Thinking Beyond Giant Cell Arteritis in COVID-19 Times.

BACKGROUND: The coronavirus disease 2019 has displayed multi-system manifestations since its first presentation. This article highlights an unusual presentation of COVID-19 that was reviewed by our instituition's otolaryngology and ophthalmology team. METHODS: We present 2 cases of COVID-19 which presented with unilateral otalgia and ipsilateral pulsatile headaches involving the temporal area. They were referred to the otolaryngology team for assessment of otalgia and subsequently referred to the ophthalmology team for possible giant cell arteritis (GCA). Both patients had no jaw claudication, scalp pain, or tenderness. RESULTS: Serology testing showed raised C-reactive protein (CRP) but normal platelets and erythrocyte sedimentation rate. Case 1 was tested for COVID-19 as part of a preoperative workup which returned positive. With a marked similarity in presentation, Case 2 was tested for COVID-19 which also returned positive. CONCLUSIONS: These 2 cases highlight another set of symptoms that COVID-19 patients may present with. In the context of a COVID-19 pandemic, if a patient presents symptoms similar to GCA but with isolated CRP, it should prompt consideration for COVID testing.

Validation of a Machine Learning Model That Outperforms Clinical Risk Scoring Systems for Upper Gastrointestinal Bleeding.

BACKGROUND & AIMS: Scoring systems are suboptimal for determining risk in patients with upper gastrointestinal bleeding (UGIB); these might be improved by a machine learning model. We used machine learning to develop a model to calculate the risk of hospital-based intervention or death in patients with UGIB and compared its performance with other scoring systems. METHODS: We analyzed data collected from consecutive unselected patients with UGIB from medical centers in 4 countries (the United States, Scotland, England, and Denmark; n = 1958) from March 2014 through March 2015. We used the data to derive and internally validate a gradient-boosting machine learning model to identify patients who met a composite endpoint of hospital-based intervention (transfusion or hemostatic intervention) or death within 30 days. We compared the performance of the machine learning prediction model with validated pre-endoscopic clinical risk scoring systems (the Glasgow-Blatchford score [GBS], admission Rockall score, and AIMS65). We externally validated the machine learning model using data from 2 Asia-Pacific sites (Singapore and New Zealand; n = 399). Performance was measured by area under receiver operating characteristic curve (AUC) analysis. RESULTS: The machine learning model identified patients who met the composite endpoint with an AUC of 0.91 in the internal validation set; the clinical scoring systems identified patients who met the composite endpoint with AUC values of 0.88 for the GBS (P = .001), 0.73 for Rockall score (P < .001), and 0.78 for AIMS65 score (P < .001). In the external validation cohort, the machine learning model identified patients who met the composite endpoint with an AUC of 0.90, the GBS with an AUC of 0.87 (P = .004), the Rockall score with an AUC of 0.66 (P < .001), and the AIMS65 with an AUC of 0.64 (P < .001). At cutoff scores at which the machine learning model and GBS identified patients who met the composite endpoint with 100% sensitivity, the specificity values were 26% with the machine learning model versus 12% with GBS (P < .001). CONCLUSIONS: We developed a machine learning model that identifies patients with UGIB who met a composite endpoint of hospital-based intervention or death within 30 days with a greater AUC and higher levels of specificity, at 100% sensitivity, than validated clinical risk scoring systems. This model could increase identification of low-risk patients who can be safely discharged from the emergency department for outpatient management.

Machine Learning to Predict Outcomes in Patients with Acute Gastrointestinal Bleeding: A Systematic Review.

