scholarly journals Accuracy of Conventional and Machine Learning Enhanced Chest Radiography for the Assessment of COVID-19 Pneumonia: Intra-Individual Comparison with CT

2020 ◽  
Vol 9 (11) ◽  
pp. 3576
Author(s):  
Katharina Martini ◽  
Christian Blüthgen ◽  
Joan E. Walter ◽  
Michael Messerli ◽  
Thi Dan Linh Nguyen-Kim ◽  
...  
Keyword(s):  
Machine Learning ◽  
Image Interpretation ◽  
Conventional Radiography ◽  
Control Group ◽  
Disease Extent ◽  
Confidence Levels ◽  
Individual Comparison ◽  
Polymerase Chain ◽  
The Cost ◽  
Detection And Quantification

Purpose: To evaluate diagnostic accuracy of conventional radiography (CXR) and machine learning enhanced CXR (mlCXR) for the detection and quantification of disease-extent in COVID-19 patients compared to chest-CT. Methods: Real-time polymerase chain reaction (rt-PCR)-confirmed COVID-19-patients undergoing CXR from March to April 2020 together with COVID-19 negative patients as control group were retrospectively included. Two independent readers assessed CXR and mlCXR images for presence, disease extent and type (consolidation vs. ground-glass opacities (GGOs) of COVID-19-pneumonia. Further, readers had to assign confidence levels to their diagnosis. CT obtained ≤ 36 h from acquisition of CXR served as standard of reference. Inter-reader agreement, sensitivity for detection and disease extent of COVID-19-pneumonia compared to CT was calculated. McNemar test was used to test for significant differences. Results: Sixty patients (21 females; median age 61 years, range 38–81 years) were included. Inter-reader agreement improved from good to excellent when mlCXR instead of CXR was used (k = 0.831 vs. k = 0.742). Sensitivity for pneumonia detection improved from 79.5% to 92.3%, however, on the cost of specificity 100% vs. 71.4% (p = 0.031). Overall, sensitivity for the detection of consolidation was higher than for GGO (37.5% vs. 70.4%; respectively). No differences could be found in disease extent estimation between mlCXR and CXR, even though the detection of GGO could be improved. Diagnostic confidence was better on mlCXR compared to CXR (p = 0.013). Conclusion: In line with the current literature, the sensitivity for detection and quantification of COVID-19-pneumonia was moderate with CXR and could be improved when mlCXR was used for image interpretation.

Probiotics in the diets of laying quails

2020 ◽  
pp. 60-66
Author(s):  
O. Merzlyakova ◽  
V. Rogachyev ◽  
V. Chegodaev
Keyword(s):  
Bacillus Subtilis ◽  
Bacillus Licheniformis ◽  
Egg Production ◽  
Positive Impact ◽  
Hematological Parameters ◽  
Economic Effect ◽  
Egg Laying ◽  
Control Group ◽  
Egg Mass ◽  
The Cost

The efficiency of introducing probiotics based on strains of Bacillus subtilis, Bacillus licheniformis and their consortium in the amount of 150 g/t of feed into the diets of laying quails has been studied. The experiment lasting 182 days has been carried out on four groups of quails with 30 heads in each. The quails have been housed in the broiler battery in compliance with the required microclimate conditions. Quails of all groups have been received the main diet (compound feed) developed taking into account their age and physiological characteristics. The quails of the 1st, 2nd and 3rd experimental groups in addition to the main diet received probiotics (150 g/t compound feed) based on strains Bacillus subtilis, Bacillus licheniformis and their consortium, respectively. It has been found that feeding the laying quails of the consortium of strains Bacillus subtilis and Bacillus licheniformis had the most significant positive impact on their productive performance, it allowed to increase egg production by 7,81 %, egg laying intensity by 5,0 %, egg mass yield by 9,77 %, while reducing feed expenditures for 10 eggs by 13,35 %. The yield of hatching eggs has been increased by 7,03 %, hatchability of chickens from laid and fertilized eggs by 8,33 and 8,35 %, brooding waste decreased by 21,74 %. Hematological parameters of quails during the whole experiment were within the physiological norm. The economic effect calculated on the basis of data on the cost of compound feed, probiotics and the cost of sold eggs of quail laying was 14,56 % in the 3rd experimental group (in relation to the control group).

