Pelvic fractures are severe injuries with frequently associated multi-system trauma and a high mortality rate. The value of the pelvic fracture pattern for predicting transfusion requirements and mortality is not entirely clear. To address hemorrhage from pelvic injuries, the early application of pelvic binders is now recommended and arterial angio-embolization is widely used for controlling arterial bleeding. Our aim was to assess the association of the pelvic fracture pattern according to the Tile classification system with transfusion requirements and mortality rates, and to evaluate the correlation between the use of pelvic binders and arterial angio-embolization and the mortality of patients with pelvic fractures. Single-center retrospective cohort study including all consecutive patients with a pelvic fracture from January 2008 to June 2015. All radiological fracture patterns were independently reviewed and grouped according to the Tile classification system. Data on patient demographics, use of pelvic binders and arterial angio-embolization, transfusion requirements and mortality were extracted from the institutional trauma registry and analyzed. The present study included 228 patients. Median patient age was 43.5 years and 68.9% were male. The two independent observers identified 105 Tile C (46.1%), 71 Tile B (31.1%) and 52 Tile A (22.8%) fractures, with substantial to almost perfect interobserver agreement (Kappa 0.70-0.83). Tile C fractures were associated with a higher mortality rate (p = 0.001) and higher transfusion requirements (p < 0.0001) than Tile A or B fractures. Arterial angio-embolization for pelvic bleeding (p = 0.05) and prehospital pelvic binder placement (p = 0.5) were not associated with differences in mortality rates. Tile C pelvic fractures are associated with higher transfusion requirements and a higher mortality rate than Tile A or B fractures. No association between the use of pelvic binders or arterial angio-embolization and survival was observed in this cohort of patients with pelvic fractures.

Background: Medical coding is the process that converts clinical documentation into standard medical codes. Codes are used for several key purposes in a hospital (eg, insurance reimbursement and performance analysis); therefore, their optimization is crucial. With the rapid growth of natural language processing technologies, several solutions based on artificial intelligence have been proposed to aid in medical coding by automatically suggesting relevant codes for clinical documents. However, their effectiveness is still limited to simple cases, and it is not yet clear how much value they can bring in improving coding efficiency and accuracy. Objective: This study aimed to bring more efficiency to the coding process to improve the selection of codes by medical coders. To achieve this, we developed an innovative multimodal machine learning–based solution that, instead of predicting codes, detects the degree of coding complexity before coding is performed. The notion of coding complexity was used to better dispatch work among medical coders to eventually minimize errors and improve throughput. Methods: To train and evaluate our approach, we collected 2060 cases rated by coders in terms of coding complexity from 1 (simplest) to 4 (most complex). We asked 2 expert coders to rate 3.01% (62/2060) of the cases as the gold standard. The agreements between experts were used as benchmarks for model evaluation. A case contains both clinical text and patient metadata from the hospital electronic health record. We extracted both text features and metadata features, then concatenated and fed them into several machine learning models. Finally, we selected 2 models. The first used cross-validated training on 1751 cases and testing on 309 cases aiming to assess the predictive power of the proposed approach and its generalizability. The second model was trained on 1998 cases and tested on the gold standard to validate the best model performance against human benchmarks. Results: Our first model achieved a macro–F1-score of 0.51 and an accuracy of 0.59 on classifying the 4-scale complexity. The model distinguished well between the simple (combined complexity 1-2) and complex (combined complexity 3-4) cases with a macro–F1-score of 0.65 and an accuracy of 0.71. Our second model achieved 61% agreement with experts’ ratings and a macro–F1-score of 0.62 on the gold standard, whereas the 2 experts had a 66% (41/62) agreement ratio with a macro–F1-score of 0.67. Conclusions: We propose a multimodal machine learning approach that leverages information from both clinical text and patient metadata to predict the complexity of coding a case in the precoding phase. By integrating this model into the hospital coding system, distribution of cases among coders can be done automatically with performance comparable with that of human expert coders, thus improving coding efficiency and accuracy at scale.

This study evaluated and compared two imaging-based scoring systems for the detection of significant blunt bowel and mesenteric injury (sBBMI) by emergency computed tomography (CT) We included all consecutive adult polytrauma patients admitted to our emergency department following a road traffic accident from January 2008 to June 2015, provided that intravenously contrast-enhanced whole-body CT examination was performed immediately after hospital admission. Two radiologists, blinded to patients’ outcome, reviewed the CT examinations for distinctive direct intestinal or mesenteric vascular injury and indirect signs of abdominal injury. These findings were correlated with the patients’ surgical or interventional radiology findings, autopsy, or clinical follow-up (>24 h). Two previously validated imaging-based bowel-injury scoring systems, the CT-based Faget score and the clinically and radiologically based Mc Nutt score (BIPS), were compared by applying each to our trauma cohort. Student t-test, chi-squared, and logistic regression were used in analyses. Twenty-one of 752 analysed patients (2.8 %) had confirmed sBBMI. Active mesenteric bleeding, mesenteric and free pneumoperitoneum, small haemoperitoneum, non-focal bowel wall thickening, mesenteric/pericolic fat stranding, and anterior abdominal wall injury were significantly correlated with sBBMI, as did the two evaluated scoring systems (p < 0.001). However, multivariate logistic regression revealed the superiority of the Faget score to the McNutt score. The prevalence of sBBMI among polytrauma patients is low. Early diagnosis is necessary to avoid increased mortality. Certain CT features are pathognomic of sBBMI and must not be overlooked. Scoring systems are helpful, especially when they are based on radiological signs.

Aim of the study: Short stay processes are incentives to unburden chronically stressed healthcare systems. The aim of this study is to analyze financial implications of day admission (DAS) and outpatient strategies for colon resections in a prospective payment system (PPS) using Diagnosis Related Group (DRG) coding.Methods: Consecutive patients undergoing left and right colonic resections between January 1, 2019 and December 31, 2020 were included. Medico-economic evaluations of the virtual outpatient and day admission surgery groups based on predefined criteria were compared to the identical group of patients who underwent surgery in the actual traditional inpatient setting. In a second step, postoperative complications of the virtual outpatient group were assessed. Cost-revenue analysis was performed using a micro-costing approach including direct medical costs.Results: Overall (N = 257), 97 (37.7%) colectomies would have been potentially eligible for an outpatient strategy. The global costs of the actual inpatient strategy totaled USD 3 634 392 with a global revenue of USD 3 571 069, corresponding to a cost coverage rate of 98%. The result of the virtual DAS strategy would have been a net loss of USD 15 800 (coverage rate of 99%) due to 4 low length of stay outliers triggering a reimbursement reduction and preventing a positive net result of USD 16 208. The pilot reference outpatient case’s revenue and cost amounted to respectively USD 7479 and USD 6911 (cost coverage of 108%).Conclusion: From both any given hospital and healthcare system point of view, elective outpatient colectomy for selected patients is the most cost-saving option. However, in a prospective payment system implemented to avoid bad incentives, the latter can unintentionally disadvantage best performing hospitals and impede widespread adoption of high-value strategies.