Explainable Prediction Model of the Need for Emergency Hemostasis Using Field Information During Physician-Staffed Helicopter Emergency Medical Service Interventions: A Single-Center, Retrospective, Observational Pilot Study.

OBJECTIVE: Early recognition of hemostasis is important to prevent trauma-related deaths. We conducted a pilot study of a predictive model of hemostatic need using factors that can be collected during helicopter emergency medical service (HEMS) interventions until transport hospital selection using cases from our institution. METHODS: This single-center, retrospective, observational pilot study included 251 trauma patients aged ≥ 18 years treated with HEMS between April 2017 and March 2022, in Nara Medical University. Cardiac arrest and pre-HEMS treatment patients were excluded. Emergency hemostatic surgery prediction models were constructed using the light gradient boosting machine cross-validation method using objective data that could be collected before hospital determination. The accuracy of this model was compared with that of the ground emergency medical service-based model, and factors influencing outcome were visualized using Shapley additive explanations. RESULTS: The predictive accuracy of the model with HEMS intervention factors was an area under the receiver operating characteristic curve of 0.80, superior to the 0.73 accuracy area under the receiver operating characteristic curve for ground emergency medical services constructed with contact information. Clinically important factors, such as shock index, blood pressure changes, and ultrasound findings, had a significant impact on outcomes, with nonmonotonic effects observed across factors. CONCLUSION: This pilot study suggests that predictive models of emergency hemostasis can be built using limited prehospital information. To validate this model, a larger, multicenter study is recommended.

Comparison of Changes in Vital Signs During Ground and Helicopter Emergency Medical Services and Hospital Interventions.

OBJECTIVE: Few studies have evaluated the effects of helicopter emergency medical services (HEMS) alone. This single-center study compared the changes in vital signs during ground emergency medical services (GEMS), HEMS, and hospital interventions to assess the impact of HEMS interventions. METHODS: This retrospective observational study included 168 trauma patients older than 18 years of age who received HEMS. Patients with cardiac arrest or those who received medical attention before HEMS were excluded. We assessed 3 intervention phases (GEMS, HEMS, and hospital). The changes in heart rate, systolic blood pressure, respiratory rate, and shock index in response to interventions were calculated and divided by the intervention time, and the changes observed during the interventions were compared. RESULTS: No changes in vital signs were observed when receiving GEMS. Systolic blood pressure increased and shock index decreased after HEMS, whereas systolic blood pressure decreased and shock index increased during hospital interventions. Heart rate showed no significant change (P = .12), and respiratory rate showed very little change. Systolic blood pressure increased significantly during HEMS compared with the pre- and postintervention periods. CONCLUSION: Changes in vital signs differed according to the intervention. Systolic blood pressure increased during HEMS but not with GEMS or hospital interventions.

A case of meningococcal meningitis with multiple cerebellar microbleeds detected by susceptibility-weighted imaging.

BACKGROUND: Bacterial meningitis is a fatal infectious disease of the central nervous system complicating intravascular involvements. Multiple microbleeds are rarely identified as complications because of the limited detection threshold of conventional imaging modalities. We report the first case of meningococcal meningitis with successful identification of multiple microbleeds in the cerebellum by susceptibility-weighted imaging. CASE PRESENTATION: A 19-year-old Japanese female was brought to our emergency department because of fever and coma. A spinal tap was performed and turbid yellow fluid was collected. A diagnosis of bacterial meningitis was established and the patient was admitted to an intensive care unit. Dexamethasone and Antibiotics were administered and Neisseria meningitides was cultured from the spinal fluid. On day 10, postcontrast magnetic resonance imaging identified enhanced subarachnoid space in the cerebellum. Susceptibility-weighted imaging showed spotty low-intensity signals in the cerebellar tissue, indicating microbleeds. The patient made a full recovery from coma and was discharged without neurological sequelae on day 24. CONCLUSION: Meningococcal meningitis can cause multiple microbleeds in the cerebellum. In this report, we successfully identified microbleeds by susceptibility-weighed imaging. Using this imaging modality, further investigations will clarify its clinical incidence and significance.

Explainable artificial intelligence-based prediction of poor neurological outcome from head computed tomography in the immediate post-resuscitation phase.

