Automated detection and classification of patient-ventilator asynchrony by means of machine learning and simulated data.

BACKGROUND AND OBJECTIVE: Mechanical ventilation is a lifesaving treatment for critically ill patients in an Intensive Care Unit (ICU) or during surgery. However, one potential harm of mechanical ventilation is related to patient-ventilator asynchrony (PVA). PVA can cause discomfort to the patient, damage to the lungs, and an increase in the length of stay in the ICU and on the ventilator. Therefore, automated detection algorithms are being developed to detect and classify PVAs, with the goal of optimizing mechanical ventilation. However, the development of these algorithms often requires large labeled datasets; these are generally difficult to obtain, as their collection and labeling is a time-consuming and labor-intensive task, which needs to be performed by clinical experts. METHODS: In this work, we aimed to develop a computer algorithm for the automatic detection and classification of PVA. The algorithm employs a neural network for the detection of the breath of the patient. The development of the algorithm was aided by simulations from a recently published model of the patient-ventilator interaction. RESULTS: The proposed method was effective, providing an algorithm with reliable detection and classification results of over 90% accuracy. Besides presenting a detection and classification algorithm for a variety of PVAs, here we show that using simulated data in combination with clinical data increases the variability in the training dataset, leading to a gain in performance and generalizability. CONCLUSIONS: In the future, these algorithms can be utilized to gain a better understanding of the clinical impact of PVAs and help clinicians to better monitor their ventilation strategies.

Advanced Practice Providers as Leaders of a Rapid Response Team: A Prospective Cohort Study.

In view of the shortage of medical staff, the quality and continuity of care may be improved by employing advanced practice providers (APPs). This study aims to assess the quality of these APPs in critical care. In a large teaching hospital, rapid response team (RRT) interventions led by APPs were assessed by independent observers and intensivists and compared to those led by medical residents MRs. In addition to mortality, the MAELOR tool (assessment of RRT intervention), time from RRT call until arrival at the scene and time until completion of clinical investigations were assessed. Process outcomes were assessed with the crisis management skills checklist, the Ottawa global rating scale and the Mayo high-performance teamwork scale. The intensivists assessed performance with the handoff CEX recipient scale. Mortality, MAELOR tool, time until arrival and clinical investigation in both groups were the same. Process outcomes and performance observer scores were also equal. The CEX recipient scores, however, showed differences between MRs and APPs that increased with experience. Experienced APPs had significantly better situational awareness, better organization, better evaluations and better judgment than MRs with equal experience (p < 0.05). This study shows that APPs perform well in leading an RRT and may provide added quality over a resident. RRTs should seriously consider the deployment of APPs instead of junior clinicians.

Advanced practice providers versus medical residents as leaders of rapid response teams: A 12-month retrospective analysis.

PURPOSE: In a time of worldwide physician shortages, the advanced practice providers (APPs) might be a good alternative for physicians as the leaders of a rapid response team. This retrospective analysis aimed to establish whether the performance of APP-led rapid response teams is comparable to the performance of rapid response teams led by a medical resident of the ICU. MATERIAL AND METHODS: In a retrospective single-center cohort study, the electronic medical record of a tertiary hospital was queried during a 12-months period to identify patients who had been visited by our rapid response team. Patient- and process-related outcomes of interventions of rapid response teams led by an APP were compared with those of teams led by a medical resident using various parameters, including the MAELOR tool, which measures the performance of a rapid response team. RESULTS: In total, 179 responses of the APP-led teams were analyzed, versus 275 responses of the teams led by a resident. Per APP, twice as many calls were handled than per resident. Interventions of teams led by APPs, and residents did not differ in number of admissions (p = 0.87), mortality (p = 0.8), early warning scores (p = 0.2) or MAELOR tool triggering (p = 0.19). Both groups scored equally on time to admission (p = 0.67) or time until any performed intervention. CONCLUSION: This retrospective analysis showed that the quality of APP-led rapid response teams was similar to the quality of teams led by a resident. These findings need to be confirmed by prospective studies with balanced outcome parameters.

Effect of Automated Closed-loop ventilation versus convenTional VEntilation on duration and quality of ventilation in critically ill patients (ACTiVE) - study protocol of a randomized clinical trial.