Risk stratification of patients with gastrointestinal bleeding (GIB) is recommended, but current risk assessment tools have variable performance. Machine learning (ML) has promise to improve risk assessment. We performed a systematic review to evaluate studies utilizing ML techniques for GIB. Bibliographic databases and conference abstracts were searched for studies with a population of overt GIB that used an ML algorithm with outcomes of mortality, rebleeding, hemostatic intervention, and/or hospital stay. Two independent reviewers screened titles and abstracts, reviewed full-text studies, and extracted data from included studies. Risk of bias was assessed with an adapted Quality in Prognosis Studies tool. Area under receiver operating characteristic curves (AUCs) were the primary assessment of performance with AUC ≥ 0.80 predefined as an acceptable threshold of good performance. Fourteen studies with 30 assessments of ML models met inclusion criteria. No study had low risk of bias. Median AUC reported in validation datasets for predefined outcomes of mortality, intervention, or rebleeding was 0.84 (range 0.40-0.98). AUCs were higher with artificial neural networks (median 0.93, range 0.78-0.98) than other ML models (0.81, range 0.40-0.92). ML performed better than clinical risk scores (Glasgow-Blatchford, Rockall, Child-Pugh, MELD) for mortality in upper GIB. Limitations include heterogeneity of ML models, inconsistent comparisons of ML models with clinical risk scores, and high risk of bias. ML generally provided good-excellent prognostic performance in patients with GIB, and artificial neural networks tended to outperform other ML models. ML was better than clinical risk scores for mortality in upper GIB.

Implementing a pandemic roster in a specialty emergency department: Challenges and benefits.

OBJECTIVE: To create a roster that eliminated unnecessary cross-staff exposure to ensure the hospital had sufficient staff to run the ED in the event that a group of staff are affected by COVID-19. This roster was aimed at providing staff with 'manageable shift lengths, down-time between shifts, regular breaks and access to refreshments' as dictated by the Victorian Department of Health and Human Services. METHODS: Creating six fixed teams in our ED. Teams work blocks of three consecutive days of 12 h shifts, each block alternates between day and night shifts. RESULTS: We managed to completely eliminate unnecessary crossover of staff thus reducing risk of having a large part of our workforce incapacitated should any member be affected by COVID. CONCLUSION: A pandemic roster plan to minimise staff exposure from other colleagues during a pandemic was possible. This helps to ensure an adequate workforce in the unfortunate event a staff contracts the disease leading to other close contact staff requiring isolation or succumbing to the same illness.

Improving the rates of electronic results acknowledgement at a tertiary eye care centre.

BACKGROUND: Hundreds of thousands of tests are performed annually in hospitals worldwide. Safety Issues arise when abnormal results are not recognized promptly resulting in delayed treatment and increased morbidity and mortality. As a result Singapore's largest healthcare group, Singhealth introduced an electronic result acknowledgement system. This system was adopted by the Singapore National Eye Centre (SNEC) in February 2016. Baseline measurements show that weekly numbers of unacknowledged results ranged from 193 to 617. The current standards of electronic results acknowledgement posts a significant patient safety hazard. METHODS: Root cause analysis was performed to identify contributory factors. Pareto principle was then used by the authors to identify the main contributory factors. We employed the rapid cycle improvement Plan-do-study-act (PDSA) strategy to test and evaluate implemented changes. Changes are implemented for 2 weeks and data collected prospectively. The data is analyzed the week after and the following PDSA actions are decided and instituted the following week. 3 PDSA cycles were undertaken in total. RESULTS: The first PDSA cycle focused on raising awareness of the problem at hand, the number of unacknowledged results drastically decreased during the 1stweek of implementation of our PDSA from 617 to 254. The second PDSA cycle targeted the lack of knowledge of doctors involved in the electronic result acknowledgement process. There was a trend downwards near the end of the cycle which continued through the week after. The third PDSA cycle targeted individual doctors and provided individual remedial training. Second line doctors were also equipped to better handle abnormal results. There was significant improvement with the number of unacknowledged abnormal results dropping to <5 a week. CONCLUSIONS: Multiple factors were identified to contribute to the low compliance to electronic acknowledgement of results. The role doctors play in the issue at hand was paramount and required careful handling in a professional manner with multiple reminders and emphasis on the importance of acknowledging and acting on the results.A significant improvement in the rates of acknowledgement of abnormal results was demonstrated with clear benefits to patient safety. Interventions can be replicated when implementing similar systems to other areas of healthcare.