Predicting poor neurological outcomes after resuscitation is important for planning treatment strategies. We constructed an explainable artificial intelligence-based prognostic model using head computed tomography (CT) scans taken immediately within 3 h of resuscitation from cardiac arrest and compared its predictive accuracy with that of previous methods using gray-to-white matter ratio (GWR). We included 321 consecutive patients admitted to our institution after resuscitation for out-of-hospital cardiopulmonary arrest with circulation resumption over 6 years. A machine learning model using head CT images with transfer learning was used to predict the neurological outcomes at 1 month. These predictions were compared with the predictions of GWR for multiple regions of interest in head CT using receiver operating characteristic (ROC)-area under curve (AUC) and precision recall (PR)-AUC. The regions of focus were visualized using a heatmap. Both methods had similar ROC-AUCs, but the machine learning model had a higher PR-AUC (0.73 vs. 0.58). The machine learning-focused area of interest for classification was the boundary between gray and white matter, which overlapped with the area of focus when diagnosing hypoxic- ischemic brain injury. The machine learning model for predicting poor outcomes had superior accuracy to conventional methods and could help optimize treatment.

Machine learning-based analysis of regional differences in out-of-hospital cardiopulmonary arrest outcomes and resuscitation interventions in Japan.

Refining out-of-hospital cardiopulmonary arrest (OHCA) resuscitation protocols for local emergency practices is vital. The lack of comprehensive evaluation methods for individualized protocols impedes targeted improvements. Thus, we employed machine learning to assess emergency medical service (EMS) records for examining regional disparities in time reduction strategies. In this retrospective study, we examined Japanese EMS records and neurological outcomes from 2015 to 2020 using nationwide data. We included patients aged ≥ 18 years with cardiogenic OHCA and visualized EMS activity time variations across prefectures. A five-layer neural network generated a neurological outcome predictive model that was trained on 80% of the data and tested on the remaining 20%. We evaluated interventions associated with changes in prognosis by simulating these changes after adjusting for time factors, including EMS contact to hospital arrival and initial defibrillation or drug administration. The study encompassed 460,540 patients, with the model's area under the curve and accuracy being 0.96 and 0.95, respectively. Reducing transport time and defibrillation improved outcomes universally, while combining transport time and drug administration showed varied efficacy. In conclusion, the association of emergency activity time with neurological outcomes varied across Japanese prefectures, suggesting the need to set targets for reducing activity time in localized emergency protocols.

Enhanced squalene production by modulation of pathways consuming squalene and its precursor.

Fermentative production of squalene in yeast as an alternative approach to extracting squalene from sharks or plants has attracted significant interest. However, squalene accumulation is limited due to its inevitable high-flux allocation toward ergosterol synthesis. In this study, we described expression control of squalene monooxygenase (Erg1p), the first-step enzyme of ergosterol synthesis from squalene, to significantly reduce squalene loss. We replaced the ERG1 promoter (PERG1) with three natural yeast promoters with different activities (PPCL2, PHCM1, and PTHI2). ERG1 controlled by PTHI2 showed 20 times higher squalene production compared with the wild-type strain, whereas the other two strains exhibited no significant difference. By combining the overexpression of rate-limiting enzyme and the deletion of non-essential competing pathway gene, the yeast Saccharomyces cerevisiae produced up to 379 mg/L of squalene.

Association of multiple rib fractures with the frequency of pneumonia in the post-resuscitation period.

Purpose: Successful cardiopulmonary resuscitation is associated with a high incidence of chest wall injuries. However, few studies have examined chest wall injury as a risk factor for respiratory complications after cardiopulmonary resuscitation. Therefore, herein, we investigated the association of multiple rib fractures on the incidence of post-resuscitation pneumonia. Methods: This single-centre retrospective cohort study enrolled adult, nontraumatic, out-of-hospital cardiac arrest patients who maintained circulation for more than 48 h between June 2015 and May 2019. Rib fractures were evaluated by computed tomography on the day of hospital admission. The association with newly developed pneumonia within 7 days of hospitalisation was analysed using a Fine-Gray proportional hazards regression model adjusted for the propensity score of multiple rib fractures estimated from age, sex, presence of witnessed status, bystander CPR, initial rhythm, and total CPR time and for previously reported risk factors for pneumonia (therapeutic hypothermia and prophylactic antibiotics). Results: Overall, 683 patients with out-of-hospital cardiac arrest were treated; 87 eligible cases were enrolled for analysis. Thirty-two (36.8%) patients had multiple rib fractures identified on computed tomography, and 35 (40.2%) patients developed pneumonia. The presence of multiple rib fractures was significantly associated with a higher incidence of pneumonia, consistently both with and without adjustment for background factors (unadjusted hazard ratio 4.63, 95% confidence interval: 2.35-9.13, p < 0.001; adjusted hazard ratio 4.03, 95% confidence interval: 2.08-7.82, p < 0.001). Conclusions: Multiple rib fractures are independently associated with the development of pneumonia after successful resuscitation.