BACKGROUND: INTELLiVENT-Adaptive Support Ventilation (ASV) is a fully automated closed-loop mode of ventilation for use in critically ill patients. Evidence for benefit of INTELLiVENT-ASV in comparison to ventilation that is not fully automated with regard to duration of ventilation and quality of breathing is largely lacking. We test the hypothesis that INTELLiVENT-ASV shortens time spent on a ventilator and improves the quality of breathing. METHODS: The "Effects of Automated Closed-loop VenTilation versus Conventional Ventilation on Duration and Quality of Ventilation" (ACTiVE) study is an international, multicenter, two-group randomized clinical superiority trial. In total, 1200 intensive care unit (ICU) patients with an anticipated duration of ventilation of > 24 h will be randomly assigned to one of the two ventilation strategies. Investigators screen patients aged 18 years or older at start of invasive ventilation in the ICU. Patients either receive automated ventilation by means of INTELLiVENT-ASV, or ventilation that is not automated by means of a conventional ventilation mode. The primary endpoint is the number of days free from ventilation and alive at day 28; secondary endpoints are quality of breathing using granular breath-by-breath analysis of ventilation parameters and variables in a time frame of 24 h early after the start of invasive ventilation, duration of ventilation in survivors, ICU and hospital length of stay (LOS), and mortality rates in the ICU and hospital, and at 28 and 90 days. DISCUSSION: ACTiVE is one of the first randomized clinical trials that is adequately powered to compare the effects of automated closed-loop ventilation versus conventional ventilation on duration of ventilation and quality of breathing in invasively ventilated critically ill patients. The results of ACTiVE will support intensivist in their choices regarding the use of automated ventilation. TRIAL REGISTRATION: ACTiVE is registered in clinicaltrials.gov (study identifier: NCT04593810 ) on 20 October 2020.

Diagnostic performance of echocardiography to predict cardiac tamponade after cardiac surgery.

OBJECTIVES: Cardiac tamponade is a life-threatening complication after cardiac surgery. Echocardiography, both transthoracic (TTE) and transesophageal (TEE), may help to identify cardiac tamponade after surgery, but its diagnostic value remains unverified after cardiac surgery. METHODS: This retrospective single-centre cohort study used the electronic medical record and echocardiography database of the Catharina Hospital Eindhoven, a tertiary referral cardiothoracic centre, to identify patients who received echocardiography because they were clinically suspected of having cardiac tamponade within the 4 weeks after cardiac surgery. Overall diagnostic accuracy of both TTE and TEE was calculated (sensitivity, specificity, positive predictive value, negative predictive value, and receiver operation characteristics curves). Subgroup analyses were performed based on the timing of the echocardiography after primary surgery (<24, 24-72, >72 h). RESULTS: The query identified 427 echocardiographs, 373 TTEs and 54 TEEs, being performed in 414 patients (65% males, mean age 67 years). Of them, 116 patients underwent surgical re-exploration in which a cardiac tamponade was determined in 105 patients with a 30-day mortality of 8.6%. The area under the receiver operation characteristics curve for echocardiography in the 4 weeks after cardiac surgery was 0.78 [95% confidence interval (CI): 0.72-0.84, P < 0.001]. In the first 24 h after surgery was the positive predictive value of echocardiography 58.3% (95% CI: 28.6-83.5) with an area under the curve of 0.64 (95% CI: 0.49-0.80, P = 0.06). The diagnostic accuracy improved over time for both TTE and TEE. CONCLUSIONS: Diagnostic accuracy of echocardiography in the 4 weeks after cardiac surgery for cardiac tamponade is acceptable and improves over time. However, in the early postoperative phase (<24 h), the diagnostic accuracy of echocardiography is poor.

Intelligent checklists improve checklist compliance in the intensive care unit: a prospective before-and-after mixed-method study.

BACKGROUND: We examined whether a context and process-sensitive 'intelligent' checklist increases compliance with best practice compared with a paper checklist during intensive care ward rounds. METHODS: We conducted a single-centre prospective before-and-after mixed-method trial in a 35 bed medical and surgical ICU. Daily ICU ward rounds were observed during two periods of 8 weeks. We compared paper checklists (control) with a dynamic (digital) clinical checklist (DCC, intervention). The primary outcome was compliance with best clinical practice, measured as the percentages of checked items and unchecked critical items. Secondary outcomes included ICU stay and the usability of digital checklists. Data are presented as median (interquartile range). RESULTS: Clinical characteristics and severity of critical illness were similar during both control and intervention periods of study. A total of 36 clinicians visited 197 patients during 352 ward rounds using the paper checklist, compared with 211 patients during 366 ward rounds using the DCC. Per ICU round, a median of 100% of items (94.4-100.0) were completed by DCC, compared with 75.1% (66.7-86.4) by paper checklist (P=0.03). No critical items remained unchecked by the DCC, compared with 15.4% (8.3-27.3) by the paper checklist (P=0.01). The DCC was associated with reduced ICU stay (1 day [1-3]), compared with the paper checklist (2 days [1-4]; P=0.05). Usability of the DCC was judged by clinicians to require further improvement. CONCLUSIONS: A digital checklist improved compliance with best clinical practice, compared with a paper checklist, during ward rounds on a mixed ICU. CLINICAL TRIAL REGISTRATION: NCT03599856.