Effectiveness the use of additive MEGA-VIT in the ration of mares of Shetland pony breed

2020 ◽  
pp. 60-67
Author(s):  
G. Uskov ◽  
A. Tsopanova ◽  
T. Perezhogina
Keyword(s):  
Physiological State ◽  
Mineral Elements ◽  
Positive Influence ◽  
Control Group ◽  
Physiological Indicators ◽  
Mineral Additive ◽  
Nutritional Needs ◽  
Young Horses ◽  
The Cost ◽  
Experimental Group

Complete feeding of ponies is provided on the basis of data on their nutritional needs depending on age, sex, physiological state and level of productivity (the amount of milk produced and the intensity of growth of young animals). Ponies are sensitive to a lack of vitamins and mineral elements in the feed. When there is a sufficient amount of organic and mineral substances, but a lack or absence of vitamins, horses and ponies have impaired metabolism. The purpose of this work is to study the effectiveness of the use of vitamin and mineral additive MEGA-VIT in the rations of pregnant and lactating mares of Shetland pony breed. It has been found during of the researches that the vitamin and mineral additive MEGA-VIT had a positive influence on the productive and physiological indicators of animals. The cost of spent feed for the entire period of experiment in the control group was 50,6 thousand rubles, and in the experimental group it was 11,8 thousand rubles more or 23,5 %. Revenue from the sale of young horses of the control group amounted to 400 thousand rubles, and experimental group – 440 thousand rubles, this is by 40 thousand rubles more than in control group. This led to the increase in profit in the experimental group of mares by 28,1 thousand rubles and accordingly the level of profitability by 3,2 %. It has been recommended on the results have been obtained on the base of researches to include 30 g/head/day in the rations of mares of Shetland pony breed during pregnancy, and 50 g/head/day during lactation.

INFLUENCE OF STOCK HOUSE LIGHT ON DAIRY PRODUCTIVITY OF COWS

2020 ◽  
Keyword(s):  
Blood Serum ◽  
Physiological State ◽  
Light Level ◽  
Inorganic Phosphorus ◽  
Control Group ◽  
Hemoglobin Content ◽  
Milk Productivity ◽  
Reproductive Ability ◽  
The Cost ◽  
Experimental Group

The article is devoted to the solution of an urgent problem- influence of different lighting modes on the dairy productivity of cows. 2 groups of cows with 20 heads each were formed. In control group, light in the cowshed was 50-75 Lux for a light period of 7.5 h in January to 16.5 h in June, and in experimental group - 150-200 Lux and 16 h, respectively. It was found that the intensity and duration of illumination affects physiological state, reproductive ability and milk productivity of cows. In the experimental group of cows, compared with the control group, hemoglobin content in blood increased by 4.6% (P < 0.01), red blood cells - by 20.6% (P < 0.05), total protein - by 11.2% (P < 0.001), glucose - by 39.1% (P < 0.05). There was a tendency to increase the total calcium and inorganic phosphorus in blood serum of cows of the experimental group. The level of alkaline phosphatase in blood serum of cows in the control group was 71.5% (P < 0.01) higher than that of cows in the experimental group. Milk yield per 1 cow in the experimental cowshed was 433 kg more than in the control. The cost of 1 kg of milk in the experimental group was 0.94 rubles lower, and the profitability of milk production and sales is 9.42% higher than in the control group. To increase the milk productivity of cows, it is recommended to increase light level in barns for tethered keeping to 150-200 Lux, with the duration of lighting in the winter and transition periods of year up to 16 hours per day.

scholarly journals Machine Learning Prediction of SARS-CoV-2 Polymerase Chain Reaction Results with Routine Blood Tests

2020 ◽  
Author(s):  
Thomas Tschoellitsch ◽  
Martin Dünser ◽  
Carl Böck ◽  
Karin Schwarzbauer ◽  
Jens Meier
Keyword(s):  
Machine Learning ◽  
Polymerase Chain Reaction ◽  
Characteristic Curve ◽  
Cohort Analysis ◽  
Rt Pcr ◽  
Chain Reaction ◽  
Blood Tests ◽  
Routine Blood ◽  
Machine Learning Model ◽  
Polymerase Chain

Abstract Objective The diagnosis of COVID-19 is based on the detection of SARS-CoV-2 in respiratory secretions, blood, or stool. Currently, reverse transcription polymerase chain reaction (RT-PCR) is the most commonly used method to test for SARS-CoV-2. Methods In this retrospective cohort analysis, we evaluated whether machine learning could exclude SARS-CoV-2 infection using routinely available laboratory values. A Random Forests algorithm with 1353 unique features was trained to predict the RT-PCR results. Results Out of 12,848 patients undergoing SARS-CoV-2 testing, routine blood tests were simultaneously performed in 1528 patients. The machine learning model could predict SARS-CoV-2 test results with an accuracy of 86% and an area under the receiver operating characteristic curve of 0.90. Conclusion Machine learning methods can reliably predict a negative SARS-CoV-2 RT-PCR test result using standard blood tests.

