ABSTRACT
Both reverse transcription-PCR (RT-PCR) and chest X-rays are used for the diagnosis of the coronavirus disease-2019 (COVID-19). However, COVID-19 pneumonia does not have a defined set of radiological findings. Our work aims to investigate radiomic features and classification models to differentiate chest X-ray images of COVID-19-based pneumonia and other types of lung patterns. The goal is to provide grounds for understanding the distinctive COVID-19 radiographic texture features using supervised ensemble machine learning methods based on trees through the interpretable Shapley Additive Explanations (SHAP) approach. We use 2,611 COVID-19 chest X-ray images and 2,611 non-COVID-19 chest X-rays. After segmenting the lung in three zones and laterally, a histogram normalization is applied, and radiomic features are extracted. SHAP recursive feature elimination with cross-validation is used to select features. Hyperparameter optimization of XGBoost and Random Forest ensemble tree models is applied using random search. The best classification model was XGBoost, with an accuracy of 0.82 and a sensitivity of 0.82. The explainable model showed the importance of the middle left and superior right lung zones in classifying COVID-19 pneumonia from other lung patterns.
ABSTRACT
Both reverse transcription-PCR (RT-PCR) and chest X-rays are used for the diagnosis of the coronavirus disease-2019 (COVID-19). However, COVID-19 pneumonia does not have a defined set of radiological findings. Our work aims to investigate radiomic features and classification models to differentiate chest X-ray images of COVID-19-based pneumonia and other types of lung patterns. The goal is to provide grounds for understanding the distinctive COVID-19 radiographic texture features using supervised ensemble machine learning methods based on trees through the interpretable Shapley Additive Explanations (SHAP) approach. We use 2,611 COVID-19 chest X-ray images and 2,611 non-COVID-19 chest X-rays. After segmenting the lung in three zones and laterally, a histogram normalization is applied, and radiomic features are extracted. SHAP recursive feature elimination with cross-validation is used to select features. Hyperparameter optimization of XGBoost and Random Forest ensemble tree models is applied using random search. The best classification model was XGBoost, with an accuracy of 0.82 and a sensitivity of 0.82. The explainable model showed the importance of the middle left and superior right lung zones in classifying COVID-19 pneumonia from other lung patterns.
ABSTRACT
The COVID-19 pandemic has forced many people, including those in the fields of science and engineering, to work from home. The new working environment caused by the pandemic is assumed to have a different impact on the amount of work that women and men can do from home. Particularly, if the major burden of child and other types of care is still predominantly on the shoulders of women. As such, a survey was conducted to assess the main issues that biomedical engineers, medical physicists (academics and professionals), and other similar professionals have been facing when working from home during the pandemic. A survey was created and disseminated worldwide. It originated from a committee of International Union for Physical and Engineering Sciences in Medicine (IUPESM; Women in Medical Physics and Biomedical Engineering Task Group) and supported by the Union. The ethics clearance was received from Carleton University. The survey was deployed on the Survey Monkey platform and the results were analyzed using IBM SPSS software. The analyses mainly consisted of frequency of the demographic parameters and the cross-tabulation of gender with all relevant variables describing the impact of work at home. A total of 921 responses from biomedical professions in 76 countries were received: 339 males, 573 females, and nine prefer-not-to-say/other. Regarding marital/partnership status, 85% of males were married or in partnership, and 15% were single, whereas 72% of females were married or in partnership, and 26% were single. More women were working from home during the pandemic (68%) versus 50% of men. More men had access to an office at home (68%) versus 64% for women. The proportion of men spending more than 3 h on child care and schooling per day was 12%, while for women it was 22%; for household duties, 8% of men spent more than 3 h; for women, this was 12.5%. It is interesting to note that 44% of men spent between 1 and 3 h per day on household duties, while for women, it was 55%. The high number of survey responses can be considered excellent. It is interesting to note that men participate in childcare and household duties in a relatively high percentage; although this corresponds to less hours daily than for women. It is far more than can be found 2 and 3 decades ago. This may reflect the situation in the developed countries only-as majority of responses (75%) was received from these countries. It is evident that the burden of childcare and household duties will have a negative impact on the careers of women if the burden is not more similar for both sexes. It is important to recognize that a change in policies of organizations that hire them may be required to provide accommodation and compensation to minimize the negative impact on the professional status and career of men and women who work in STEM fields.