Fully automated postoperative ventilation in cardiac surgery patients: a randomised clinical trial.

BACKGROUND: Ensuring that lung-protective ventilation is achieved at scale is challenging in perioperative practice. Fully automated ventilation may be more effective in delivering lung-protective ventilation. Here, we compared automated lung-protective ventilation with conventional ventilation after elective cardiac surgery in haemodynamically stable patients. METHODS: In this single-centre investigator-led study, patients were randomly assigned at the end of cardiac surgery to receive either automated (adaptive support ventilation) or conventional ventilation. The primary endpoint was the proportion of postoperative ventilation time characterised by exposure to predefined optimal, acceptable, and critical (injurious) ventilatory parameters in the first three postoperative hours. Secondary outcomes included severe hypoxaemia (Spo2 <85%) and resumption of spontaneous breathing. Data are presented as mean (95% confidence intervals [CIs]). RESULTS: We randomised 220 patients (30.4% females; age: 62-76 yr). Subjects randomised to automated ventilation (n=109) spent a 29.7% (95% CI: 22.1-37.4) higher mean proportion of postoperative ventilation time receiving optimal postoperative ventilation after surgery (P<0.001) compared with subjects receiving conventional postoperative ventilation (n=111). Automated ventilation also reduced the proportion of postoperative ventilation time that subjects were exposed to injurious ventilatory settings by 2.5% (95% CI: 1-4; P=0.003). Severe hypoxaemia was less likely in subjects randomised to automated ventilation (risk ratio: 0.26 [0.22-0.31]; P<0.01). Subjects resumed spontaneous breathing more rapidly when randomised to automated ventilation (hazard ratio: 1.38 [1.05-1.83]; P=0.03). CONCLUSIONS: Fully automated ventilation in haemodynamically stable patients after cardiac surgery optimised lung-protective ventilation during postoperative ventilation, with fewer episodes of severe hypoxaemia and an accelerated resumption of spontaneous breathing. CLINICAL TRIAL REGISTRATION: NCT03180203.

Identify Facilitators and Challenges in Computerized Checklist Implementation.

Safety checklists have been considered as a promising tool for improving patient safety for decades. Computerized checklists have better performance compared with paper-based checklists, though there are barriers to their adoption. Given previous literature, it is still unclear what assists implementations and their challenges. To address this issue, this paper summarizes the implementation of two successful computerized checklist implementations in two countries for two different clinical scenarios and analyzes their facilitators and challenges.

Implementation of an automated early warning scoring system in a surgical ward: Practical use and effects on patient outcomes.

INTRODUCTION: Early warning scores (EWS) are being increasingly embedded in hospitals over the world due to their promise to reduce adverse events and improve the outcomes of clinical patients. The aim of this study was to evaluate the clinical use of an automated modified EWS (MEWS) for patients after surgery. METHODS: This study conducted retrospective before-and-after comparative analysis of non-automated and automated MEWS for patients admitted to the surgical high-dependency unit in a tertiary hospital. Operational outcomes included number of recorded assessments of the individual MEWS elements, number of complete MEWS assessments, as well as adherence rate to related protocols. Clinical outcomes included hospital length of stay, in-hospital and 28-day mortality, and ICU readmission rate. RESULTS: Recordings in the electronic medical record from the control period contained 7929 assessments of MEWS elements and were performed in 320 patients. Recordings from the intervention period contained 8781 assessments of MEWS elements in 273 patients, of which 3418 were performed with the automated EWS system. During the control period, 199 (2.5%) complete MEWS were recorded versus 3991 (45.5%) during intervention period. With the automated MEWS systems, the percentage of missing assessments and the time until the next assessment for patients with a MEWS of ≥2 decreased significantly. The protocol adherence improved from 1.1% during the control period to 25.4% when the automated MEWS system was involved. There were no significant differences in clinical outcomes. CONCLUSION: Implementation of an automated EWS system on a surgical high dependency unit improves the number of complete MEWS assessments, registered vital signs, and adherence to the EWS hospital protocol. However, this positive effect did not translate into a significant decrease in mortality, hospital length of stay, or ICU readmissions. Future research and development on automated EWS systems should focus on data management and technology interoperability.

Impact of the Advanced Practice Provider in Adult Critical Care: A Systematic Review and Meta-Analysis.

