BackgroundThe purpose of this study was to build a model of machine learning (ML) for the prediction of mortality in patients with isolated moderate and severe traumatic brain injury (TBI).MethodsHospitalized adult patients registered in the Trauma Registry System between January 2009 and December 2015 were enrolled in this study. Only patients with an Abbreviated Injury Scale (AIS) score ≥ 3 points related to head injuries were included in this study. A total of 1734 (1564 survival and 170 non-survival) and 325 (293 survival and 32 non-survival) patients were included in the training and test sets, respectively.ResultsUsing demographics and injury characteristics, as well as patient laboratory data, predictive tools (e.g., logistic regression [LR], support vector machine [SVM], decision tree [DT], naive Bayes [NB], and artificial neural networks [ANN]) were used to determine the mortality of individual patients. The predictive performance was evaluated by accuracy, sensitivity, and specificity, as well as by area under the curve (AUC) measures of receiver operator characteristic curves. In the training set, all five ML models had a specificity of more than 90% and all ML models (except the NB) achieved an accuracy of more than 90%. Among them, the ANN had the highest sensitivity (80.59%) in mortality prediction. Regarding performance, the ANN had the highest AUC (0.968), followed by the LR (0.942), SVM (0.935), NB (0.908), and DT (0.872). In the test set, the ANN had the highest sensitivity (84.38%) in mortality prediction, followed by the SVM (65.63%), LR (59.38%), NB (59.38%), and DT (43.75%).ConclusionsThe ANN model provided the best prediction of mortality for patients with isolated moderate and severe TBI.

Objectives: The shock index (SI) and its derivations, the modified shock index (MSI) and the age shock index (Age SI), have been used to identify trauma patients with unstable hemodynamic status. The aim of this study was to evaluate their use in predicting the requirement for massive transfusion (MT) in trauma patients upon arrival at the hospital. Participants: A patient receiving transfusion of 10 or more units of packed red blood cells or whole blood within 24 h of arrival at the emergency department was defined as having received MT. Detailed data of 2490 patients hospitalized for trauma between 1 January 2009, and 31 December 2014, who had received blood transfusion within 24 h of arrival at the emergency department, were retrieved from the Trauma Registry System of a level I regional trauma center. These included 99 patients who received MT and 2391 patients who did not. Patients with incomplete registration data were excluded from the study. The two-sided Fisher exact test or Pearson chi-square test were used to compare categorical data. The unpaired Student t-test was used to analyze normally distributed continuous data, and the Mann-Whitney U-test was used to compare non-normally distributed data. Parameters including systolic blood pressure (SBP), heart rate (HR), hemoglobin level (Hb), base deficit (BD), SI, MSI, and Age SI that could provide cut-off points for predicting the patients’ probability of receiving MT were identified by the development of specific receiver operating characteristic (ROC) curves. High accuracy was defined as an area under the curve (AUC) of more than 0.9, moderate accuracy was defined as an AUC between 0.9 and 0.7, and low accuracy was defined as an AUC less than 0.7. Results: In addition to a significantly higher Injury Severity Score (ISS) and worse outcome, the patients requiring MT presented with a significantly higher HR and lower SBP, Hb, and BD, as well as significantly increased SI, MSI, and Age SI. Among these, only four parameters (SBP, BD, SI, and MSI) had a discriminating power of moderate accuracy (AUC > 0.7) as would be expected. A SI of 0.95 and a MSI of 1.15 were identified as the cut-off points for predicting the requirement of MT, with an AUC of 0.760 (sensitivity: 0.563 and specificity: 0.876) and 0.756 (sensitivity: 0.615 and specificity: 0.823), respectively. However, in the groups of patients with comorbidities such as hypertension, diabetes mellitus, or coronary artery disease, the discriminating power of these three indices in predicting the requirement of MT was compromised. Conclusions: This study reveals that the SI is moderately accurate in predicting the need for MT. However, this predictive power may be compromised in patients with HTN, DM or CAD. Moreover, the more complex calculations of MSI and Age SI failed to provide better discriminating power than the SI.

Jejunal flap has a significantly lower rate of stricture for reconstruction of circumferential pharyngeal defects when compared with RFF or ALT flaps.

The combination of peripheral arterial intervention and free tissue transfer resulted in successful wound healing and limb salvage instead of amputation in select diabetic patients with difficult-to-heal wounds.

In our study, the differences of complication rates and flap necrosis rate between these groups were not statistically significant. Further investigations should be conducted.

BackgroundThe aim of this study was to develop an effective surgical site infection (SSI) prediction model in patients receiving free-flap reconstruction after surgery for head and neck cancer using artificial neural network (ANN), and to compare its predictive power with that of conventional logistic regression (LR).Materials and methodsThere were 1,836 patients with 1,854 free-flap reconstructions and 438 postoperative SSIs in the dataset for analysis. They were randomly assigned tin ratio of 7:3 into a training set and a test set. Based on comprehensive characteristics of patients and diseases in the absence or presence of operative data, prediction of SSI was performed at two time points (pre-operatively and post-operatively) with a feed-forward ANN and the LR models. In addition to the calculated accuracy, sensitivity, and specificity, the predictive performance of ANN and LR were assessed based on area under the curve (AUC) measures of receiver operator characteristic curves and Brier score.ResultsANN had a significantly higher AUC (0.892) of post-operative prediction and AUC (0.808) of pre-operative prediction than LR (both P<0.0001). In addition, there was significant higher AUC of post-operative prediction than pre-operative prediction by ANN (p<0.0001). With the highest AUC and the lowest Brier score (0.090), the post-operative prediction by ANN had the highest overall predictive performance.ConclusionThe post-operative prediction by ANN had the highest overall performance in predicting SSI after free-flap reconstruction in patients receiving surgery for head and neck cancer.

