortality.
Subject(s)
Cardiac Surgical Procedures , Delirium , Stroke , Cardiac Surgical Procedures/adverse effects , Delirium/diagnosis , Delirium/epidemiology , Delirium/etiology , Hemoglobins , Humans , Length of Stay , Postoperative Complications/epidemiology , Postoperative Complications/etiology , Retrospective Studies , Risk Factors , Stroke/etiology , Treatment OutcomeABSTRACT
We investigated whether in patients undergoing off-pump coronary artery bypass grafting surgery a single bolus of 1 g tranexamic acid (TXA) impacts the risk of postoperative delirium using the propensity score matching approach. In 2,757 pairs, the risk of delirium was 4.2% (TXA group) and 5.0% (non-TXA group), with a relative risk in the TXA versus the non-TXA group of 0.83 (95% confidence interval: 0.65-1.07; p = 0.16). There was no significant interaction between TXA administration and renal function on the risk of delirium (p = 0.12). Data indicate that a single bolus of 1 g TXA does not increase the risk of delirium in patients undergoing off-pump surgery.
ABSTRACT
Pediatric cardiac anesthesia is a subspecialty of cardiac and pediatric anesthesiology dedicated to the perioperative care of patients with congenital heart disease. Members of the Congenital and Education Subcommittees of the European Association of Cardiothoracic Anaesthesiology and Intensive Care (EACTAIC) agreed on the necessity to develop an EACTAIC pediatric cardiac anesthesia fellowship curriculum. This manuscript represents a consensus on the composition and the design of the EACTAIC Pediatric Cardiac Anesthesia Fellowship program. This curriculum provides a basis for the training of future pediatric cardiac anesthesiologists by clearly defining the theoretical and practical requirements for fellows and host centers.
Subject(s)
Anesthesia, Cardiac Procedures , Anesthesiology , Anesthesiology/education , Child , Critical Care , Curriculum , Fellowships and Scholarships , HumansABSTRACT
BACKGROUND: Machine learning algorithms are currently used in a wide array of clinical domains to produce models that can predict clinical risk events. Most models are developed and evaluated with retrospective data, very few are evaluated in a clinical workflow, and even fewer report performances in different hospitals. In this study, we provide detailed evaluations of clinical risk prediction models in live clinical workflows for three different use cases in three different hospitals. OBJECTIVE: The main objective of this study was to evaluate clinical risk prediction models in live clinical workflows and compare their performance in these setting with their performance when using retrospective data. We also aimed at generalizing the results by applying our investigation to three different use cases in three different hospitals. METHODS: We trained clinical risk prediction models for three use cases (ie, delirium, sepsis, and acute kidney injury) in three different hospitals with retrospective data. We used machine learning and, specifically, deep learning to train models that were based on the Transformer model. The models were trained using a calibration tool that is common for all hospitals and use cases. The models had a common design but were calibrated using each hospital's specific data. The models were deployed in these three hospitals and used in daily clinical practice. The predictions made by these models were logged and correlated with the diagnosis at discharge. We compared their performance with evaluations on retrospective data and conducted cross-hospital evaluations. RESULTS: The performance of the prediction models with data from live clinical workflows was similar to the performance with retrospective data. The average value of the area under the receiver operating characteristic curve (AUROC) decreased slightly by 0.6 percentage points (from 94.8% to 94.2% at discharge). The cross-hospital evaluations exhibited severely reduced performance: the average AUROC decreased by 8 percentage points (from 94.2% to 86.3% at discharge), which indicates the importance of model calibration with data from the deployment hospital. CONCLUSIONS: Calibrating the prediction model with data from different deployment hospitals led to good performance in live settings. The performance degradation in the cross-hospital evaluation identified limitations in developing a generic model for different hospitals. Designing a generic process for model development to generate specialized prediction models for each hospital guarantees model performance in different hospitals.
Subject(s)
Electronic Health Records , Machine Learning , Hospitals , Humans , ROC Curve , Retrospective StudiesABSTRACT
In this prospective observational pilot study patients with the diagnosis of end-stage lung disease and listed for lung transplantation underwent a cognitive function test battery before and after lung transplantation to investigate postoperative cognitive function in three domains (visual and verbal memory, executive functioning, concentration/speed of processing). Additionally we investigated intraoperative risk factors for postoperative cognitive dysfunction. In total, 24 patients were included in this pilot study. The incidence of postoperative cognitive dysfunction was 58.3%. In the cognitive dysfunction group, the domains executive functioning and concentration/attention were significantly impaired whereas memory was not affected. Patients with cognitive impairment had a significantly longer ICU stay. The strongest independent risk factor for the development of cognitive dysfunction was operation time. No influence of cerebral oxygen desaturations on cognitive dysfunction was found. This might have important implications for early psychological rehabilitation strategies in this high-risk patient collective.
