Calibration Assessment of Low-Cost Carbon Dioxide Sensors Using the Extremely Randomized Trees Algorithm

As the monitoring of carbon dioxide is an important proxy to estimate the air quality of indoor and outdoor environments, it is essential to obtain trustful data from CO₂ sensors. However, the use of widely available low-cost sensors may imply lower data quality, especially regarding accuracy. This paper proposes a new approach for enhancing the accuracy of low-cost CO₂ sensors using an extremely randomized trees algorithm. It also reports the results obtained from experimental data collected from sensors that were exposed to both indoor and outdoor environments. The indoor experimental set was composed of two metal oxide semiconductors (MOS) and two non-dispersive infrared (NDIR) sensors next to a reference sensor for carbon dioxide and independent sensors for air temperature and relative humidity. The outdoor experimental exposure analysis was performed using a third-party dataset which fit into our goals: the work consisted of fourteen stations using low-cost NDIR sensors geographically spread around reference stations. One calibration model was trained for each sensor unit separately, and, in the indoor experiment, it managed to reduce the mean absolute error (MAE) of NDIR sensors by up to 90%, reach very good linearity with MOS sensors in the indoor experiment (r² value of 0.994), and reduce the MAE by up to 98% in the outdoor dataset. We have found in the outdoor dataset analysis that the exposure time of the sensor itself may be considered by the algorithm to achieve better accuracy. We also observed that even a relatively small amount of data may provide enough information to perform a useful calibration if they contain enough data variety. We conclude that the proper use of machine learning algorithms on sensor readings can be very effective to obtain higher data quality from low-cost gas sensors either indoors or outdoors, regardless of the sensor technology.

Arrhythmogenic Cardiomyopathy as a Late Complication of COVID-19-Induced Myocarditis

COVID-19 has become a global health problem. So far, more than 281 million COVID-19 cases have been confirmed. The vast majority of patients diagnosed with COVID-19 infection present only with respiratory signs and symptoms. A small amount of patients, however, show signs and symptoms of cardiovascular involvement like a myocardial injury. Myocarditis is one of the possible complications, and cases of clinically suspected myocarditis have been reported in the setting of COVID-19. Herein, we present a case of inflammatory cardiomyopathy, a different type of arrhythmogenic cardiomyopathy, in a 32-year-old man, 40 days after being diagnosed with COVID-19.

Primary Sternal Osteomyelitis Caused by Methicillin-Sensitive Staphylococcus aureus: A Diagnosis Rare in Healthy Adults

Primary sternal osteomyelitis (PSO) is a rare clinical entity, and usually, it is associated with predisposing factors such as intravenous drug use, diabetes mellitus, or human deficiency virus infection. In an otherwise healthy adult, it becomes an even rarer entity. Early diagnosis and treatment minimize associated morbidity, like the need for surgical debridement, longer courses of medication, and length of in-hospital stay.

We describe the case of a 54-year-old man without any predisposing risk factors for PSO, who presented with chest pain, erythema, tenderness, and warmth at the right parasternal region. A non-enhanced thoracic tomography showed a 33 mm suspicious pulmonary nodule and no signs of sternum abnormalities. To better evaluate this finding, a positron emission tomography with fluorine-18 fluorodeoxyglucose was performed, showing abnormal uptake of the radionuclide at the sternomanubrial synchondrosis and no abnormal uptake at the lung parenchyma. The presence of Staphylococcus aureus in blood cultures, in conjunction with these results, supported the diagnosis of PSO. The patient completed six weeks of microbiologically oriented antibacterial therapy with complete recovery.

From Kidney to Brain: An Uncommon Severe Relapse of Myeloperoxidase Anti-Neutrophil Cytoplasmic Antibody (MPO-ANCA) Vasculitis

Anti-neutrophil cytoplasmic antibody (ANCA)-associated vasculitis (AAV) is a group of rare autoimmune diseases that affect medium and small blood vessels, with uncommon, variable central nervous system (CNS) involvement. It poses diagnosis challenges due to the limited accuracy of conventional imaging and vast differential diagnosis.

