I am a postdoc at the Center for Artificial Intelligence in Medicine & Imaging (AIMI) at Stanford University. As a medical doctor, epidemiologist, and scientist, my aim is to optimize healthcare through predictive modeling with a focus on deep learning in medical imaging.
Prior to joining AIMI, I obtained a PhD at the Department of Trauma Surgery at the University of Utrecht in the Netherlands. During my PhD, I developed mobile and desktop applications with integrated machine learning models (the Trauma Triage App) to aid field triage of trauma patients on the scene of injury. In addition, I worked on various deep learning projects, including fracture detection, localization, and classification, semantic segmentation of videos from robot-assisted surgery, and NLP-related projects.
Curtis Langlotz, Postdoctoral Faculty Sponsor
Evaluating the effect of driving distance to the nearest higher level trauma centre on undertriage: a cohort study.
Emergency medicine journal : EMJ
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.
View details for DOI 10.1136/emermed-2021-211635
View details for PubMedID 34593562
The impact of prehospital time intervals on mortality in moderately and severely injured patients.
The journal of trauma and acute care surgery
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 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) that 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 h 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. 24 h and 30-day mortality were 1.3% and 7.3%, respectively. On-scene time per minute was significantly associated with 24 h (relative risk [RR] 1.029; 95% CI, 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 h (RR 1.797; 1.406-2.296) and 30-day mortality (RR 1.298; 1.180-1.428). Total prehospital (24 h: RR 0.998; 0.990-1.007; 30-day: RR 1.000, 0.997-1.004) and transport (24 h: RR 0.996; 0.982-1.010; 30-day: RR 0.995; 0.989-1.001) time were not associated with mortality.CONCLUSIONS: 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. Additionally, transport time was found not to be associated with mortality.LEVEL OF EVIDENCE: Prognostic study, level III.
View details for DOI 10.1097/TA.0000000000003380
View details for PubMedID 34407005
Priority accuracy by dispatch centers and Emergency Medical Services professionals in trauma patients: a cohort study.
European journal of trauma and emergency surgery : official publication of the European Trauma Society
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.
View details for DOI 10.1007/s00068-021-01685-1
View details for PubMedID 34019106
Optimal timing of cholecystectomy after necrotising biliary pancreatitis.
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.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.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)).The optimal timing of cholecystectomy after necrotising biliary pancreatitis, in the absence of peripancreatic collections, is within 8 weeks after discharge.
View details for DOI 10.1136/gutjnl-2021-324239
View details for PubMedID 34272261