Machine-Learning Approaches for Predicting the Need of Oxygen Therapy in Early-Stage COVID-19 in Japan: Multicenter Retrospective Observational Study.

Background: Early prediction of oxygen therapy in patients with coronavirus disease 2019 (COVID-19) is vital for triage. Several machine-learning prognostic models for COVID-19 are currently available. However, external validation of these models has rarely been performed. Therefore, most reported predictive performance is optimistic and has a high risk of bias. This study aimed to develop and validate a model that predicts oxygen therapy needs in the early stages of COVID-19 using a sizable multicenter dataset. Methods: This multicenter retrospective study included consecutive COVID-19 hospitalized patients confirmed by a reverse transcription chain reaction in 11 medical institutions in Fukui, Japan. We developed and validated seven machine-learning models (e.g., penalized logistic regression model) using routinely collected data (e.g., demographics, simple blood test). The primary outcome was the need for oxygen therapy (≥1 L/min or SpO2 ≤ 94%) during hospitalization. C-statistics, calibration slope, and association measures (e.g., sensitivity) evaluated the performance of the model using the test set (randomly selected 20% of data for internal validation). Among these seven models, the machine-learning model that showed the best performance was re-evaluated using an external dataset. We compared the model performances using the A-DROP criteria (modified version of CURB-65) as a conventional method. Results: Of the 396 patients with COVID-19 for the model development, 102 patients (26%) required oxygen therapy during hospitalization. For internal validation, machine-learning models, except for the k-point nearest neighbor, had a higher discrimination ability than the A-DORP criteria (P < 0.01). The XGboost had the highest c-statistic in the internal validation (0.92 vs. 0.69 in A-DROP criteria; P < 0.001). For the external validation with 728 temporal independent datasets (106 patients [15%] required oxygen therapy), the XG boost model had a higher c-statistic (0.88 vs. 0.69 in A-DROP criteria; P < 0.001). Conclusions: Machine-learning models demonstrated a more significant performance in predicting the need for oxygen therapy in the early stages of COVID-19.

A comprehensive validation of very early rule-out strategies for non-ST-segment elevation myocardial infarction in emergency departments: protocol for a multicentre prospective cohort study.

INTRODUCTION: Recent advances in troponin sensitivity enabled early and accurate judgement of ruling-out myocardial infarction, especially non-ST elevation myocardial infarction (NSTEMI) in emergency departments (EDs) with development of various prediction-rules and high-sensitive-troponin-based strategies (hs-troponin). Reliance on clinical impression, however, is still common, and it remains unknown which of these strategies is superior. Therefore, our objective in this prospective cohort study is to comprehensively validate the diagnostic accuracy of clinical impression-based strategies, prediction-rules and hs-troponin-based strategies for ruling-out NSTEMIs. METHODS AND ANALYSIS: In total, 1500 consecutive adult patients with symptoms suggestive of acute coronary syndrome will be prospectively recruited from five EDs in two tertiary-level, two secondary-level community hospitals and one university hospital in Japan. The study has begun in July 2018, and recruitment period will be about 1 year. A board-certified emergency physician will complete standardised case report forms, and independently perform a clinical impression-based risk estimation of NSTEMI. Index strategies to be compared will include the clinical impression-based strategy; prediction rules and hs-troponin-based strategies for the following types of troponin (Roche Elecsys hs-troponin T; Abbott ARCHITECT hs-troponin I; Siemens ADVIA Centaur hs-troponin I; Siemens ADVIA Centaur sensitive-troponin I). The reference standard will be the composite of type 1 MI and cardiac death within 30 days after admission to the ED. Outcome measures will be negative predictive value, sensitivity and effectiveness, defined as the proportion of patients categorised as low risk for NSTEMI. We will also evaluate inter-rater reliability of the clinical impression-based risk estimation. ETHICS AND DISSEMINATION: The study is approved by the Ethics Committees of the Kyoto University Graduate School and Faculty of Medicine and of the five hospitals where we will recruit patients. We will disseminate the study results through conference presentations and peer-reviewed journals.

Blunt thoracic aortic injury with small pseudoaneurysm may be managed by nonoperative treatment.

OBJECTIVE: The efficacy of nonoperative management of blunt thoracic aortic injury (BTAI) was evaluated in patients with pseudoaneurysm. METHODS: A retrospective review was done for patients with BTAI at Fukui Prefectural Hospital during a 9-year period. Charts were reviewed for age, gender, Injury Severity Score, Abbreviated Injury Scale for each body area, initial type of aortic injury, site of aortic injury, type of definitive management, complications, and outcomes. RESULTS: Eighteen patients with BTAI were treated at Fukui Prefectural Hospital. Of 18 patients with pseudoaneurysm, seven patients were hemodynamically unstable and four patients died because of associated injuries; there were no aortic-related deaths. All 14 surviving patients were followed up for an average of 40.9 months. Only two patients with pseudoaneurysm required operative management because of the progression of the pseudoaneurysm. The pseudoaneurysm/normal aortic diameter ratio of those with any intervention was higher than that of those with nonoperative management. CONCLUSIONS: BTAI with pseudoaneurysm can be managed nonoperatively, with about 10% risk of progression to require surgical repair.

