Severe/critical COVID-19 early warning system based on machine learning algorithms using novel imaging scores

BACKGROUND Early identification of severe/critical coronavirus disease 2019(COVID-19)is crucial for timely treatment and intervention.Chest computed tomography(CT)score has been shown to be a significant factor in the diagnosis and treatment of pneumonia,however,there is currently a lack of effective early warning systems for severe/critical COVID-19 based on dynamic CT evolution.AIM To develop a severe/critical COVID-19 prediction model using a combination of imaging scores,clinical features,and biomarker levels.METHODS This study used an improved scoring system to extract and describe the chest CT characteristics of COVID-19 patients.The study also took into consideration the general clinical indicators such as dyspnea,oxygen saturation,alternative lengthening of telomeres(ALT),and androgen suppression treatment(AST),which are commonly associated with severe/critical COVID-19 cases.The study employed lasso regression to evaluate and rank the significance of different disease characteristics.RESULTS The results showed that blood oxygen saturation,ALT,IL-6/IL-10,combined score,ground glass opacity score,age,crazy paving mode score,qsofa,AST,and overall lung involvement score were key factors in predicting severe/critical COVID-19 cases.The study established a COVID-19 severe/critical early warning system using various machine learning algorithms,including XGBClassifier,Logistic Regression,MLPClassifier,RandomForestClassifier,and AdaBoost Classifier.The study concluded that the prediction model based on the improved CT score and machine learning algorithms is a feasible method for early detection of severe/critical COVID-19 evolution.CONCLUSION The findings of this study suggest that a prediction model based on improved CT scores and machine learning algorithms is effective in detecting the early warning signals of severe/critical COVID-19.

Empirical rock physics relationships on carbonate dry-frame elastic properties

Laboratory tests were conducted to analyze the ultrasonic velocity response to the pressure change in dry carbonate rocks from the Weyburn oilfield,Canada.Twenty-four samples are from seven wells with helium porosities ranging from 1%to 29%.Thin-section images,SEM and mercury intrusion porosimetry were performed to show their inner structures and pore throat size distributions.P-and S-wave velocities(V_(p) and V_(s))measurements were first done under hydrostatic loading and then while unloading,with confining pressures varying between 3 and 35 MPa.The results indicate that V_(p) and V_(s) in these samples follow a linear relation independent of the pressure change.The ratio V_(p)/V_(s) is more responsive to pressure change irrespective of the pore volume.One-third of the carbonate samples show abnormal V_(p)/V_(s) reduction with the increase in the effective pressure.The pressure dependence of velocities(PDV)of Weyburn carbonate rocks varies widely even for samples from the same formation with similar sedimentary history.Samples with loosely packed crystals and/or relatively large dominant pore diameter have higher PDV.The exponential empirical model V=A−Ce^(DPe) was tested;therein,V is the elastic wave velocity,Pe is the effective confining pressure,and A,C and D are the best fitting coefficients determined by curve fitting.The model gives good fits for most of the Weyburn carbonate samples.From a statistical point of view,there is no difference between the V_(p)-and V_(s)-derived exponential coefficient D.

Tilt and decentration with various intraocular lenses: A narrative review

We find that tilt and decentration of intraocular lens (IOL) commonly cause visualquality deterioration after cataract surgery. Multiple factors affect IOL tilt anddecentration in the pre-, mid-, and post-operation phases. Moreover, the tilt anddecentration of 1-piece IOL are less correlated with internal ocular HOAs thanthose of 3-piece IOL. Aspherical IOLs are more sensitive to decentration or tiltthan spherical IOLs. Furthermore, the optical performance of toric IOLs with anaccurate axis remains stable irrespective of tilt and decentration. The opticalquality of asymmetric multifocal IOLs varies significantly after decentration andtilt in different directions. The image quality enhances or deteriorates in thedirection of the decentered IOL. An extended depth of focus IOL can achievegood visual acuity in the distant, intermediate, and near range. Additionally, itstilt and decentration have less impact on the vision than bifocal and trifocal IOL.This is the first review that compares the effect of IOL tilt and decentration onimage quality for various IOL designs. The result indicates that a deeperunderstanding of tilt and decentration of various IOLs can help achieve a bettervisual effect to visually improve refractive cataract surgery.

Epibulbar osseous choristoma:Two case reports

BACKGROUND Choristoma is a rare,benign,congenital proliferative tumor,with osseous choristoma being the rarest.Although the tumor is benign,effective identification is needed for its diagnosis and treatment.Here,we report the diagnosis and successful surgical treatment of two patients with osseous choristoma.CASE SUMMARY Two patients,a young female and young male patient,were found to have a mass on the ocular surface.The tumor presented on the superior temporal bulbar conjunctiva in the first patient and on the upper eyelid in the second patient.Ultrasound biomicroscopy detected a strong echo with clear boundaries covering the lower echo,and computed tomography examination revealed calcification.Both patients underwent surgery,and histopathological evaluation of the mass showed osseous choristoma.They were treated by excision and subsequently cured.CONCLUSION Osseous choristomas are usually asymptomatic.Our patients were cured immediately after surgery,suggesting that surgical treatment is an effective strategy.