A vision-language foundation model for the generation of realistic chest X-ray images.

The paucity of high-quality medical imaging datasets could be mitigated by machine learning models that generate compositionally diverse images that faithfully represent medical concepts and pathologies. However, large vision-language models are trained on natural images, and the diversity distribution of the generated images substantially differs from that of medical images. Moreover, medical language involves specific and semantically rich vocabulary. Here we describe a domain-adaptation strategy for large vision-language models that overcomes distributional shifts. Specifically, by leveraging publicly available datasets of chest X-ray images and the corresponding radiology reports, we adapted a latent diffusion model pre-trained on pairs of natural images and text descriptors to generate diverse and visually plausible synthetic chest X-ray images (as confirmed by board-certified radiologists) whose appearance can be controlled with free-form medical text prompts. The domain-adaptation strategy for the text-conditioned synthesis of medical images can be used to augment training datasets and is a viable alternative to the sharing of real medical images for model training and fine-tuning.

Accuracy of Prehospital Triage of Adult Patients With Traumatic Injuries Following Implementation of a Trauma Triage Intervention.

Importance: Adequate prehospital triage is pivotal to enable optimal care in inclusive trauma systems and reduce avoidable mortality, lifelong disabilities, and costs. A model has been developed to improve the prehospital allocation of patients with traumatic injuries and was incorporated in an application (app) to be implemented in prehospital practice. Objective: To evaluate the association between the implementation of a trauma triage (TT) intervention with an app and prehospital mistriage among adult trauma patients. Design, Setting, and Participants: This population-based, prospective quality improvement study was conducted in 3 of the 11 Dutch trauma regions (27.3%), with full coverage of the corresponding emergency medical services (EMS) regions participating in this study. Participants included adult patients (age ≥16 years) with traumatic injuries who were transported by ambulance between February 1, 2015, and October 31, 2019, from the scene of injury to any emergency department in the participating trauma regions. Data were analyzed between July 2020 and June 2021. Exposures: Implementation of the TT app and the awareness of need for adequate triage created by its implementation (ie, the TT intervention). Main Outcomes and Measures: The primary outcome was prehospital mistriage, evaluated in terms of undertriage and overtriage. Undertriage was defined as the proportion of patients with an Injury Severity Score (ISS) of 16 or greater who were initially transported to a lower-level trauma center (designated to treat patients who are mildly and moderately injured) and overtriage as the proportion of patients with an ISS of less than 16 who were initially transported to a higher-level trauma center (designated to treat patients who are severely injured). Results: A total of 80 738 patients were included (40 427 [50.1%] before and 40 311 [49.9%] after implementation of the intervention), with a median (IQR) age of 63.2 (40.0-79.7) years and 40 132 (49.7%) male patients. Undertriage decreased from 370 of 1163 patients (31.8%) to 267 of 995 patients (26.8%), while overtriage rates did not increase (8202 of 39 264 patients [20.9%] vs 8039 of 39 316 patients [20.4%]). The implementation of the intervention was associated with a statistically significantly reduced risk for undertriage (crude risk ratio [RR], 0.95; 95% CI, 0.92 to 0.99, P = .01; adjusted RR, 0.85; 95% CI, 0.76-0.95; P = .004), but the risk for overtriage was unchanged (crude RR, 1.00; 95% CI, 0.99-1.00; P = .13; adjusted RR, 1.01; 95% CI, 0.98-1.03; P = .49). Conclusions and Relevance: In this quality improvement study, implementation of the TT intervention was associated with improvements in rates of undertriage. Further research is needed to assess whether these findings are generalizable to other trauma systems.

Short-term and Long-term Outcomes of a Disruption and Disconnection of the Pancreatic Duct in Necrotizing Pancreatitis: A Multicenter Cohort Study in 896 Patients.

