Project description:Syndromic surveillance detects and monitors individual and population health indicators through sources such as emergency department records. Automated classification of these records can improve outbreak detection speed and diagnosis accuracy. Current syndromic systems rely on hand-coded keyword-based methods to parse written fields and may benefit from the use of modern supervised-learning classifier models. In this paper, we implement two recurrent neural network models based on long short-term memory (LSTM) and gated recurrent unit (GRU) cells and compare them to two traditional bag-of-words classifiers: multinomial naïve Bayes (MNB) and a support vector machine (SVM). The MNB classifier is one of only two machine learning algorithms currently being used for syndromic surveillance. All four models are trained to predict diagnostic code groups as defined by Clinical Classification Software, first to predict from discharge diagnosis, and then from chief complaint fields. The classifiers are trained on 3.6 million de-identified emergency department records from a single United States jurisdiction. We compare performance of these models primarily using the F1 score, and we measure absolute model performance to determine which conditions are the most amenable to surveillance based on chief complaint alone. Using discharge diagnoses, the LSTM classifier performs best, though all models exhibit an F1 score above 96.00. Using chief complaints, the GRU performs best (F1 = 47.38), and MNB with bigrams performs worst (F1 = 39.40). We also note that certain syndrome types are easier to detect than others. For example, chief complaints using the GRU model predicts alcohol-related disorders well (F1 = 78.91) but predicts influenza poorly (F1 = 14.80). In all instances, the RNN models outperformed the bag-of-words classifiers suggesting deep learning models could substantially improve the automatic classification of unstructured text for syndromic surveillance.
Project description:BackgroundUnderstanding heterogeneity of the respiratory rate (RR) as a risk stratification marker across chief complaints is important to reduce misinterpretation of the risk posed by outcome events and to build accurate risk stratification tools. This study was conducted to investigate the associations between RR and clinical outcomes according to the five most frequent chief complaints in an emergency department (ED): fever, shortness of breath, altered mental status, chest pain, and abdominal pain.MethodsThis retrospective cohort study examined ED data of all adult patients who visited the ED of a tertiary medical center during April 2018-September 2019. The primary exposure was RR at the ED visit. Outcome measures were hospitalization and mechanical ventilation use. We used restrictive cubic spline and logistic regression models to assess the association of interest.ResultsOf 16 956 eligible ED patients, 4926 (29%) required hospitalization; 448 (3%) required mechanical ventilation. Overall, U-shaped associations were found between RR and the risk of hospitalization (eg, using RR = 16 as the reference, the odds ratio [OR] of RR = 32, 6.57 [95% CI 5.87-7.37]) and between RR and the risk of mechanical ventilation. This U-shaped association was driven by patients' association with altered mental status (eg, OR of RR = 12, 2.63 [95% CI 1.25-5.53]). For patients who have fever or shortness of breath, the risk of hospitalization increased monotonously with increased RR.ConclusionsU-shaped associations of RR with the risk of overall clinical outcomes were found. These associations varied across chief complaints.
Project description:Adrenal myelolipoma is a benign tumor of the adrenal cortex composed predominantly of fat and hematopoietic tissue. These lesions are usually asymptomatic, and most often incidentally detected on imaging. Uncommonly, they present with retroperitoneal hemorrhage, and these have been traditionally treated with emergent surgery. Although, transarterial embolization has been effectively and safely used in patients presenting with active hemorrhage from acute traumatic and nontraumatic causes, literature specifically pertaining to adrenal artery embolization is scant, perhaps due to smaller size and variability of adrenal arteries. With recent advances in endovascular techniques and imaging, there are emerging case reports and series of adrenal artery embolization in acute and nonacute settings. We report a case of spontaneous hemorrhage within an adrenal myelolipoma in a 43-year-old male patient, successfully treated with transarterial embolization, thereby avoiding major surgery. Our report adds to the growing body of literature pertaining to adrenal artery embolization.
Project description:IntroductionThis study aimed to conduct a clinical review and analysis to recommend options for the prevention and treatment of postoperative hemorrhage.Patients and methodsA total of 138 patients who experienced postoperative hemorrhage after abdominal surgery in the period between January 2015 and December 2020 at the Sir Run Run Shaw Hospital, affiliated to Zhejiang University School of Medicine, participated in this study. They were divided into a group with primary bleeding only and a secondary bleeding group. Univariate and multivariate statistical analyses were performed, followed by plotting of cumulative hazard and survival curves for the two groups.ResultsThe main factors of interest found to be associated with secondary hemorrhage were duration of the operation, the time of the first bleeding incident, intervention time, performance of combined organ resection, use of surgical intervention, occurrence of abdominal infection, admission to the intensive care unit (ICU), postoperative length of stay, and total hospitalization expenses. Among these, a long operative duration (>5 h) and an extended intervention time (>5 h) were identified as independent predictors of risk of secondary hemorrhage.ConclusionsSecondary hemorrhage after abdominal surgery is mainly associated with subjective human factors, and it is an important cause of poor prognosis and even death. Proper reductions in operation time and implementation of a quick response to bleeding are the key factors in tackling bleeding. Further reduction in the rates of postoperative hemorrhage and mortality will require a concerted effort by surgeons in terms of both intraoperative surgical techniques and postoperative management.