OBJECTIVES: To evaluate the effects on quality and efficiency of implementation of the advanced practice provider in critical care. DATA SOURCES: PubMed, Embase, The Cochrane Library, and CINAHL were used to extract articles regarding advanced practice providers in critical care. STUDY SELECTION: Articles were selected when reporting a comparison between advanced practice providers and physician resident/fellows regarding the outcome measures of mortality, length of stay, or specific tasks. Descriptive studies without comparison were excluded. The methodological quality of the included studies was rated using the Newcastle-Ottawa scale. The agreement between the reviewers was assessed with Cohen's kappa. A meta-analysis was constructed on mortality and length of stay. DATA EXTRACTION AND SYNTHESIS: One-hundred fifty-six studies were assessed by full text. Thirty comparative cohort studies were selected and analyzed. These compared advanced practice providers with physician resident/fellows. All studies comprised adult intensive care. Most of the included studies showed a moderate to good quality. Over time, the study designs advanced from retrospective designs to include prospective and comparative designs. DATA SYNTHESIS: Four random effects meta-analyses on length of stay and mortality were constructed from the available studies. These meta-analyses showed no significant difference between performance of advanced practice providers on the ICU and physician residents/fellows on the ICU, suggesting the quality of care of both groups was equal. Mean difference for length of stay on the ICU was 0.34 (95% CI, -0.31 to 1.00; I = 99%) and for in hospital length of stay 0.02 (95% CI, -0.85 to 0.89; I = 91%); whereas the odds ratio for ICU mortality was 0.98 (95% CI, 0.81-1.19; I = 37.3%) and for hospital mortality 0.92 (95% CI, 0.79-1.07; I = 28%). CONCLUSIONS: This review and meta-analysis shows no differences between acute care given by advanced practice providers compared with physician resident/fellows measured as length of stay or mortality. However, advanced practice providers might add value to care in several other ways, but this needs further study.

Crisis checklists for in-hospital emergencies: expert consensus, simulation testing and recommendations for a template determined by a multi-institutional and multi-disciplinary learning collaborative.

BACKGROUND: 'Failure to rescue' of hospitalized patients with deteriorating physiology on general wards is caused by a complex array of organisational, technical and cultural failures including a lack of standardized team and individual expected responses and actions. The aim of this study using a learning collaborative method was to develop consensus recomendations on the utility and effectiveness of checklists as training and operational tools to assist in improving the skills of general ward staff on the effective rescue of patients with abnormal physiology. METHODS: A scoping study of the literature was followed by a multi-institutional and multi-disciplinary international learning collaborative. We sought to achieve a consensus on procedures and clinical simulation technology to determine the requirements, develop and test a safe using a checklist template that is rapidly accessible to assist in emergency management of common events for general ward use. RESULTS: Safety considerations about deteriorating patients were agreed upon and summarized. A consensus was achieved among an international group of experts on currently available checklist formats performing poorly in simulation testing as first responders in general ward clinical crises. The Crisis Checklist Collaborative ratified a consensus template for a general ward checklist that provides a list of issues for first responders to address (i.e. 'Check In'), a list of prompts regarding common omissions (i.e. 'Stop & Think'), and, a list of items required for the safe "handover" of patients that remain on the general ward (i.e. 'Check Out'). Simulation usability assessment of the template demonstrated feasibility for clinical management of deteriorating patients. CONCLUSIONS: Emergency checklists custom-designed for general ward patients have the potential to guide the treatment speed and reliability of responses for emergency management of patients with abnormal physiology while minimizing the risk of adverse events. Interventional trials are needed.

The correlation of age with chemotherapy-induced ovarian function failure in breast cancer patients.

PURPOSE: To assess the incidence of chemotherapy-induced ovarian function failure (COFF) based on estradiol and follicle stimulating hormone (FSH) monitoring in premenopausal women with hormone-receptor positive breast cancer treated with second and third generation (neo-)adjuvant chemotherapy. RESULTS: We identified 115 eligible women. Two years after start of chemotherapy, COFF was significantly more often present in women ≥ 40 years (85.6%) as compared to women < 40 years (8.7%). Only age was significantly associated with COFF two years after start of chemotherapy (HR 12.26; 95% CI 5.21-28.86). In 50% of the patients, premenopausal hormone levels were the first or only evidence of ovarian function recovery (OFR). MATERIALS AND METHODS: We included all premenopausal women with hormone-receptor positive breast cancer treated with anthracycline-based chemotherapy, with or without taxanes, in our university hospital in the Netherlands in the years 2005-2013. Patients were 3-monthly monitored for ovarian function. Cox proportional hazards model was used to determine the predictive impact of various parameters on the occurrence of COFF. CONCLUSIONS: After second- or third generation (neo-)adjuvant chemotherapy, COFF was still present in 8.7% of patients < 40 years after two years. FSH and estradiol monitoring may be relevant for those in whom ovarian function suppression is considered an additional effective endocrine treatment.