INTRODUCTION: Necrotizing pancreatitis may result in a disrupted or disconnected pancreatic duct (DPD) with the potential for long-lasting negative impact on a patient's clinical outcome. There is a lack of detailed data on the full clinical spectrum of DPD, which is critical for the development of better diagnostic and treatment strategies. METHODS: We performed a long-term post hoc analysis of a prospectively collected nationwide cohort of 896 patients with necrotizing pancreatitis (2005-2015). The median follow-up after hospital admission was 75 months (P25-P75: 41-151). Clinical outcomes of patients with and without DPD were compared using regression analyses, adjusted for potential confounders. Predictive features for DPD were explored. RESULTS: DPD was confirmed in 243 (27%) of the 896 patients and resulted in worse clinical outcomes during both the patient's initial admission and follow-up. During hospital admission, DPD was associated with an increased rate of new-onset intensive care unit admission (adjusted odds ratio [aOR] 2.52; 95% confidence interval [CI] 1.62-3.93), new-onset organ failure (aOR 2.26; 95% CI 1.45-3.55), infected necrosis (aOR 4.63; 95% CI 2.87-7.64), and pancreatic interventions (aOR 7.55; 95% CI 4.23-13.96). During long-term follow-up, DPD increased the risk of pancreatic intervention (aOR 9.71; 95% CI 5.37-18.30), recurrent pancreatitis (aOR 2.08; 95% CI 1.32-3.29), chronic pancreatitis (aOR 2.73; 95% CI 1.47-5.15), and endocrine pancreatic insufficiency (aOR 1.63; 95% CI 1.05-2.53). Central or subtotal pancreatic necrosis on computed tomography (OR 9.49; 95% CI 6.31-14.29) and a high level of serum C-reactive protein in the first 48 hours after admission (per 10-point increase, OR 1.02; 95% CI 1.00-1.03) were identified as independent predictors for developing DPD. DISCUSSION: At least 1 of every 4 patients with necrotizing pancreatitis experience DPD, which is associated with detrimental, short-term and long-term interventions, and complications. Central and subtotal pancreatic necrosis and high levels of serum C-reactive protein in the first 48 hours are independent predictors for DPD.

The influence of inter-hospital transfers on mortality in severely injured patients.

PURPOSE: The importance of treating severely injured patients in higher-level trauma centers is undisputable. However, it is uncertain whether severely injured patients that were initially transported to a lower-level trauma center (i.e., undertriage) benefit from being transferred to a higher-level trauma center. METHODS: This observational study included all severely injured patients (i.e., Injury Severity Score ≥ 16) that were initially transported to a lower-level trauma center within eight ambulance regions. The exposure of interest was whether a patient was transferred to a higher-level trauma center. Primary outcomes were 24-h and 30-day mortality. Generalized linear models including inverse probability weights for several potential confounders were constructed to evaluate the association between transfer status and mortality. RESULTS: We included 165,404 trauma patients that were transported with high priority to a trauma center, of which 3932 patients were severely injured. 1065 (27.1%) patients were transported to a lower-level trauma center of which 322 (30.2%) were transferred to a higher-level trauma center. Transferring undertriaged patients to a higher-level trauma center was significantly associated with reduced 24-h (relative risk [RR] 0.26, 95%-CI 0.10-0.68) and 30-day mortality (RR 0.65, 0.46-0.92). Similar results were observed in patients with critical injuries (24-h: RR 0.35, 0.16-0.77; 30-day: RR 0.55, 0.37-0.80) and patients with traumatic brain injury (24-h: RR 0.31, 0.11-0.83; 30-day: RR 0.66, 0.46-0.96). CONCLUSIONS: A minority of the undertriaged patients are transferred to a higher-level trauma center. An inter-hospital transfer appears to be safe and may improve the survival of severely injured patients initially transported to a lower-level trauma center.

Evaluating pre-hospital triage and decision-making in patients who died within 30 days post-trauma: A multi-site, multi-center, cohort study.

INTRODUCTION: Evaluating pre-hospital triage and decision-making in patients who died post-trauma is crucial to decrease undertriage and improve future patients' chances of survival. A study that has adequately investigated this is currently lacking. The aim of this study was therefore to evaluate pre-hospital triage and decision-making in patients who died within 30 days post-trauma. MATERIALS AND METHODS: A multi-site, multi-center, cohort study was conducted. Trauma patients who were transported from the scene of injury to a trauma center by ambulance and died within 30 days post-trauma, were included. The main outcome was undertriage, defined as erroneously transporting a severely injured patient (Injury Severity Score ≥ 16) to a lower-level trauma center. RESULTS: Between January 2015 and December 2017, 2116 patients were included, of whom 765 (36.2%) were severely injured. A total of 103 of these patients (13.5%) were undertriaged. Undertriaged patients were often elderly with a severe head and/or thoracic injury as a result of a minor fall (< 2 m). A majority of the undertriaged patients were triaged without assistance of a specialized physician (100 [97.1%]), did not meet field triage criteria for level-I trauma care (81 [78.6%]), and could have been transported to the nearest level-I trauma center within 45 min (93 [90.3%]). CONCLUSION: Approximately 14% of the severely injured patients who died within 30 days were undertriaged and could have benefited from treatment at a level-I trauma center (i.e., specialized trauma care). Improvement of pre-hospital triage is needed to potentially increase future patients' chances of survival.

Evaluating the effect of driving distance to the nearest higher level trauma centre on undertriage: a cohort study.