Elevated maternal serum α-fetoprotein after minor trauma during pregnancy may predict adverse fetal outcomes.

BACKGROUND: We evaluated the relationship between minor trauma during pregnancy and elevated maternal serum α-fetoprotein level. METHODS: This is a retrospective review of pregnant patients admitted to Fukui Prefectural Hospital with trauma during a 10-year period. Charts were reviewed for maternal age, gestational age, injury characteristics, Injury Severity Score, the presence of abdominal pain, systolic pressure and heart rate on arrival, fetal hemoglobin level, and maternal serum α-fetoprotein (MSAFP) concentration on arrival. RESULTS: Fifty-one pregnant patients with any trauma were treated at Fukui Prefectural Hospital. All patients were hemodynamically stable and had minor trauma. An adverse pregnancy outcome occurred in three patients (5%). One patient's fetus had a left kidney injury. Intrauterine fetal death occurred in two patients. The time from injury to fatal death was 180 minutes in one patient and 18 hours in the other patient. The mean ± SD fetal hemoglobin was 0.57% ± 0.88%. The mean ± SD MSAFP was 511 ng/mL ± 1,263 ng/mL. Three patients with adverse pregnancy outcome had a high MSAFP of greater than 1,000 ng/mL. CONCLUSION: High level of MSAFP may be a predictor of poor fetal outcome following trauma during pregnancy regardless of the severity of the trauma or the mother's hemodynamic status. LEVEL OF EVIDENCE: Epidemiologic study, level V.

Time to pelvic embolization for hemodynamically unstable pelvic fractures may affect the survival for delays up to 60 min.

INTRODUCTION: We evaluated the relationship between survival and time from arrival to angiography for hemodynamically unstable patients with pelvic trauma. METHODS: A retrospective review of patients admitted to Fukui Prefectural Hospital with pelvic fractures during a 7.5-year period. Charts were reviewed for age, injury characteristics, injury severity score, systolic blood pressure and heart rate on arrival, base deficit, and the lactate concentration on arrival, transfusion requirement, fracture pattern, the time from hospital arrival to angiography, and the time spent in the angiography suite. RESULTS: Of a total of 140 patients, 68 patients underwent pelvic angiography and embolization. Of the patients, 24 patients were hemodynamically unstable. The average injury severity score was 41.7. Of the patients, 17 had major ligamentous disruption. The average time from hospital arrival to angiography suite was 76 min. Of the hemodynamically unstable 24 patients, there were 12 deaths (50%). Patients who were embolized within 60 min of arrival had a significantly lower mortality rate (16 vs. 64%; p=0.04). There was no embolization-related complication and repeat angiography was not required in all patients. CONCLUSION: Earlier pelvic embolization within 60 min may affect the survival of hemodynamically unstable patients with pelvic fracture.

Early embolization without external fixation in pelvic trauma.

PURPOSES: In this retrospective study, we reviewed our protocol consisting of early embolization without acute external fixation in patients with pelvic fracture. PATIENTS AND METHODS: Eighty-eight patients with pelvic fracture were identified by reviewing the records of the Fukui Prefectural Hospital from April 2005 through September 2009. We managed the patients with a treatment protocol consisting of hemodynamic resuscitation and early pelvic embolization. Patients with hemodynamic instability without nonpelvic hemorrhage or extravasation of contrast in the pelvis by computed tomography (CT) were indicated to angiography and embolization. External fixation of the pelvic ring was not used in our protocol. RESULTS: Of the 88 patients with pelvic fractures, 43 underwent angiography. Twenty-eight patients (65%) were hemodynamically unstable. Twenty-five patients (58%) had major ligamentous disruption. Computed tomography detected extravasation in 21 patients (48%). Of the 43 patients who underwent angiography, 29 (67%) were positive. The average time from hospital arrival to angiography was 76.3 ± 34.5 minutes. The packed red blood cell requirement in the initial 24 hours was 8.4 ± 8.2 U, required in the embolization group. There was no complication-related embolization. Repeat angiography was not required in all patients. The mortality rate of patients requiring angiography was 11%. CONCLUSIONS: Early pelvic embolization without external fixation may be useful for the initial treatment for patients with hemodynamic instability without nonpelvic hemorrhage or with extravasation of contrast in the pelvis by CT.