Background: Polytrauma patients are expected to have a higher risk of mortality than that obtained by the summation of expected mortality owing to their individual injuries. This study was designed to investigate the outcome of patients with polytrauma, which was defined using the new Berlin definition, as cases with an Abbreviated Injury Scale (AIS) ≥ 3 for two or more different body regions and one or more additional variables from five physiologic parameters (hypotension [systolic blood pressure ≤ 90 mmHg], unconsciousness [Glasgow Coma Scale score ≤ 8], acidosis [base excess ≤ −6.0], coagulopathy [partial thromboplastin time ≥ 40 s or international normalized ratio ≥ 1.4], and age [≥70 years]). Methods: We retrieved detailed data on 369 polytrauma patients and 1260 non-polytrauma patients with an overall Injury Severity Score (ISS) ≥ 18 who were hospitalized between 1 January 2009 and 31 December 2015 for the treatment of all traumatic injuries, from the Trauma Registry System at a level I trauma center. Patients with burn injury or incomplete registered data were excluded. Categorical data were compared with two-sided Fisher exact or Pearson chi-square tests. The unpaired Student t-test and the Mann–Whitney U-test was used to analyze normally distributed continuous data and non-normally distributed data, respectively. Propensity-score matched cohort in a 1:1 ratio was allocated using the NCSS software with logistic regression to evaluate the effect of polytrauma on patient outcomes. Results: The polytrauma patients had a significantly higher ISS than non-polytrauma patients (median (interquartile range Q1–Q3), 29 (22–36) vs. 24 (20–25), respectively; p < 0.001). Polytrauma patients had a 1.9-fold higher odds of mortality than non-polytrauma patients (95% CI 1.38–2.49; p < 0.001). Compared to non-polytrauma patients, polytrauma patients had a substantially longer hospital length of stay (LOS). In addition, a higher proportion of polytrauma patients were admitted to the intensive care unit (ICU), spent longer LOS in the ICU, and had significantly higher total medical expenses. Among 201 selected propensity score-matched pairs of polytrauma and non-polytrauma patients who showed no significant difference in sex, age, co-morbidity, AIS ≥ 3, and Injury Severity Score (ISS), the polytrauma patients had a significantly higher mortality rate (OR 17.5, 95% CI 4.21–72.76; p < 0.001), and a higher proportion of patients admitted to the ICU (84.1% vs. 74.1%, respectively; p = 0.013) with longer stays in the ICU (10.3 days vs. 7.5 days, respectively; p = 0.003). The total medical expenses for polytrauma patients were 35.1% higher than those of non-polytrauma patients. However, there was no significant difference in the LOS between polytrauma and non-polytrauma patients (21.1 days vs. 19.8 days, respectively; p = 0.399). Conclusions: The findings of this propensity-score matching study suggest that the new Berlin definition of polytrauma is feasible and applicable for trauma patients.

BackgroundTransportation by motorcycle and bicycle has become popular in Taiwan, this study was designed to investigate the protective effect of helmet use during motorcycle and bicycle accidents by using a propensity score–matched study based on trauma registry system data.MethodsData of adult patients hospitalized for motorcycle or bicycle accidents between January 1, 2009 and December 31, 2015 were retrieved from the Trauma Registry System. These included 7735 motorcyclists with helmet use, 863 motorcyclists without helmet use, 76 bicyclists with helmet use, and 647 bicyclists without helmet use. The primary outcome measurement was in-hospital mortality. Secondary outcomes were the hospital length of stay (LOS), intensive care unit (ICU) admission rate, and ICU LOS. Normally distributed continuous data were analyzed by the unpaired Student t-test, and non-normally distributed data were compared using the Mann–Whitney U-test. Two-sided Fisher exact or Pearson chi-square tests were used to compare categorical data. Propensity score matching (1:1 ratio using optimal method with a 0.2 caliper width) was performed using NCSS software, adjusting for the following covariates: sex, age, and comorbidities. Further logistic regression was used to evaluate the effect of helmet use on mortality rates of motorcyclists and bicyclists, respectively.ResultsThe mortality rate for motorcyclists with helmet use (1.1%) was significantly lower than for motorcyclists without helmet use (4.2%; odds ratio [OR] 0.2; 95% confidence interval [CI]: 0.17–0.37; p < 0.001). Among bicyclists, there was no significant difference in mortality rates between the patients with helmet use (5.3%) and those without helmet use (3.7%; OR 1.4; 95% CI: 0.49–4.27; p = 0.524). After propensity-score matching for covariates, including sex, age, and comorbidities, 856 well-balanced pairs of motorcyclists and 76 pairs of bicyclists were identified for outcome comparison, showing that helmet use among motorcyclists was associated with lower mortality rates (OR 0.2; 95% CI: 0.09–0.44; p < 0.001). In contrast, helmet use among bicyclists was not associated with a decrease in mortality (OR 1.3; 95% CI: 0.30–5.96; p = 0.706). The hospital LOS was also significantly shorter for motorcyclists with helmet use than for those without (9.5 days vs. 12.0 days, respectively, p < 0.001) although for bicyclists, helmet use was not associated with hospital LOS. Fewer motorcyclists with helmet use were admitted to the ICU, regardless of the severity of injury; however, no significant difference of ICU admission rates was found between bicyclists with and without helmets.ConclusionsMotorcycle helmets provide protection to adult motorcyclists involved in traffic accidents and their use is associated with a decrease in mortality rates and the risk of head injuries. However, no such protective effect of helmet use was observed for bicyclists involved in collisions.Electronic supplementary materialThe online version of this article (doi:10.1186/s12889-017-4649-1) contains supplem...