BACKGROUND: It is of great importance that emergency medical services professionals transport trauma patients in need of specialised care to higher level trauma centres to achieve optimal patient outcomes. Possibly, undertriage is more likely to occur in patients with a longer distance to the nearest higher level trauma centre. This study aims to determine the association between driving distance and undertriage. METHOD: This prospective cohort study was conducted from January 2015 to December 2017. All trauma patients in need of specialised care that were transported to a trauma centre by emergency medical services professionals from eight ambulance regions in the Netherlands were included. Patients with critical resource use or an Injury Severity Score ≥16 were defined as in need of specialised care. Driving distance was calculated between the scene of injury and the nearest higher level trauma centre. Undertriage was defined as transporting a patient in need of specialised care to a lower level trauma centre. Generalised linear models adjusting for confounders were constructed to determine the association between driving distance to the nearest higher level trauma centre per 1 and 10 km and undertriage. A sensitivity analysis was conducted with a generalised linear model including inverse probability weights. RESULTS: 6101 patients, of which 4404 patients with critical resource use and 3760 patients with an Injury Severity Score ≥16, were included. The adjusted generalised linear model demonstrated a significant association between a 1 km (OR 1.04; 95% CI 1.04 to 1.05) and 10 kilometre (OR 1.50; 95% CI 1.42 to 1.58) increase in driving distance and undertriage in patients with critical resource use. Also in patients with an Injury Severity Score ≥16, a significant association between driving distance (1 km (OR 1.06; 95% CI 1.06 to 1.07), 10 km (OR 1.83; 95% CI 1.71 to 1.95)) and undertriage was observed. CONCLUSION: Patients in need of specialised care are less likely to be transported to the appropriate trauma centre with increasing driving distance. Our results suggest that emergency medical services professionals incorporate driving distance into their decision making regarding transport destinations, although distance is not included in the triage protocol.

Priority accuracy by dispatch centers and Emergency Medical Services professionals in trauma patients: a cohort study.

PURPOSE: Priority-setting by dispatch centers and Emergency Medical Services professionals has a major impact on pre-hospital triage and times of trauma patients. Patients requiring specialized care benefit from expedited transport to higher-level trauma centers, while transportation of these patients to lower-level trauma centers is associated with higher mortality rates. This study aims to evaluate the accuracy of priority-setting by dispatch centers and Emergency Medical Services professionals. METHODS: This observational study included trauma patients transported from the scene of injury to a trauma center. Priority-setting was evaluated in terms of the proportion of patients requiring specialized trauma care assigned with the highest priority (i.e., sensitivity), undertriage, and overtriage. Patients in need of specialized care were defined by a composite resource-based endpoint. An Injury Severity Score ≥ 16 served as a secondary reference standard. RESULTS: Between January 2015 and December 2017, records of 114,459 trauma patients were collected, of which 3327 (2.9%) patients were in need of specialized care according to the primary reference standard. Dispatch centers and Emergency Medical Services professionals assigned 83.8% and 74.5% of these patients with the highest priority, respectively. Undertriage rates ranged between 22.7 and 65.5% in the different prioritization subgroups. There were differences between dispatch and transport priorities in 17.7% of the patients. CONCLUSION: The majority of patients that required specialized care were assigned with the highest priority by the dispatch centers and Emergency Medical Services professionals. Highly accurate priority criteria could improve the quality of pre-hospital triage.

The impact of prehospital time intervals on mortality in moderately and severely injured patients.

BACKGROUND: Modern trauma systems and emergency medical services aim to reduce prehospital time intervals to achieve optimal outcomes. However, current literature remains inconclusive on the relationship between time to definitive treatment and mortality. The aim of this study was to investigate the association between prehospital time and mortality. METHODS: All moderately and severely injured trauma patients (i.e., patients with an Injury Severity Score of 9 or greater) who were transported from the scene of injury to a trauma center by ground ambulances of the participating emergency medical services between 2015 and 2017 were included. Exposures of interest were total prehospital time, on-scene time, and transport time. Outcomes were 24-hour and 30-day mortality. Generalized linear models including inverse probability weights for several potential confounders were constructed. A generalized additive model was constructed to enable visual inspection of the association. RESULTS: We included 22,525 moderately and severely injured patients. Twenty-four-hour and 30-day mortality were 1.3% and 7.3%, respectively. On-scene time per minute was significantly associated with 24-hour (relative risk [RR], 1.029; 95% confidence interval, 1.018-1.040) and 30-day mortality (RR, 1.013; 1.008-1.017). We found that this association was also present in patients with severe injuries, traumatic brain injury, severe abdominal injury, and stab or gunshot wound. An on-scene time of 20 minutes or longer demonstrated a strong association with 24-hour (RR, 1.797; 1.406-2.296) and 30-day mortality (RR, 1.298; 1.180-1.428). Total prehospital (24-hour: RR, 0.998; 0.990-1.007; 30-day: RR, 1.000, 0.997-1.004) and transport (24-hour: RR, 0.996; 0.982-1.010; 30-day: RR, 0.995; 0.989-1.001) time were not associated with mortality. CONCLUSION: A prolonged on-scene time is associated with mortality in moderately and severely injured patients, which suggests that a reduced on-scene time may be favorable for these patients. In addition, transport time was found not to be associated with mortality. LEVEL OF EVIDENCE: Prognostic and Epidemiologic; level III.