Subject(s)
Lung Transplantation , Postoperative Cognitive Complications , Cognition , Executive Function , Humans , Lung Transplantation/adverse effects , Neuropsychological Tests , Pilot Projects , Prospective StudiesABSTRACT
PURPOSE OF REVIEW: Preoperative evaluation of older and more morbid patients in thoracic surgery is getting more advanced. In this context, early risk stratification has a crucial role for adequate informed decision-making, and thus for generating favourable effects of clinical outcome. RECENT FINDINGS: Recent findings confirm that many risk factors impair mortality and morbidity beyond classical medical findings like results of lung function tests and values of the revised cardiac risk index. Especially results from holistic views on patients' functional status like frailty assessments are linked with long-term survival after lung resection. SUMMARY: A comprehensive risk stratification by anaesthesiologists generates valuable guidance for the best strategy of clinical treatment. This includes preoperative, peri-operative and postoperative interventions, provided by interdisciplinary healthcare providers, resulting in an Early Risk Stratification and Strategy ('ERSAS') pathway.
Subject(s)
Frailty , Thoracic Surgery , Thoracic Surgical Procedures , Humans , Postoperative Complications/diagnosis , Postoperative Complications/epidemiology , Postoperative Complications/therapy , Preoperative Care , Risk Assessment , Risk Factors , Thoracic Surgical Procedures/adverse effectsABSTRACT
Objectives: This work aims to evaluatecomprehensive geriatric assessment (CGA) tools to better guide patients with urogenital carcinomas perioperatively and, consequently, to intensify or reduce hospital resource use. Methods: After informed consent, 111patients were included, all aged more than 65 years, with oncological surgery (with proof of a malignancy), a Mini Mental State Examination (MMSE) score of at least 23 points, and a prospective life expectancy of more than 2 months. Patients were divided into 2 groups: prostate cancer (n = 88) and distal urinary tract cancer (n = 29). Further CGA tools were Instrumental Activities of Daily Living (iADL), Activities of Daily Living (ADL), and the Charlson Comorbidity Index (CCI). The relationships between CGA and complications, hospital duration, death rate, and baseline characteristics were analyzed. Results: In comparison with the patients with prostate cancer, those with kidney/distal urinary tract cancer had higher CCI scores (median, 3 vs 2; P <.001), MMSE scores (29 vs 28; P = .031), complication rates (55.2% vs 22.0%; P = .001), and hospital duration (16 vs 10 days; P <.001), as well as more deaths in the group (8 vs 0). Comorbidities (6 vs 2; P <.001), Physical Status Classification System (ASA state [3 vs 2; P <.001]), and median age (74 vs 71 years; P =.008) were all higher in the kidney/distal urinary tract group, and they had fewer problems with postoperative ADL items, which were significantly lower than those of the prostate group (P = .043). Intra- and intergroup comparisons of preoperative and 1-year ADL/iADL values did not differ significantly. Conclusion: These study results underscore the importance of CGA in patients with genitourinary carcinoma; most patients have high regenerative potential. Patients with kidney/distal urinary tract cancers are older, have more comorbidities, and have more postoperative impairments than patients with prostate cancer.