scholarly journals OP0198-HPR A STRUCTURED MODEL FOR OA CARE IN PRIMARY HEALTHCARE IS A COST-EFFECTIVE ALTERNATIVE COMPARED TO USUAL CARE FOR PEOPLE WITH HIP AND KNEE OA

2021 ◽  
Vol 80 (Suppl 1) ◽  
pp. 119-120
Author(s):  
N. Østerås ◽  
E. Aas ◽  
T. Moseng ◽  
L. Van Bodegom-Vos ◽  
K. Dziedzic ◽  
...  
Keyword(s):  
Usual Care ◽  
Primary Healthcare ◽  
Intervention Group ◽  
Cost Effective ◽  
Cost Utility ◽  
Control Group ◽  
Structured Model ◽  
Knee Oa ◽  
Cost Effective Alternative ◽  
The Cost

Background:To improve quality of care for patients with hip and knee osteoarthritis (OA), a structured model for integrated OA care was developed based on international treatment recommendations. A previous analysis of a cluster RCT (cRCT) showed that compared to usual care, the intervention group reported higher quality of care and greater satisfaction with care. Also, more patients were treated according to international guidelines and fulfilled recommendations for physical activity at the 6-month follow-up.Objectives:To assess the cost-utility of a structured model for hip or knee OA care.Methods:A cRCT with stepped-wedge cohort design was conducted in 6 Norwegian municipalities (clusters) in 2015-17. The OA care model was implemented in one cluster at the time by switching from “usual care” to the structured model. The implementation of the model was facilitated by interactive workshops for general practitioners (GPs) and physiotherapists (PTs) with an update on OA treatment recommendations. The GPs explained the OA diagnosis and treatment alternatives, provided pharmacological treatment when appropriate, and suggested referral to physiotherapy. The PT-led patient OA education programme was group-based and lasted 3 hours followed by an 8–12-week individually tailored resistance exercise programme with twice weekly 1-hour supervised group sessions (5–10 patients per PT). An optional 10-hours Healthy Eating Program was available. Participants were ≥45 years with symptomatic hip or knee OA.Costs were measured from the healthcare perspective and collected from several sources. Patients self-reported visits in primary healthcare at 3, 6, 9 and 12 months. Secondary healthcare visits and joint surgery data were extracted from the Norwegian Patient Register. The health outcome, quality-adjusted life-year (QALY), was estimated based on the EQ-5D-5L scores at baseline, 3, 6, 9 and 12 months. The result of the cost-utility analysis was reported using the incremental cost-effectiveness ratio (ICER), defined as the incremental costs relative to incremental QALYs (QALYs gained). Based on Norwegian guidelines, the threshold is €27500. Sensitivity analyses were performed using bootstrapping to assess the robustness of reported results and presented in a cost-effectiveness plane (Figure 1).Results:The 393 patients’ mean age was 63 years (SD 9.6) and 74% were women. 109 patients were recruited during control periods (control group), and 284 patients were recruited during interventions periods (intervention group). Only the intervention group had a significant increase in EQ-5D-5L utility scores from baseline to 12 months follow-up (mean change 0.03; 95% CI 0.01, 0.05) with QALYs gained: 0.02 (95% CI -0.08, 0.12). The structured OA model cost approx. €301 p.p. with an additional €50 for the Healthy Eating Program. Total 12 months healthcare cost p.p. was €1281 in the intervention and €3147 in the control group, resulting in an incremental cost of -€1866 (95% CI -3147, -584) p.p. Costs related to surgical procedures had the largest impact on total healthcare costs in both groups. During the 12-months follow-up period, 5% (n=14) in the intervention compared to 12% (n=13) in the control group underwent joint surgery; resulting in a mean surgical procedure cost of €553 p.p. in the intervention as compared to €1624 p.p. in the control group. The ICER was -€93300, indicating that the OA care model resulted in QALYs gained and cost-savings. At a threshold of €27500, it is 99% likely that the OA care model is a cost-effective alternative.Conclusion:The results of the cost-utility analysis show that implementing a structured model for OA care in primary healthcare based on international guidelines is highly likely a cost-effective alternative compared to usual care for people with hip and knee OA. More studies are needed to confirm this finding, but this study results indicate that implementing structured OA care models in primary healthcare may be beneficial for the individual as well as for the society.Disclosure of Interests:None declared

scholarly journals Quality Classification of Injection-Molded Components by Using Quality Indices, Grading, and Machine Learning

Polymers ◽  
2021 ◽  
Vol 13 (3) ◽  
pp. 353
Author(s):  
Kun-Cheng Ke ◽  
Ming-Shyan Huang
Keyword(s):  
Machine Learning ◽  
Integrated Circuit ◽  
Quality Indices ◽  
Statistical Process ◽  
Suitable Alternative ◽  
Quality Grading ◽  
Quality Of Products ◽  
The Cost ◽  
Mlp Model