Optimal timing of cholecystectomy after necrotising biliary pancreatitis.

OBJECTIVE: Following an episode of acute biliary pancreatitis, cholecystectomy is advised to prevent recurrent biliary events. There is limited evidence regarding the optimal timing and safety of cholecystectomy in patients with necrotising biliary pancreatitis. DESIGN: A post hoc analysis of a multicentre prospective cohort. Patients with biliary pancreatitis and a CT severity score of three or more were included in 27 Dutch hospitals between 2005 and 2014. Primary outcome was the optimal timing of cholecystectomy in patients with necrotising biliary pancreatitis, defined as: the optimal point in time with the lowest risk of recurrent biliary events and the lowest risk of complications of cholecystectomy. Secondary outcomes were the number of recurrent biliary events, periprocedural complications of cholecystectomy and the protective value of endoscopic sphincterotomy for the recurrence of biliary events. RESULTS: Overall, 248 patients were included in the analysis. Cholecystectomy was performed in 191 patients (77%) at a median of 103 days (P25-P75: 46-222) after discharge. Infected necrosis after cholecystectomy occurred in four (2%) patients with persistent peripancreatic collections. Before cholecystectomy, 66 patients (27%) developed biliary events. The risk of overall recurrent biliary events prior to cholecystectomy was significantly lower before 10 weeks after discharge (risk ratio 0.49 (95% CI 0.27 to 0.90); p=0.02). The risk of recurrent pancreatitis before cholecystectomy was significantly lower before 8 weeks after discharge (risk ratio 0.14 (95% CI 0.02 to 1.0); p=0.02). The complication rate of cholecystectomy did not decrease over time. Endoscopic sphincterotomy did not reduce the risk of recurrent biliary events (OR 1.40 (95% CI 0.74 to 2.83)). CONCLUSION: The optimal timing of cholecystectomy after necrotising biliary pancreatitis, in the absence of peripancreatic collections, is within 8 weeks after discharge.

The impact of the Trauma Triage App on pre-hospital trauma triage: design and protocol of the stepped-wedge, cluster-randomized TESLA trial.

BACKGROUND: Field triage of trauma patients is crucial to get the right patient to the right hospital within a particular time frame. Minimization of undertriage, overtriage, and interhospital transfer rates could substantially reduce mortality rates, life-long disabilities, and costs. Identification of patients in need of specialized trauma care is predominantly based on the judgment of Emergency Medical Services professionals and a pre-hospital triage protocol. The Trauma Triage App is a smartphone application that includes a prediction model to aid Emergency Medical Services professionals in the identification of patients in need of specialized trauma care. The aim of this trial is to assess the impact of this new digital approach to field triage on the primary endpoint undertriage. METHODS: The Trauma triage using Supervised Learning Algorithms (TESLA) trial is a stepped-wedge cluster-randomized controlled trial with eight clusters defined as Emergency Medical Services regions. These clusters are an integral part of five inclusive trauma regions. Injured patients, evaluated on-scene by an Emergency Medical Services professional, suspected of moderate to severe injuries, will be assessed for eligibility. This unidirectional crossover trial will start with a baseline period in which the default pre-hospital triage protocol is used, after which all clusters gradually implement the Trauma Triage App as an add-on to the existing triage protocol. The primary endpoint is undertriage on patient and cluster level and is defined as the transportation of a severely injured patient (Injury Severity Score ≥ 16) to a lower-level trauma center. Secondary endpoints include overtriage, hospital resource use, and a cost-utility analysis. DISCUSSION: The TESLA trial will assess the impact of the Trauma Triage App in clinical practice. This novel approach to field triage will give new and previously undiscovered insights into several isolated components of the diagnostic strategy to get the right trauma patient to the right hospital. The stepped-wedge design allows for within and between cluster comparisons. TRIAL REGISTRATION: Netherlands Trial Register, NTR7243. Registered 30 May 2018, https://www.trialregister.nl/trial/7038.