Subject(s)
Geriatric Assessment , Urogenital Neoplasms/surgery , Activities of Daily Living , Aged , Aged, 80 and over , Humans , Length of StayABSTRACT
OBJECTIVE: Machine learning (ML) algorithms are now widely used in predicting acute events for clinical applications. While most of such prediction applications are developed to predict the risk of a particular acute event at one hospital, few efforts have been made in extending the developed solutions to other events or to different hospitals. We provide a scalable solution to extend the process of clinical risk prediction model development of multiple diseases and their deployment in different Electronic Health Records (EHR) systems. MATERIALS AND METHODS: We defined a generic process for clinical risk prediction model development. A calibration tool has been created to automate the model generation process. We applied the model calibration process at four hospitals, and generated risk prediction models for delirium, sepsis and acute kidney injury (AKI) respectively at each of these hospitals. RESULTS: The delirium risk prediction models have on average an area under the receiver-operating characteristic curve (AUROC) of 0.82 at admission and 0.95 at discharge on the test datasets of the four hospitals. The sepsis models have on average an AUROC of 0.88 and 0.95, and the AKI models have on average an AUROC of 0.85 and 0.92, at the day of admission and discharge respectively. DISCUSSION: The scalability discussed in this paper is based on building common data representations (syntactic interoperability) between EHRs stored in different hospitals. Semantic interoperability, a more challenging requirement that different EHRs share the same meaning of data, e.g. a same lab coding system, is not mandated with our approach. CONCLUSIONS: Our study describes a method to develop and deploy clinical risk prediction models in a scalable way. We demonstrate its feasibility by developing risk prediction models for three diseases across four hospitals.
Subject(s)
Electronic Health Records , Machine Learning , Hospitalization , Hospitals , Humans , ROC CurveABSTRACT
BACKGROUND: The scientific working group for "Anaesthesia in thoracic surgery" of the German Society of Anaesthesiology and Intensive Care Medicine (DGAI) has performed an online survey to assess the current standards of care and structural properties of anaesthesia workstations in thoracic surgery. METHODS: All members of the European Society of Anaesthesiology (ESA) were invited to participate in the study. RESULTS: Thoracic anaesthesia was most commonly performed by specialists/board-certified anaesthetists and/or senior/attending physicians. Across Europe, the double lumen tube (DLT) was most commonly chosen as the primary device for lung separation (461/ 97.3%). Bronchial blockers were chosen less frequently (9/ 1.9%). Throughout Europe, bronchoscopy was not consistently used to confirm correct double lumen tube positioning. Respondents from Eastern Europe (32/ 57.1%) frequently stated that there were not enough bronchoscopes available for every intrathoracic operation. A specific algorithm for difficult airway management in thoracic anaesthesia was available to only 18.6% (n = 88) of the respondents. Thoracic epidural analgesia (TEA) is the most commonly used form of regional analgesia for thoracic surgery in Europe. Ultrasonography was widely available 93,8% (n = 412) throughout Europe and was predominantly used for central line placement and lung diagnostics. CONCLUSIONS: While certain "gold standards "are widely met, there are also aspects of care requiring substantial improvement in thoracic anaesthesia throughout Europe. Our data suggest that algorithms and standard operating procedures for difficult airway management in thoracic anaesthesia need to be established. A European recommendation for the basic requirements of an anaesthesia workstation for thoracic anaesthesia is expedient and desirable, to improve structural quality and patient safety.
Subject(s)
Airway Management/statistics & numerical data , Anesthesia, Conduction/statistics & numerical data , Anesthesiology/statistics & numerical data , Airway Management/methods , Algorithms , Anesthesiology/methods , Bronchoscopy/statistics & numerical data , Cross-Sectional Studies , Europe , Health Care Surveys , Humans , Thoracic Surgical Procedures/methods , Thoracic Surgical Procedures/statistics & numerical dataABSTRACT
Postoperative delirium is associated with worse outcome. The aim of this study was to understand present strategies for delirium screening and therapy in German Post-Anesthesia-Caring-Units (PACU). We designed a German-wide web-based questionnaire which was sent to 922 chairmen of anesthesiologic departments and to 726 anesthetists working in ambulatory surgery. The response rate was 30% for hospital anesthesiologists. 10% (95%-confidence interval: 8-12) of the anesthesiologists applied a standardised screening for delirium. Even though not on a regular basis, in 44% (41-47) of the hospitals, a recommended and validated screening was used, the Nursing Delirium Screening Scale (NuDesc) or the Confusion Assessment Method for the Intensive Care Unit (CAM-ICU). If delirium was likely to occur, 46% (43-50) of the patients were examined using a delirium tool. 20% (17-23) of the patients were screened in intensive care units. For the treatment of delirium, alpha-2-agonists (83%, 80-85) were used most frequently for vegetative symptoms, benzodiazepines for anxiety in 71% (68-74), typical neuroleptics in 77% (71-82%) of patients with psychotic symptoms and in 20% (15-25) in patients with hypoactive delirium. 45% (39-51) of the respondents suggested no therapy for this entity. Monitoring of delirium is not established as a standard procedure in German PACUs. However, symptom-oriented therapy for postoperative delirium corresponds with current guidelines.