Conventional methods for assessing the quality of components mass produced using injection molding are expensive and time-consuming or involve imprecise statistical process control parameters. A suitable alternative would be to employ machine learning to classify the quality of parts by using quality indices and quality grading. In this study, we used a multilayer perceptron (MLP) neural network along with a few quality indices to accurately predict the quality of “qualified” and “unqualified” geometric shapes of a finished product. These quality indices, which exhibited a strong correlation with part quality, were extracted from pressure curves and input into the MLP model for learning and prediction. By filtering outliers from the input data and converting the measured quality into quality grades used as output data, we increased the prediction accuracy of the MLP model and classified the quality of finished parts into various quality levels. The MLP model may misjudge datapoints in the “to-be-confirmed” area, which is located between the “qualified” and “unqualified” areas. We classified the “to-be-confirmed” area, and only the quality of products in this area were evaluated further, which reduced the cost of quality control considerably. An integrated circuit tray was manufactured to experimentally demonstrate the feasibility of the proposed method.

scholarly journals Smooth input preparation for quantum and quantum-inspired machine learning

2021 ◽  
Vol 3 (1) ◽  
Author(s):  
Zhikuan Zhao ◽  
Jack K. Fitzsimons ◽  
Patrick Rebentrost ◽  
Vedran Dunjko ◽  
Joseph F. Fitzsimons
Keyword(s):  
Machine Learning ◽  
Quantum Algorithms ◽  
Machine Learning Algorithms ◽  
Low Rank ◽  
Smoothed Analysis ◽  
Machine Learning Applications ◽  
Data Points ◽  
Input Model ◽  
The Cost ◽  
Input Perturbation

AbstractMachine learning has recently emerged as a fruitful area for finding potential quantum computational advantage. Many of the quantum-enhanced machine learning algorithms critically hinge upon the ability to efficiently produce states proportional to high-dimensional data points stored in a quantum accessible memory. Even given query access to exponentially many entries stored in a database, the construction of which is considered a one-off overhead, it has been argued that the cost of preparing such amplitude-encoded states may offset any exponential quantum advantage. Here we prove using smoothed analysis that if the data analysis algorithm is robust against small entry-wise input perturbation, state preparation can always be achieved with constant queries. This criterion is typically satisfied in realistic machine learning applications, where input data is subjective to moderate noise. Our results are equally applicable to the recent seminal progress in quantum-inspired algorithms, where specially constructed databases suffice for polylogarithmic classical algorithm in low-rank cases. The consequence of our finding is that for the purpose of practical machine learning, polylogarithmic processing time is possible under a general and flexible input model with quantum algorithms or quantum-inspired classical algorithms in the low-rank cases.

scholarly journals Loss of Smell and Taste Can Accurately Predict COVID-19 Infection: A Machine-Learning Approach

2021 ◽  
Vol 10 (4) ◽  
pp. 570
Author(s):  
María A Callejon-Leblic ◽  
Ramon Moreno-Luna ◽  
Alfonso Del Cuvillo ◽  
Isabel M Reyes-Tejero ◽  
Miguel A Garcia-Villaran ◽  
...  
Keyword(s):  
Machine Learning ◽  
Modelling Framework ◽  
Visual Analog Scales ◽  
Average Accuracy ◽  
Machine Learning Approach ◽  
Taste Disorders ◽  
Polymerase Chain ◽  
Fold Cross Validation ◽  
Validation Scheme ◽  
Control Study

The COVID-19 outbreak has spread extensively around the world. Loss of smell and taste have emerged as main predictors for COVID-19. The objective of our study is to develop a comprehensive machine learning (ML) modelling framework to assess the predictive value of smell and taste disorders, along with other symptoms, in COVID-19 infection. A multicenter case-control study was performed, in which suspected cases for COVID-19, who were tested by real-time reverse-transcription polymerase chain reaction (RT-PCR), informed about the presence and severity of their symptoms using visual analog scales (VAS). ML algorithms were applied to the collected data to predict a COVID-19 diagnosis using a 50-fold cross-validation scheme by randomly splitting the patients in training (75%) and testing datasets (25%). A total of 777 patients were included. Loss of smell and taste were found to be the symptoms with higher odds ratios of 6.21 and 2.42 for COVID-19 positivity. The ML algorithms applied reached an average accuracy of 80%, a sensitivity of 82%, and a specificity of 78% when using VAS to predict a COVID-19 diagnosis. This study concludes that smell and taste disorders are accurate predictors, with ML algorithms constituting helpful tools for COVID-19 diagnostic prediction.

Sign in / Sign up

Export Citation Format

Share Document