We describe the case of a 76-year-old man with a previously diagnosed myeloperoxidase (MPO)-positive AAV with exclusive renal involvement. The patient presented to our emergency department (ED) with sudden-onset weakness of the right side of the body, difficulty speaking, fever, and a history of progressive cognitive impairment in the previous three months (loss of memory, time and space disorientation, acalculia). Brain imaging showed multiple acute and subacute ischemic lesions, suggesting CNS vasculitic involvement. The patient was treated with methylprednisolone pulses, followed by rituximab, with motor and cognitive improvement.

Timely diagnosis and adequate treatment of AAV as a cause for new-onset neurological symptoms are crucial to improve outcomes. Otherwise, a higher risk of relapse remains, and extensive neurological deficits may become permanent. Evidence regarding the best treatment options in these patients is scarce and case reports provide further data on this topic.

A Real-World Approach on the Problem of Chart Recognition Using Classification, Detection and Perspective Correction

Data charts are widely used in our daily lives, being present in regular media, such as newspapers, magazines, web pages, books, and many others. In general, a well-constructed data chart leads to an intuitive understanding of its underlying data. In the same way, when data charts have wrong design choices, a redesign of these representations might be needed. However, in most cases, these charts are shown as a static image, which means that the original data are not usually available. Therefore, automatic methods could be applied to extract the underlying data from the chart images to allow these changes. The task of recognizing charts and extracting data from them is complex, largely due to the variety of chart types and their visual characteristics. Other features in real-world images that can make this task difficult are photo distortions, noise, alignment, etc. Two computer vision techniques that can assist this task and have been little explored in this context are perspective detection and correction. These methods transform a distorted and noisy chart in a clear chart, with its type ready for data extraction or other uses. This paper proposes a classification, detection, and perspective correction process that is suitable for real-world usage, when considering the data used for training a state-of-the-art model for the extraction of a chart in real-world photography. The results showed that, with slight changes, chart recognition methods are now ready for real-world charts, when taking time and accuracy into consideration.

Predictive variables affecting transfusion requirements in orthotopic liver transplantation

INTRODUCTION AND AIMS

Adult orthotopic liver transplantation (OLT) is associated with considerable blood product requirements. The aim of this study was to assess the ability of preoperative information to predict intraoperative red blood cell (RBC) transfusion requirements among adult liver recipients.

METHODS

Preoperative variables with previously demonstrated relationships to intraoperative RBC transfusion were identified from the literature: sex, age, pathology, prothrombin time (PT), factor V, hemoglobin (Hb), and platelet count (plt). These variables were then retrospectively collected from 758 consecutive adult patients undergoing OLT from 1997 to 2007. Relationships between these variables and intraoperative blood transfusion requirements were examined by both univariate analysis and multiple linear regression analysis.

RESULTS

Univariate analysis confirmed significant associations between RBC transfusion and PT, factor V, Hb, Plt, pathology, and age (P values all < .001). However, stepwise backward multivariate analysis excluded variables Plt and factor V from the multiple regression linear model. The variables included in the final predictive model were PT, Hb, age, and pathology. Patients suffering from liver carcinoma required more blood products than those suffering from other pathologies. Yet, the overall predictive power of the final model was limited (R(2) = .308; adjusted R(2) = .30).

CONCLUSION

Preoperative variables have limited predictive power for intraoperative RBC transfusion requirements even when significant statistical associations exist, identifying only a small portion of the observed total transfusion variability. Preoperative PT, Hb, age, and liver pathology seem to be the most significant predictive factors but other factors like severity of liver disease, surgical technique, medical experience in liver transplantation, and other noncontrollable human variables may play important roles to determine the final transfusion requirements.

Autologous blood donation in cardiac patients

Despite the advantages of autologous blood transfusion, doubt still remains about its safety in cardiac patients. We report our experience with 439 cardiac patients who donated a total of 1692 units of blood before coronary, valvular, or congenital cardiac operations. During the collections, patients were continuously monitored with ECG, blood pressure, and heart rate. In 22 collections we observed vasovagal reactions, which represents an incidence of 1.3% of the total number of collections. The patients recovered quickly and only in 3 cases was volume replacement with saline needed. There were no other complications which could be related to the preoperative autologous donation program. We feel that, with careful selection of the patients and of the circumstances surrounding the collection of blood, autologous blood donation in cardiac patients is a safe and beneficial experience.