Visual assessment of interactions among resuscitation activity factors in out-of-hospital cardiopulmonary arrest using a machine learning model.

AIM: The evaluation of the effects of resuscitation activity factors on the outcome of out-of-hospital cardiopulmonary arrest (OHCA) requires consideration of the interactions among these factors. To improve OHCA success rates, this study assessed the prognostic interactions resulting from simultaneously modifying two prehospital factors using a trained machine learning model. METHODS: We enrolled 8274 OHCA patients resuscitated by emergency medical services (EMS) in Nara prefecture, Japan, with a unified activity protocol between January 2010 and December 2018; patients younger than 18 and those with noncardiogenic cardiopulmonary arrest were excluded. Next, a three-layer neural network model was constructed to predict the cerebral performance category score of 1 or 2 at one month based on 24 features of prehospital EMS activity. Using this model, we evaluated the prognostic impact of continuously and simultaneously varying the transport time and the defibrillation or drug-administration time in the test data based on heatmaps. RESULTS: The average class sensitivity of the prognostic model was more than 0.86, with a full area under the receiver operating characteristics curve of 0.94 (95% confidence interval of 0.92-0.96). By adjusting the two time factors simultaneously, a nonlinear interaction was obtained between the two adjustments, instead of a linear prediction of the outcome. CONCLUSION: Modifications to the parameters using a machine-learning-based prognostic model indicated an interaction among the prognostic factors. These findings could be used to evaluate which factors should be prioritized to reduce time in the trained region of machine learning in order to improve EMS activities.

A new quantitative assessment method for predicting pneumonia caused by chest wall injury.

BACKGROUND: The severity of rib fractures has been previously evaluated by combining categorical data, but these methods have only low predictive capability for respiratory complications and mortality. This study aimed to establish a more accurate method for predicting the development of pneumonia, a frequent complication in chest injuries, using anatomical relationships. METHODS: We analyzed three-dimensional reconstructed images of 644 consecutive trauma patients who underwent whole-body computed tomography (CT) in our institution within a 36-month study period from April 2017. The anatomical relationship between the right and left thoracic volumes of non-rib fracture patients was used to estimate thoracic volume changes on the injured side in unilateral rib fracture patients. The predictive capability of changes in thoracic volume for the development of pneumonia was evaluated according to the area under the receiver operating characteristic curve and compared with that of previous chest wall severity evaluation methods. RESULTS: Of the 644 patients, 133 and 478 patients had unilateral rib fractures and non-rib fractures, respectively. The amount of change in thoracic volume due to unilateral rib fractures was significantly greater in pneumonia patients (400 mL vs. 160 mL, p < 0.01). The area under the receiver operating characteristic curve for the development of pneumonia was 0.83, which tended to be higher than that of the previous severity scoring methods. CONCLUSION: The amount of change in chest volume, which can be estimated using CT images, has better predictive capability for pneumonia than previous severity assessment methods based on categorical data. The amount of change in chest volume measured using whole-body CT can be used to rapidly determine the optimal treatment for severe chest wall injuries. LEVEL OF EVIDENCE: Prognostic study, level IV.

Periprosthetic tibial fracture after total knee arthroplasty with popliteal artery injury-A case report.

We present the case of a 79-year-old woman who presented at our center with a periprosthetic tibial fracture with a popliteal artery injury after total knee arthroplasty. Anastomosis of the popliteal artery was performed on the day of injury, and was later treated by open reduction and internal fixation. The patient was able to walk 3 months after injury. The present case was difficult to treat because of the arterial injury associated with periprosthetic fracture. Although revision of the implant was considered, open reduction and internal fixation was selected because of the severity of soft-tissue damage. The mechanism of injury is not uncommon, and it is expected that similar fractures will become more prevalent in the future as the number of knee replacement surgeries increases.