Project description:Intra-leiomyoma hemorrhage in postmenopausal woman is a very rare complication. This case report represents a case report of spontaneous hemorrhage inside the uterine leiomyoma in postmenopausal woman who presented with acute abdomen. A 55-year-old woman, multipara, postmenopausal for 7 years, known case of multiple fibroid uteruses, was presented to the emergency department of Ahmadi Hospital, Kuwait Oil Company, with acute abdominal pain and vomiting, without any reported trauma and/or associated vaginal bleeding. The studied woman was generally stable regarding her vital signs, her hemoglobin dropped from 12 to 10.2 g/dl. Abdominal examination revealed; palpable pelvi-abdominal mass firms in consistency with tenderness and guarding which provisionally support the diagnosis of degenerated fibroids or intra-leiomyoma hemorrhage. The diagnosis was confirmed by basic pelvi-abdominal ultrasound, followed by correction of the patient's general condition and total abdominal hysterectomy with bilateral salpingo-oophrectomy (TAHBSO). Bisected largest cystic fibroid showed brownish serous fluid inside with organized clotted hematoma which confirmed the diagnosis of intra-leiomyoma hemorrhage. Postoperatively, the studied woman received an unit of packed red blood cells for correction of the postoperative anemia and discharged from the hospital in good general condition for postoperative follow-up in the outpatients' department on iron tablets. This case report represents a rare complication of intra-leiomyoma hemorrhage in postmenopausal, diagnosed by the basic clinical and ultrasound findings. The case was managed by TAHBSO after correction of the general condition because of the increased risk of the sarcomatous changes of the uterine fibroid in postmenopausal women.
Project description:Background and aimNew York City (NYC) is an epicenter of the COVID-19 pandemic in the United States. Proper triage of patients with possible COVID-19 via chief complaint is critical but not fully optimized. This study aimed to investigate the association between presentation by chief complaints and COVID-19 status.MethodsWe retrospectively analyzed adult emergency department (ED) patient visits from five different NYC hospital campuses from March 1, 2020 to May 13, 2020 of patients who underwent nasopharyngeal COVID-19 RT-PCR testing. The positive and negative COVID-19 cohorts were then assessed for different chief complaints obtained from structured triage data. Sub-analysis was performed for patients older than 65 and within chief complaints with high mortality.ResultsOf 11,992 ED patient visits who received COVID-19 testing, 6524/11992 (54.4%) were COVID-19 positive. 73.5% of fever, 67.7% of shortness of breath, and 65% of cough had COVID-19, but others included 57.5% of weakness/fall/altered mental status, 55.5% of glycemic control, and 51.4% of gastrointestinal symptoms. In patients over 65, 76.7% of diarrhea, 73.7% of fatigue, and 69.3% of weakness had COVID-19. 45.5% of dehydration, 40.5% of altered mental status, 27% of fall, and 24.6% of hyperglycemia patients experienced mortality.ConclusionA novel high risk COVID-19 patient population was identified from chief complaint data, which is different from current suggested CDC guidelines, and may help triage systems to better isolate COVID-19 patients. Older patients with COVID-19 infection presented with more atypical complaints warranting special consideration. COVID-19 was associated with higher mortality in a unique group of complaints also warranting special consideration.
Project description:ObjectivesDerive and validate a shortlist of chief complaints to describe unscheduled acute and emergency care in Uganda.SettingA single, private, not-for profit hospital in rural, southwestern Uganda.ParticipantsFrom 2009 to 2015, 26 996 patient visits produced 42 566 total chief complaints for the derivation dataset, and from 2015 to 2017, 10 068 visits produced 20 165 total chief complaints for the validation dataset.MethodsA retrospective review of an emergency centre quality assurance database was performed. Data were abstracted, cleaned and refined using language processing in Stata to produce a longlist of chief complaints, which was collapsed via a consensus process to produce a shortlist and turned into a web-based tool. This tool was used by two local Ugandan emergency care practitioners to categorise complaints from a second longlist produced from a separate validation dataset from the same study site. Their agreement on grouping was analysed using Cohen's kappa to determine inter-rater reliability. The chief complaints describing 80% of patient visits from automated and consensus shortlists were combined to form a candidate chief complaint shortlist.ResultsAutomated data cleaning and refining recognised 95.8% of all complaints and produced a longlist of 555 chief complaints. The consensus process yielded a shortlist of 83 grouped chief complaints. The second validation dataset was reduced in Stata to a longlist of 451 complaints. Using the shortlist tool to categorise complaints produced 71.5% agreement, yielding a kappa of 0.70 showing substantial inter-rater reliability. Only one complaint did not fit into the shortlist and required a free-text amendment. The two shortlists were identical for the most common 14 complaints and combined to form a candidate list of 24 complaints that could characterise over 80% of all emergency centre chief complaints.ConclusionsShortlists of chief complaints can be generated to improve standardisation of data entry, facilitate research efforts and be employed for paper chart usage.
Project description:Bilateral adrenal hemorrhage is a rare condition, which is burdened by potentially life-threatening consequences related to the development of acute adrenal insufficiency. Despite treatment with stress-dose glucocorticoids, a mortality rate of 15% has been reported, which varies according to the severity of underlying predisposing illness and could be much more higher if the adrenal insufficiency is not promptly recognized. An early diagnosis is crucial, though, because of nonspecific clinical and laboratory findings, adrenal hemorrhage is rarely suspected. Therefore, imaging has a pivotal role for the diagnosis of this uncommon condition but, despite adrenal hematomas characteristically appear round or oval with peripheral fat stranding, their initial presentation could be ambiguous. The authors describe a case of postoperative bilateral adrenal hemorrhage initially presenting at computed tomography scan as thickening of both glands surrounded by fat stranding, which led to close monitoring of adrenal function before unequivocal hemorrhage developed.
Project description:Grey Turner's and Cullen's signs are rare clinical signs, which most appear in patients with severe acute pancreatitis. The present patient complained of abdominal pain after coughing. However, contrast-enhanced CT revealed a hemorrhage of the abdominal wall. Therefore, spontaneous hemorrhage of the abdominal wall was diagnosed. The patient recovered through immobilization and hemostasis therapy. This case report and literature review aims to remind clinicians of manifestations and treatment of spontaneous hemorrhage.